Article

Automatic vehicle detection based on automatic histogram-based fuzzy C-means algorithm and perceptual grouping using very high-resolution aerial imagery and road vector data

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

This study presents an approach for the automatic detection of vehicles using very high-resolution images and road vector data. Initially, road vector data and aerial images are integrated to extract road regions. Then, the extracted road/street region is clustered using an automatic histogram-based fuzzy C-means algorithm, and edge pixels are detected using the Canny edge detector. In order to automatically detect vehicles, we developed a local perceptual grouping approach based on fusion of edge detection and clustering outputs. To provide the locality, an ellipse is generated using characteristics of the candidate clusters individually. Then, ratio of edge pixels to nonedge pixels in the corresponding ellipse is computed to distinguish the vehicles. Finally, a point-merging rule is conducted to merge the points that satisfy a predefined threshold and are supposed to denote the same vehicles. The experimental validation of the proposed method was carried out on six very high-resolution aerial images that illustrate two highways, two shadowed roads, a crowded narrow street, and a street in a dense urban area with crowded parked vehicles. The evaluation of the results shows that our proposed method performed 86% and 83% in overall correctness and completeness, respectively. © 2016 Society of Photo-Optical Instrumentation Engineers (SPIE).

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... The disadvantage of this method was the poor identification of parking spaces in outdoor parking lots. In consideration of this issue, a detection method (called ParkLotD) [5] Sensors 2022, 22 ...
Article
Full-text available
The parking problem, which is caused by a low parking space utilization ratio, has always plagued drivers. In this work, we proposed an intelligent detection method based on deep learning technology. First, we constructed a TensorFlow deep learning platform for detecting vehicles. Second, the optimal time interval for extracting video stream images was determined in accordance with the judgment time for finding a parking space and the length of time taken by a vehicle from arrival to departure. Finally, the parking space order and number were obtained in accordance with the data layering method and the TimSort algorithm, and parking space vacancy was judged via the indirect Monte Carlo method. To improve the detection accuracy between vehicles and parking spaces, the distance between the vehicles in the training dataset was greater than that of the vehicles observed during detection. A case study verified the reliability of the parking space order and number and the judgment of parking space vacancies.
... Hence, remote sensing data due to providing spatial information and different physical features of the urban areas can be used for this purpose [30][31][32]. Remote sensing images have also been used to extract land cover and land use maps [33][34][35][36] as well as other urban objects [37][38][39]. Slum detection and extraction from remote sensing images was also the focus of several studies [40]. While early studies in this topic used traditional image processing methods [32,[41][42][43], recent ones used more advanced machine learning methods [44] such as SVM [45,46], Random Forest [47], and CNN-based approaches [48,49]. ...
Article
Full-text available
Rapid urbanization and increasing population in cities with a large portion of them settled in deprived neighborhoods, mostly defined as slum areas, have escalated inequality and vulnerability to natural disasters. As a result, monitoring such areas is essential to provide information and support decision-makers and urban planners, especially in case of disaster recovery. Here, we developed an approach to monitor the urban deprived areas over a four-year period after super Typhoon Haiyan, which struck Tacloban city, in the Philippines, in 2013, using high-resolution satellite images and machine learning methods. A Support Vector Machine classification method supported by a local binary patterns feature extraction model was initially performed to detect slum areas in the pre-disaster, just after/event, and post-disaster images. Afterward, a dense conditional random fields model was employed to produce the final slum areas maps. The developed method detected slum areas with accuracies over 83%. We produced the damage and recovery maps based on change analysis over the detected slum areas. The results revealed that most of the slum areas were reconstructed 4 years after Typhoon Haiyan, and thus, the city returned to the pre-existing vulnerability level.
... The study of atrial fibrillation is also in depth at home. In addition, the introduction of automatic detection algorithm improves the processing ability of dynamic data (Ghaffarian Set al 2016) [9]. The application of automatic detection algorithm in the analysis of dynamic electrocardiogram data has been gradually developed in China. ...
Article
Full-text available
With the approaching of the aging of the population in China, the risk of heart disease increases with age. Atrial fibrillation as a common heart disease has seriously affected people’s lives and health. A study of atrial fibrillation, dynamic electrocardiogram is usually used to analyze atrial fibrillation. But the accuracy of this analytical method may be artificially disturbed, which causes errors in the process of data analysis. Therefore, the computation analysis is carried by combining the automatic detection algorithm. By using the calculation of computer algorithm, the accuracy of data analysis of dynamic electrocardiogram can be increased. And through the test of automatic detection algorithm, the effectiveness of the algorithm can be found.
... However, there is some common computation complexity, application narrow and low accuracy in these mainstream approaches. In contrast, the fuzzy C-means clustering (FCM) can get each data sample's membership of all types of class centers and then determine the ownership of sample points [14], [15]. This also has great application potential in the volcanic ash cloud detection. ...
Article
Remote sensing classification for volcanic ash cloud is a difficult task in the remote sensing application, and how to accurately obtain the volcanic ash cloud information from remote sensing image has become a key step in remote sensing classification of volcanic ash cloud. Aiming at the characteristics of the remote sensing images, via introducing the neighborhood pixels based on the classical fuzzy C-means clustering (FCM) algorithm, this paper proposed a new fuzzy clustering remote sensing classification method with neighborhood distance constraint for volcanic ash cloud. The current study are tested from simulation texture image and moderate resolution imaging spectroradiometer (MODIS) remote sensing image, and finally explored the Sangeang Api volcanic ash cloud case on 30 May 2014. Our experiments show that the proposed method can effectively classify the volcanic ash cloud from remote sensing images, and the overall classification accuracy and Kappa coefficient reach 88.4% and 0.8064. To some extent, it overcomes the deficiency of the approaches in traditional volcanic ash cloud remote sensing classification.
Article
Full-text available
Currently, deep learning has been widely applied in the field of object detection, and some relevant scholars have applied it to vehicle detection. In this paper, the deep learning EfficientDet model is analyzed, and the advantages of the model in the detection of hazardous good vehicles are determined. The adaptive training model is built based on the optimization of the training process, and the training model is used to detect hazardous goods vehicles. The detection results are compared with Cascade R-CNN and CenterNet, and the results show that the proposed method is superior to the other two methods in two aspects of computational complexity and detection accuracy. Simultaneously, the proposed method is suitable for the detection of hazardous goods vehicles in different scenarios. We make statistics on the number of detected hazardous goods vehicles at different times and places. The risk grade of different locations is determined according to the statistical results. Finally, the case study shows that the proposed method can be used to detect hazardous goods vehicles and determine the risk level of different places.
Article
The railway turnout system is a critical infrastructure that is responsible for steering trains. The closeness state of the turnout is directly related to the safety of the passing trains. To avoid derailment accidents caused by insufficient turnout closeness degrees, it is necessary to monitor the closeness degrees of the turnout. This article introduces a new condition-monitoring strategy that evaluates the turnout closeness degree by measuring the size of the switch gap. To implement this strategy, a detector based on image sensors is designed, and an automatic algorithm is proposed to measure the size of the switch gap based on the images acquired by the detector. The proposed algorithm directly processes the original images of the switch gap and can adaptively extract the region of interest (ROI) and the hysteresis threshold of the Canny operator for each image, which enables workers to avoid using a fixed ROI and hysteresis threshold with different images. Finally, the turnout closeness degree is calculated through a simple conversion of the size of the switch gap, measured by the proposed algorithm. Experiments based on data collected from the actual turnouts of a station show that the proposed turnout closeness monitoring method has high accuracy and robustness, which simplifies the turnout closeness maintenance process and improves its efficiency.
Article
Detecting vehicles from satellite images is of great importance for both traffic monitoring and urban planning. However, it is still a challenging task, because vehicles are small and the background is complex. To deal with the issue, an improved morphological reconstruction approach is proposed to model the complex background in satellite images. Bright building regions are first removed by the normalized difference built-up index. Directional filters are next designed to generate the marker image for morphological reconstruction. As the directional filters can match any directional structure of the background, the newly proposed approach has a good ability to eliminate the complex background in satellite images. Finally, vehicles are detected using the Reed-Xiaoli algorithm. The proposed method is applied to real QuickBird images for vehicle detection. The results show that the proposed approach has strong robustness and high efficiency merits and can be used for vehicle detection in city areas. © 2018 Society of Photo-Optical Instrumentation Engineers (SPIE).
Article
Vehicle detection in high-resolution aerial images has received widespread interests when it comes to providing the required information for traffic management and urban planning. It is challenging due to the relatively small size of the vehicles and the complex background. Furthermore, it is particularly challenging if the higher detection efficiency is required. Therefore, an urban vehicle detection algorithm is proposed via improved entropy rate clustering (IERC) and correlation-based sequential dictionary learning (CSDL). First, to enhance the detection accuracy, IERC is designed to generate more regular superpixels. It aims to avoid the situation that one superpixel sometimes straddles multiple vehicles. The generated superpixels are then treated as the seeds for the training sample selection. Then, CSDL is constructed to achieve a fast sequential training and updating of the dictionary. In CSDL, only the atoms correlated with the sparse representation of the new training data are inferred. Finally, comprehensive analyses and comparisons on two data sets demonstrate that the proposed method generates satisfactory and competitive results.
Conference Paper
Full-text available
Robust and efficient detection of cars in urban scenes has many useful applications. This paper introduces a framework for car detection from high-resolution satellite images, wherein a novel extended image descriptor is used to depict the geometric, spectral and colour distribution properties of cars. The proposed framework is based on a sliding-window detection approach and it begins with a pre-prepossessing stage, which discards detection windows that are very unlikely to contain cars, e.g., plain areas and vegetation, followed by the computation of a concatenated feature vector of Histogram of Oriented Gradients, Fourier and truncated Pyramid Colour Self-Similarity image descriptors that is then fed to a pre-trained linear Support Vector Machine classifier to discriminate between the feature and non-feature subspaces. For post-processing, a non-maximum suppression technique is used to eliminate multiple detections. The performance of the proposed framework has been assessed on the Vaihingen dataset and results show that it exceeds the performance of the current state-of-the-art car detection algorithms.
Article
Full-text available
Fuzzy C-means (FCM) clustering has been widely used in analyzing and understanding remote sensing images. However, the conventional FCM algorithm is sensitive to initialization, and it requires estimations from expert users to determine the number of clusters. To overcome the limitations of the FCM algorithm, an automatic histogram-based fuzzy C-means (AHFCM) algorithm is presented in this paper. Our proposed algorithm has two primary steps: 1 – clustering each band of a multispectral image by calculating the slope for each point of the histogram, in two directions, and executing the FCM clustering algorithm based on specific rules, and 2 – automatic fusion of labeled images is used to initialize and determine the number of clusters in the FCM algorithm for automatic multispectral image clustering. The performance of our proposed algorithm is first tested on clustering a very high resolution aerial image for various numbers of clusters and, next, on clustering two very high resolution aerial images, a high resolution Worldview2 satellite image, a Landsat8 satellite image and an EO-1 hyperspectral image, for a constant number of clusters. The superiority of the new method is demonstrated by comparing it with the well-known methods of FCM, K-means, fast global FCM (FGFCM) and kernelized fast global FCM (KFGFCM) clustering algorithms, both quantitatively by calculating the DB, XB and SC indices and qualitatively by visualizing the cluster results.
Article
Full-text available
Vehicle detection has been an important research field for years as there are a lot of valuable applications, ranging from support of traffic planners to real-time traffic management. Especially detection of cars in dense urban areas is of interest due to the high traffic volume and the limited space. In city areas many car-like objects (e.g., dormers) appear which might lead to confusion. Additionally, the inaccuracy of road databases supporting the extraction process has to be handled in a proper way. This paper describes an integrated real-time processing chain which utilizes multiple occurrence of objects in images. At least two subsequent images, data of exterior orientation, a global DEM, and a road database are used as input data. The segments of the road database are projected in the non-geocoded image using the corresponding height information from the global DEM. From amply masked road areas in both images a disparity map is calculated. This map is used to exclude elevated objects above a certain height (e.g., buildings and vegetation). Additionally, homogeneous areas are excluded by a fast region growing algorithm. Remaining parts of one input image are classified based on the ‘Histogram of oriented Gradients (HoG)’ features. The implemented approach has been verified using image sections from two different flights and manually extracted ground truth data from the inner city of Munich. The evaluation shows a quality of up to 70 percent.
Conference Paper
Full-text available
Caused by the rising interest in traffic surveillance for simulations and decision management many publications concentrate on automatic vehicle detection or tracking. Quantities and velocities of different car classes form the data basis for almost every traffic model. Especially during mass events or disasters a wide-area traffic monitoring on demand is needed which can only be provided by airborne systems. This means a massive amount of image information to be handled. In this paper we present a combination of vehicle detection and tracking which is adapted to the special restrictions given on image size and flow but nevertheless yields reliable information about the traffic situation. Combining a set of modified edge filters it is possible to detect cars of different sizes and orientations with minimum computing effort, if some a priori information about the street network is used. The found vehicles are tracked between two consecutive images by an algorithm using Singular Value Decomposition. Concerning their distance and correlation the features are assigned pairwise with respect to their global positioning among each other. Choosing only the best correlating assignments it is possible to compute reliable values for the average velocities.
Article
Full-text available
This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
Article
Full-text available
Car detection from aerial images has been studied for years. However, given a large-scale aerial image with typical car and background appearance variations, robust and efficient car detection is still a challenging problem. In this paper, we present a novel and robust framework for automatic car detection from aerial images. The main contribution is a new on-line boosting algorithm for efficient car detection from large-scale aerial images. Boosting with interactive on-line training allows the car detector to be trained and improved efficiently. After training, detection is performed by exhaustive search. For post processing, a mean shift clustering method is employed, improving the detection rate significantly. In contrast to related work, our framework does not rely on any priori knowledge of the image like a site-model or contextual information, but if necessary this information can be incorporated. An extensive set of experiments on high resolution aerial images using the new UltraCamD shows the superiority of our approach.
Conference Paper
Full-text available
This work presents a method for motion reconstruction. The approach is based on image moments and the bsp-tree data structure. We use invariant properties of these moments to construct a bsp-tree and determine a set of ellipses that approximates the object's shape in each frame. These ellipsoidal structures are matched, which allow us to track the object. Motion is represented by the geometric transformations between the sets of ellipses and stored in the hierarchical structure. Motion reconstruction is done by interpolating these transformations.
Conference Paper
Full-text available
This paper demonstrates how to reduce the hand labeling effort considerably by 3D information in an object detection task. In particular, we demonstrate how an efficient car detector for aerial images with minimal hand labeling effort can be build. We use an on-line boosting algorithm to incrementally improve the detection results. Initially, we train the classifier with a single positive (car) example, randomly drawn from a fixed number of given samples. When applying this detector to an image we obtain many false positive detections. We use information from a stereo matcher to detect some of these false positives (e.g. detected cars on a facade) and feed back this information to the classifier as negative updates. This improves the detector considerably, thus reducing the number of false positives. We show that we obtain similar results to hand labeling by iteratively applying this strategy. The performance of our algorithm is demonstrated on digital aerial images of urban environments.
Article
Full-text available
Research has been performed investigating the use of moments for pattern recognition in recent years. The basic problem of the influence of discretization and noise on moment accuracy as object descriptors, has been barely investigated. In this paper, the detailed error analysis involved in the moment method is discussed. Several new techniques to increase the accuracy and efficiency of moment descriptor are proposed. We utilize these results for the problem of image reconstruction from the orthogonal Legendre moments computed from discrete and noisy data. The automatic selection of an optimal number of moments is also discussed
Article
Vehicle counts and truck percentages are important input variables in both noise pollution and air quality models, but the acquisition of these variables through fixed-point methods can be expensive, labor-intensive, and provide incomplete spatial sampling. The increasing availability and decreasing cost of high spatial resolution imagery provides an opportunity to improve the descriptive ability of traffic volume analysis. This study describes an object-based classification technique to extract vehicle volumes and vehicle type distributions from aerial photos sampled throughout a large metropolitan area. We developed rules for optimizing segmentation parameters, and used feature space optimization to choose classification attributes and develop fuzzy-set memberships for classification. Vehicles were extracted from street areas with 91.8 percent accuracy. Furthermore, separation of vehicles into classes based on car, medium-sized truck, and buses/heavy truck definitions was achieved with 87.5 percent accuracy. We discuss implications of these results for traffic volume analysis and parameterization of existing noise and air pollution models, and suggest future work for traffic assessment using high-resolution remotely-sensed imagery.
Article
This paper presents a new method for the automatic detection of cars in unmanned aerial vehicle (UAV) images acquired over urban contexts. UAV images are characterized by an extremely high spatial resolution, which makes the detection of cars particularly challenging. The proposed method starts with a screening operation in which the asphalted areas are identified in order to make the car detection process faster and more robust. Subsequently, filtering operations in the horizontal and vertical directions are performed to extract histogram-of-gradient features and to yield a preliminary detection of cars after the computation of a similarity measure with a catalog of cars used as reference. Three different strategies for computing the similarity are investigated. Successively, for the image points identified as potential cars, an orientation value is computed by searching for the highest similarity value in 36 possible directions. The last step is devoted to the merging of the points which belong to the same car because it is likely that a car is identified by more than one point due to the extremely high resolution of UAV images. As outcomes, the proposed method provides the number of cars in the image, as well as the position and orientation for each of them. Interesting experimental results, conducted on a set of real UAV images acquired over an urban area, are presented and discussed.
Conference Paper
In recent years, unmanned aerial vehicles (UAVs) have gained a great importance in both military and civilian applications. In this paper, we proposed a vehicle detection method from UAVs which integrated of Scalar Invariant Feature Transform (SIFT) and Implicit Shape Model (ISM). Firstly, a set of key points was detected in the testing image by using SIFT. Secondly, feature descriptors around the key points were generated by using the ISM. Support Vector Machines (SVMs) were applied during the key points selection. The experiment used a video shoot by a UAV in a highway and the results showed the performance and the effectiveness of the method.
Article
This study presents an approach for the automatic extraction of dynamic sub-boundaries within existing agricultural fields from remote sensing imagery using perceptual grouping. We define sub-boundaries as boundaries, where a change in crop type takes a place within the fixed geometry of an agricultural field. To perform field-based processing and analysis operations, the field boundary data and satellite imagery are integrated. The edge pixels are detected using the Canny edge detector. The edge pixels are then analyzed to find the connected edge chains and from these chains the line segments are detected using the graph-based vectorization method. The spurious line segments are eliminated through a line simplification process. The perceptual grouping of the line segments is employed for detecting sub-boundaries and constructing sub-fields within the fixed geometry of agricultural fields. Our strategy for perceptual grouping involves the Gestalt laws of proximity, continuation, symmetry and closure. The processing and analysis operations are carried out on field-by-field basis. For each field, the geometries of sub-boundaries are determined through analyzing the line segments that fall within the field and the extracted sub-boundaries are integrated with the fixed geometry of the field.
Article
Moment functions have a broad spectrum of applications in image analysis, such as invariant pattern recognition, object classification, pose estimation, image coding and reconstruction. A set of moments computed from a digital image, generally represents global characteristics of the image shape, and provides a lot of information about different types of geometrical features of the image. The feature representation capability of image moments has been widely used in object identification techniques in several areas of computer vision and robotics. Geometric moments were the first ones to be applied to images, as they are computationally very simple. With the progress of research in image processing, many new types of moment functions have been introduced in the recent past, each having its own advantages in specific application areas. For example, moment invariants with respect to image rotation can be easily derived from complex moments. Orthogonal moments, on the other hand, characterize independent features of the image and thus have minimum information redundancy in a set. The properties of image moments have the following analogies in statistics and mechanics. Moments of orders zero, one, and two of a probability density function represent the total probability, the expectation, and variance respectively. In mechanics, these moments of a spatial distribution of mass give the total mass, the centroid position, and the inertia values respectively. Considering an image as a two-dimensional intensity distribution, the geometric moment functions of the pixel values with respect to their spatial locations in the image, can similarly provide the shape information such as the total image area, the coordinates of the image centroid, and the orientation. These shape characteristics can be further used to construct feature vectors that are invariant with respect to image translation, rotation and scaling. While moments of orders zero up to three are used to represent gross level image features, higher order moments contain finer details about the image and are often more sensitive to image noise. This book presents a survey of image moment functions, their properties, computational aspects and applications. The purpose of this work is (i) to provide a global view of the utility of moment functions in image analysis, (ii) to serve as a compilation of fundamental concepts and applications of moments reported in literature, and (iii) to aid researchers and academicians in the area of computer vision and image analysis with adequate reference material on moment functions. The book is organized into two parts. The mathematical framework underlying basic theoretical concepts on image moments is presented in Part 1. This includes moment definitions, derivations of important formulae and the description of significant results and algorithms. Several applications of image moments in the field of image analysis, and the description of related algorithms are given in Part 2. The first part of this monograph introduces different types of moment functions that are commonly used in image analysis, beginning with a detailed description of geometric moments and their invariant functions (Chapter 2). This chapter also gives numerical algorithms for fast computation of geometric moments of binary images. The concept of complex moments and their properties are presented in Chapter 3. These are moments with complex kernels such as radial, Fourier-Mellin and complex-domain functions. Two important orthogonal moments which have found several applications in image representation are Legendre moments and Zernike moments. The properties of Legendre polynomials, and the algorithms related to the computation of Legendre moments are given in Chapter 4. An introduction of the radial polynomials of Zernike, and the characteristics of the associated moments (Zernike moments and Pseudo-Zernike moments), and Zernike moment invariants are included in Chapter 5. Fast methods to compute Zernike moments of binary and gray-level images are also discussed. The properties of geometric moments when viewed as contravariant symmetric tensors are given in Chapter 6. The second part of this book describes the main application areas of moment functions in image analysis. The capability of moments to provide shape characteristics of an image has been widely put to use in many pattern recognition applications. Moment based algorithms in pattern recognition are briefly discussed in Chapter 7. Moment invariants have also been used as feature descriptors to identify objects, independent of the translation, rotation and scale factors of the image introduced by the camera view geometry. Object identification and classification methods are also included in Chapter 7. Object pose recovery using image moments has found several applications in computer vision. The problem of estimating the object orientation and position parameters with the help of moments computed from images is detailed in Chapter 8, together with the mathematical derivations leading to the solutions of object pose parameters for various object-camera configurations. Miscellaneous applications of moment functions in image analysis are described in Chapter 9. These include moment based algorithms for edge detection, texture segmentation, image reconstruction, clustering and thresholding. An exhaustive list of invariant functions of geometric moments is given in Appendix 1. Analytical expressions of geometric and Zernike moments of a general elliptical shape are provided in Appendix 2. The bibliographical list given in the end of this book, contains references primarily on the theory and applications of moment functions, reported in the open literature, and covers most of the important technical journals and conference proceedings in the areas of computer vision, image processing, pattern recognition, optical engineering, and robotics. The motivation for this work came from the need for a survey and compilation of various aspects of moment functions, considering their potential uses and applications in various realms of computer vision and image analysis. An attempt is made to present all important theoretical and application oriented details on most of the commonly used types of image moments. Due to obvious reasons, every method and theory on moments reported in literature could not be included. Only representative algorithms in primary application areas are discussed in detail. Among the many schemes and diverse moment based techniques developed over the past as well as in recent years, a majority of the work has been referred in bibliography, and fundamental concepts and methods have been outlined in the text.
Article
Traffic monitoring is a very important task in today’s traffic control and flow management. The acquisition of traffic data in almost real-time is essential to swiftly react to current situations. Stationary data collectors such as induction loops and video cameras mounted on bridges or traffic lights are matured methods. The latter have been thoroughly studied for instance in [1, 2], and in [5, 9] even for moving cameras. However, they deliver only local data and are not able to observe the global traffic situation. Spaceborne sensors do cover very large areas. Because of their relatively short acquisition time and their long revisit period, such systems contribute to the periodic collection of statistical traffic data to validate and improve certain traffic models.
Article
Current traffic research is mostly based on data from fixed-installed sensors like induction loops, bridge sensors, and cameras. Thereby, the traffic flow on main roads can partially be acquired, while data from the major part of the entire road network are not available. Today's optical sensor systems on satellites provide large-area images with 1-m resolution and better, which can deliver complement information to traditional acquired data. In this paper, we present an approach for automatic vehicle detection from optical satellite images. Therefore, hypotheses for single vehicles are generated using adaptive boosting in combination with Haar-like features. Additionally, vehicle queues are detected using a line extraction technique since grouped vehicles are merged to either dark or bright ribbons. Utilizing robust parameter estimation, single vehicles are determined within those vehicle queues. The combination of implicit modeling and the use of a priori knowledge of typical vehicle constellation leads to an enhanced overall completeness compared to approaches which are only based on statistical classification techniques. Thus, a detection rate of over 80% is possible with very high reliability. Furthermore, an approach for movement estimation of the detected vehicle is described, which allows the distinction of moving and stationary traffic. Thus, even an estimate for vehicles' speed is possible, which gives additional information about the traffic condition at image acquisition time.
Article
We have performed an end-to-end analysis of a simple model-based vehicle detection algorithm for aerial parking lot images. We constructed a vehicle detection operator by combining four elongated edge operators designed to collect edge responses from the sides of a vehicle. We derived the detection and localization performance of this algorithm, and verified them by experiments. Performance degradation due to different camera angles and illuminations was also examined using simulated images. Another important aspect of performance characterization — whether and how much prior information about the scene improves performance — was also investigated. As a statistical diagnostic tool for the detection performance, a computational approach employing bootstrap was used.
Article
The paper deals with moment invariants, which are invariant under general affine transformation and may be used for recognition of affine-deformed objects. Our approach is based on the theory of algebraic invariants. The invariants from second- and third-order moments are derived and shown to be complete. The paper is a significant extension and generalization of recent works. Several numerical experiments dealing with pattern recognition by means of the affiné moment invariants as the features are described.
Article
A fuzzy set is a class of objects with a continuum of grades of membership. Such a set is characterized by a membership (characteristic) function which assigns to each object a grade of membership ranging between zero and one. The notions of inclusion, union, intersection, complement, relation, convexity, etc., are extended to such sets, and various properties of these notions in the context of fuzzy sets are established. In particular, a separation theorem for convex fuzzy sets is proved without requiring that the fuzzy sets be disjoint.
Article
We present a system to detect passenger cars in aerial images along the road directions where cars appear as small objects. We pose this as a 3D object recognition problem to account for the variation in viewpoint and the shadow. We started from psychological tests to find important features for human detection of cars. Based on these observations, we selected the boundary of the car body, the boundary of the front windshield, and the shadow as the features. Some of these features are affected by the intensity of the car and whether or not there is a shadow along it. This information is represented in the structure of the Bayesian network that we use to integrate all features. Experiments show very promising results even on some very challenging images.
Article
The theory of possibility described in this paper is related to the theory of fuzzy sets by defining the concept of a possibility distribution as a fuzzy restriction which acts as an elastic constraint on the values that may be assigned to a variable. More specifically, if F is a fuzzy subset of a universe of discourse U={u} which is characterized by its membership function μF, then a proposition of the form “X is F,” where X is a variable taking values in U, induces a possibility distribution ∏X which equates the possibility of X taking the value u to μF(u)—the compatibility of u with F. In this way, X becomes a fuzzy variable which is associated with the possibility distribution ∏x in much the same way as a random variable is associated with a probability distribution. In general, a variable may be associated both with a possibility distribution and a probability distribution, with the weak connection between the two expressed as the possibility/probability consistency principle.A thesis advanced in this paper is that the imprecision that is intrinsic in natural languages is, in the main, possibilistic rather than probabilistic in nature. Thus, by employing the concept of a possibility distribution, a proposition, p, in a natural language may be translated into a procedure which computes the probability distribution of a set of attributes which are implied by p. Several types of conditional translation rules are discussed and, in particular, a translation rule for propositions of the form “X is F is α-possible,” where α is a number in the interval [0, 1], is formulated and illustrated by examples.
Conference Paper
Detection and extraction of vehicle objects in high resolution satellite imagery are required in many transportation applications. This paper presents an approach to automatic vehicle detection from aerial images. The initial extraction of candidate vehicle is based on Mean-shift algorithm with symmetric character of blob-like car structure. By fusing the density and the symmetry, the method can remove the ambiguous blobs and reduce the cost of the detected ROI processing in the subsequent stage. To verify the blob as a vehicle, log-polar shape descriptor is used for measuring similarity. The edge strengths are obtained and represented as its spatial histogram by the orientation and distance from the center of blob. The proposed algorithm is able to successfully detect the vehicle and very useful for the traffic surveillance system.
Article
Steganography is the art and science of hiding data into information. The secret message is hidden in such a way that no one can apart from the sender or the intended recipient. The least significant bit (LSB) substitution mechanism is the most common steganographic technique for embedding a secret message in an image with high capacity, while the human visual system (HVS) would be unable to notice the hidden message in the cover image. In this paper, besides employing the LSB substitution technique as a fundamental stage, we take advantage of edge detection technique. The experimental results show that the proposed scheme not only achieves high embedding capacity but also enhances the quality of the stego image from the HVS by an edge detection technique. Moreover, based on that the secret message is replaced with different LSBs, our scheme can effectively resist the image steganalysis.
Conference Paper
We present a system to detect passenger cars in aerial images where cars appear as small objects. We pose this as a 3D object recognition problem to account for the variation in viewpoint and the shadow. We started from psychological tests to find important features for human detection of cars. Based on these observations, we selected the boundary of the car body, the boundary of the front windshield and the shadow as the features. Some of these features are affected by the intensity of the car and whether or not there is a shadow along it. This information is represented in the structure of the Bayesian network that we use to integrate all features. Experiments show very promising results even on some very challenging images
The role of perceptual organization in computer vision systems is explored. This is done from four vantage points. A brief history of perceptual organization research in both humans and computer vision is offered. A classificatory structure in which to cast perceptual organization research to clarify both the nomenclature and the relationships among the many contributions is proposed. The perceptual organization work in computer vision in the context of this classificatory structure is reviewed. The array of computational techniques applied to perceptual organization problems in computer vision is surveyed
Automatic vehicle detection based on automatic histogram-based fuzzy C-means
  • Gökaşar Ghaffarian
Ghaffarian and Gökaşar: Automatic vehicle detection based on automatic histogram-based fuzzy C-means... Journal of Applied Remote Sensing 015011-14
  • W Köhler
W. Köhler, Gestalt Psychology, Liveright, New York (1929).
Laws of Organization in Perceptual Forms
  • M Wertheimer
M. Wertheimer, Laws of Organization in Perceptual Forms, Routledge & Kegan, London (1923).