基于图像力场理论的ORB特征优化方法  

ORB feature optimization method based on image force field theory

作　　者：张凤[1] 孙恩泽 袁帅[1,2] 郭鹏程[1] ZHANG Feng;SUN En-ze;YUAN Shuai;GUO Peng-cheng(School of Information and Control Engineering,Shenyang Jianzhu University,Shenyang 110168,China;State Key Laboratory of Robotics,Shenyang Institute of Automation of China Academy of Sciences,Shenyang 110000,China)

机构地区：[1]沈阳建筑大学信息与控制工程学院,沈阳110168 [2]中国科学院沈阳自动化研究所机器人学国家重点实验室,沈阳110000

出　　处：《沈阳工业大学学报》2019年第6期675-680,共6页Journal of Shenyang University of Technology

基　　金：国家自然科学基金青年科学基金项目(61305125);辽宁省自然科学基金计划重点项目(20180520037);辽宁省高等学校基本科研项目(LJZ2017020);沈阳建筑大学学科内容教育工程(XKHY2-66)

摘　　要：针对现有的移动机器人视觉图像ORB特征受图像尺度、光照和旋转影响比较大的问题,提出了一种基于图像力场理论转换的优化ORB算法.通过计算图像熵值确定图像金字塔尺度,构建稳定的ORB特征,以此解决ORB特征点的尺度不变性.采用ORB特征点的引力方向作为特征点描述子的主方向,优化ORB算法的旋转不变性.利用PROSAC算法剔除冗余ORB特征点.结果表明,本文方法在一定程度上提高了ORB特征点描述子的准确度和匹配正确率.Aiming at the problem that the ORB feature of mobile robot vision image is greatly affected by the image scale,illumination and rotation,an optimized ORB algorithm based on the image force field theory for transformation was proposed. The image pyramid scale was determined through calculating the image entropy value,and the stable ORB features were established to solve the scale invariance of ORB feature points. The gravitational direction of ORB feature points was used as the main direction of feature point descriptor to optimize the rotation invariance of ORB algorithm. The redundant ORB feature points were eliminated with the PROSAC algorithm. The results show that the as-proposed method improves the accuracy and matching accuracy of ORB feature point descriptor to a certain extent.

关 键 词：ORB特征 力场转换理论 图像熵 特征匹配 PROSAC算法 尺度不变性 光照不变性 旋转不变性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]