Chu He

Texture Classification of PolSAR Data Based on Sparse Coding of Wavelet Polarization Textons

This paper presents a frame for classifying polarimetric synthetic aperture radar (PolSAR) data. The frame is based on the combination of wavelet polarization information, textons, and sparse coding. Polarimetric synthesis unites with the discrete wavelet frame to obtain wavelet polarization variance through the calculation of the wavelet variance in the space of polarization states. The K-means cluster algorithm is implemented to cluster the wavelet polarization variance vectors of the training samples for the purpose of constructing a texton dictionary. A patch, in which all the wavelet polarization variance vectors match those in the texton dictionary, is used to obtain a statistical histogram. Sparse coding is applied to describe the histogram feature and generate a new texture feature called sparse coding of a wavelet polarization texton. Finally, support vector machine is used for the classification. All experiments are carried out on five sets of PolSAR data. The experimental results confirm that the proposed method effectively classifies PolSAR data.

Learning Based Compressed Sensing for SAR Image Super-Resolution

This paper presents a novel approach for the reconstruction of super-resolution (SR) synthetic aperture radar (SAR) images in the compressed sensing (CS) theory framework. Recent research has shown that super-resolved data can be reconstructed from an extremely small set of measurements compared to that currently required. Therefore, a CS to produce SAR super-resolution images is introduced in the present work. The proposed approach contributes in three ways. First, enhanced SR results are achieved using a framework that combines CS with a multi-dictionary. Then, the multi-dictionary pairs are trained after classifying the training images through a sparse coding spatial pyramid machine. Each dictionary pair containing low- and high-resolution dictionaries are jointly trained. Finally, the gradient-descent optimization approach is applied to decrease the mutual coherence between the measurement matrix and the representation basis. The CS reconstruction effect is related to incoherence. The effectiveness of this method is demonstrated on TerraSAR-X data.

Road Extraction From SAR Imagery Based on Multiscale Geometric Analysis of Detector Responses

In this paper, a road network grouping algorithm for Synthetic Aperture Radar (SAR) images is proposed by exploiting multiscale geometric analysis of detector responses. Before running the algorithm, a response map made up of responses, which is binarized, skeletonized, and vectorized to generate road candidates, is obtained by applying a local detector to a SAR image first. Then the proposed method identifies real road segments among the candidates and fills gaps between them. It works in three steps. 1) Guidance segments are extracted at different resolutions from the response map using multiscale techniques and merged to get a more appropriate approximation. 2) Segments are labeled “road” or “noise” using relaxation labeling techniques, among which “road” ones are grouped as they may lie on different roads. 3) Connection points between candidates are acquired by mapping candidates to grouped “road” guidance segments. Those connection points are linked with straight lines or curvilinear segments after a segmentation process. The experiments on TerraSAR images show the effectiveness of this new method.

Nonlinear Compressed Sensing-Based LDA Topic Model for Polarimetric SAR Image Classification

In this paper, a nonlinear compressed sensing-based LDA Topic (NCSLT) model is proposed for the classification of polarimetric synthetic aperture radar (PolSAR) images. The CS theory shows that when a signal is sparsely rendered on some basis, it can be recovered exactly by a relatively small set of random measurements of the original signal. In this paper, such notion is applied to a more general case to analyze nonlinear PolSAR data. Therefore, the NCSLT model is presented with the following two objectives: to capture the nonlinear structure of PolSAR data on a manifold surface using the CS theory and to provide a generative explanation for the relationship between the image pixels and high-level complex scenes for image classification by establishing a Texture-CS-Topic model. Compared with the other traditional SAR image-classification methods, the proposed method displayed potential achievements when applied to two sets of PolSAR image data.

Stereoscopic Road Network Extraction by Decision-Level Fusion of Optical and SAR Imagery

A new stereoscopic road network extraction framework based on the decision-level fusion of optical and Synthetic Aperture Radar (SAR) imagery is proposed in this paper. Three steps are included in this framework: 1) road segment extraction and structure optimization through SAR imagery, 2) road segment extraction and stereoscopic information collection through optical imagery, and 3) fusion of the SAR result with the optical image and the stereoscopic information. In this study, our new road network grouping algorithm called road network grouping based on the multi-scale geometric analysis of detector Response is used, with the improved footprint method, and the stereoscopic inversion algorithm. The most important finding of our work lies in the fusion step, by which a stereoscopic road network can be acquired after going through the three aforementioned processes and by fusing the stereoscopic information obtained from optical imagery and road network extracted from SAR imagery. Our algorithm is tested on the real TerraSAR-X and QuickBird data.

A learning-based target decomposition method using Kernel KSVD for polarimetric SAR image classification

In this article, a learning-based target decomposition method based on Kernel K-singular vector decomposition (Kernel KSVD) algorithm is proposed for polarimetric synthetic aperture radar (PolSAR) image classification. With new methods offering increased resolution, more details (structures and objects) could be exploited in the SAR images, thus invalidating the traditional decompositions based on specific scattering mechanisms offering low-resolution SAR image classification. Instead of adopting fixed bases corresponding to the known scattering mechanisms, we propose a learning-based decomposition method for generating adaptive bases and developing a nonlinear extension of the KSVD algorithm in a nonlinear feature space, called as Kernel KSVD. It is an iterative method that alternates between sparse coding in the kernel feature space based on the nonlinear dictionary and a process of updating each atom in the dictionary. The Kernel KSVD-based decomposition not only generates a stable and adaptive representation of the images but also establishes a curvilinear coordinate that goes along the flow of nonlinear polarimetric features. This proposed approach was verified on two sets of SAR data and found to outperform traditional decompositions based on scattering mechanisms.

A novel linear feature detector for SAR images

A new linear feature detector for synthetic aperture radar (SAR) images is presented in this article by embedding a three-region filter into the wedgelet analysis framework. One of its main features is that it can detect linear features with a range of varying widths and orientations in the same image by changing the direction and size of the detector mask within a multiscale framework. In addition, this detector takes into account both statistical and geometrical characteristics to detect line segments directly instead of detecting target pixels. To show its effectiveness, the detector is applied to extract one of the most important linear features: roads. Results and comparisons with several multiscale analysis techniques as well as ratio correlation detector on DLR E-SAR images reveal its advantages.

Adaptive Component Selection-Based Discriminative Model for Object Detection in High-Resolution SAR Imagery

This paper proposes an innovative Adaptive Component Selection-Based Discriminative Model (ACSDM) for object detection in high-resolution synthetic aperture radar (SAR) imagery. In order to explore the structural relationships between the target and the components, a multi-scale detector consisting of a root filter and several part filters is established, using Histogram of Oriented Gradient (HOG) features to describe the object from different resolutions. To make the detected components of practical significance, the size and anchor position of each component are determined through statistical methods. When training the root model and the corresponding part models, manual annotation is adopted to label the target in the training set. Besides, a penalty factor is introduced to compensate information loss in preprocessing. In the detection stage, the Small Area-Based Non-Maximum Suppression (SANMS) method is utilised for filtering out duplicate results. In the experiments, the aeroplanes in TerraSAR-X SAR images are detected by the ACSDM algorithm and different comparative methods. The results indicate that the proposed method has a lower false alarm rate and can detect the components accurately.

Target detection on high-resolution SAR image using Part-based CFAR Model

This letter proposed a Part-based CFAR Model for object detection of power tower on high-resolution SAR images. Firstly, Part-based Model is used to describe the structure feature of the target, then Compressing Sensing approach is added to reduce the speckle by means of rebuilding background clutter, next, CFAR method is used to extract local shape and scale parameters, at last, Part-based CFAR Model combines these procedures together to form the finally algorithm, not only includes the distribution features, but also considers the structure relationship in the proposed approach. The algorithm is tested on TerraSAR-X data set with the resolution of 1m and 3m. Experiments show that unlike the CFAR method can only gives the high-light points of the targets; Part-based CFAR Model illuminates the target and its local components by plotting the bounding boxes around them.

A novel over-segmentation method for polarimetric SAR images classification

This paper, we propose a novel over-segmentation method Feature Geometry Space Fusion (FGSF) for polarimetric SAR (POLSAR) data classification, which uses the polarimetric feature and geometric feature. In order to exam its performance, experiments on the data acquired by AIRSAR show that the over segment regions segmented by FGSF method performs better than mean shift when used for classification.