[1]于蕾,王萌萌,刘立,等.基于核相关滤波器的TLD目标跟踪算法[J].应用科技,2018,45(01):77-83.[doi:10.11991/yykj.201611008]
 YU Lei,WANG Mengmeng,LIU Li,et al.TLD object tracking algorithm based on kernelized correlation filters[J].Applied science and technology,2018,45(01):77-83.[doi:10.11991/yykj.201611008]
点击复制

基于核相关滤波器的TLD目标跟踪算法(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第45卷
期数:
2018年01期
页码:
77-83
栏目:
现代电子技术
出版日期:
2018-02-05

文章信息/Info

Title:
TLD object tracking algorithm based on kernelized correlation filters
作者:
于蕾1 王萌萌1 刘立2 李伟3
1. 哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001;
2. 沈阳新松机器人自动化股份有限公司, 辽宁 沈阳 110168;
3. 中国人民解放军94503部队, 山东 济南 250000
Author(s):
YU Lei1 WANG Mengmeng1 LIU Li2 LI Wei3
1. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China;
2. SIASUN Robot and Automation Company Limited, Shenyang 110168, China;
3. Unit 94503 of PLA, Jinan 250000, China
关键词:
目标跟踪TLD核相关滤波器特征融合循环矩阵跟踪成功率跟踪精度长期跟踪
Keywords:
object trackingTLDkernel correlation filtersfeature integrationcirculant matricestracking success ratetracking precisionlong-term tracking
分类号:
TN911.73
DOI:
10.11991/yykj.201611008
文献标志码:
A
摘要:
TLD(tracking-learning-detection)跟踪算法在目标作平面外旋转、快速移动和非刚性形变的情况下易跟踪失败,而核相关滤波器(kernelized correlation filters,KCF)跟踪算法可以有效应对上述跟踪情景但缺乏跟踪失败恢复机制,导致目标重新出现后无法继续跟踪。针对以上问题,通过有效结合这两种算法,提出一种基于TLD框架下的核相关滤波器跟踪检测算法。在跟踪模块中融入颜色特征,进一步增强算法的整体跟踪性能。通过在不同视频序列上进行对比实验,结果表明,与原算法相比,改进后的算法可以长时间准确地跟踪目标,并具有更高的成功率。
Abstract:
Tracking-learning-detection (TLD) tracking algorithm may fail in case of fast motion, full out-of-plane rotation and non-rigid deformation of target, while kernel correlation filter (KCF) tracking algorithm can effectively deal with the above-mentioned tracking situations, however, it lacks tracking failure recovery mechanism, so it is hard to resume tracking once the disappeared object reappears. Aiming at the above problems, an efficient combination of the two tracking algorithms was presented to devise a KCF target tracking algorithm based on TLD framework. Moreover, color feature was incorporated into the tracker to further boost the overall tracking performance. Finally, the results of contrast experiments on different video sequences show that the improved algorithm can track the target accurately for a long time and it has a higher success rate.

参考文献/References:

[1] LI Yang, ZHU Jianke, HOI S C H. Reliable patch trackers:robust visual tracking by exploiting reliable patches[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA:IEEE, 2015:353-361.
[2] SMEULDERS A W M, CHU D M, CUCCHIARA R, et al. Visual tracking:an experimental survey[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 36(7):1442-1468.
[3] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2012, 34(7):1409-1422.
[4] KALAL Z, MATAS J, MIKOLAJCZYK K. Online learning of robust object detectors during unstable tracking[C]//Proceedings of the IEEE 12th International Conference on Computer Vision Workshops. Kyoto, Japan:IEEE, 2009:1417-1424.
[5] 金哲, 刘传才. 加速的TLD算法及其在多目标跟踪中的应用[J]. 计算机系统应用, 2016, 25(6):196-201.
[6] 邢藏菊, 温兰兰, 何苏勤. TLD视频目标跟踪器快速匹配的研究[J]. 小型微型计算机系统, 2015, 36(5):1113-1116.
[7] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(3):583-596.
[8] KALAL Z, MATAS J, MIKOLAJCZYK K. P-N learning:bootstrapping binary classifiers by structural constraints[C]//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA:IEEE, 2010:49-56.
[9] VAN DE WEIJER J, SCHMID C, VERBEEK J, et al. Learning color names for real-world applications[J]. IEEE transactions on image processing, 2009, 18(7):1512-1523.
[10] WU Yi, LIM J, YANG M H. Online object tracking:a benchmark[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA:IEEE, 2013:2411-2418.
[11] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The Pascal visual object classes (VOC) challenge[J]. International journal of computer vision, 2010, 88(2):303-338.
[12] WU Yunxia, JIA Ni, SUN Jiping. Real-time multi-scale tracking based on compressive sensing[J]. The visual computer, 2015, 31(4):471-484.

相似文献/References:

[1]焦安霞,姜弢.视频序列中动目标快速跟踪新算法的研究[J].应用科技,2008,35(12):7.
 JIAO An-xia,JIANG Tao.A fast tracking algorithm for video sequence moving object[J].Applied science and technology,2008,35(01):7.
[2]赵龙,郭宝,李铁军.基于边缘增强模板匹配的PTZ主动目标跟踪系统[J].应用科技,2014,41(04):1.
 ZHAO Long,GUO Bao,LI Tiejun.Active camera tracking system for PTZ camera based on EETM algorithm[J].Applied science and technology,2014,41(01):1.
[3]诸小熊,江加和.基于核相关滤波器的目标跟踪算法[J].应用科技,2017,44(03):48.[doi:10.11991/yykj.201605013]
 ZHU Xiaoxiong,JIANG Jiahe.Visual tracking algorithm based on kernelized correlation filters[J].Applied science and technology,2017,44(01):48.[doi:10.11991/yykj.201605013]
[4]张天翼,杨忠,韩家明,等.基于连续自适应均值漂移和立体视觉的无人机目标跟踪方法[J].应用科技,2018,45(02):55.[doi:10.11991/yykj.201706012]
 ZHANG Tianyi,YANG Zhong,HAN Jiaming,et al.Approach of vision navigation of UAV based on continuously adaptive mean-shift and stereo vision[J].Applied science and technology,2018,45(01):55.[doi:10.11991/yykj.201706012]

备注/Memo

备注/Memo:
收稿日期:2016-11-11。
基金项目:国家自然科学基金项目(61003128).
作者简介:于蕾(1977-),女,副教授,博士.
通讯作者:王萌萌,E-mail:wmm0224@126.com
更新日期/Last Update: 2018-03-14