Search

Aiming at the problem of high false alarm rate and missing rate with single detection method, an improved target detection algorithm for crashed plane detection is proposed in this paper. The method firstly detects the possible existence of the crashed plane with Yamaguchi decomposition and Constant False Alarm Rate (CFAR). Then, the detection results of the two methods are processed by pre-determination, and the final result is achieved by fusion and complementary detection. Simulation experimental results with real polarimetric data from NASA/JPL UAVSAR system demonstrate that the proposed method decreases the false alarm rate and missing rate effectively.

Based on the analysis of the polarization scattering characteristics of aircraft targets, using aircraft tail dihedral returns strong double-bounce and helix scattering signatures, a novel method of automatic target detection for crashed aircraft based on Yamaguchi polarimetric decomposition is proposed.

River boundaries extraction on SAR images is valuable for flood monitoring. Traditional methods usually failed in high relief areas. We proposed a river boundaries extraction method to conquer the difficulty to discriminate rivers from mountain shadows through fusing GIS information.

In this paper, an iterative algorithm, which is based on support vector machine (SVM), is proposed for synthetic aperture radar (SAR) image segmentation. The proposed method considers the SAR image segmentation as the pixel classification. The pixels of the previous segmented image are regarded as the training samples for SVM, which is used to re-segment the image. These iterations are repeated until the convergence, which is determined by checking the relative change of the entropy between two consecutive segmented images. Experimental results show that compared with, the proposed algorithm can achieve much better segmented results than the Markov random field (MRF) algorithm, and the proposed method dramatically reduces the influence of initial segmentation on the final result.