【作者】 杨华； 邹月娴； 刘志刚； 时广轶； 关佩； 王一言；

【Author】 Yang Hua~1 Zou Yuexian~2 Liu Zhigang~1 Shi Guangyi~2 Guan Pei~1 Wang Yiyan~2 (1 Southwest Jiaotong University,Traction Power State Key Laboratory Chengdu 610031 China; 2 Shenzhen Graduate School of Peking University Key Laboratory of Integrated Microsystems Shenzhen 518055 China)

【机构】 西南交通大学牵引动力国家重点实验室； 北京大学深圳研究生院集成微系统科学工程与应用国家级重点实验室；

【摘要】 基于视频的车辆跟踪技术已经成为车辆跟踪技术的主要研究方向。能否在复杂的交通场景下,鲁棒地、实时地对车辆进行跟踪成为衡量跟踪方法优劣的重要标准。本文介绍了四种主要的基于视频的车辆跟踪方法,并分别讨论了这些方法在复杂交通场景下的适用性和性能。文章着重介绍了一种基于区域特征匹配的车辆跟踪算法,运用该跟踪算法能有效地对交叉路口的车辆进行跟踪。更多还原

【Abstract】 Video-based vehicle tracking techniques have become the main research direction of vehicle tracking. The studies of vehicles tracking focus on how to obtain robust and real-time vehicle tracking in complex traffic scenes.In this paper,four mainstream methods are introduced for video-based vehicle tracking,and the applicability and tracking capability of these methods are discussed in complex traffic scenes.Additionally,a vehicle tracking algorithm based on regional characteristic matching is mainly introduced,which can track vehicles efficiently at traffic intersections.更多还原