No abstract

Abstract:In recent years, sparse representation-based techniques have shown great potential for pattern recognition problems. In this paper, the problem of polarimetric synthetic aperture radar (PolSAR) image classification is investigated using sparse representation-based classifiers (SRCs). We propose to take advantage of both polarimetric information and contextual information by combining sparsity-based classification methods with the concept of superpixels. Based on polarimetric feature vectors constructed by stacking a variety of polarimetric signatures and a superpixel map, two strategies are considered to perform polarimetric-contextual classification of PolSAR images. The first strategy starts by classifying the PolSAR image with pixel-wise SRC. Then, spatial regularization is imposed on the pixel-wise classification map by using majority voting within superpixels. In the second strategy, the PolSAR image is classified by taking superpixels as processing elements. The joint sparse representation-based classifier (JSRC) is employed to combine the polarimetric information contained in feature vectors and the contextual information provided by superpixels. Experimental results on real PolSAR datasets demonstrate the feasibility of the proposed approaches. It is proven that the classification performance is improved by using contextual information. A comparison with several other approaches also verifies the effectiveness of the proposed approach.

In this paper, we propose a variational multiphase segmentation framework for synthetic aperture radar (SAR) images based on the statistical model and active contour methods. The proposed method is inspired by the multiregion level set partition approaches but with two improvements. First, an energy functional which combines the region information and edge information is defined. The regional term is based on the G 0 statistical model. The flexibility of G 0 distribution makes the proposed approach to segment SAR images of various types. Second, we use fuzzy membership functions to represent the regions. The total variation of the membership functions is used to ensure the regularity. This not just guarantees the energy functional to be convex with respect to the membership functions but also enables us to adopt a fast iteration scheme to solve the minimization problem. The proposed method can segment SAR images of N regions with N − 1 membership functions. The flexibility of the proposed method is demonstrated by experiments on SAR images of different resolutions and scenes. The computational efficiency is also verified by comparing with the level-set-method-based SAR image segmentation approach.

No abstract

Synthetic aperture radar (SAR) automatic target recognition (ATR) is playing a very important role in military and civil field. Much work has been done to improve the performance of SAR ATR systems. It is well-known that ensemble methods can be used for improving prediction performance. Thus recognition using multiple classifiers fusion (MCF) has become a research hotspot in SAR ATR. Most current researchers focus on the fusion methods by parallel structure. However, such parallel structure has some disadvantages, such as large time consumption, features attribution conflict and low capability on confuser recognition. A hierarchical propelled strategy for multi-classifier fusion (HPSMCF) is proposed in this paper. The proposed HPSMCF has the characters both of series and parallel structure. Features can be used more effective and the recognition efficiency can be improved by extracting features and fusing the probabilistic outputs in a hierarchical propelled way. Meanwhile, the confuser recognition can be achieved by setting thresholds for the confidence in each level. Experiments on MSTAR public data demonstrate that the proposed HPSMCF is robust for variant recognition conditions. Compared with the parallel structure, HPSMCF has better performance both on time consumption and recognition rate.