Figure 4 - uploaded by Sachit Rajbhandari
Content may be subject to copyright.
Source publication
Ontology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects. In fusing data from multiple sensors, the number of feature variables is increased and object identification becomes a challenging task. We propose a methodological contribution that extends feature variable characterisation. T...
Context in source publication
Context 1
... for each segmented image objects, features are extracted from different data sources. We fused three different types of data, namely a RapidEye satellite image (Tiff file), LiDAR data (RData file), and Photo Interpretation data (Shapefile) as shown in Figure 4. For segmentation and feature extraction, eCognition Developer Version 9.3.0 from Trimble, Germany was used. ...
Citations
... It is also known as multispectral image when only spectral channels are included. Semantic segmentation of multichannel image is the basis for many remote sensing applications, such as cloud detection [1]- [3], land use/ land cover classification [4], [5] and forest monitoring [6], [7]. ...
Semantic segmentation of multichannel images is a fundamental task for many applications. Selecting an appropriate channel combination from the original multichannel image can improve the accuracy of semantic segmentation and reduce the cost of data storage, processing and future acquisition. Existing channel selection methods typically use a reasonable selection procedure to determine a desirable channel combination, and then train a semantic segmentation network using that combination. In this study, the concept of pruning from a supernet is used for the first time to integrate the selection of channel combination and the training of a semantic segmentation network. Based on this concept, a One-Shot Task-Adaptive (OSTA) channel selection method is proposed for the semantic segmentation of multichannel images. OSTA has three stages, namely the supernet training stage, the pruning stage and the fine-tuning stage. The outcomes of six groups of experiments (L7Irish3C, L7Irish2C, L8Biome3C, L8Biome2C, RIT-18 and Semantic3D) demonstrated the effectiveness and efficiency of OSTA. OSTA achieved the highest segmentation accuracies in all tests (62.49% (mIoU), 75.40% (mIoU), 68.38% (mIoU), 87.63% (mIoU), 66.53% (mA) and 70.86% (mIoU), respectively). It even exceeded the highest accuracies of exhaustive tests (61.54% (mIoU), 74.91% (mIoU), 67.94% (mIoU), 87.32% (mIoU), 65.32% (mA) and 70.27% (mIoU), respectively), where all possible channel combinations were tested. All of this can be accomplished within a predictable and relatively efficient timeframe, ranging from 101.71% to 298.1% times the time required to train the segmentation network alone. In addition, there were interesting findings that were deemed valuable for several fields.
... From the proposals [23][24][25] implemented through the GeoDMA framework (GEOBIA), in synthesis provides the realization of the steps of segmentation of satellite images, extraction of attributes, creation of classification rules, hierarchical classification and visualization of results. Additionally, the works [19,[26][27][28][29] describe in detail the precautions to be taken in image acquisition and processing. In particular, according to [27,30], the monitoring of the interactions with the terrestrial surfaces is very important, where each intensity of the solar radiation must be observed. ...
... The availability of images from satellites and aerial platforms over the Earth's surface in the most diverse resolutions has been enabling an unprecedented approach between technology and society, as [28] the processing of large volumes of data and geolocation for the use of mobile devices in most different devices makes the insertion of various technologies flexible. However, large volumes of data are generated, and for analysis, new challenges arise involving interoperability, from those related to data collection and storage, through ethics and privacy [33][34][35], to the development of efficient and robust algorithms to extract the most unimaginable information. ...
Due to the increasing urban development, it has become important for municipalities to permanently understand land use and ecological processes, and make cities smart and sustainable by implementing technological tools for land monitoring. An important problem is the absence of technologies that certify the quality of information for the creation of strategies. In this context, expressive volumes of data are used, requiring great effort to understand their structures, and then access information with the desired quality. This study are designed to provide an initial response to the need for mapping zones in the city of Itajaí (SC), Brazil. The solution proposes to aid object recognition employing object-based classifiers OneR, NaiveBayes, J48, IBk, and Hoeffding Tree algorithms used together with GeoDMA, and a first approach in the use of Region-based Convolutional Neural Network (R-CNN) and the YOLO algorithm. All this is to characterize vegetation zones, exposed soil zones, asphalt, and buildings within an urban and rural area. Through the implemented model for active identification of geospatial objects with similarity levels, it was possible to apply the data crossover after detecting the best classifier with accuracy (85%) and the kappa agreement coefficient (76%). The case study presents the dynamics of urban and rural expansion, where expressive volumes of data are obtained and submitted to different methods of cataloging and preparation to subsidize rapid control actions. Finally, the research describes a practical and systematic approach, evaluating the extraction of information to the recommendation of knowledge with greater scientific relevance. Allowing the methods presented to apply the calibration of values for each object, to achieve results with greater accuracy, which is proposed to help improve conservation and management decisions related to the zones within the city, leaving as a legacy the construction of a minimum technological infrastructure to support the decision.
... But some studies were contradictory to our results, e.g., Tong et al. (2019) indicated that salinity, NO 3 -N and pH shaped the structure of bacterial community in mangroves across China. Due to choosing influential and non-influential attributes in an unbiased and consistent manner (Rajbhandari et al., 2019), Boruta algorithm analysis further was adopted and proved temperature was the most important factor regulating Bacillus community in mangrove ecosystem. Bacillus community was sensitive to temperature change (Yi et al., 2012), and could develop timely "coping strategies" in the face of temperature change to regulate the microbial community , consistent with our results. ...
Mangroves are located at the interface of terrestrial and marine environments, and experience fluctuating conditions, creating a need to better explore the relative role of the bacterial community. Bacillus has been reported to be the dominant group in the mangrove ecosystem and plays a key role in maintaining the biodiversity and function of the mangrove ecosystem. However, studies on bacterial and Bacillus community across four seasons in the mangrove ecosystem are scarce. Here, we employed seasonal large-scale sediment samples collected from the mangrove ecosystem in southeastern China and utilized 16S rRNA gene amplicon sequencing to reveal bacterial and Bacillus community structure changes across seasons. Compared with the whole bacterial community, we found that Bacillus community was greatly affected by season (temperature) rather than site. The key factors, NO3-N and NH4-N showed opposite interaction with superabundant taxa Bacillus taxa (SAT) and three rare Bacillus taxa including high rare taxa (HRT), moderate rare taxa (MRT) and low rare taxa (LRT). Network analysis suggested the co-occurrence of Bacillus community and Bacillus-bacteria, and revealed SAT had closer relationship compared with rare Bacillus taxa. HRT might act crucial response during the temperature decreasing process across seasons. This study fills a gap in addressing the assembly of Bacillus community and their role in maintaining microbial diversity and function in mangrove ecosystem.
... As summarized by Lu and Weng [15], some potential methods such as graphic analysis, statistical methods, and the fuzzy-logic expert system have been used to identify optimal combination of variables. An alternative is to use random forest (RF) method because of the ability to provide importance ranking of variables [3,16,17]. Too many variables used in a classification procedure cannot guarantee the best classification result, but selection of the optimal variable combination from a wide range of variables is critical for separation of specific classes [6]. Many previous studies have proven that, when multisource data are used, machine learning algorithms (e.g., artificial neural networks (ANN), support vector machine (SVM), classification and regression trees (CART), and RF) have advantages over traditional classification methods/techniques (e.g., maximum likelihood classifier (MLC) and minimum distance) in dealing with complex data, thus, providing better classification [10,18,19]. ...
Tree species distribution is valuable for forest resource management. However, it is a challenge to classify tree species in subtropical regions due to complex landscapes and limitations of remote sensing data. The objective of this study was to propose a modified hierarchy-based classifier (MHBC) by optimizing the classification tree structures and variable selection method. Major steps to create an MHBC include automatic determination of classification tree structures based on the Z -score algorithm, selection and optimization of variables for each node, and classification using the optimized model. Experiments based on the fusion of Gaofen-1/Ziyuan-3 panchromatic (GF-1/ZY-3 PAN) and Sentinel-2 multispectral (MS) data indicated that (1) the MHBC provided overall classification accuracies of 85.19% for Gaofeng Forest Farm in China’s southern subtropical region and 94.4% for Huashi Township in China’s northern subtropical region, which had higher accuracies than random forest (RF) and classification and regression tree (CART); (2) critical variables for each class can be identified using the MHBC, and optimal variables of most nodes are spectral bands and vegetation indices; (3) compared to results from RF and CART, MHBC mainly improved the accuracies of the lower levels of classification tree structures (difficult classes to separate). The novelty in using MHBC is its simple and practical operation, easy-to-understand, and visualized variables that were selected in each node of the automatically constructed hierarchical trees. The robust performance of MHBC implies the potential to apply this approach to other sites for accurate classification of forest types.
... Moreover, since the relationship between adjacent pixels in the high spatial resolution image is not considered, the pixel-based method may cause the phenomenon of "salt and pepper" in the classification results (Yu et al., 2006). To achieve the representative characteristics of the interest targets and overcome the "salt and pepper" phenomenon, object-based image analysis (OBIA), as an alternative to the pixel-based method, is being used more and more widely (Blaschke et al., 2014;Rajbhandari et al., 2019;Yu et al., 2006). OBIA groups the spectrally homogenous neighboring pixels as an object. ...
As a common phenomenon along the global coastline, beach wrack, which is part of the blue carbon ecosystems (BCEs), has significant ecological values. However, the excessive accumulation of beach wrack can be a nuisance for local residents and tourism. Meanwhile, beach wrack can become a source of greenhouse gas due to the decomposition. Hence, effective monitoring of beach wrack has become a priority for coastal environmental management. As a cost- and labor-saving approach, unmanned aerial vehicles (UAVs) can perform customized flight tasks and achieve aerial images with sub-decimeter spatial resolution. This study investigated the feasibility of using UAVs to map wrack on three different types of beaches. The method of object-based image analysis (OBIA) was applied to classify the aerial images. Three typical machine learning methods, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forests (RF), were examined with different feature spaces at several segmentation levels. The results showed that the three machine learning methods performed well with the overall classification accuracy >75%. The tested algorithm, SVM with only RGB as feature space at the segmentation scale 50, was geographically transferable to beaches with different characteristics. This study demonstrated that UAVs can be developed as an applicable tool for beach wrack mapping and monitoring, which will help to better explore the role of beach wrack in BCEs and assist the local municipalities in environmental management of the coastal zone.
... Six investigations have been found in the land domain, more concretely, on landslide , terrain elevation (Zhang & Tang, 2015), geology aspects (Baru & Lin, 2009), and land cover & use (Jones et al., 1999;Liu et al., 2021;Rajbhandari et al., 2019). ...
... Among these contributions, on the one hand, we discovered two articles that dealt with diverse semantic resources (ontologies/vocabularies) to set mappings across multiple geoscience information sources (Baru & Lin, 2009) and promote the classification of forest types (Rajbhandari et al., 2019). On the other hand, Jones et al. (1999), Zhang and Tang (2015), employed several attributes from the information sources analyzed. ...
... Zhang and Tang (2015) centered on scale and "semantics" associated with irregularly sampled quasi-points, and Zhu et al. (2019) tackled multiple-association relationships. Liu et al. (2021), Rajbhandari et al. (2019), Zhu et al. (2019), and Zhang and Tang (2015) considered instances, and Jones et al. (1999) and Baru and Lin (2009) concentrated on the schema. These authors used diverse similarity metrics to address semantic conflation issues. ...
Manifold providers from a wide range of initiatives (private organizations, volunteered efforts, social media, etc.) offer enormous data amounts with geospatial characteristics. These efforts of many data providers entail multiple data scenarios and imply many viewpoints about the same feature, involving different representations, accuracy, models, vocabularies, etc. Various techniques or processes are employed to deal with these heterogeneity problems related to diverse data sources within the conflation research area. However, semantic conflation has not been addressed widely in the literature, unlike geometrical conflation. Hence, it is unclear what issues semantic conflation tries to solve and what activities, methods, metrics, and techniques have been used in existing GIScience investigations. In this article, we carry out a systematic review of approaches that focus on semantic aspects for geospatial data conflation. Besides, we analyze a wide selection of contributions following different criteria to depict a detailed semantic conflation status in GIScience. Our contributions are: (i) an overview of semantic conflation application domains, (ii) a characterization of semantic issues within these domains, (iii) the recognition of gaps and weaknesses of collected researches, and (iv) several open challenges and opportunities for next steps in this GIScience research area.
... Ontology-driven classifications provide the identification of meaningful and communicable features [54]. In this study, false colour image classifications are driven by ontology. ...
To facilitate the simplification, visualisation and communicability of satellite imagery classifications, this study applied visual analytics to validate a colourimetric approach via the direct and scalable measurement of hue angle from enhanced false colour band ratio RGB composites. A holistic visual analysis of the landscape was formalised by creating and applying an ontological image interpretation key from an ecological-colourimetric deduction for rainforests within the variegated landscapes of south-eastern Australia. A workflow based on simple one-class, one-index density slicing was developed to implement this deductive approach to mapping using freely available Sentinel-2 imagery and the super computing power from Google Earth Engine for general public use. A comprehensive accuracy assessment based on existing field observations showed that the hue from a new false colour blend combining two band ratio RGBs provided the best overall results, producing a 15 m classification with an overall average accuracy of 79%. Additionally, a new index based on a band ratio subtraction performed better than any existing vegetation index typically used for tropical evergreen forests with comparable results to the false colour blend. The results emphasise the importance of the SWIR1 band in discriminating rainforests from other vegetation types. While traditional vegetation indices focus on productivity, colourimetric measurement offers versatile multivariate indicators that can encapsulate properties such as greenness, wetness and brightness as physiognomic indicators. The results confirmed the potential for the large-scale, high-resolution mapping of broadly defined vegetation types.
... Remote sensing scientists mapped various types of objects on planetary surfaces to collect information about their status [10], composition, distribution, dynamics [11], [12] and species [13], and related applications [14]- [16] on the basis of selecting appropriate spatial resolutions and scale parameters for image processing [17]. An appropriate image spatial resolution is the optimum pixel size to capture the homogeneity of object properties in a single pixel. ...
Identifying the spatial structure of lunar impact craters is necessary to increase our understanding of past geologic processes on the Moon. However, detecting multiscale spatial structures of craters in images in appropriate resolutions using optimum scale parameters has not been quantified. This paper presents a semivariogram approach for this purpose. The range of the semivariogram model represents the minimum average size of the crater type detected in an image of a spatial resolution. The feature lag distances of the semivariogram model indicate that a series of appropriate spatial resolutions rather than a single spatial resolution are required to address multiscale lunar impact crater structures. The optimum scale parameters for delineating multiscale crater structures in segmentation are constrained by the range and feature lag distances derived from semivariogram of the corresponding image in a certain spatial resolution. This research fills the gap in quantifying multiscale spatial structure of impact craters using semivariogram analysis for optimizing object-based crater mapping.
... According to [1], the enhanced spatial resolution of available orbital sensors creates the possibility to apply geographic object-based image analysis (GEOBIA), to perform SITS classification. GEOBIA provides a powerful framework for overcoming the limitations of conventional pixel-based image classification since it provides features associated with Manuscript the shape, texture, contextual, and semantic relationships of objects [6]- [8]. ...
Classifying dense satellite image time series has become a necessity, especially with the recent efforts to create analysis ready data cubes. Approaches developed to perform this task are usually pixel-based. Even though these approaches can achieve good results, they do not take advantage of the intrinsic spatial correlation of geographic data nor do they consider spatial heterogeneity along with the time series. Region-based classification is a suitable solution to incorporate contextual information for dense satellite image time series classification. In this article, we introduce a new segmentation method based on a superpixel approach. This method creates multitemporal superpixels, which are meaningful regions in space and time. To evaluate the performance of the proposed method, tests were performed on two data sets using a total of 23 ground-truth references. Experimental results showed that the method performed well, achieving a good boundary agreement and obtaining high scores on the three metrics used for evaluation.
... For databases to be compatible, metadata must be thorough (and codified) to enable researchers to locate and compare different information based on search-terms. As such, the development of ontologiesor shared conceptswithin both database creation and different computer analysis techniques, have permitted for better sharing of information and improved performance of data analysis (Arvor et al., 2013(Arvor et al., , 2019Binding et al., 2008;Rajbhandari et al., 2019; also see Magnini and Bettineschi, 2019). ...
In the 21st century, advances in computer science have impacted archaeology, most recently in the development of automated algorithms. Like most technology, these methods have been the source of ongoing debate, particularly in their utility for archaeology. Here, I focus on a contribution of automation and machine learning in archaeology that is often overlooked: the ability of computer algorithms to codify unambiguous, semantically consistent definitions. Archaeology has long struggled with establishing consistent characterizations of the phenomena it studies. As such, I argue that the procedures used for automated methods are useful for archaeologists-even outside of automated analyses-by allowing for the creation of consistent definitions which permit for reproducible research designs.
