分块鲁棒主成分分析的撞击坑图像检测识别

A Robust Crater Detection and Recognition Method Based on Blocked Principal Components Analysis

针对遥感图像地形背景复杂的问题,提出分块鲁棒主成分分析的撞击坑候选区域自动提取方法.基于图像分块,采用交替方向乘子算法进行结构稀疏的低秩分解,低秩成分表示冗余相似的背景,稀疏成分代表包含潜在撞击坑的显著区域.针对显著的区域图采用数学形态运算分割获取候选的撞击坑图像,并通过对候选图像进行稀疏表示的分类,识别出真实撞击坑.基于火星和月球图像的实验结果表明,该方法能去除复杂地形和光照的干扰,检测率达到91.7%.

Crater is important for analyzing the relative dating of planetary and lunar surfaces. For the complex terrains in remote sensing images,a robust blocked principal components analysis（ RPCA） approach was proposed to automatically detect crater candidate regions. An alternating direction multipliers algorithm was presented for RPCA based on the blocked planetary images. The background is modeled as a low-rank matrix,and the salient regions map is represented by structure sparse parts that contain potential craters. The crater candidates are obtained by mathematical morphological operations for the saliency regions map,they are precisely distinguished from falsely detected ones through a sparse representation classifier in feature space. Experiments on the images from Mars and Moon demonstrate show that the accuracy rate of crater recognition can reach up to 91. 7% by effectively eliminating the effects of background and illumination.