利用亮度排序的快速鲁棒特征描述与匹配算法  

Speeded Up Robust Feature Descriptors and Matching Algorithm Based on Brightness Order

作　　者：乔玉庆 耿则勋[1] 徐志军 卢兰鑫 QIAO Yuqing;GENG Zexun;XU Zhijun;LU Lanxin(Information Engineering University,Zhengzhou 450001,China;63883 Troops,Luoyang 471000,China)

机构地区：[1]信息工程大学 [2]63883部队

出　　处：《测绘科学技术学报》2017年第6期617-621,共5页Journal of Geomatics Science and Technology

基　　金：国家自然科学基金项目(11373043)

摘　　要：针对快速鲁棒特征SURF描述符匹配精度不高且对光照变化不具有鲁棒性的问题,提出利用亮度排序的快速鲁棒特征描述与匹配算法。该方法在SURF算法的基础上,对特征邻域像素的灰度值进行排序和分段。通过建立索引表对每段的像素进行表示形成描述子,再将每段的描述子串联形成特征描述符对影像进行匹配。实验表明,该算法较SURF算法匹配精度高,匹配可靠性方面提高74.7%,且对线性及非线性光照变化均具有较好的鲁棒性。A speeded up robust feature descriptors and matching algorithm based on brightness order is designed to overcome the problems of precision and robustness of the original SURF algorithm.Pixels are sorted and segmented according to gray values in the features support region based on the SURF algorithm.By establishing an index table,each segment of the pixel is represented to form a descriptor,and each segment of the descriptor is serially connected to form a feature descriptor to match the image.The experimental results show that the proposed method is more higher matching accuracy whose matching reliability is improved by 74.4%,and better robustness to linear or nonlinear illumination changes compared with SURF.

关 键 词：SURF算法 亮度排序 特征匹配 索引表 特征描述符 

分 类 号：P237[天文地球—摄影测量与遥感]