Parallel matching of mining area remote sensing images based on maximum stable extreme region

摘要：

　　In this paper, the stability and the accuracy of stereo image matching is not currently widespread at the same time.we use the Pyramid and the partition strategy, first of all, using the affine transformation of ellipse in the multi scale space to fit maximally stable extreme region to obtain the initial large feature points, and then through the restriction order Pyramid image of the initial feature point of bad pixels to obtain good initial feature points, finally through the block image parallel SIFT algorithm to achieve accurate matching, improving efficiency.Experiments show that the remote sensing stereo images parallel matching based on maximally stable extreme region can improve the matching efficiency ,the rotation, the zoom, and the view of transformation of the images are more resistant, the matching precision can be to sub-pixel, applicable to a wide range of remote sensing images matching.

关键词： Maximum stable extreme region Parallel matching Affine transformation model

作者: Wenping Song Zhiqiang Yang Jiang Wu Ying Lu

作者单位: Geological Engineering and Geomatics School of Changan University, Xian 710054, China Geological Engineering and Geomatics School of Changan University, Xian 710054, China;Geology Scho Northwest Land Resources Research Center of Shaanxi Normal University, Xian 710054, China

会议类型: 国际会议

会议名称: 2015 International Academic Forum for Mine Surveying in China(2015中国国际矿山测量学术论坛)

会议地点: 北京

会议语种:英文

页码: 450-454

在线出版日期: 2015-10-16（万方平台首次上网日期，不代表论文的发表时间）