Kefeng Ji

Region-Based Classification of Polarimetric SAR Images Using Wishart MRF

The scattering measurements of individual pixels in polarimetric SAR images are affected by speckle; hence, the performance of classification approaches, taking individual pixels as elements, would be damaged. By introducing the spatial relation between adjacent pixels, a novel classification method, taking regions as elements, is proposed using a Markov random field (MRF). In this method, an image is oversegmented into a large amount of rectangular regions first. Then, to use fully the statistical a priori knowledge of the data and the spatial relation of neighboring pixels, a Wishart MRF model, combining the Wishart distribution with the MRF, is proposed, and an iterative conditional mode algorithm is adopted to adjust oversegmentation results so that the shapes of all regions match the ground truth better. Finally, a Wishart-based maximum likelihood, based on regions, is used to obtain a classification map. Real polarimetric images are used in experiments. Compared with the other three frequently used methods, higher accuracy is observed, and classification maps are in better agreement with the initial ground maps, using the proposed method.

Ship Classification in TerraSAR-X Images With Feature Space Based Sparse Representation

Ship classification is the key step in maritime surveillance using synthetic aperture radar (SAR) imagery. In this letter, we develop a new ship classification method in TerraSAR-X images based on sparse representation in feature space, in which the sparse representation classification (SRC) method is exploited. In particular, to describe the ship more accurately and to reduce the dimension of the dictionary in SRC, we propose to employ a representative feature vector to construct the dictionary instead of utilizing the image pixels directly. By testing on a ship data set collected from TerraSAR-X images, we show that the proposed method is superior to traditional methods such as the template matching (TM), K-nearest neighbor (K-NN), Bayes and Support Vector Machines (SVM).

A Bilateral CFAR Algorithm for Ship Detection in SAR Images

A bilateral constant false alarm rate (CFAR) algorithm for ship detection in synthetic aperture radar (SAR) images is proposed in this letter. Compared to the standard CFAR algorithm, the proposed algorithm can reduce the influence of SAR ambiguities and sea clutter, by means of a combination of the intensity distribution and the spatial distribution of SAR images. The spatial distribution plays an equally important role as the intensity distribution. It is estimated before ship detection by a new kernel density estimation algorithm proposed in this letter. The experimental results of typical SAR images show that the algorithm is effective.

Local Sparsity Divergence for Hyperspectral Anomaly Detection

Anomaly detection (AD) has increasingly become important in hyperspectral imagery (HSI) owing to its high spatial and spectral resolutions. Many anomaly detectors have been proposed, and most of them are based on a Reed-Xiaoli (RX) detector, which assumes that the spectrum signature of HSI pixels can be modeled with Gaussian distributions. However, recent studies show that the Gaussian and other unimodal distributions are not a good fit to the data and often lead to many false alarms. This letter proposes a novel hyperspectral AD algorithm based on local sparsity divergence (LSD) without any distribution hypothesis. Our algorithm exploits the fact that targets and background lie in different low-dimensional subspaces and that targets cannot be effectively represented by their local surrounding background. A sliding dual-window strategy is first adopted to construct local spectral and spatial dictionaries, which enable the extraction of the sparse coefficients of each HSI pixel. Then, a consistent sparsity divergence index is proposed to compute the LSD map at each spectral band separately. Finally, joint segmentation of LSD maps over different bands is performed for AD. Experimental results on both simulated data and recorded data demonstrate the effectiveness of the proposed algorithm.

Ship Surveillance by Integration of Space-borne SAR and AIS – Review of Current Research

Ship surveillance is important for maritime security and safety. It plays important roles in many applications including ocean environment monitoring, search and rescue, anti-piracy and military reconnaissance. Among various sensors used for maritime surveillance, space-borne Synthetic Aperture Radar (SAR) is valued for its high resolution over wide swaths and all-weather working capabilities. However, the state-of-the-art algorithms for ship detection and identification do not always achieve a satisfactory performance. With the rapid development of space-borne Automatic Identification System (AIS), near real-time and global surveillance has become feasible. However, not all ships are equipped with or operate AIS. Space-borne SAR and AIS are considered to be complementary, and ship surveillance using an integrated combination has attracted much attention. In order to summarize the achievements and present references for further research, this paper attempts to explicitly review the developments in previous research as the basis of a brief introduction to space-borne SAR and AIS.

Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection

Synthetic aperture radar (SAR) ship detection has been playing an increasingly essential role in marine monitoring in recent years. The lack of detailed information about ships in wide swath SAR imagery poses difficulty for traditional methods in exploring effective features for ship discrimination. Being capable of feature representation, deep neural networks have achieved dramatic progress in object detection recently. However, most of them suffer from the missing detection of small-sized targets, which means that few of them are able to be employed directly in SAR ship detection tasks. This paper discloses an elaborately designed deep hierarchical network, namely a contextual region-based convolutional neural network with multilayer fusion, for SAR ship detection, which is composed of a region proposal network (RPN) with high network resolution and an object detection network with contextual features. Instead of using low-resolution feature maps from a single layer for proposal generation in a RPN, the proposed method employs an intermediate layer combined with a downscaled shallow layer and an up-sampled deep layer to produce region proposals. In the object detection network, the region proposals are projected onto multiple layers with region of interest (ROI) pooling to extract the corresponding ROI features and contextual features around the ROI. After normalization and rescaling, they are subsequently concatenated into an integrated feature vector for final outputs. The proposed framework fuses the deep semantic and shallow high-resolution features, improving the detection performance for small-sized ships. The additional contextual features provide complementary information for classification and help to rule out false alarms. Experiments based on the Sentinel-1 dataset, which contains twenty-seven SAR images with 7986 labeled ships, verify that the proposed method achieves an excellent performance in SAR ship detection.

Ship Surveillance by Integration of Space-borne SAR and AIS – Further Research

Many countries are making increased efforts to improve marine security and safety and develop ship surveillance techniques to satisfy the increasing demands. Space-borne Synthetic Aperture Radar (SAR) delivers high performance day/night all weather capabilities and a space-based Automatic Identification System (AIS) can give near real time and global coverage. Limited by the development of sensors and data processing techniques, the integration of space-borne SAR and AIS has much to offer ship surveillance. State-of-the-art data fusion methods have generally provided satisfactory performance. However, in high-density shipping or high sea-states, performance quality is less assured. This paper firstly investigates improved data association methods. The association methods based on the position feature are improved, and multi-feature-based association methods are proposed. Then, ship identification and tracking by the integration of space-borne SAR and AIS are researched further. Multi-source data fusion strategy is also investigated. Finally, the discussion is presented and the future works are emphasized in the conclusion.

Region-Based Classification of SAR Images Using Kullback–Leibler Distance Between Generalized Gamma Distributions

For the classification of synthetic aperture radar (SAR) images, traditional pixel-based Bayesian classifiers suffer from an intrinsic flaw that categories with serious overlapped probability density functions cannot be well classified. To solve this problem, in this letter, a region-based classifier for SAR images is proposed, where regions, instead of individual pixels, are treated as elements for classification. In the algorithm, each region is assigned to the class that minimizes a criterion referring to the Kullback-Leibler distance. Besides, the generalized gamma distribution (GΓD), a flexible empirical model, is employed for the statistical modeling of SAR images. Finally, with a synthetic image and an actual SAR image acquired by the EMISAR system, the effectiveness of the proposed algorithm is validated, compared with the pixel-based maximum-likelihood method and two region-based Bayesian classifiers.

A modified faster R-CNN based on CFAR algorithm for SAR ship detection

SAR ship detection is essential to marine monitoring. Recently, with the development of the deep neural network and the spring of the SAR images, SAR ship detection based on deep neural network has been a trend. However, the multi-scale ships in SAR images cause the undesirable differences of features, which decrease the accuracy of ship detection based on deep learning methods. Aiming at this problem, this paper modifies the Faster R-CNN, a state-of-the-art object detection networks, by the traditional constant false alarm rate (CFAR). Taking the objects proposals generated by Faster R-CNN for the guard windows of CFAR algorithm, this method picks up the small-sized targets. By reevaluating the bounding boxes which have relative low classification scores in detection network, this method gain better performance of detection.

Deep Convolutional Highway Unit Network for SAR Target Classification With Limited Labeled Training Data

The deep convolutional neural network (CNN) has been widely used for target classification, because it can learn highly useful representations from data. However, it is difficult to apply a CNN for synthetic aperture radar (SAR) target classification directly, for it often requires a large volume of labeled training data, which is impractical for SAR applications. The highway network is a newly proposed architecture based on CNN that can be trained with smaller data sets. This letter proposes a novel architecture called the convolutional highway unit to train deeper networks with limited SAR data. The unit architecture is formed by modified convolutional highway layers, a maxpool layer, and a dropout layer. Then, the networks can be flexibly formed by stacking the unit architecture to extract deep feature representations for classification. Experimental results on the moving and stationary target acquisition and recognition data set indicate that the branched ensemble model based on the unit architecture can achieve 99% classification accuracy with all training data. When the training data are reduced to 30%, the classification accuracy of the ensemble model can still reach 94.97%.