[1]程旭,郭海燕,李拟珺,等.一种基于超像素的局部判别式跟踪算法[J].东南大学学报(自然科学版),2014,44(6):1105-1110.[doi:10.3969/j.issn.1001-0505.2014.06.002]
 Cheng Xu,Guo Haiyan,Li Nijun,et al.Local discriminative tracking algorithm based on superpixel[J].Journal of Southeast University (Natural Science Edition),2014,44(6):1105-1110.[doi:10.3969/j.issn.1001-0505.2014.06.002]
点击复制

一种基于超像素的局部判别式跟踪算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
44
期数:
2014年第6期
页码:
1105-1110
栏目:
计算机科学与工程
出版日期:
2014-11-20

文章信息/Info

Title:
Local discriminative tracking algorithm based on superpixel
作者:
程旭1郭海燕12李拟珺1周同驰1周琳1吴镇扬1
1东南大学信息科学与工程学院, 南京 210096; 2南京农业大学工学院, 南京 210031
Author(s):
Cheng Xu1 Guo Haiyan12 Li Nijun1 Zhou Tongchi1 Zhou Lin1 Wu Zhenyang1
1School of Information Science and Engineering, Southeast University, Nanjing 210096, China
2College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
关键词:
视频监控 稀疏表示 目标跟踪 表观更新 超像素
Keywords:
video surveillance sparse representation object tracking appearance updating superpixel
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2014.06.002
摘要:
针对目标在复杂环境下容易受到外界干扰而发生漂移的问题,提出了一种基于超像素的局部判别式跟踪方法.首先,对视频序列前10帧的目标区域进行分割,得到超像素,并利用k-means方法对其进行聚类以构造初始字典;其次,通过训练样本集来训练线性分类器;然后,为了减少目标发生漂移的可能性,将初始训练的分类器与更新后的分类器线性加权之和定义为似然函数;最后,在粒子滤波的框架下,将似然函数值最大的粒子作为跟踪的结果,每运行U帧更新一次字典和分类器参数,以捕获目标表观的变化.仿真结果表明,所提算法在目标发生遮挡、光照变化的复杂环境下仍然能够跟踪目标.
Abstract:
To solve the drifting problem of objects caused by external disturbances under complex circumstances, a local discriminative tracking method based on superpixel is proposed. First, the objects from the first ten frames of a video are segmented into superpixels, which are clustered by the k-means algorithm to construct the initial dictionary. Secondly, a linear classifier is trained by the training sample set. Then, to reduce the possibility of the object drifting, the likelihood function is defined as a linear weighted combination of the initial classifier and the updated classifier. Finally, under the particle filter framework, the particle with the highest likelihood confidence is considered as the tracking result. The dictionary and the parameters of the classifier are updated once every U frames to capture the variation of the object appearance. The simulation results show that the proposed algorithm can track the object under the complex circumstance with object occlusion and illumination change.

参考文献/References:

[1] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5):564-577.
[2] Adam A, Rivlin E, Shimshoni I. Robust fragments-based tracking using the integral histogram [C]//2006 IEEE Conference on Computer Vision and Pattern Recognition. New York, USA, 2006:798-805.
[3] Cheng X, Li N, Zhang S, et al. Robust visual tracking with SIFT features and fragments based on particle swarm optimization [J]. Circuits, Systems, and Signal Processing, 2014, 33(5):1507-1526.
[4] Ross D A, Lim J, Lin R S, et al. Incremental learning for robust visual tracking [J]. International Journal of Computer Vision, 2008, 77(1/2/3):125-141.
[5] Kwon J, Lee K. Visual tracking decomposition [C]//2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA, 2010:1269-1276.
[6] Avidan S. Ensemble tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2):261-271.
[7] Babenko B, Yang M H, Belongie S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632.
[8] Wang S, Lu H, Yang F, et al. Superpixel tracking [C]//2011 IEEE International Conference on Computer Vision. Barcelona, Spain, 2011:1323-1330.
[9] Mei X, Ling H. Robust visual tracking and vehicle classification via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11):2259-2272.
[10] Bao C, Wu Y, Ling H, et al. Real time robust L1 tracker using accelerated proximal gradient approach [C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island, USA, 2012:1830-1837.
[11] Zhang T, Ghanem B, Liu S, et al. Robust visual tracking via structured multi-task sparse learning [J]. International Journal of Computer Vision, 2013, 101(2):367-383.
[12] Achanta R, Shaji A, Smith K, et al. SLIC superpixels [R]. Zurich, Switzerland:EPFL, 2010.
[13] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[14] Chen J J, Zhang S F, An G C, et al. A generalized mean shift tracking algorithm[J]. Science China Information Sciences, 2011, 54(11): 2373-2385.
[15] Wang Q, Chen F, Xu W, et al. Online discriminative object tracking with local sparse representation [C]//2012 IEEE Workshop on Applications of Computer Vision. Breckenridge, CO, USA, 2012:425-432.

相似文献/References:

[1]余丰,奚吉,赵力,等.基于CS与K-SVD的欠定盲源分离稀疏分量分析[J].东南大学学报(自然科学版),2011,41(6):1127.[doi:10.3969/j.issn.1001-0505.2011.06.002]
 Yu Feng,Xi Ji,Zhao Li,et al.Sparse presentation of underdetermined blind source separation based on compressed sensing and K-SVD[J].Journal of Southeast University (Natural Science Edition),2011,41(6):1127.[doi:10.3969/j.issn.1001-0505.2011.06.002]
[2]满君丰,李倩倩,温向兵.视频监控中可变人体行为的识别[J].东南大学学报(自然科学版),2011,41(3):492.[doi:10.3969/j.issn.1001-0505.2011.03.012]
 Man Junfeng,Li Qianqian,Wen Xiangbing.Recognition for changable human behaviors in video surveillance[J].Journal of Southeast University (Natural Science Edition),2011,41(6):492.[doi:10.3969/j.issn.1001-0505.2011.03.012]
[3]李邺,等.一种结合稀疏表示和切比雪夫矩的人脸识别算法[J].东南大学学报(自然科学版),2012,42(2):249.[doi:10.3969/j.issn.1001-0505.2012.02.011]
 Li Ye,Chen Beijing,et al.Face recognition algorithm by using sparse representation and Tchebichef moments[J].Journal of Southeast University (Natural Science Edition),2012,42(6):249.[doi:10.3969/j.issn.1001-0505.2012.02.011]
[4]朱永成,陈阳,罗立民,等.基于字典学习的低剂量X-ray CT图像去噪[J].东南大学学报(自然科学版),2012,42(5):864.[doi:10.3969/j.issn.1001-0505.2012.05.013]
 Zhu Yongcheng,Chen Yang,Luo Limin,et al.Dictionary learning based denoising of low-dose X-ray CT image[J].Journal of Southeast University (Natural Science Edition),2012,42(6):864.[doi:10.3969/j.issn.1001-0505.2012.05.013]
[5]程旭,张毅锋,刘袁,等.基于深度特征的目标跟踪算法[J].东南大学学报(自然科学版),2017,47(1):1.[doi:10.3969/j.issn.1001-0505.2017.01.001]
 Cheng Xu,Zhang Yifeng,Liu Yuan,et al.Object tracking algorithm based on deep feature[J].Journal of Southeast University (Natural Science Edition),2017,47(6):1.[doi:10.3969/j.issn.1001-0505.2017.01.001]

备注/Memo

备注/Memo:
收稿日期: 2014-06-12.
作者简介: 程旭(1983—),男,博士生;吴镇扬(联系人),男,教授,博士生导师,zhenyang@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(60971098, 61201345, 61302152)、现代信息科学与网络技术北京市重点实验室开放课题资助项目(XDXX1308).
引用本文: 程旭,郭海燕,李拟珺,等.一种基于超像素的局部判别式跟踪算法[J].东南大学学报:自然科学版,2014,44(6):1105-1110. [doi:10.3969/j.issn.1001-0505.2014.06.002]
更新日期/Last Update: 2014-11-20