Wenxian Yu

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.

Superpixel-Based Classification With an Adaptive Number of Classes for Polarimetric SAR Images

Polarimetric synthetic aperture radar (PolSAR) image classification, an important technique in the remote sensing area, has been deeply studied for a couple of decades. In order to develop a robust automatic or semiautomatic classification system for PolSAR images, two important problems should be addressed: 1) incorporation of spatial relations between pixels; 2) estimation of the number of classes in the image. Therefore, in this paper, we present a novel superpixel-based classification framework with an adaptive number of classes for PolSAR images. The approach is mainly composed of three operations. First, the PolSAR image is partitioned into superpixels, which are local, coherent regions and preserve most of the characteristics necessary for image information extraction. Then, the number of classes and each class center within the data are estimated using the pairwise dissimilarity information between superpixels, followed by the final classification operation. The proposed framework takes the spatial relations between pixels into consideration and makes good use of the inherent statistical characteristics and contour information of PolSAR data. The framework is capable of improving the classification accuracy, making the results more understandable and easier for further analyses, and providing robust performance under various numbers of classes. The performance of the proposed classification framework on one synthetic and three real data sets is presented and analyzed; and the experimental results show that the framework provides a promising solution for unsupervised classification of PolSAR images.

A High-Performance Feature-Matching Method for Image Registration by Combining Spatial and Similarity Information

A crucial problem that involves feature-based image registration algorithms is how to reliably establish the correspondence between the features detected in the sensed image and those detected in the reference image. Generally, most existing methods only use spatial relations or feature similarity, or a simple combination of them, to solve this problem, and all have some limitations. In this paper, a new feature-matching strategy is developed. It is realized by introducing a function whose independent variable is the match matrix, which describes the correspondence of the features, to combine spatial relations and organically feature similarity, and its global maximum is assumed to be reached if the sensed image is completely aligned with the reference image. Thus, the feature correspondence can be estimated by finding the maximum of the function. Two approaches are devised to solve the optimization problem. One is based on the branch-and-bound strategy to yield a global optimal solution, and the other uses an iterative algorithm that combines graduated assignment and variable metric methods to search for a local optimal solution with low computational complexity. The proposed method can work without the limitations of feature type, similarity criterion, and transform model, and its performance is evaluated using a variety of real images. Compared with some existing methods, it is fast and robust, and has the highest accuracy.

An ISAR Imaging Method Based on MIMO Technique

With the inverse synthetic aperture radar (ISAR) imaging model, targets should move smoothly during the coherent processing interval (CPI). Since the CPI is quite long, fluctuations of a targets velocity and gesture will deteriorate image quality. This paper presents a multiple-input-multiple-output (MIMO)-ISAR imaging method by combining MIMO techniques and ISAR imaging theory. By using a special M-transmitter N-receiver linear array, a group of M orthogonal phase-code modulation signals with identical bandwidth and center frequency is transmitted. With a matched filter set, every target response corresponding to the orthogonal signals can be isolated at each receiving channel, and range compression is completed simultaneously. Based on phase center approximation theory, the minimum entropy criterion is used to rearrange the echo data after the targets velocity has been estimated, and then, the azimuth imaging will finally finish. The analysis of imaging and simulation results show that the minimum CPI of the MIMO-ISAR imaging method is 1/MN of the conventional ISAR imaging method under the same azimuth-resolution condition. It means that most flying targets can satisfy the condition that targets should move smoothly during CPI; therefore, the applicability and the quality of ISAR imaging will be improved.

StructSLAM: Visual SLAM With Building Structure Lines

We propose a novel 6-degree-of-freedom (DoF) visual simultaneous localization and mapping (SLAM) method based on the structural regularity of man-made building environments. The idea is that we use the building structure lines as features for localization and mapping. Unlike other line features, the building structure lines encode the global orientation information that constrains the heading of the camera over time, eliminating the accumulated orientation errors and reducing the position drift in consequence. We extend the standard extended Kalman filter visual SLAM method to adopt the building structure lines with a novel parameterization method that represents the structure lines in dominant directions. Experiments have been conducted in both synthetic and real-world scenes. The results show that our method performs remarkably better than the existing methods in terms of position error and orientation error. In the test of indoor scenes of the public RAWSEEDS data sets, with the aid of a wheel odometer, our method produces bounded position errors about 0.79 m along a 967-m path although no loop-closing algorithm is applied.

Numerical Simulation of Vector Wave Scattering From the Target and Rough Surface Composite Model With 3-D Multilevel UV Method

Numerical simulation of vector wave scattering from three-dimensional (3-D) target and rough surface composite model is investigated with a 3-D multilevel UV method. Due to the adoption of RWG basis functions for accurate modeling of vector current, the oscillation of the interaction matrix elements brings difficulty to directly apply the UV decomposition method. Based on the reordering of the interaction strength and the sampling according to the characteristics distribution of the interaction, an EM-interaction-based sampling algorithm is developed for the accurate reconstruction of the far interaction submatrix with UV decomposition method. Combined with multilevel division of the total composite model, the 3-D multilevel UV method incorporating the new sampling algorithm is developed for vector wave scattering from 3-D complex target above or on a random rough surface. The 3-D multilevel UV method yields a complexity of O(N log N) for the setup time of the impedance matrix, the solve time of the matrix iterative solution and also for the memory requirements. The accuracy and the efficiency of the 3-D multilevel UV method is compared and validated with the full MOM method and the ACA method in the tested cases. Finally, the applications of a target above or on the rough surface, for example, a ship on the sea surface, have been accomplished and analyzed.

SAR Image Classification Based on CRFs With Integration of Local Label Context and Pairwise Label Compatibility

Context information plays a critical role in SAR image classification, as high-resolution SAR data provides more information on scene context and visual structures. This paper presents a novel classification method for SAR images based on conditional random fields (CRFs) with integration of low-level features, local label context, and pairwise label compatibility. First, we extract the low-level features used in the SVM-based unary classifier for SAR images. The supertexture is newly introduced as one of the low-level features to model the texture context between image patches. Then, we describe the context information, including local context potential and pairwise potential. Incorporation of the category context helps to resolve the ambiguities of the unary classifier. The performance of our approach in both accuracy and visual appearance for high-resolution SAR image classification is proved in the experiments.

Edge Extraction for Polarimetric SAR Images Using Degenerate Filter With Weighted Maximum Likelihood Estimation

The classic region-based filter for edge extraction for polarimetric synthetic aperture radar images is theoretically founded and efficient. However, in practical use, its performance is limited because the assumption of independence and identical distribution is often not met, particularly in heterogeneous areas. In this letter, we present a degenerate filter design integrated with the weighted maximum likelihood estimation to overcome this limitation. The performance of the proposed methodology is presented and analyzed on both simulated and real experimental data sets using visual presentation, as well as numerical evaluation and comparison with the classic method. They both demonstrate the availability and advantage of the proposed method.

Automatic Incorporation of Surface Wave Poles in Discrete Complex Image Method

Discrete complex image method is introduced to get a closed-form dyadic Green’s function by a sum of spherical waves. However, the simulation result by the traditional discrete complex image method is only valid in near-field for several wavelengths. In this paper, we analyze the form of spectral domain dyadic Green’s function in the whole kρ plane and the variety of valid range of simulation results by different sampling paths in two-level discrete complex image method. Consequently, for dyadic Green’s function, surface wave pole contribution both in spectral domain and spatial domain is clarified. We introduce the automatic incorporation of surface wave poles in discrete complex image method without extracting surface wave poles. The contribution of surface wave poles in spectral domain and spatial domain dyadic Green’s function is further confirmed in the new

The BCGS-FFT Method Combined With an Improved Discrete Complex Image Method for EM Scattering From Electrically Large Objects in Multilayered Media

This paper presents an efficient algorithm combining the stabilized biconjugate gradient fast Fourier transform (BCGS-FFT) method with an improved discrete complex image method (DCIM) for electromagnetic scattering from electrically large objects in both lossless and lossy multilayered media. The required spatial Greens functions obtained by the improved DCIM are accurate both in the near- and far-field regions without any quasi-static and surface-wave extraction. Then, the scattering by buried objects is considered using the BCGS-FFT method combined with the improved DCIM. Numerical results show the improved DCIM can save tremendous CPU time in scattering involving buried objects.