面向煤矸体积检测的图像特征匹配算法研究  

Research on Image Feature Matching Algorithm for Volume Detection of Coal and Gangue

作　　者：曹现刚[1,2] 袁娜 王鹏 吴旭东 岳东 CAO Xiangang;YUAN Na;WANG Peng;WU Xudong;YUE Dong(School of Mechanical Engineering,Xi'an University of Science and Technology,Xi'an 710054,China;Key Laboratory of Mechanical and Electrical Equipment in Shaanxi Mine,Xi'an 710054,China;Tongchuan Mining Co.,Ltd.,Tongchuan 727000,China)

机构地区：[1]西安科技大学机械工程学院,西安710054 [2]陕西省矿山机电装备智能检测重点实验室,西安710054 [3]铜川矿业有限公司,陕西铜川727000

出　　处：《煤炭技术》2023年第2期175-178,共4页Coal Technology

基　　金：国家自然科学基金面上项目(51975468);陕西省重点研发计划项目(2018GY-160)。

摘　　要：针对煤矸体积检测过程中,SIFT特征匹配算法因时间复杂度高无法满足实时性要求,提出一种基于BRIEF描述子的改进SIFT算法。首先利用BRIEF描述子替代SIFT算法的128维特征向量,利用最小距离筛选机制结合RANSAC算法完成误匹配点对的去除。实验证明:提出的算法相较SIFT算法匹配速度提高了41.3%,而煤矸体积计算速度提高了20.2%。In the process of SIFT, SIFT cannot meet the time complexity. As a result, an improved SIFT algorithm based on BRIEF descriptor is proposed. First, the 128-dimensional feature vector of the SIFT algorithm is replaced by the BRIEF descriptor, and the minimum distance screening mechanism is used to complete the removal of mismatch point pairs combined with the RANSAC algorithm. The experiment proves that the proposed algorithm improves the matching speed by 41.3% compared with that of the SIFT algorithm, while the calculation speed of coal gangue volume increases by 20.2%.

关 键 词：煤矸体积 双目视觉 特征匹配 SIFT BRIEF 

分 类 号：TD94[矿业工程—选矿]