基于激光点云全局特征匹配处理的目标跟踪算法  

Object Tracking Algorithm Based on Global Feature Matching Processing of Laser Point Cloud

作　　者：钱其姝 胡以华 赵楠翔[1,2] 李敏乐 邵福才[3] Qian Qishu;Hu Yihua;Zhao Nanxiang;Li Minle;Shao Fucai(State Key Laboratory of Pulsed Power Laser Technology,College of Electronic Engineering,National University of Defense Technology,Hefei,Anhui 230037,China;Anhui Provincial Key Laboratory of Electronic Restriction,Hefei,Anhui 230037,China;Military Representative Bureau of the Ministry of Equipment Development of the Central Military Commission in Beijing,Beijing 100191,China)

机构地区：[1]国防科技大学电子对抗学院脉冲功率激光技术国家重点实验室,安徽合肥230037 [2]安徽省电子制约技术重点实验室,安徽合肥230037 [3]中央军委装备发展部驻北京地区军事代表局,北京100191

出　　处：《激光与光电子学进展》2020年第6期149-156,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61271353,61871389);国防科技大学重大基金(ZK18-01-02)。

摘　　要：实际场景中各物体的尺寸差异导致激光三维数据中各物体对应的三维积分区域(SVR)存在差异。在初始帧中,借助于SVR筛选与全局特征匹配完成目标识别,实现对待跟踪目标的自动选取,并且比较四种全局特征描述子的识别能力及运行速度。得到初始帧中的目标位置后,提出了利用全局特征匹配在后续帧中实施目标跟踪的方法。实验结果表明,SVR筛选有利于提高识别跟踪的准确率及算法整体运行速度。The difference in size between different kinds of objects will lead to the difference in summed volume region(SVR)of corresponding laser point cloud.In the first frame,object recognition is accomplished based on SVR selection and global feature matching to automatically select the interested object.The performance and execution time of four global feature descriptors are compared.After obtaining the position of the interested object in the first frame,an object tracking method based on global feature matching processing of laser point cloud is put forward for subsequent frames.The experimental results show that adding SVR selection is helpful to improve the accuracy of recognition and tracking and the overall running speed of the algorithm.

关 键 词：图像处理 目标跟踪 激光点云 目标识别 三维全局特征 激光雷达 

分 类 号：TN958.98[电子电信—信号与信息处理]