正在加载图片...
第10卷第2期 智能系统学报 Vol.10 No.2 2015年4月 CAAI Transactions on Intelligent Systems Apr.2015 D0:10.3969/j.issn.1673-4785.201401002 网s络出版地址:http:/www.cnki.net/kcms/detail/23.1538.TP.20150302.1106.010.html 基于轨迹聚类的超市顾客运动跟踪 王熙1,吴为2,钱法涛 (1.浙江大学计算机科学与技术学院,浙江杭州310027;2.浙江省网络系统及信息安全重点实验室,浙江杭州310006) 摘要:针对超市等复杂应用环境下的运动目标轨迹跟踪问题,将轨迹聚类运用于目标跟踪中,提出了一种超市顾 客运动跟踪方法。该方法对Kanade--Lucas-Tomasi(KLT)算法提取并跟踪得到的特征点轨迹进行预处理,滤除背景和 短时特征点以分离出运动目标所在区域的关键特征点:进而采用均值漂移(meanshift)算法进行轨迹聚类,解决了单 帧静态特征点聚类时的目标遮挡问题:最后采用运动跟踪匹配算法对前后帧的特征点进行最优匹配,解决了目标出 入视频区域以及具有复杂路线时的稳定跟踪问题,得到顾客的完整运动轨迹。实验结果表明,该方法能够在超市入 口、生鲜区以及收银台等各种典型超市区域中完成顾客轨迹的运动跟踪,并对顾客部分遮挡、复杂运动轨迹以及异 步运动等多种特殊情况具有较高的鲁棒性。 关键词:目标跟踪:特征匹配:轨迹聚类;运动分析 中图分类号:TP391.4文献标志码:A文章编号:1673-4785(2015)02-0187-06 中文引用格式:王熙,吴为,钱沅涛.基于轨迹聚类的超市顾客运动跟踪[J】.智能系统学报,2015,10(2):187-192. 英文引用格式:WANG Xi,WU Wei,,QIAN Yuntao..Trajectory clustering based customer movement tracking in a supermarket[J]. CAAI Transactions on Intelligent Systems,2015,10(2):187-192. Trajectory clustering based customer movement tracking in a supermarket WANG Xi',WU Wei2,QIAN Yuntao' (1.College of Computer Science,Zhejiang University,Hangzhou 310027,China;2.Zhejiang Key Laboratory of Network Technology and Information Security,Hangzhou 310006,China) Abstract:Tracking the moving targets in complex scenarios such as supermarkets can be a challenging task.This paper proposes a method to track moving customers in a supermarket by clustering the trajectories of the targets.In this method,all the background and short-time feature points are removed in the preprocessing step in order to re- fine the feature points,which were detected and tracked by the Kanade-Lucas-Tomasi (KLT)algorithm.The occlu- sion problem of single frame static feature point clustering is solved by applying the mean shift algorithm to the traj- ectories of moving objects.Finally,the full trajectories of moving customers are generated by the matching algorithm of movement tracking.The algorithm tackles the stable tracking problem by optimally matching the feature point clusters between successive frames when the target goes across the boundary of the video region or has a complex trajectory.Experimental results showed that the proposed method can successfully track the trajectories of customers in various typical regions of the supermarket such as entrance,fresh area and checkout stand.This method is robust under partial occlusion,complex trajectory and asynchronous moving. Keywords:object tracking;feature matching;trajectory clustering;feature point refining 收稿日期:2014-01-13.网络出版日期:2015-03-02. 在计算机视觉领域的各种研究和应用中,目标跟 基金项目:国家科技支撑计划资助项目(201BA2403)浙江省网络系踪一直是一项重要而又兼具挑战性的技术。目标跟 统及信息安全重点实验室开放基金资助项目(2013002). 通信作者:钱沄涛.E-mail:ytqian(@u.cdu.cm. 踪的主要任务在于对视频流中的运动信息进行分析第 10 卷第 2 期 智 能 系 统 学 报 Vol.10 №.2 2015 年 4 月 CAAI Transactions on Intelligent Systems Apr. 2015 DOI:10.3969 / j.issn.1673⁃4785.201401002 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20150302.1106.010.html 基于轨迹聚类的超市顾客运动跟踪 王熙1 ,吴为2 ,钱沄涛1 (1.浙江大学 计算机科学与技术学院,浙江 杭州 310027; 2.浙江省网络系统及信息安全重点实验室,浙江 杭州 310006) 摘 要:针对超市等复杂应用环境下的运动目标轨迹跟踪问题,将轨迹聚类运用于目标跟踪中,提出了一种超市顾 客运动跟踪方法。 该方法对 Kanade⁃Lucas⁃Tomasi(KLT)算法提取并跟踪得到的特征点轨迹进行预处理,滤除背景和 短时特征点以分离出运动目标所在区域的关键特征点;进而采用均值漂移(meanshift)算法进行轨迹聚类,解决了单 帧静态特征点聚类时的目标遮挡问题;最后采用运动跟踪匹配算法对前后帧的特征点进行最优匹配,解决了目标出 入视频区域以及具有复杂路线时的稳定跟踪问题,得到顾客的完整运动轨迹。 实验结果表明,该方法能够在超市入 口、生鲜区以及收银台等各种典型超市区域中完成顾客轨迹的运动跟踪,并对顾客部分遮挡、复杂运动轨迹以及异 步运动等多种特殊情况具有较高的鲁棒性。 关键词:目标跟踪;特征匹配;轨迹聚类;运动分析 中图分类号:TP391.4 文献标志码:A 文章编号:1673⁃4785(2015)02⁃0187⁃06 中文引用格式:王熙,吴为,钱沄涛. 基于轨迹聚类的超市顾客运动跟踪[J]. 智能系统学报, 2015, 10(2): 187⁃192. 英文引用格式:WANG Xi, WU Wei, QIAN Yuntao. Trajectory clustering based customer movement tracking in a supermarket[J]. CAAI Transactions on Intelligent Systems, 2015, 10(2): 187⁃192. Trajectory clustering based customer movement tracking in a supermarket WANG Xi 1 , WU Wei 2 , QIAN Yuntao 1 (1. College of Computer Science, Zhejiang University, Hangzhou 310027, China; 2. Zhejiang Key Laboratory of Network Technology and Information Security, Hangzhou 310006, China) Abstract:Tracking the moving targets in complex scenarios such as supermarkets can be a challenging task. This paper proposes a method to track moving customers in a supermarket by clustering the trajectories of the targets. In this method, all the background and short⁃time feature points are removed in the preprocessing step in order to re⁃ fine the feature points, which were detected and tracked by the Kanade⁃Lucas⁃Tomasi (KLT) algorithm. The occlu⁃ sion problem of single frame static feature point clustering is solved by applying the mean shift algorithm to the traj⁃ ectories of moving objects. Finally, the full trajectories of moving customers are generated by the matching algorithm of movement tracking. The algorithm tackles the stable tracking problem by optimally matching the feature point clusters between successive frames when the target goes across the boundary of the video region or has a complex trajectory. Experimental results showed that the proposed method can successfully track the trajectories of customers in various typical regions of the supermarket such as entrance, fresh area and checkout stand. This method is robust under partial occlusion, complex trajectory and asynchronous moving. Keywords:object tracking; feature matching; trajectory clustering; feature point refining 收稿日期:2014⁃01⁃13. 网络出版日期:2015⁃03⁃02. 基金项目:国家科技支撑计划资助项目(2011BAD24B03)浙江省网络系 统及信息安全重点实验室开放基金资助项目(2013002). 通信作者:钱沄涛. E⁃mail:ytqian@ zju.edu.cn. 在计算机视觉领域的各种研究和应用中,目标跟 踪一直是一项重要而又兼具挑战性的技术。 目标跟 踪的主要任务在于对视频流中的运动信息进行分析
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有