微信服务号

微信订阅号

2025-6-5- 6
Home > Archive>Volume 26, Issue 10, 2015 >2733-2747. DOI:10.13328/j.cnki.jos.004737
PDF HTML XML Export Cite reminder
Object Tracking Based on Component-Level Appearance Model
Author:
Affiliation:

  • Article
    • | |
  • Metrics
    • |
  • Reference [39]
    • |
  • Related [20]
    • |
  • Cited by [1]
    • | |
  • Comments
    Abstract:

    Abstract: Dealing with factors such as overlap, blurs from quickly moving and severe deformation, accurate and stable object tracking has become a critical challenge in compute vision field. First, in this paper, superpixels are used as middle level visual clue to describe the components of object/background with the color histograms of components as their features. The initial appearance model is proposed by clustering the features of a component library. The locality and flexibility of components representations allow the appearance model to describe object/background much more accurately. Then, the Bayesian filter model is used to compute the initial state of target region, and an algorithm is proposed to check and deal with the disturbance introduced by similar objects to avoid drift and obtain more robust tracking result. Finally, to reduce the influences of deformation, overlap and blurs to better preserve the features of object, an online appearance model update algorithm is developed based on the complementary set of the features of components library to enable the appearance model to reflect the real-time variation of object/background by the changes of components. Many experiments on video sequences with different tracking challenges (totally about 12 sequences) show that, compared with the existing object tracking methods, the proposed tracking algorithm results in less error of center position and more successful frame, and therefore can track an object more accurately, stably and effectively.

    Reference
    [1] Yilmaz A, Javed O, Shah M. Object tracking: A survey. ACM Computing Surveys, 2006,38(4). [doi: 10.1145/1177352.1177355]
    [2] Yang HX, Shao L, Zheng F, Wang L, Song Z. Recent advances and trends in visual tracking: A review. Neurocomputing, 2011, 74(18):3823-3831. [doi: 10.1016/j.neucom.2011.07.024]
    [3] Avidan S. Ensemble tracking. In: Proc. of the 18th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). San Diego, 2005. 494-501. [doi: 10.1109/CVPR.2005.144]
    [4] Hua S, Li CH, Wei FM, Wang HW. Moving object tracking based on location and confidence of pixels. Journal of Computer Research and Development, 2008,42(10):1726-1732 (in Chinese with English abstract).
    [5] Lim J, Ross D, Lin RS, Yang MH. Incremental learning forvisual tracking. In: Proc. of the Neural Information Processing Systems Foundation. 2005. 793-800. http://papers.nips.cc/book/advances-in-neural-information-processing-systems-18-2005
    [6] Babenko B, Yang MH, Belongie S. Visual tracking with onlinemultiple instance learning. In: Proc. of the 22th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). 2009. 983-990. [doi: 10.1109/CVPR.2009.5206737]
    [7] Mei X, Ling H. Robust visual tracking using l1 minimization. In: Proc. of the 12th IEEE Int'l Conf. on Computer Vision (ICCV). Kyoto, 2009. 1436-1443. [doi: 10.1109/ICCV.2009.5459292]
    [8] Kwon J, LeeK M. Visual tracking decomposition. In: Proc. of the 23th IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). San Francisco, 2010. 1269-1276. [doi: 10.1109/CVPR.2012.6247880]
    [9] Godec M, Roth PM, Bischof H. Hough-Based tracking of non-rigid objects. In: Proc. of the 13th IEEE Int'l Conf. on Computer Vision (ICCV). Barcelona, 2011. 81-88. [doi: 10.1109/ICCV.2011.6126228]
    [10] Wang S, Lu H, Yang F, Yang MH. Superpixel tracking. In: Proc. of the 13th IEEE Int'l Conf. on Computer Vision (ICCV). Barcelona, 2011. 1323-1330. [doi: 10.1109/ICCV.2011.6126385]
    [11] Wang JY, Chen XL, Gao W, Zhao DB. Adaptive appearance model robust to background variations. Ruan Jian Xue Bao/Journal of Software, 2006,17(5):1001-1008 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/17/1001.htm
    [12] Ren X, Malik J. Learning a classification model for segmentation. In: Proc. of the 9th IEEE Int'l Conf. on Computer Vision (ICCV). Nice, 2003. 10-17. [doi: 10.1109/ICCV.2003.1238308]
    [13] Mori G, Ren X, Efros A, Malik J. Recovering human body configurations: Combining segmentation and recognition. In: Proc. of the 17th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVRP). Washington, 2004,2:326-333. [doi: 10.1109/ CVPR.2004.1315182]
    [14] Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking. In: Proc. of the 10th European Conf. on Computer Vision (ECCV). Marseille: Springer-Verlag, 2008. 705-718. [doi: 10.1007/978-3-540-88693-8_52]
    [15] Levinshtein A, Stere A, Kutulakos K, Fleet D, Dickinson S, Siddiqi K. Turbopixels: Fast superpixels using geometric flows. IEEE Trans. on Pattern Analysis and Machine Intellience, 2009,31(12):2290-2297. [doi: 10.1109/TPAMI.2009.96]
    [16] Radhakrishna A, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S. Slicsuperpixels. Technical Report, 149300, EPFL, 2010.
    [17] Ai HZ, Liang LH, Xu GY, Zhang B. Face detection based on skin color and template. Ruan Jian Xue Bao/Journal of Software, 2001, 12(12):1784-1792 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/20011207.htm [doi: 10.13328/j.cnki.jos. 2001.12.007]
    [18] Li HQ, Liu ZK, Zhan S. A segmentation method of color texture image. Chinese Journal of Computers, 2001,24(9):965-971 (in Chinese with English abstract). [doi: 10.3321/j.issn:0254-4164.2001.09.011]
    [19] Li Y, Huang G, Nevatia R. Learning to associtate: HybridBoosted multi-target tracker for crowded scene. In: Proc. of the 22th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Miami, 2009. 2953-2960. [doi: 10.1109/CVPR.2009. 5206735]
    [20] Comaniciu D, Ramesh V, Meer P. Kernel-Based object tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2003, 25:564-577. [doi: 10.1109/TPAMI.2003.1195991]
    [21] Li XR, Wu FC, Hu ZY. Convergence of a mean shift algorithm. Ruan Jian Xue Bao/Journal of Software, 2005,16(3):365-374 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/16/365.htm
    [22] Wen ZQ, Cai ZX. Convergence analysis of mean shift algorithm. Ruan Jian Xue Bao/Journal of Software, 2007,18(2):205-212 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/18/205.htm [doi: 10.1360/jos180205]
    [23] Sun JG, Liu J, Zhao LY. Clustering algorithms research. Ruan Jian Xue Bao/Journal of Software, 2008,19(1):48-61 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/19/48.htm [doi: 10.3724/SP.J.1001.2008.00048]
    [24] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002,24(5):603-619. [doi: 10.1109/34.1000236]
    [25] Kwon J, Lee KM. Tracking by sampling tracker. In: Proc. of the 13th IEEE Int'l Conf. on Computer Vision (ICCV). Barcelona, 2011. 1195-1202. [doi: 10.1109/ICCV.2011.6126369]
    [26] Kwon J, Lee KM. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling. In: Proc. of the 22th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Miami, 2009. 1208-1215. [doi: 10.1109/CVPR.2009.5206502]
    [27] Zhong W, Lu HC, Yang MH. Robust object tracking via sparsity-based collaborative model. In: Proc. of the 25th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Providence, 2012. 1838-1845. [doi: 10.1109/CVPR.2012.6247882]
    [28] Jia X, Lu HC, Yang MH. Visual tracking via adaptive structural local sparse appearance model. In: Proc. of the 23th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Providence, 2012.1822-1829. [doi: 10.1109/CVPR.2012.6247880]
    [29] Oron S, Bar-Hillel A, Levi D, Avidan S. Locally orderless tracking. In: Proc. of the 23th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Providence, 2012. 1940-1947. [doi: 10.1109/CVPR.2012.6247895]
    [30] Everingham M, Gool LV, Williams C, Winn J, Zisserman A. The pascal visual object classes (VOC) challenge. Int'l Journal of Computer Vision (IJCV), 2010,88(2):303-338. [doi: 10.1007/s11263-009-0275-4]
    [31] Wu Y, Lim J, Yang MH, Online object tracking: A benchmark. In: Proc. of the 26th IEEE Int'l Conf. on Computer Vision and Pattern Recognition (CVPR). Portland, 2013. 2411-2418. [doi: 10.1109/CVPR.2013.312]
    附中文参考文献:
    [4] 施华,李翠华,韦凤梅,王华伟.基于像素可信度和空间位置的运动目标跟踪.计算机研究与发展,2005,42(10):1726-1732.
    [11] 王建宇,陈熙霖,高文,赵德斌.背景变化鲁棒的自适应视觉跟踪目标模型.软件学报,2006,17(5):1001-1008. http://www.jos.org.cn/ 1000-9825/17/1001.htm
    [17] 艾海舟,梁路宏,徐光祐,张钹.基于肤色和模板的人脸检测.软件学报,2001,12(12):1784-1792. http://www.jos.org.cn/1000-9825/ 20011207.htm [doi: 10.13328/j.cnki.jos.2001.12.007]
    [18] 李厚强,刘政凯,詹曙.一种彩色纹理图像的分割方法.计算机学报,2001,24(9):965-971. [doi: 10.3321/j.issn:0254-4164.2001.09. 011]
    [21] 李乡儒,吴福朝,胡占义.均值漂移算法的收敛性.软件学报,2005,16(3):365-374. http://www.jos.org.cn/1000-9825/16/365.htm
    [22] 文志强,蔡自兴.Mean Shift算法的收敛性分析.软件学报,2007,18(2):205-212. http://www.jos.org.cn/1000-9825/18/205.htm [doi: 10.1360/jos180205]
    [23] 孙吉贵,刘杰,赵连宇.聚类算法研究.软件学报,2008,19(1):48-61. http://www.jos.org.cn/1000-9825/19/48.htm [doi: 10.3724/SP.J. 1001.2008.00048]
    Comments
    Comments
    分享到微博
    Submit
Get Citation

王美华,梁云,刘福明,罗笑南.部件级表观模型的目标跟踪方法.软件学报,2015,26(10):2733-2747

Copy
Share
Article Metrics
  • Abstract:3705
  • PDF: 4887
  • HTML: 1834
  • Cited by: 0
History
  • Received:October 17,2013
  • Revised:September 28,2014
  • Online: October 10,2015
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2051267Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063