No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Random Forest Ensembles and Extended Multi-Extinction Profiles for Hyperspectral Image Classification
... The supervised methods provide a promising way to distinguish the cropland objects in complex scenes containing many uncertainties and intricate relations among classes. For this reason, neural network [11], support vector machine [12,13], and other machine learning methods [14][15][16] are used to build a mapping model between the feature space and the segmentation target, which has become a new development trend. Csillik and Belgiu [17] evaluate how a time-weighted dynamic time-warping (TWDTW) method that uses Sentinel-2 time series performs when applied to pixel-based and object-based classifications of various crop types in three different study areas. ...
... Remote Sens. 2022,14, 2157 ...
The quantity and quality of cropland are the key to ensuring the sustainable development of national agriculture. Remote sensing technology can accurately and timely detect the surface information, and objectively reflect the state and changes of the ground objects. Using high-resolution remote sensing images to accurately extract cropland is the basic task of precision agriculture. The traditional model of cropland semantic segmentation based on the deep learning network is to down-sample high-resolution feature maps to low resolution, and then restore from low-resolution feature maps to high-resolution ideas; that is, obtain low-resolution feature maps through a network, and then recover to high resolution by up-sampling or deconvolution. This will bring about the loss of features, and the segmented image will be more fragmented, without very clear and smooth boundaries. A new methodology for the effective and accurate semantic segmentation cropland of high spatial resolution remote sensing images is presented in this paper. First, a multi-temporal sub-meter cropland sample dataset is automatically constructed based on the prior result data. Then, a fully convolutional neural network combined with contextual feature representation (HRNet-CFR) is improved to complete the extraction of cropland. Finally, the initial semantic segmentation results are optimized by the morphological post-processing approach, and the broken spots are ablated to obtain the internal homogeneous cropland. The proposed method has been validated on the Jilin-1 data and Gaofen Image Dataset (GID) public datasets, and the experimental results demonstrate that it outperforms the state-of-the-art method in cropland extraction accuracy. We selected the comparison of Deeplabv3+ and UPerNet methods in GID. The overall accuracy of our approach is 92.03%, which is 3.4% higher than Deeplabv3+ and 5.12% higher than UperNet.
... In a random forest, ensemble learning is utilized to handle regression and classification problems [20]. It combines decision trees and establishes results based on those trees. ...
... Examples of different augmentation of an image (left to right: segmented image, rotate 300, rotate -300, transform(20, 10), and transform (-10, 0) ...
Human hand gestures are becoming one of the most important, intuitive, and essential means of recognizing sign language. Sign language is used to convey different meanings through visual-manual methods. Hand gestures help the hearing impaired to communicate. Nevertheless, it is very difficult to achieve a high recognition rate of hand gestures due to the environment and physical anatomy of human beings such as light condition, hand size, position, and uncontrolled environment. Moreover, the recognition of appropriate gestures is currently considered a major challenge. In this context, this paper proposes a probabilistic soft voting-based ensemble model to recognize Bengali sign gestures. We have divided this study into pre-processing, data augmentation and ensemble model-based voting process, and classification for gesture recognition. The purpose of pre-processing is to remove noise from input images, resize it, and segment hand gestures. Data augmentation is applied to create a larger database for in-depth model training. Finally, the ensemble model consists of a support vector machine (SVM), random forest (RF), and convolution neural network (CNN) is used to train and classify gestures. Whereas, the ReLu activation function is used in CNN to solve neuron death problems and to accelerate RF classification through principal component analysis (PCA). A Bengali Sign Number Dataset named “BSN-Dataset” is proposed for model performance. The proposed technique enhances sign gesture recognition capabilities by utilizing segmentation, augmentation, and soft-voting classifiers which have obtained an average of 99.50% greater performance than CNN, RF, and SVM individually, as well as significantly more accuracy than existing systems.
... Once information regarding each class is achieved, the image is categorized by observing each pixel and checking which signature it resembles the most. To implement this, some classification algorithms and regression techniques including linear regression [9], logistic regression [11], neural networks(NN) [12], decision tree [13], support vector machine [14], random forest [15,16], naive Bayes [14][15][16], and k-nearest neighbour [17][18][19][20] have been proposed. Unsupervised learning algorithms include clustering, detection of anomaly, techniques to learn latent variable models [21][22][23]. ...
... Once information regarding each class is achieved, the image is categorized by observing each pixel and checking which signature it resembles the most. To implement this, some classification algorithms and regression techniques including linear regression [9], logistic regression [11], neural networks(NN) [12], decision tree [13], support vector machine [14], random forest [15,16], naive Bayes [14][15][16], and k-nearest neighbour [17][18][19][20] have been proposed. Unsupervised learning algorithms include clustering, detection of anomaly, techniques to learn latent variable models [21][22][23]. ...
In computer vision, object classification is the most essential stage for recognizing the class of the image using its features. Many models have been presented in the last few years for the classification of still images. A simple linear classification technique with moderate accuracy and low run-time complexity for still images is proposed in this paper. The proposed scheme is compared with the other state-of-the-art techniques and experimental results show the effectiveness of the proposed scheme in terms of time complexity. Thus, the proposed work can be proved beneficial for real-time applications where low computational time is required.KeywordsArtificial neural network (ANN)Support vector machine (SVM)Logistic regression (LR)Run-time complexityData classification
... For all methods in comparison, such as RF, MLP, LightGBM, CatBoost, XGBoost, and CAE, parameters were estimated according to [28][29][30][31][32]35,41,53,54]. For our proposed methods, the Adam optimizer was used to estimate the optimal parameters. ...
... Classification accuracies in terms of overall accuracy, average accuracy, Kappa coefficients, and per-class accuracy are enlisted in Tables 8-13. It can be observed that TabNet shows better classification accuracy than the other methods of RF [28][29][30], MLP [35], LightGBM [54], CatBoost [53], and XGBoost [31,32]. In addition, TabNet with spatial attention (TabNets) and its unsupervised pretrained version (uTabNets) outperform TabNet and its unsupervised version uTabNet in all three datasets. ...
Tree-based methods and deep neural networks (DNNs) have drawn much attention in the classification of images. Interpretable canonical deep tabular data learning architecture (TabNet) that combines the concept of tree-based techniques and DNNs can be used for hyperspectral image classification. Sequential attention is used in such architecture for choosing appropriate salient features at each decision step, which enables interpretability and efficient learning to increase learning capacity. In this paper, TabNet with spatial attention (TabNets) is proposed to include spatial information, in which a 2D convolution neural network (CNN) is incorporated inside an attentive transformer for spatial soft feature selection. In addition, spatial information is exploited by feature extraction in a pre-processing stage, where an adaptive texture smoothing method is used to construct a structure profile (SP), and the extracted SP is fed into TabNet (sTabNet) to further enhance performance. Moreover, the performance of TabNet-class approaches can be improved by introducing unsupervised pretraining. Overall accuracy for the unsupervised pretrained version of the proposed TabNets, i.e., uTabNets, can be improved from 11.29% to 12.61%, 3.6% to 7.67%, and 5.97% to 8.01% in comparison to other classification techniques, at the cost of increases in computational complexity by factors of 1.96 to 2.52, 2.03 to 3.45, and 2.67 to 5.52, respectively. Experimental results obtained on different hyperspectral datasets demonstrated the superiority of the proposed approaches in comparison with other state-of-the-art techniques including DNNs and decision tree variants.
... Machine learning architectures [10] such as Support Vector machines, Boosting and Bagging algorithms and Random Forests perform this analysis by assigning sentiment scores to the categories, within a phrase in a sentence used to determine its polarity. [12] is shown between January 2017 and December 2020, along with the pre-crash high on 12 February, and the subsequent crash during the COVID-19 pandemic and recovery to new highs later that year. ...
... Random Forests [11] are built using multiple decision trees merged together for an accurate and stable prediction. This algorithm also adds randomness to the data for enhancing its performance, while training using the data bagging algorithm [12]. Having low bias and a property of high variance, the splitting of nodes is done by selecting the best performing feature from the generated subset of features. ...
Mapping the variations of stock prices in the market has proven to be a challenge to, considering impact of macroeconomic factors, such as news headlines on them. In this paper, a novel framework is implemented for predicting the effect of rate of change of stock prices through news sentiment by using a standard dataset with closing stock price rates for a chosen period. Random Forest classifier to extract the sentiments from day-today news articles to identify their polarity as positive, or negative. Bi-directional Long Short-Term models are implemented to map the sliding windows of prices along with corresponding sliding windows of sentiment scores of the articles. Thus, hybrid architecture that combines a Bi-LSTM based time series prediction model with a Random Forest based sentiment analysis model is developed and compared with some of the existing state-of-the-art methodologies. The polarity of news sentiment is determined with an accuracy of 84.92% and the price prediction model performs best with 10 headlines achieving a R-squared score of 74.84%.
... It was concluded that radial basis function RBF-SVM is more efficient compared with Linear-SVM, k-nearest neighbours (KNN), and other RBF kernel methods. Two classifiers based on the Random Forest (RF) methods were investigated in [18] to enhance generalisation in HSI classification. This study showed that applying RF ensembles instead of a single tree, enhance classification accuracy. ...
... For each method we optimised hyperparameters within the Nested-CV as shown in table IV. For HCapsNet to determine the best parameters, vector lengths n and m are selected between (n : 6,8,10) and (m : 14,16,18). The number of filters implemented in the 2D-CNN and 3D-CNN classifiers is chosen between 16, 32, 64. ...
Limited training data, high dimensionality, image complexity, and similarity between classes are the main challenges confronting Hyperspectral Image (HSI) classification which may result in suboptimal classification performance. To address such issues, here we introduce the Capsule Network (CapsNet) approach. CapsNet preserves the hierarchy between different parts of the entity in an image by replacing scalar representations with vectors. Motivated by CapsNet, this paper presents a novel end-to-end deep learning (DL) architecture, the Hybrid Capsule Network (HCapsNet), for HSI classification. HCapsNet employs 2D and 3D Convolutional Neural Networks (CNNs) to extract higher-level spatial and spectral features. In order to establish a route between capsules in the lower layers to the most-related capsule in the higher layer, dynamic routing (DR) is used to identify several overlapped objects during training sessions. Hyperparameter optimization is performed using nested cross-validation (Nested-CV) to ensure through generalisiation evaluation. The proposed HCapsNet significantly outperformed the state-of-the-art methods in terms of overall classification accuracy on three widely used hyperspectral datasets, Indian Pines dataset achieving (>3%, p < 110<sup>-8</sup>), the University of Pavia dataset (>4%, p< 110<sup>-6</sup>), the Salinas Valley dataset (>3%, p < 110<sup>-11</sup>) when using only 1% of the data for training. The performance of all CNN-based approaches degraded significantly with smaller training sample sizes. HCapsNet, therefore, offers significant potential in situations with low sample sizes outperforming state-of-the-art methods.
... Thus, it is difficult to accurately extract lithological spectral features in hyperspectral images containing many high-dimensional spectral channels. Compared with traditional feature selection methods, tree-based methods, such as random forest (RF) [38,39], gradient boosting decision tree (GBDT) [40,41], and Light Gradient Boosting Machine (Light GBM) [42,43], can extract the optimal feature system that suits the needs of the model in a more targeted way, and their decision-making process is more similar to human thinking, making the model easy to understand. Its dimensional reduction speed is fast, and it can process continuous and discrete data and solve the multi-output problem. ...
Lithology classification is important in mineral resource exploration, engineering geological exploration, and disaster monitoring. Traditional laboratory methods for the qualitative analysis of rocks are limited by sampling conditions and analytical techniques, resulting in high costs, low efficiency, and the inability to quickly obtain large-scale geological information. Hyperspectral remote sensing technology can classify and identify lithology using the spectral characteristics of rock, and is characterized by fast detection, large coverage area, and environmental friendliness, which provide the application potential for lithological mapping at a large regional scale. In this study, ZY1-02D hyperspectral images were used as data sources to construct a new two-layer extreme gradient boosting (XGBoost) lithology classification model based on the XGBoost decision tree and an improved greedy search algorithm. A total of 153 spectral bands of the preprocessed hyperspectral images were input into the first layer of the XGBoost model. Based on the tree traversal structural characteristics of the leaf nodes in the XGBoost model, three built-in XGBoost importance indexes were split and combined. The improved greedy search algorithm was used to extract the spectral band variables, which were imported into the second layer of the XGBoost model, and the bat algorithm was used to optimize the modeling parameters of XGBoost. The extraction model of rock classification information was constructed, and the classification map of regional surface rock types was drawn. Field verification was performed for the two-layer XGBoost rock classification model, and its accuracy and reliability were evaluated based on four indexes, namely, accuracy, precision, recall, and F1 score. The results showed that the two-layer XGBoost model had a good lithological classification effect, robustness, and adaptability to small sample datasets. Compared with the traditional machine learning model, the two-layer XGBoost model shows superior performance. The accuracy, precision, recall, and F1 score of the verification set were 0.8343, 0.8406, 0.8350, and 0.8157, respectively. The variable extraction ability of the constructed two-layer XGBoost model was significantly improved. Compared with traditional feature selection methods, the GREED-GFC method, when applied to the two-layer XGBoost model, contributes to more stable rock classification performance and higher lithology prediction accuracy, and the smallest number of extracted features. The lithological distribution information identified by the model was in good agreement with the lithology information verified in the field.
... In the initial exploration of hyperspectral image classification, researchers primarily focused on the spectral information contained within these images, which can effectively capture and reflect the internal mechanisms and chemical composition of ground objects. Specifically, traditional classification methods have harnessed the abundance of bands in hyperspectral images to execute machine learning algorithms for classification purposes with great efficacy, including random forest [13], decision trees [14], support vector machine [15] and K-nearest neighbor [16] algorithms. Relying solely on spectral information, these methods are capable of performing simple classification without the need for feature extraction. ...
... Similarly, machine learning technology has been successfully applied to hyperspectral image classification tasks. Many algorithms for HSI classification have been developed in recent decades, including morphology morphology [4,5,34], k-means [13], Gaussian process [3], support vector machine [42], random forest [47], extreme machine learning [14] and so on. Bandos et al. [2] developed a regularized linear discriminant analysis, which converts the data subspace into a linear molecular space. ...
Convolutional Neural Network(CNN) has been widely employed in hyperspectral image(HSI) classification. However, CNN cannot attain the relative location relation of spatial information well, hindering the further improvement of classification performance. Capsule Network(CapsNet) has been presented recently and represents features by vectors, which enhances the ability to attain feature space information and identify relative positions, and makes up for the shortcomings of CNN. To further improve the classification performance of HSI using CapsNet under limited labeled samples, this article proposes a multi-scale residual capsule network(MR-CapsNet). The proposed method adopts extended multi-scale convolution blocks to fully extract spectral-spatial features. Subsequently, the features extracted by convolution kernels of different sizes are fused by pointwise convolution. The residual structure is used for splicing with the input data, preventing the problem of vanishing gradients and overfitting. Finally, the fused feature information is classified at the capsule layer through the dynamic routing mechanism. Comparative experiments were carried out on three public datasets of hyperspectral images. The experimental results indicate that the overall classification accuracy of the proposed method has a 4.13%, 2.98%, and 1.43% improvement over the recent DC-CapsNet on three datasets, respectively.
... The RF algorithm has been widely used in remote sensing image classification. Xia et al. [51] proposed a Bagging RF (B-RF), which achieved good results in the HRS image classification. ...
This research explores a new hyperspectral remote sensing processing method that combines remote sensing and ground data, and builds a model based on a novel 3D convolutional neural network and fusion data. The method can monitor and map changes in iron ore stopes. First, we used an unmanned aerial vehicle-borne hyperspectral imager to take a hyperspectral image of the iron ore stope; second, collected iron ore samples and then used a ground-based spectrometer to measure the spectral data of these samples; third, combined the hyperspectral remote sensing data with the ground data and then proposed a data augmentation method. Fourth, based on the 3D convolutional neural network and deep residual network, an iron ore stope classification model is proposed. Finally, the model is applied to monitor and map iron ore stopes. The experimental results show that the proposed method is effective, and the overall accuracy is 99.62% for the five-class classification problem. The method provides a quick, accurate, and low-cost way to monitor iron ore stopes.
... Junshi Xia và cộng sự (2017) (Xia et al., 2017) đã sử dụng rừng ngẫu nhiên để phân loại hình ảnh. Trong công trình này, nhóm tác giả đã thực hiện một phương pháp phân loại hình ảnh bằng rừng ngẫu nhiên mở rộng nhằm nâng cao hiệu suất phân loại hình ảnh. ...
Trong bài báo này, một phương pháp phân lớp hình ảnh dựa trên cấu trúc KD-Tree Random Forest được đề xuất nhằm thực hiện phân lớp ảnh bằng nhiều cấu trúc KD-Tree độc lập. Trong đó, mỗi cấu trúc KD-Tree được sử dụng phân lớp nhiều lần cho một ảnh đầu vào theo mô hình phân lớp đa tầng. Quá trình phân lớp ảnh dựa trên cấu trúc KD-Tree Random Forest thực hiện theo phương pháp xây dựng cấu trúc KD-Tree Random Forest và huấn luyện bộ vector phân lớp. Vì vậy các thuật toán phân lớp hình ảnh dựa trên cấu trúc KD-Tree Random Forest, huấn luyện bộ véc-tơ phân lớp và mô hình phân lớp ảnh được đề xuất. Dựa trên cơ sở lý thuyết này, thực nghiệm được xây dựng trên bộ ảnh Clatech256 và so sánh với các công trình khác cùng bộ dữ liệu để minh chứng tính khả thi của phương pháp đề xuất. Theo kết quả thực nghiệm cho thấy phương pháp của chúng tôi là hiệu quả và có thể áp dụng được cho các hệ phân loại hình ảnh thuộc các lĩnh vực khác nhau.
... The First phase is feature extraction [2]; we will use different methods such as histogram gradients, HOG [3], and convolution neural network CNN [4]. The second phase is the classification mode used as support vector machine SVM [5] and Random Forest RF ensemble learning methods [6]. In the third phase, we will use clustering methods such as structural similarity index matrix SSIM [7] to put output images into similar groups to begin the final step, which is to analyze and recognize the nature of objects in the images to be as input for automated recognition system used in applications such mentioned above for CCTV system [27] and other systems that required to detect and recognize the objects on images. ...
Feature extraction is the most vital step in image classification to produce high-quality and good content images for further analysis, image detection, segmentation, and object recognition. Using machine learning algorithms, profound learning like convolutional neural network CNN became necessary to train, classify, and recognize images and objects like humans. Combined feature extraction and machine learning classification to locate and identify objects on images can then be an input of automatic recognition systems ATR such as surveillance systems CCTV, to enhance these systems and reduce time and effort for object detection and recognition in images based on digital image processing techniques especially image segmentation that differentiate from computer vision approach. This article will use machine learning and deep learning algorithms to facilitate and achieve the study's objectives.
... The dataset consisted of common rust, leaf spot, northern leaf blight disease images, and healthy images. The whole training dataset consisted of 7308 images,1634 images for leaf spot, 1907 images for common rust,1908 images for northern leaf blight, and 1859 for healthy leaf images [21]. The whole testing dataset consisted of 1826 images, 407 images for leaf spot, 477 images for common rust, 477 images for northern leaf blight, and 465 for healthy leaf images. ...
The paper presents feature extraction methods and classification algorithms used to classify maize leaf disease images. From maize disease images, features are extracted and passed to the machine learning classification algorithm to identify the possible disease based on the features detected using the feature extraction method. The maize disease images used include images of common rust, leaf spot, and northern leaf blight and healthy images. An evaluation was done for the feature extraction method to see which feature extraction method performs best with image classification algorithms. Based on the evaluation, the outcomes revealed Histogram of Oriented Gradients performed best with classifiers compared to KAZE and Oriented FAST and rotated BRIEF. The random forest classifier emerged the best in terms of image classification, based on four performance metrics which are accuracy, precision, recall, and F1-score. The experimental outcome indicated that the random forest had 0.74 accuracy, 0.77 precision, 0.77 recall, and 0.75 F1-score.
... As already shown in [112], random forest can considerably improve the performance by increasing the number of spectral bands in high spatial resolution images. Moreover, the random forest algorithm not only offers significant performance for dealing with multi-dimensional complex data [113], [114], but also requires only slight parameter tuning [115]. Therefore, random forest is more likely to be robust to performance degradation when multiple bands are used. ...
Forests can be efficiently monitored by automatic semantic segmentation of trees using satellite and/or aerial images. Still, several challenges can make the problem difficult, including the varying spectral signature of different trees, lack of sufficient labelled data, and geometrical occlusions. In this paper, we address the tree segmentation problem using multispectral imagery. While we carry out large-scale experiments on several deep learning architectures using various spectral input combinations, we also attempt to explore whether hand-crafted spectral vegetation indices can improve the performance of deep learning models in the segmentation of trees. Our experiments include benchmarking a variety of multispectral remote sensing image sets, deep semantic segmentation architectures, and various spectral bands as inputs, including a number of hand-crafted spectral vegetation indices. From our large-scale experiments, we draw several useful conclusions. One particularly important conclusion is that, with no additional computation burden, combining different categories of multispectral vegetation indices, such as NVDI, ARVI, and SAVI, within a single three-channel input, and using the state-of-the-art semantic segmentation architectures, tree segmentation accuracy can be improved under certain conditions, compared to using high-resolution visible and/or nearinfrared input.
... Boualleg et al. [10] proposed an integrated learning-based deep forest (DF) model that fully uses the CNN's capability to extract features and DF classification interpretability to mine high-quality information from remote sensing scene images. A random forest classifier for hyperspectral remote sensing image classification was proposed in [28,29], improving classification performance. However, the forest becomes intractable because of the decision paths that follow the set of trees, thus sacrificing the intrinsic interpretability of the decision tree intuition. ...
Remote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. Here, we propose a bidirectional flow decision tree (BFDT) module to create a reliable RS scene classification framework. Our algorithm combines BFDT and Convolutional Neural Networks (CNNs) to make the decision process easily interpretable. First, we extract multilevel feature information from the pretrained CNN model, which provides the basis for constructing the subsequent hierarchical structure. Then the model uses the discriminative nature of scene features at different levels to gradually refine similar subsets and learn the interclass hierarchy. Meanwhile, the last fully connected layer embeds decision rules for the decision tree from the bottom up. Finally, the cascading softmax loss is used to train and learn the depth features based on the hierarchical structure formed by the tree structure that contains rich remote sensing information. We also discovered that superclass results can be obtained well for unseen classes due to its unique tree structure hierarchical property, which results in our model having a good generalization effect. The experimental results align with theoretical predictions using three popular datasets. Our proposed framework provides explainable results, leading to correctable and trustworthy approaches.
... In the last few years, a great many of supervised methods have been proposed for HSI classification. In the early stage, many methods based on machine learning are used, such as Support Vector Machine (SVM) (Melgani and Bruzzone 2004), Random Forest (Xia et al. 2017), Multiple Logistic Regression (Li, Bioucas-Dias and Plaza 2012) and weighted Markov random Fields (Sun et al. 2014). However, these methods only utilize spectral features from pixels and rely on handcrafted feature heavily. ...
Hyperspectral image (HSI) contains hundreds of contiguous spectral bands compared with red green blue (RGB) image, making the precise identification of materials possible by capturing subtle spectral and spatial features. Owing to the special advantage in image processing, convolutional neural networks (CNNs) have been proven to be a successful architecture in HSI classification. However, due to the limitation of receptive field of fixed convolution kernel, CNNs can only extract local features of hyperspectral image. Besides, CNNs fail to mine and represent the sequence attributes of spectral bands because of the limitations of its inherent network backbone. With the emergence of vision transformer, the network can break through the limitation of receptive field and obtain the global correlation of the whole image, but it only focuses on the global information of the object and ignores the local information existing in the sequence and images. Moreover, the correlation of spectral information will be destroyed if traditional methods are directly used to convert hyperspectral images into sequence. To solve this issue, a novel convolution and vision transformer fusion network called CAVFN is devised which contains a new cube-embedding module that can reduce the loss of spectral information effectively by dividing the large HSI cube into several small cubes and encoding them into sequences. More significantly, this paper also combines 1D-CNN and 2D-CNN with vision transformer to extract the local features of sequences and patches, and combines them with global features to obtain better classification results. Finally, this paper evaluates the classification results of the proposed network on three HSI datasets by conducting extensive experiments, showing that our network outperforms other state-of-the-art methods.
... • Random forest (RF) is a meta classifier that combines a multitude of decision trees on various subsamples of the data set and uses randomness and averaging to improve the classification performance and avoid overfitting (Breiman, 2001). In recent image classification tasks, RF has shown good performance in hyperspectral image classification (Xia et al., 2017) and remote sensing image classification (Imani, 2020). The RF is configured with 100 trees without limiting the tree depth and Gini as the splitting criteria. ...
Sourness is one of the basic yet essential tastes of coffee that is chemically composed of acids and quantitatively represented in the pH scale. Current tools for measuring the acidity level in roasted coffee beans, including traditional methods, require brewing sample coffee and probing the chemical components, limiting the applicability to end customers seeking to estimate the acidity level before choosing the right coffee beans to purchase. This paper proposes a novel approach to directly estimate the acidity levels from roasted coffee beans images by framing the problem into an image classification task, where a picture of roasted coffee beans is categorized into its appropriate pH range. As a result, end customers could simply estimate coffee beans' acidity levels by taking photos with conventional cameras. Multiple traditional machine learning and deep learning algorithms are validated for their ability to predict the correct acidity levels. The experiment results reveal that EfficientNet yields the best performance with an average F1 of 0.71 when trained with images from separate portable devices.
Practical Applications
The research's findings could also be extended to applications in the coffee‐industrial settings, such as automatically monitoring roasted coffee beans' quality from image and video streams. For end customers, the trade‐off between efficacy and efficiency of the EfficientNet algorithm is also investigated, which sheds light on the implementation aspects of state‐of‐the‐art deep learning models in portable devices such as smartphones or cameras. Such applications could prove to be a cost‐effective and convenient solution for customers to quickly measure roasted coffee beans' sourness before deciding to purchase.
... Therefore, ensemble learning-based methods can produce more robust classification results. There are a series of shallow ensemble learning methods: ensemble frameworks based on k-nearest class collaborative representation [33], ensemble SVM [34], [35], ensemble extreme learning machine (ELM) [36], [37], random forest [38], rotation forest [39], [40], and so on. For example, Waske et al. [34] constructed an ensemble framework by integrating SVM and random subspace (RS) strategy. ...
With the continuous progress of computer deep learning technology, convolutional neural network (CNN), as a representative approach, provides a unique solution for hyperspectral image (HSI) classification. However, the parameters of CNN cannot be well-tuned when the number of training samples is insufficient, resulting in unsatisfactory classification performance. To tackle the thorny problem, a deep ensemble CNN method based on sample expansion for HSI classification is studied in this article. In particular, spatial information is first extracted and fused with original spectral bands to help classifiers obtain discriminant spectral–spatial features. Then, we use the pixel-pair feature (PPF) to expand the number of training samples so that the parameters of CNN structure can be fully trained. In addition, deep ensemble CNN is employed in this article, enabling the trained model to obtain better generalization ability and more robust classification results. Ultimately, the proposed method is applied to classify four widely used hyperspectral datasets. Experimental results show that the studied approach yields higher classification accuracy than some CNN-based methods even under the condition of small-size training set.
... The dataset consisted of common rust, leaf spot, northern leaf blight disease images, and healthy images. The whole training dataset consisted of 7308 images,1634 images for leaf spot, 1907 images for common rust,1908 images for northern leaf blight, and 1859 for healthy leaf images [21]. The whole testing dataset consisted of 1826 images, 407 images for leaf spot, 477 images for common rust, 477 images for northern leaf blight, and 465 for healthy leaf images. ...
The paper presents feature extraction methods and classification algorithms used to classify maize leaf disease images. From maize disease images, features are extracted and passed to the machine learning classification algorithm to identify the possible disease based on the features detected using the feature extraction method. The maize disease images used include images of common rust, leaf spot, and northern leaf blight and healthy images. An evaluation was done for the feature extraction method to see which feature extraction method performs best with image classification algorithms. Based on the evaluation, the outcomes revealed Histogram of Oriented Gradients performed best with classifiers compared to KAZE and Oriented FAST and rotated BRIEF. The random forest classifier emerged the best in terms of image classification, based on four performance metrics which are accuracy, precision, recall, and F1-score. The experimental outcome indicated that the random forest had 0.74 accuracy, 0.77 precision, 0.77 recall, and 0.75 F1-score.
... The earlier feature extraction methods are designed manually with the help of machine learning methods for HSI classification. For example, principal component analysis (PCA) [12], random forest (RF) [13] and support vector machine (SVM) [14] based on the spectral information were proposed. Morphological profiles (MPs) [15], Markov random field [16] and 2D Gabor filters [17] based on the spatial information were proposed. ...
Deep learning has achieved impressive results on hyperspectral image (HSI) classification. Among them, both convolutional neural networks (CNNs) and graph neural networks (GNNs) have great potential for HSI classification. Supervised CNNs can efficiently extract hierarchical spatial-spectral features of HSIs, but these methods face the problem of high time complexity as the number of network layers increases. Semisupervised GNNs can rapidly capture the structural information of HSIs, while they cannot be well extended to HSI applications because of the process of adjacency matrix consuming large amount of memory resources. In this article, we propose a fast dynamic graph convolutional network and CNN (FDGC) parallel network for HSI classification. We first obtain two classification features by flattening and pooling operations on the results of the convolution layers, which fully exploits the spatial-spectral information contained in the hyperspectral data cube. Then, a dynamic graph convolution module is applied to extract the intrinsic structural information of each patch. Finally, we can obtain the HSI classification results based on these spatial, spectral, and structural features. By using three branches, FDGC can parallelly process multiple features of HSI in a supervised learning manner. In addition, regularization techniques, such as DropBlock and label smoothing, are applied to further improve the generalization capability of the model. Experimental results on three datasets show that our proposed algorithm is comparable with the state-of-the-art supervised learning models in terms of accuracy while also significantly outperforming in terms of training and inference time.
... Dense Convolution Neural Network classifiers model on basis of dynamic strategies to yield efficient performance than any CNN classifiers. The land cover classification with multiple classes is considered as final outcome of the proposed model [9]. ...
Hyperspectral Imaging is employed to monitor the earth regions on basis of spectral continuous data ranges initializing from visible wave infrared region to short wave infrared region of the electromagnetic spectrum. It authorizes the detailed recognition and classification of land cover on account of spectral feature space. Hyperspectral images seemed to be presented by employing traditional unsupervised and supervised classifier with regards to classification. Various problems seemed to cause Hughes phenomenon as it represents the curse of dimensionality issues. In spite of mitigating those challenges, a deep ensemble classification model seemed to be proposed in this work. It process the data features using various convolution layers of the network along modelling the activation function as a simple structure for classification of the hyperspectral data based on the spectral values using Softmax layer and error function to minimize the losses. Dense Connected Convolution Neural Network projected in this work as it has high potential to effectively classify the spectral features with learnt weights from one individual convolution layer to convolution layers. The main idea of Dense Convolution Neural Network is to produce discriminative classification results and to enhance the accuracy and diversity of a classifier simultaneously.
... Due to the rich information present in HSIs, it is applied in various other domains like intrusion detection in border areas, mineral mapping, quantification of soil properties, etc. Classification of HSIs is a popular domain in remote sensing. Every object has a unique spectral signature, due to which there are many spectral matching techniques used in which the most employed distance metrics are cosine angle similarity [30], Euclidean distance, spectral correlation mapper [2] etc. Machine learning techniques like the random forest, decision trees [34], Support Vector Machine (SVM) [4] can also be employed for classification. But due to the curse of dimensionality, these algorithms cannot form meaningful connections, which results in lower classification accuracy. ...
Hyperspectral images constitute a substantial amount of data in the form of spectral bands. This information is used for land cover analysis, specifically in classifying a hyperspectral pixel, which is a popular domain in remote sensing. This paper proposed an efficient framework to classify spectral-spatial hyperspectral images by employing multiobjective optimization. Spectral-spatial features of hyperspectral images are passed for optimization. As hyperspectral images have a high dimensional feature set, many classifiers cannot perform well. Multiobjective optimization reduces the feature set without affecting the discrimination ability of the classifier. The proposed work is validated on a standard hyperspectral image set, Pavia University and Kennedy Space Centre.
... Due to the high spectral resolution of hyperspectral images, there must be redundant bands. Principal component analysis [6] and independent component analysis [7] are widely used for redundancy elimination and have achieved good results.In the early stage of research, people mostly combine manual feature extraction methods with traditional classifiers, such as Logistic regression [8], decision tree [9], random forest [10], and SVM [11] to classify the ground objects by spectral information.However, the imaging distance of HSI is distant and there are many inference factors in this process. Therefore, the spectral curve of different surface objects is not always easy to distinguish. ...
Hyperspectral images (HSI) not only have a broad macroscopic field of view but also contain rich spectral information, and the types of surface objects can be identified through spectral information, which is one of the main applications in hyperspectral image related research.In recent years, more and more deep learning methods have been proposed, among which convolutional neural networks (CNN) are the most influential. However, CNN-based methods are difficult to capture long-range dependencies, and also require a large amount of labeled data for model training.Besides, most of the self-supervised training methods in the field of HSI classification are based on the reconstruction of input samples, and it is difficult to achieve effective use of unlabeled samples. To address the shortcomings of CNN networks, we propose a noval multi-scale convolutional embedding module for HSI to realize effective extraction of spatial-spectral information, which can be better combined with Transformer network.In order to make more efficient use of unlabeled data, we propose a new self-supervised pretask. Similar to Mask autoencoder, but our pre-training method only masks the corresponding token of the central pixel in the encoder, and inputs the remaining token into the decoder to reconstruct the spectral information of the central pixel.Such a pretask can better model the relationship between the central feature and the domain feature, and obtain more stable training results.
... 12], and random forest (RF) [13]. However, with these methods, the spectral and spatial information are usually processed separately, and different land-covers cannot be distinguished accurately by employing the spectral features only [14]. ...
With limited number of labeled samples, hyperspectral image (HSI) classification is a difficult Problem in current research. The graph neural network (GNN) has emerged as an approach to semi-supervised classification, and the application of GNN to hyperspectral images has attracted much attention. However, in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features, which does not take full advantage of various graph neural networks (graph filters). Moreover, the traditional GNNs have the problem of oversmoothing. To alleviate these shortcomings, we introduce a deep hybrid multi-graph neural network (DHMG), where two different graph filters, i.e., the spectral filter and the autoregressive moving average (ARMA) filter, are utilized in two branches. The former can well extract the spectral features of the nodes, and the latter has a good suppression effect on graph noise. The network realizes information interaction between the two branches and takes good advantage of different graph filters. In addition, to address the problem of oversmoothing, a dense network is proposed, where the local graph features are preserved. The dense structure satisfies the needs of different classification targets presenting different features. Finally, we introduce a GraphSAGE-based network to refine the graph features produced by the deep hybrid network. Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-of-the-art models.
... In addition, image quality is a big concern in the area of multi-spectral image classification. To tackle this pitfall, the research community proposed different approaches such as denoising [25,41,42] feature reconstruction, superresolution methodologies and image recovering technique. On the other hand, Xia and his colleague [43] the proposed Random Forest ensemble where extended multi-extinction profiles are implemented to improve classification performance. ...
Higher dimensionality, Hughes phenomenon, spatial resolution of image data, and presence of mixed pixels are the main challenges in a multi-spectral image classification process. Most of the classical machine learning algorithms suffer from scoring optimal classification performance over multi-spectral image data. In this study, we propose stack-based ensemble-based learning approach to optimize image classification performance. In addition, we integrate the proposed ensemble learning with XGBoost method to further improve its classification accuracy. To conduct the experiment, the Landsat image data has been acquired from Bishoftu town located in the Oromia
region of Ethiopia. The current study’s main objective was to assess the performance of land cover and land use analysis using multi-spectral image data. Results from our experiment indicate that, the proposed ensemble learning method outperforms any strong base classifiers with 99.96% classification performance accuracy.
... By effectively improving the accuracy of image description and the precision of image classification [20], combines the principal component analysis (PCA) and processed scale-invariant feature transform (P-SIFT). However, machine learning methods have been developing in RS, such as the support vector machine (SVM) [21] iterative self-organizing data analysis (ISOTA) [22], back propagation [23], random forest [24], harming distance [25] and multiscale segmentation [26]. ...
Remote sensing scene classification is a fundamental responsibility of earth observation, aiming to identify information granular for land cover classification. The multi-granular land use for multi-source remotely sensed image categories is now a principal task in remote sensing data augmentation and data selection. Understanding image representations are meaningful for the scene classification task. Training deep learning model-based approaches has to do with scene classification and brings about fantastic achievement. At the same time, these high-level approaches are computationally expensive and time–consuming. This paper introduces multi-granularity Neural Network Encoding architecture base on InceptionV3, InceptionReseNetV2, VGG16, and DenseNet201 architecture into remote sensing scene classification. To improve performance and to solve intra-class variation for multi-class scene issues remote sensing dataset. By using pre-trained CNN, activation function and ensemble learning have been adopting. InceptionV3 and VGG16 are used to extract features. InceptionResNetV2 use for fine-tuning, which consists of unfreezing the entre model and retraining the new data with a lower learning rate. The proposed fine-tune whole pre-trained model produces better results of test set up to 97.84 % than features extracted by InceptionResNetV2. Also, we use DCNNs ensemble average and weighted average to achieve better outcomes for 97.3.6% and 99.10%. In our experiments, we attempted to fine-tune the deep convolutional neural networks (DCNNs) training method for remote sensing scene classification on two public datasets UCM, SIRI-WHU, and one dataset I collected through the google earth engine from East Africa Community Countries (EACC) within nine classes within total 2112 labeled images. The results indicate that our proposed fine-tuning of the pre-trained model with few epochs and less computational time increases accuracy.
Recent years, in order to solve the problem of lacking accurately labeled hyperspectral image data, self-supervised learning has become an effective method for hyperspectral image classification. The core idea of self-supervised learning is to define a pretext task which helps to train the model without the labels. By exploiting both the information of the labeled and unlabeled samples, self-supervised learning shows enormous potential to handle many different tasks in the field of hyperspectral image processing. Among the vast amount of self-supervised methods, contrastive learning and masked autoencoder are well known because of their impressive performance. This article proposes a Transformer based masked autoencoder using contrastive learning (TMAC), which tries to combine these two methods and improve the performance further. TMAC has two branches, the first branch has an encoder-decoders structure, it has an encoder to capture the latent image representation of the masked hyperspectral image and two decoders where the pixel decoder aims to reconstruct the hyperspectral image at pixel-level and the feature decoder is built to extract the high-level feature of the reconstructed image. The second branch consists of a momentum encoder and a standard projection head to embed the image into the feature space. Then, by combining the output of feature decoder and the embedding vectors via contrastive learning to enhance the model’s classification performance. According to the experiments, our model shows powerful feature extraction capability and gets outstanding results on hyperspectral image datasets.
One of the major difficulties for hyperspectral imagery (HSI) classification is the hyperspectral-heterospectra, which refers to the same material presenting different spectra. Although joint spatial-spectral classification methods can relieve this problem, they may lead to falsely high accuracy because the test samples may be involved during the training process. How to address the hyperspectral-heterospectra problem remains a great challenge for pixel-wise hyperspectral imagery classification methods. Domain generalization is a promising technique that may contribute to the heterospectra problem, where the different spectra of the same material can be considered as several domains. In this paper, inspired by the theory of domain generalization, we provide a formulaic expression for hyperspectral-heterospectra. To be specific, we consider the spectra of one material as a conditional distribution and propose a domain-generalization-based method for pixel-wise HSI classification. The key of our proposed method is a new Label-indicate-Conditional-alignment (LiCa) block that focuses on aligning the spectral conditional distributions of different domains. In the LiCa block, we define two loss functions, cross-domain conditional alignment, and cross-domain entropy, to describe the heterogeneity of HSI. Moreover, we have provided the theoretical foundation for the newly-proposed loss functions, by analyzing the upper bound of classification error in any target domains. Experiments on several public data sets indicate that the LiCa block has achieved better generalization performance when compared with other pixel-wise classification methods.
The Hyperspectral Image (HSI) classification aims to assign each pixel to a land cover category. It is receiving increasing attention from both industry and academia. The main challenge lies in capturing reliable and informative spatial and spectral dependencies concealed in the HSI for each class. To address the challenge, we propose a Spatial-Spectral 1DSwin Transformer with Group-wise Feature Tokenization (SS1DSwin) for HSI classification. Specifically, we reveal local and hierarchical spatial-spectral relationships from two different perspectives. It mainly consists of a Group-wise Feature Tokenization Module (GFTM) and a 1DSwin Transformer with Cross-block Normalized Connection Module (TCNCM). For GFTM, we reorganize an image patch into overlapping cubes, and further generate group-wise token embeddings with Multi-head Self-Attention (MSA) to learn the local spatial-spectral relationship along the spatial dimension. For TCNCM, we adopt the shifted windowing strategy when acquiring the hierarchical spatial-spectral relationship along the spectral dimension with 1D Window based Multi-head Self-Attention (1DW-MSA) and 1D Shifted Window based Multi-head Self-Attention (1DSW-MSA), and leverage Cross-block Normalized Connection (CNC) to adaptively fuse the feature maps from different blocks. In SS1DSwin, we apply these two modules in order and predict the class label for each pixel. To test the effectiveness of the proposed method, extensive experiments are conducted on four HSI datasets, and the results indicate that SS1DSwin outperforms several current state-of-the-art methods. The source code of the proposed method is available at https://github.com/Minato252/SS1DSwin.
The number of data points predicted correctly out of the total data points is known as accuracy in image classification models. Assessment of the accuracy is very important since it compares the correct images to the ones that have been classified by the image classification models. Image classification accuracy is a challenge since image classification models classify images to the class they don't belong to hence there is an inaccurate relationship between the predicted class and the actual class which results in a low model accuracy score. Therefore, there is a need for a model that can classify the images with the highest accuracy. The paper presents image classification models together with the feature extraction methods used to classify maize disease images.
Over the past decades, land‐cover classification has become a main topic in hyperspectral (HS) remote‐sensing applications. HS image can achieve much higher classification accuracies and is able to recognize more categories. This chapter focuses on the collaborative classification of HS‐centered multisource images, including HS image, high‐resolution panchromatic, and long‐wave infrared HS images. It reviews the current existing works of collaborative processing of multisource images and presents the main problems and challenges in multisource image collaborative processing. A comprehensive exploration of collaborative classification of multisource images is of great significance in enhancing the ability of data utilization and information acquisition, as well as the extension of the remote‐sensing application. The chapter focuses on a decision level‐based collaborative classification method for infrared HS and visible color images. High‐resolution images usually present more ground details, thereby making the extraction of finer detailed spatial information possible.
In recent years, hyperspectral image (HSI) classification methods based on generative adversarial networks (GANs) have been proposed and have made great progress, which can alleviate the dilemma of limited training samples. However, GAN-based HSI classification methods are heavily affected by the problem of imbalanced training data. The discriminator always tries to associate false labels with a few samples, which will reduce the classification accuracy. Another problem is the mode collapse based on the GAN network, which hinders the classification performance of HSI. A combined Transformer and GAN (TransGAN) model for HSI classification is proposed in this paper. First, in order to solve the problem of reduced classification accuracy caused by imbalanced training data, the discriminator is adjusted to a classifier with only one output. Second, the generator is constructed by using the Transformer, and the discriminator is added with a multi-scale pooling module (MSPM) to alleviate the problem of GAN model collapse. Experimental results on two HSI datasets show that the proposed TransGAN achieves better performance.
KeywordsMulti-scale pooling moduleTransformerGenerative adversarial networkHyperspectral image classification
Hyperspectral sensors provide an opportunity to capture the intensity of high spatial/spectral information and enable applications for high-level earth observation missions, such as accurate land cover mapping and target/object detection. Currently, convolutional neural networks (CNNs) are good at coping with hyperspectral image processing tasks because of the strong spatial and spectral feature extraction ability brought by hierarchical structures, but the convolution operation in CNNs is limited to local feature extraction in both dimensions. In the meanwhile, the introduction of the Transformer structure has provided an opportunity to capture long-distance dependencies between tokens from a global perspective; however, Transformer-based methods have a restricted ability to extract local information because they have no inductive bias, as CNNs do. To make full use of these two methods’ advantages in hyperspectral image processing, a dual-flow architecture named Hyper-LGNet to couple local and global features is firstly proposed by integrating CNN and Transformer branches to deal with HSI spatial-spectral information. In particular, a spatial-spectral feature fusion module (SSFFM) is designed to maximally integrate spectral and spatial information. Three mainstream hyperspectral datasets (Indian Pines, Pavia University and Houston 2013) are utilized to evaluate the proposed method’s performance. Comparative results show that the proposed Hyper-LGNet achieves state-of-the-art performance in comparison with the other nine approaches concerning overall accuracy (OA), average accuracy (AA) and kappa index. Consequently, it is anticipated that, by coupling CNN and Transformer structures, this study can provide novel insights into hyperspectral image analysis.
In recent years, convolutional neural networks have continuously dominated the downstream tasks on hyperspectral remote sensing images with its strong local feature extraction capability. However, convolution operations cannot effectively capture the long-range dependencies and repeatedly stacking convolutional layers to pursue a hierarchical structure can only make this problem alleviated but not completely solved. Meantime, the appearance of Transformer happens to cope with this problem and provides an opportunity to capture long-distance dependencies between tokens. Although Transformer has been introduced into HSI classification field recently, most of these related works only focus on exploiting a single kind of spatial or spectral information and neglect to explore the optimal fusion method for these two different-level features. Therefore, to fully exploit the abundant spatial information and spectral correlations in HSIs in a highly effective and efficient way, we present the initial attempt to explore the Transformer architecture in a dual-branch manner and propose a novel bilateral classification network named Hyper-ES²T. Besides, the Aggregated Feature Enhancement Module is proposed for effective feature aggregation and further spatial–spectral feature enhancement. Furthermore, to tackle the problem of high computational costs brought by vanilla self-attention block in Transformer, we design the Efficient Multi-Head Self-Attention block, pursuing the trade-off between model accuracy and efficiency. The proposed Hyper-ES²T reaches new state-of-the-art performance and outperforms previous methods by a significant margin on four benchmark datasets for HSI classification, which demonstrates the powerful generalization ability and superior feature representation capability of our Hyper-ES²T. It can be anticipated that this work provides a novel insight to design network architecture based on Transformer with superior performance and great model efficiency, which may inspire more following research in this direction of HSI processing field. The source codes will be available at https://github.com/Wenxuan-1119/Hyper-ES2T.
Recently, convolutional neural networks have demonstrated excellent prediction performance in hyperspectral image (HSI) classification. However, in traditional methods, the specific design of classification networks requires extensive professional knowledge, and the fixed network architecture lacks adaptability to different datasets. In this paper, a spectral feature perception evolving network (SFPEN), which is a dataset-oriented network method, is proposed. First, to overcome the drawbacks of traditional methods and improve the classification accuracy, an SFPEN driven by an evolutionary algorithm is proposed. The SFPEN automatically designs the network architecture based on a given HSI. Second, spectral feature perception modules are designed to extract the spectral features of HSIs and eliminate redundant information in the HSI narrow bands. Finally, a two-stage network fitness evaluation strategy is designed to reduce the number of training epochs of numerous networks and improve the efficiency of the network evaluation. The experimental results for the available datasets indicate that the proposed method achieves high classification accuracy and demonstrates great adaptability to different datasets.
Recent advances in airborne and space-based remote sensing technologies and a rapid increase in the use of machine learning (ML) techniques in digital image processing applications have led to a renewed interest in the classification of satellite imagery. Decision-tree based ensemble learning (EL) algorithms, one of the popular ML techniques, have received considerable attention from researchers due to their simplicity, computational effectiveness and interpretability compared to black-box algorithms. The main goal of this study is to evaluate the supervised classification performance of the advanced decision-tree based EL algorithms, including rotation forest (RotFor), random ferns (RFerns), canonical correlation forest (CCF), extreme gradient boosting (XGBoost), light gradient boosting machines (LightGBM) and categorical boosting (CatBoost) using satellite imagery with different spatial and spectral resolutions. Two well-known EL algorithms, namely, adaptive boosting (AdaBoost) and random forest (RF), were also considered to compare their classification performances. In order to achieve the desired goal, three satellite imagery, namely WorldView-2, Sentinel-2 and hyperspectral ROSIS, were utilized as the fundamental datasets. Results of the study showed that the highest overall accuracy values (i.e. 92.65% for WorldView-2, 92.80% for Sentinel-2 and 95.70% for Pavia datasets) were estimated using CCF, LightGBM and RotFor algorithms, respectively. According to McNemar’s test result, the difference between the predictions of RotFor and CCF algorithms on test samples of the hyperspectral image was found to be statistically insignificant. On the other hand, the lowest classification accuracy values were obtained by the RFerns algorithm in all cases. In addition, while the CCF showed superior classification performance for high spatial resolution WorldView-2 and Pavia images, the highest classification performance was acquired with the LightGBM algorithm for medium spatial resolution Sentinel-2 image. As a result, the performances of advanced EL algorithms were found to be more robust than the well-known RF and AdaBoost ensemble classifiers.
Hyperspectral image classification (HSIC) is essential in remote sensing image analysis. Applying a graph neural network (GNN) to hyperspectral image (HSI) classification has attracted increasing attention. However, the available GNNs for HSIC only adopt a kind of graph filter and an aggregator, which cannot well deal with the problems of land cover discrimination, noise impaction, and spatial feature learning. To overcome these problems, a graph convolution with adaptive filters and aggregator fusion (AF2GNN) is developed for HSIC. To reduce the number of graph nodes, a superpixel segment algorithm is employed to refine the local spatial features of the HSI. A two-layer 1D CNN is proposed to transform the spectral features of superpixels. In addition, a linear function is designed to combine the different graph filters, with which the graph filter can be adaptively determined by training different weight matrices. Moreover, degree-scalers are defined to combine the multiple filters and present the graph structure. Finally, the AF2GNN is proposed to realize the adaptive filters and aggregator fusion mechanism within a single network. In the proposed network, a softMax function is utilized for graph feature interpretation and pixel-label prediction. Compared with state-of-the-art methods, the proposed method achieves superior experimental results.
Land cover classification of mountainous environments continues to be a challenging remote sensing problem, owing to landscape complexities exhibited by the region. This study explored a multiple classifier system (MCS) approach to the classification of mountain land cover for the Khumbu region in the Himalayas using Sentinel-2 images and a cloud-based model framework. The relationship between classification accuracy and MCS diversity was investigated, and the effects of different diversification and combination methods on MCS classification performance were comparatively assessed for this environment. We present ten MCS models that implement a homogeneous ensemble approach, using the high performing Random Forest (RF) algorithm as the selected classifier. The base classifiers of each MCS model were developed using different combinations of three diversity techniques: (1) distinct training sets, (2) Mean Decrease Accuracy feature selection, and (3) ‘One-vs-All’ problem reduction. The base classifier predictions of each RF-MCS model were combined using: (1) majority vote, (2) weighted argmax, and (3) a meta RF classifier. All MCS models reported higher classification accuracies than the benchmark classifier (overall accuracy with 95% confidence interval: 87.33%±0.97%), with the highest performing model reporting an overall accuracy (±95% confidence interval) of 90.95%±0.84%. Our key findings include: (1) MCS is effective in mountainous environments prone to noise from landscape complexities, (2) problem reduction is indicated as a stronger method over feature selection in improving the diversity of the MCS, (3) although the MCS diversity and accuracy have a positive correlation, our results suggest this is a weak relationship for mountainous classifications, and (4) the selected diversity methods improve the discriminability of MCS against vegetation and forest classes in mountainous land cover classifications and exhibit a cumulative effect on MCS diversity for this context.
In only 2016, across the globe 17.9 million people died from cardiovascular diseases (CVDs) where 75% of CVDs deaths turn up from less and average income country like Bangladesh. In real-world perspective, cardiovascular surgery (CVS) is very expensive. Billions of dollar expense behind the CVS globally each year. According to statistics, three out of four people are affected in CVDs in Bangladesh, and one die in every 38 s in USA. We have developed a new idea for curing the CVDs via simulation. We have also developed algorithms, designed cost-effective new drugs and stimulus focusing the blocked vessels through angiogram and collected ECG data for observing blood flow, mass and heat transfer via simulation of heart and vessels. We used bio-fluid mechanics property (Navier–Stokes equations of Newtonian flow), BVP model and Hodgkin–Huxley (1952) mathematical model for heart simulation and transport phenomena of blood. We developed two new algorithms to design a primer individually. We have shown the genetic engineering techniques for pushing the condition on primer. Traditional CVS are time-consuming, risky and entirely not effective or accurate especially over seventy years old peoples. We wish to turn the method of traditional CVS into a simulation-based algorithm which is a time-saving, cost-effective and more accurate technique for curing CVDs.KeywordsCardiovascular diseases (CVDs)Cardiovascular surgery (CVS)StimulusAction potentialBlood flow velocityBVP modelLaminar flow
Given an aerial image, aerial scene parsing (ASP) targets to interpret the semantic structure of the image content, e.g., by assigning a semantic label to every pixel of the image. With the popularization of data-driven methods, the past decades have witnessed promising progress on ASP by approaching the problem with the schemes of tile-level scene classification or segmentation-based image analysis, when using high-resolution aerial images. However, the former scheme often produces results with tile-wise boundaries, while the latter one needs to handle the complex modeling process from pixels to semantics, which often requires large-scale and well-annotated image samples with pixel-wise semantic labels. In this paper, we address these issues in ASP, with perspectives from tile-level scene classification to pixel-wise semantic labeling. Specifically, we first revisit aerial image interpretation by a literature review. We then present a large-scale scene classification dataset that contains one million aerial images termed Million-AID. With the presented dataset, we also report benchmarking experiments using classical convolutional neural networks (CNNs). Finally, we perform ASP by unifying the tile-level scene classification and object-based image analysis to achieve pixel-wise semantic labeling. Intensive experiments show that Million-AID is a challenging yet useful dataset, which can serve as a benchmark for evaluating newly developed algorithms. When transferring knowledge from Million-AID, fine-tuning CNN models pretrained on Million-AID perform consistently better than those pretrained ImageNet for aerial scene classification. Moreover, our designed hierarchical multi-task learning method achieves the state-of-the-art pixel-wise classification on the challenging GID, bridging the tile-level scene classification toward pixel-wise semantic labeling for aerial image interpretation.
Hyperspectral image (HSI) classification using convolutional neural networks (CNNs) has always been a hot topic in the field of remote sensing. This is owing to the high level feature extraction offered by CNNs that enables efficient encoding of the features at several stages. However, the drawback with CNNs is that for exceptional performance, they need a deeper and wider architecture along with humongous amount of training data, which is often impractical and infeasible. Furthermore, the reliance on just forward connections leads to inefficient information flow that further limits the classification. Hence, to mitigate these issues, we propose a self-looping convolution network for more efficient HSI classification. In our method, each layer in a self-looping block contains both forward and backward connections, which means that each layer is the input and the output of every other layer, thus forming a loop. These loopy connections within the network allow for maximum information flow, thereby giving us a high level feature extraction. The self-looping connections enable us to efficiently control the network parameters, further allowing us to go for a wider architecture with a multiscale setting, thus giving us abstract representation at different spatial levels. We test our method on four benchmark hyperspectral datasets: Two Houston hyperspectral datasets (DFC 2013 and DFC 2018), Salinas Valley dataset and combined Pavia University and Centre datasets, where our method achieves state of the art performance (highest percentage kappa of 87.28%, 71.08%, 99.24% and 68.44% respectively for the four datasets).
Random Forest (RF) is a widely used classifier to show a good performance of hyperspectral data classification. However, such performance could be improved by increasing the diversity that characterizes the ensemble architecture. In this paper, we propose a novel ensemble approach, namely rotation random forest via kernel principal component analysis (RoRF-KPCA). In particular, the original feature space is first randomly split into several subsets, and KPCA is performed on each subset to extract high order statistics. The obtained feature sets are merged and used as input to an RF classifier. Finally, the results achieved at each step are fused by a majority vote. Experimental analysis is conducted using real hyperspectral remote sensing images to evaluate the performance of the proposed method in comparison with RF, rotation forest, support vector machines, and RoRF-PCA. The obtained results demonstrate the effectiveness of the proposed method.
In this letter, a self-improving convolutional neural network (CNN) based method is proposed for the classification of hyperspectral data. This approach solves the so-called curse of dimensionality and the lack of available training samples by iteratively selecting the most informative bands suitable for the designed network via fractional order Darwinian particle swarm optimization. The selected bands are then fed to the classification system to produce the final classification map. Experimental results have been conducted with two well-known hyperspectral data sets: Indian Pines and Pavia University. Results indicate that the proposed approach significantly improves a CNN-based classification method in terms of classification accuracy. In addition, this letter uses the concept of dither for the first time in the remote sensing community to tackle overfitting.
With different principles, support vector machines (SVMs) and multiple classifier systems (MCSs) have shown excellent performances for classifying hyperspectral remote sensing images. In order to further improve the performance, we propose a novel ensemble approach, namely, rotation-based SVM (RoSVM), which combines SVMs and MCSs together. The basic idea of RoSVM is to generate diverse SVM classification results using random feature selection and data transformation, which can enhance both individual accuracy and diversity within the ensemble simultaneously. Two simple data transformation methods, i.e., principal component analysis and random projection, are introduced into RoSVM. An empirical study on three hyperspectral data sets demonstrates that the proposed RoSVM ensemble method outperforms the single SVM and random subspace SVM. The impacts of the parameters on the overall accuracy of RoSVM (different training sets, ensemble sizes, and numbers of features in the subset) are also investigated in this paper.
Hyperspectral imaging records a detailed spectrum of the received light in each spatial position in the image. Since different substances exhibit different spectral signatures, hyperspectral imagery is a well-suited technology for accurate image classification, which is an important task in many application domains. However, the high dimensionality of the data presents challenges for image analysis. While most of the previously proposed classification techniques process each pixel independently without considering information about spatial structures, recent research in image processing has highlighted the importance of the incorporation of spatial context in a classifier. In this thesis, we propose and develop novel spectral-spatial methods and algorithms for accurate classification of hyperspectral data. First, the integration of the Support Vector Machines (SVM) technique within a Markov Random Fields (MRFs) framework for context classification is investigated. SVM and MRF models are two powerful tools for high-dimensional data classification and for contextual image analysis, respectively. In a second step, we propose classification methods using adaptive spatial neighborhoods derived from region segmentation results. Different segmentation techniques are investigated and extended to the case of hyperspectral images. Then, approaches for combining the extracted spatial regions with spectral information in a classifier are developed. In a third step, we concentrate on approaches to reduce oversegmentation in an image, which is achieved by automatically “marking” the spatial structures of interest before performing a marker-controlled segmentation. Our proposal is to analyze probabilistic classification results for selecting the most reliably classified pixels as markers of spatial regions. Several marker selection methods are proposed, using either individual classifiers, or a multiple classifier system. Then, different approaches for marker-controlled region growing are developed, using either watershed or Minimum Spanning Forest methods and resulting in both segmentation and context classification maps. Finally, we explore possibilities of high-performance parallel computing on commodity processors for reducing computational loads. The new techniques, developed in this thesis, improve classification results, when compared to previously proposed methods, and thus show great potential for various image analysis scenarios.
Classification is one of the most important techniques to the analysis of hyperspectral remote sensing images. Nonetheless, there are many challenging problems arising in this task. Two common issues are the curse of dimen-sionality and the spatial information modeling. In this work, we present a new general framework to train series of effective classifiers with spatial information for classifying hyperspectral data. The proposed framework is based on the two key observations: 1) the curse of dimensionality and the high feature-to-instance ratio can be alleviated by using Random Subspace (RS) ensembles; 2) the spatial-contextual information is modeled by the extended multi-attribute profiles (EMAPs). Two fast learning algorithms, decision tree (DT) and extreme learning machine (ELM), are selected as the base classifiers. Six RS ensemble methods, including Random subspace with DT (RSDT), Random Forest (RF), Rotation Forest (RoF), Rotation Random Forest (RoRF), RS with ELM (RSELM) and Rotation subspace with ELM (RoELM), are constructed by the multiple base learners. Experimental results on both simulated and real hyperspectral data verify the effectiveness of the RS ensemble methods for the classification of both spectral and spatial information (EMAPs). On the University of Pavia ROSIS image, our proposed approaches, both RSELM and RoELM with EMAPs, achieve the state-of-the-art performances, which demonstrates the advantage of the proposed methods. The key parameters in RS ensembles and the computational complexity are also investigated in this study.
In this paper, we propose a new spectral-spatial classification strategy to enhance the classification performances obtained on hyperspectral images by integrating rotation forests and Markov random fields (MRFs). First, rotation forests are performed to obtain the class probabilities based on spectral information. Rotation forests create diverse base learners using feature extraction and subset features. The feature set is randomly divided into several disjoint subsets; then, feature extraction is performed separately on each subset, and a new set of linear extracted features is obtained. The base learner is trained with this set. An ensemble of classifiers is constructed by repeating these steps several times. The weak classifier of hyperspectral data, classification and regression tree (CART), is selected as the base classifier because it is unstable, fast, and sensitive to rotations of the axes. In this case, small changes in the training data of CART lead to a large change in the results, generating high diversity within the ensemble. Four feature extraction methods, including principal component analysis (PCA), neighborhood preserving embedding (NPE), linear local tangent space alignment (LLTSA), and linearity preserving projection (LPP), are used in rotation forests. Second, spatial contextual information, which is modeled by MRF prior, is used to refine the classification results obtained from the rotation forests by solving a maximum a posteriori problem using the α-expansion graph cuts optimization method. Experimental results, conducted on three hyperspectral data with different resolutions and different contexts, reveal that rotation forest ensembles are competitive with other strong supervised classification methods, such as support vector machines. Rotation forests with local feature extraction methods, including NPE, LLTSA, and LPP, can lead to higher classification accuracies than that achieved by PCA. With the help of MRF, the proposed algo- ithms can improve the classification accuracies significantly, confirming the importance of spatial contextual information in hyperspectral spectral-spatial classification.
Just over a decade has passed since the concept of morphological profile was defined for the analysis of remote sensing images. Since then, the morphological profile has largely proved to be a powerful tool able to model spatial information (e.g., contextual relations) of the image. However, due to the shortcomings of using the morphological profiles, many variants, extensions, and refinements of its definition have appeared stating that the morphological profile is still under continuous development. In this case, recently introduced theoretically sound attribute profiles (APs) can be considered as a generalization of the morphological profile, which is a powerful tool to model spatial information existing in the scene. Although the concept of the AP has been introduced in remote sensing only recently, an extensive literature on its use in different applications and on different types of data has appeared. To that end, the great amount of contributions in the literature that address the application of the AP to many tasks (e.g., classification, object detection, segmentation, change detection, etc.) and to different types of images (e.g., panchromatic, multispectral, and hyperspectral) proves how the AP is an effective and modern tool. The main objective of this survey paper is to recall the concept of the APs along with all its modifications and generalizations with special emphasis on remote sensing image classification and summarize the important aspects of its efficient utilization while also listing potential future works.
Hyperspectral remote sensing technology allows one to acquire a sequence of possibly hundreds of contiguous spectral images from ultraviolet to infrared. Conventional spectral classifiers treat hyperspectral images as a list of spectral measurements and do not consider spatial dependences, which leads to a dramatic decrease in classification accuracies. In this paper, a new automatic framework for the classification of hyperspectral images is proposed. The new method is based on combining hidden Markov random field segmentation with support vector machine (SVM) classifier. In order to preserve edges in the final classification map, a gradient step is taken into account. Experiments confirm that the new spectral and spatial classification approach is able to improve results significantly in terms of classification accuracies compared to the standard SVM method and also outperforms other studied methods.
In this letter, an ensemble learning approach, Rotation Forest, has been applied to hyperspectral remote sensing image classification for the first time. The framework of Rotation Forest is to project the original data into a new feature space using transformation methods for each base classifier (decision tree), then the base classifier can train in different new spaces for the purpose of encouraging both individual accuracy and diversity within the ensemble simultaneously. Principal component analysis (PCA), maximum noise fraction, independent component analysis, and local Fisher discriminant analysis are introduced as feature transformation algorithms in the original Rotation Forest. The performance of Rotation Forest was evaluated based on several criteria: different data sets, sensitivity to the number of training samples, ensemble size and the number of features in a subset. Experimental results revealed that Rotation Forest, especially with PCA transformation, could produce more accurate results than bagging, AdaBoost, and Random Forest. They indicate that Rotation Forests are promising approaches for generating classifier ensemble of hyperspectral remote sensing.
Tree species diversity is a key parameter to describe forest ecosystems. It is, for example, important for issues such as wildlife habitat modeling and close-to-nature forest management. We examined the suitability of 8-band WorldView-2 satellite data for the identification of 10 tree species in a temperate forest in Austria. We performed a Random Forest (RF) classification (object-based and pixel-based) using spectra of manually delineated sunlit regions of tree crowns. The overall accuracy for classifying 10 tree species was around 82% (8 bands, object-based). The class-specific producer's accuracies ranged between 33% (European hornbeam) and 94% (European beech) and the user's accuracies between 57% (European hornbeam) and 92% (Lawson's cypress). The object-based approach outperformed the pixel-based approach. We could show that the 4 new WorldView-2 bands (Coastal, Yellow, Red Edge, and Near Infrared 2) have only limited impact on classification accuracy if only the 4 main tree species (Norway spruce, Scots pine, European beech, and English oak) are to be separated. However, classification accuracy increased significantly using the full spectral resolution if further tree species were included. Beside the impact on overall classification accuracy, the importance of the spectral bands was evaluated with two measures provided by RF. An in-depth analysis of the RF output was carried out to evaluate the impact of reference data quality and the resulting reliability of final class assignments. Finally, an extensive literature review on tree species classification comprising about 20 studies is presented.
We propose a novel semisupervised local discriminant analysis method for feature extraction in hyperspectral remote sensing imagery, with improved performance in both ill-posed and poor-posed conditions. The proposed method combines unsupervised methods (local linear feature extraction methods and supervised method (linear discriminant analysis) in a novel framework without any free parameters. The underlying idea is to design an optimal projection matrix, which preserves the local neighborhood information inferred from unlabeled samples, while simultaneously maximizing the class discrimination of the data inferred from the labeled samples. Experimental results on four real hyperspectral images demonstrate that the proposed method compares favorably with conventional feature extraction methods.
Opening and closing are common operators used for removing struc-tures from images according to a predeened size and shape criterion. Families of openings or closings of increasing size are at the basis of the granulometric analysis. In this paper we deene a new granulometric operator which v al-uates the extrema of greyscale images and the structures they point out with a measurement of their persistence when applying openings or closings of increasing size. The proposed mea-surement is called extinction value. The rela-tionships b e t ween extinction values and area openings or closings lead to an ecient a r e a extinction values algorithm. This transforma-tion can be seen as the spatial equivalent o f dynamics.
Connected operators are filtering tools that act by merging elementary
regions of an image. A popular strategy is based on tree-based image
representations: for example, one can compute an attribute on each node of the
tree and keep only the nodes for which the attribute is sufficiently strong.
This operation can be seen as a thresholding of the tree, seen as a graph whose
nodes are weighted by the attribute. Rather than being satisfied with a mere
thresholding, we propose to expand on this idea, and to apply connected filters
on this latest graph. Consequently, the filtering is done not in the space of
the image, but on the space of shapes build from the image. Such a processing
is a generalization of the existing tree-based connected operators. Indeed, the
framework includes classical existing connected operators by attributes. It
also allows us to propose a class of novel connected operators from the
leveling family, based on shape attributes. Finally, we also propose a novel
class of self-dual connected operators that we call morphological shapings.
Morphological attribute profiles (APs) are defined as a generalization of the recently proposed morphological profiles (MPs). APs provide a multilevel characterization of an image created by the sequential application of morphological attribute filters that can be used to model different kinds of the structural information. According to the type of the attributes considered in the morphological attribute transformation, different parametric features can be modeled. The generation of APs, thanks to an efficient implementation, strongly reduces the computational load required for the computation of conventional MPs. Moreover, the characterization of the image with different attributes leads to a more complete description of the scene and to a more accurate modeling of the spatial information than with the use of conventional morphological filters based on a predefined structuring element. Here, the features extracted by the proposed operators were used for the classification of two very high resolution panchromatic images acquired by Quickbird on the city of Trento, Italy. The experimental analysis proved the usefulness of APs in modeling the spatial information present in the images. The classification maps obtained by considering different APs result in a better description of the scene (both in terms of thematic and geometric accuracy) than those obtained with an MP.
Support vector machines (SVM) are attractive for the classification of remotely sensed data with some claims that the method is insensitive to the dimensionality of the data and, therefore, does not require a dimensionality-reduction analysis in preprocessing. Here, a series of classification analyses with two hyperspectral sensor data sets reveals that the accuracy of a classification by an SVM does vary as a function of the number of features used. Critically, it is shown that the accuracy of a classification may decline significantly (at 0.05 level of statistical significance) with the addition of features, particularly if a small training sample is used. This highlights a dependence of the accuracy of classification by an SVM on the dimensionality of the data and, therefore, the potential value of undertaking a feature-selection analysis prior to classification. Additionally, it is demonstrated that, even when a large training sample is available, feature selection may still be useful. For example, the accuracy derived from the use of a small number of features may be noninferior (at 0.05 level of significance) to that derived from the use of a larger feature set providing potential advantages in relation to issues such as data storage and computational processing costs. Feature selection may, therefore, be a valuable analysis to include in preprocessing operations for classification by an SVM.
Diversity among the members of a team of classifiers is deemed to be a key issue in classifier combination. However, measuring diversity is not straightforward because there is no generally accepted formal definition. We have found and studied ten statistics which can measure diversity among binary classifier outputs (correct or incorrect vote for the class label): four averaged pairwise measures (the Q statistic, the correlation, the disagreement and the double fault) and six non-pairwise measures (the entropy of the votes, the difficulty index, the Kohavi-Wolpert variance, the interrater agreement, the generalized diversity, and the coincident failure diversity). Four experiments have been designed to examine the relationship between the accuracy of the team and the measures of diversity, and among the measures themselves. Although there are proven connections between diversity and accuracy in some special cases, our results raise some doubts about the usefulness of diversity measures in building classifier ensembles in real-life pattern recognition problems.
Predictive models benefit from a compact, non-redundant subset of features that improves interpretability and generalization. Modern data sets are wide, dirty, mixed with both numerical and categorical predictors, and may contain interactive effects that require complex models. This is a challenge for filters, wrappers, and embedded feature selection methods. We describe details of an algorithm using tree-based ensembles to generate a compact subset of non-redundant features. Parallel and serial ensembles of trees are combined into a mixed method that can uncover masking and detect features of secondary effect. Simulated and actual examples illustrate the effectiveness of the approach.
This paper introduces a new supervised segmentation algorithm for remotely sensed hyperspectral image data which integrates the spectral and spatial information in a Bayesian framework. A multinomial logistic regression (MLR) algorithm is first used to learn the posterior probability distributions from the spectral information, using a subspace projection method to better characterize noise and highly mixed pixels. Then, contextual information is included using a multilevel logistic Markov–Gibbs Markov random field prior. Finally, a maximum a posteriori segmentation is efficiently computed by the $\alpha$-Expansion min-cut-based integer optimization algorithm. The proposed segmentation approach is experimentally evaluated using both simulated and real hyperspectral data sets, exhibiting state-of-the-art performance when compared with recently introduced hyperspectral image classification methods. The integration of subspace projection methods with the MLR algorithm, combined with the use of spatial–contextual information, represents an innovative contribution in the literature. This approach is shown to provide accurate characterization of hyperspectral imagery in both the spectral and the spatial domain.
In this letter, a technique based on independent component analysis (ICA) and extended morphological attribute profiles (EAPs) is presented for the classification of hyperspectral images. The ICA maps the data into a subspace in which the components are as independent as possible. APs, which are extracted by using several attributes, are applied to each image associated with an extracted independent component, leading to a set of extended EAPs. Two approaches are presented for including the computed profiles in the analysis. The features extracted by the morphological processing are then classified with an SVM. The experiments carried out on two hyperspectral images proved the effectiveness of the proposed technique.
We propose a method for generating classifier ensembles based on feature extraction. To create the training data for a base classifier, the feature set is randomly split into K subsets (K is a parameter of the algorithm) and Principal Component Analysis (PCA) is applied to each subset. All principal components are retained in order to preserve the variability information in the data. Thus, K axis rotations take place to form the new features for a base classifier. The idea of the rotation approach is to encourage simultaneously individual accuracy and diversity within the ensemble. Diversity is promoted through the feature extraction for each base classifier. Decision trees were chosen here because they are sensitive to rotation of the feature axes, hence the name "forest." Accuracy is sought by keeping all principal components and also using the whole data set to train each base classifier. Using WEKA, we examined the Rotation Forest ensemble on a random selection of 33 benchmark data sets from the UCI repository and compared it with Bagging, AdaBoost, and Random Forest. The results were favorable to Rotation Forest and prompted an investigation into diversity-accuracy landscape of the ensemble models. Diversity-error diagrams revealed that Rotation Forest ensembles construct individual classifiers which are more accurate than these in AdaBoost and Random Forest, and more diverse than these in Bagging, sometimes more accurate as well.
This paper sets out a new representation of an image which is contrast independent. The image is decomposed into a tree of "shapes" based on connected components of level sets, which provides a full and nonredundant representation of the image. A fast algorithm to compute the tree, the fast level lines transform (FLLT), is explained in detail. Some simple and direct applications of this representation are shown.
New remote sensing sensors will acquire High spectral, spatial and temporal Resolution Satellite Image Time Series (HR-SITS). These new data are of great interest to map land cover thanks to the combination of the three high resolutions that will allow a depiction of scene dynamics. However, their efficient exploitation involves new challenges, especially for adapting traditional classification schemes to data complexity. More specifically, it requires: (1) to determine which classifier algorithms can handle the amount and the variability of data; (2) to evaluate the stability of classifier parameters; (3) to select the best feature set used as input data in order to find the good trade-off between classification accuracy and computational time; and (4) to establish the classifier accuracy over large areas. This work aims at studying these different issues, and more especially at demonstrating the ability of state-of-the-art classifiers, such as Random Forests (RF) or Support Vector Machines (SVM), to classify HR-SITS. For this purpose, several studies are carried out by using SPOT-4 and Landsat-8 HR-SITS in the south of France. Firstly, the choice of the classifier is discussed by comparing RF and SVM algorithms on HR-SITS. Both classifiers show their ability to tackle the classification problem with an Overall Accuracy (OA) of 83.3 % for RF and 77.1 % for SVM. But RF have some advantages such as a small training time, and an easy parameterization. Secondly, the stability of RF parameters is appraised. RF parameters appear to cause little influence on the classification accuracy, about 1% OA difference between the worst and the best parameter configuration. Thirdly, different input data – composed of spectral bands with or without spectral and/or temporal features – are proposed in order to enhance the characterization of land cover. The addition of features improves the classification accuracy, but the gain in OA is weak compared with the increase in the computational cost. Eventually, the classifier accuracy is assessed on a larger area where the landscape variabilities affect the classification performances.
This letter proposes a new approach for the spectral–spatial classification of hyperspectral images, which is based on a novel extrema-oriented connected filtering technique, entitled as extended extinction profiles. The proposed approach progressively simplifies the first informative features extracted from hyperspectral data considering different attributes. Then, the classification approach is applied on two well-known hyperspectral data sets, i.e., Pavia University and Indian Pines, and compared with one of the most powerful filtering approaches in the literature, i.e., extended attribute profiles. Results indicate that the proposed approach is able to efficiently extract spatial information for the classification of hyperspectral images automatically and swiftly. In addition, an array-based node-oriented max-tree representation was carried out to efficiently implement the proposed approach.
With respect to recent advances in remote sensing technologies, the spatial resolution of airborne and spaceborne sensors is getting finer, which enables us to precisely analyze even small objects on the Earth. This fact has made the research area of developing efficient approaches to extract spatial and contextual information highly active. Among the existing approaches, morphological profile and attribute profile (AP) have gained great attention due to their ability to classify remote sensing data. This paper proposes a novel approach that makes it possible to precisely extract spatial and contextual information from remote sensing images. The proposed approach is based on extinction filters, which are used here for the first time in the remote sensing community. Then, the approach is carried out on two well-known high-resolution panchromatic data sets captured over Rome, Italy, and Reykjavik, Iceland. In order to prove the capabilities of the proposed approach, the obtained results are compared with the results from one of the strongest approaches in the literature, i.e., APs, using different points of view such as classification accuracies, simplification rate, and complexity analysis. Results indicate that the proposed approach can significantly outperform its alternative in terms of classification accuracies. In addition, based on our implementation, profiles can be generated in a very short processing time. It should be noted that the proposed approach is fully automatic.
Attribute filters and extinction filters are connected filters used to simplify greyscale images. The first kind is widely explored in the image processing literature, while the second is not much explored yet. Both kind of filters can be efficiently implemented on the max-tree. In this work, we compare these filters in terms of processing time, simplification of flat zones and reduction of max-tree nodes. We also compare their influence as a pre-processing step before extracting affine regions used in matching and pattern recognition. We perform repeatability tests using extinction filters and attribute filters, set to preserve the same number of extrema, as a pre-processing step before detecting Hessian-Affine and Maximally Stable Extremal Regions (MSER) affine regions. The results indicate that using extinction filters as pre-processing obtain a significantly higher (more than 5% on average) number of correspondences on the repeatability tests than the attribute filters. The results in processing natural images show that preserving 5% of images extrema using extinction filters achieve on average 95% of the number of correspondences compared to applying the affine region detectors directly to the unfiltered images, and the average number of max-tree nodes is reduced by a factor greater than 3. Therefore, we can conclude that extinction filters are better than attribute filters with respect to preserving the number of correspondences found by affine detectors, while simplifying the max-tree structure. The use of extinction filters as a pre-processing step is recommended to accelerate image recognition tasks.
Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes characteristics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.
Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, ***, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
Extended attribute profiles and extended multi-attribute profiles are presented for the analysis of hyperspectral high-resolution images. These extended profiles are based on morphological attribute filters and, through a multi-level analysis, are capable of extracting spatial features that can better model the spatial information, with respect to conventional extended morphological profiles. The features extracted by the proposed extended profiles were considered for a classification task. Two hyperspectral high-resolution datasets acquired for the city of Pavia, Italy, were considered in the analysis. The effectiveness of the introduced operators in modelling the spatial information was proved by the higher classification accuracies obtained with respect to those achieved by a conventional extended morphological profile.
Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.
This paper introduces a novel classification method termed Alternating Decision Forests (ADFs), which formulates the training of Random Forests explicitly as a global loss minimization problem. During training, the losses are minimized via keeping an adaptive weight distribution over the training samples, similar to Boosting methods. In order to keep the method as flexible and general as possible, we adopt the principle of employing gradient descent in function space, which allows to minimize arbitrary losses. Contrary to Boosted Trees, in our method the loss minimization is an inherent part of the tree growing process, thus allowing to keep the benefits of common Random Forests, such as, parallel processing. We derive the new classifier and give a discussion and evaluation on standard machine learning data sets. Furthermore, we show how ADFs can be easily integrated into an object detection application. Compared to both, standard Random Forests and Boosted Trees, ADFs give better performance in our experiments, while yielding more compact models in terms of tree depth.
Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy.
The formulation of conditional probability models for finite systems of spatially interacting random variables is examined. A simple alternative proof of the Hammersley–Clifford theorem is presented and the theorem is then used to construct specific spatial schemes on and off the lattice. Particular emphasis is placed upon practical applications of the models in plant ecology when the variates are binary or Gaussian. Some aspects of infinite lattice Gaussian processes are discussed. Methods of statistical analysis for lattice schemes are proposed, including a very flexible coding technique. The methods are illustrated by two numerical examples. It is maintained throughout that the conditional probability approach to the specification and analysis of spatial interaction is more attractive than the alternative joint probability approach.