一种基于加权时空上下文的鲁棒视觉跟踪算法

徐建强; 陆耀

doi:10.16383/j.aas.2015.c150073

一种基于加权时空上下文的鲁棒视觉跟踪算法

doi: 10.16383/j.aas.2015.c150073

徐建强^1,2,
陆耀^1,2, ,

1.
北京理工大学计算机学院北京 100081;
2.
智能信息技术北京市重点实验室北京 100081

基金项目:

国家自然科学基金(61273273,61271374),高等学校博士学科点专项科研基金(20121101110034)资助

详细信息

作者简介:
徐建强北京理工大学计算机学院博士研究生.主要研究方向为目标跟踪,计算机视觉,模式识别.E-mail:xujq@bit.edu.cn

通讯作者:
陆耀北京理工大学计算机学院教授.主要研究方向为神经网络,图像和信号处理,模式识别.本文通信作者.E-mail:vis_ly@bit.edu.cn

计量
- 文章访问数: 2376
- HTML全文浏览量: 142
- PDF下载量: 1155
- 被引次数: 0
出版历程
- 收稿日期: 2015-02-04
- 修回日期: 2015-07-11
- 刊出日期: 2015-11-20

Robust Visual Tracking via Weighted Spatio-temporal Context Learning

XU Jian-Qiang^1,2,
LU Yao^{1,2
, ,}

1.
School of Computer Science, Beijing Institute of Technology, Beijing 100081;
2.
Beijing Laboratory of Intelligent Information Technology, Beijing 100081

Funds:

Supported by National Natural Science Foundation of China (61273273, 61271374) and Research Fund for the Doctoral Program of Higher Education of China (20121101110034)

摘要

摘要: 由于光照及外观变化、复杂背景、目标旋转与遮挡等因素的影响, 给实现鲁棒的视觉跟踪带来困难. 有效利用上下文(Context)中包含的有用信息有助于提升上述条件下视觉跟踪的鲁棒性. 时空上下文 (Spatio-temporal context, STC)算法是新近提出的一种基于时空上下文的目标跟踪算法, 它利用目标周围的稠密上下文信息, 取得了良好的跟踪效果. STC的不足是其同等对待整个上下文区域, 没有对上下文做进一步的区分, 减弱了上下文的作用. 本文采用动态分区处理思想, 根据上下文中不同区域与跟踪目标运动相似度大小, 赋予不同权值, 提出了基于加权时空上下文(Weighted spatio-temporal context, WSTC)的鲁棒视觉跟踪算法. 最后在公共数据集上进行的对比实验表明, 本文所提出的算法具有更好的跟踪效果和鲁棒性.
- 视觉跟踪 /
- 上下文 /
- 时空上下文 /
- 加权时空上下文
Abstract: Implementing a robust visual tracker is a challenging task due to many disturbing factors such as illumination changes, appearance changes, rotation, partial or full occlusion, etc. The local context surrounding of the target could provide much effective information in getting a robust tracker. The spatio-temporal context (STC) learning algorithm proposed recently considers the information of the dense context around the target and has achieved a better performance. However, STC treats the whole region of the context equally, which weakens the effectiveness of the context information. In this paper, we propose a novel weighted spatio-temporal context (WSTC) learning algorithm. Our algorithm considers the surrounding context discriminatively and incorporates a weighted matrix by evaluating the motion consistencies of different regions with the tracking target. Extensive experimental results on public benchmark databases show that our algorithm outperforms the original STC algorithm and other state-of-the-art algorithms.
- Visual tracking /
- context /
- spatio-temporal context (STC) /
- weighted spatio-temporal context (WSTC)

HTML全文

参考文献(25)

[1]	Babenko B, Yang M H, Belongie S. Robust object tracking with online multiple instance learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8):1619-1632
[2]	Wang Li-Jia, Jia Song-Min, Li Xiu-Zhi, Wang Shuang. Person following for mobile robot using improved multiple instance learning. Acta Automatica Sinica, 2014, 40(12):2916-2925(王丽佳, 贾松敏, 李秀智, 王爽. 基于改进在线多示例学习算法的机器人目标跟踪. 自动化学报, 2014, 40(12):2916-2925)
[3]	[3] Ross D A, Lim J, Lin R S, Yang M H. Incremental learning for robust visual tracking. International Journal of Computer Vision, 2008, 77(1-3):125-141
[4]	[4] Zhang K H, Zhang L, Yang M H. Fast compressive tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10):2002-2015
[5]	[5] Kwon J, Lee K M. Visual tracking decomposition. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA, USA:IEEE, 2010. 1269-1276
[6]	[6] Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422
[7]	Li Zhen-Xing, Liu Jin-Mang, Li Song, Bai Dong-Ying, Ni Peng. Group targets tracking algorithm based on box particle filter. Acta Automatica Sinica, 2015, 41(4):785-798(李振兴, 刘进忙, 李松, 白东颖, 倪鹏. 基于箱式粒子滤波的群目标跟踪算法. 自动化学报, 2015, 41(4):785-798)
[8]	[8] Zhou X Z, Lu Y, Lu J W, Zhou J. Abrupt motion tracking via intensively adaptive Markov chain Monte Carlo sampling. IEEE Transactions on Image Processing, 2012, 21(2):789-801
[9]	[9] Zhou T F, Lu Y, Di H J. Nearest neighbor field driven stochastic sampling for abrupt motion tracking. In:Proceedings of the 2014 International Conference on Multimedia and Expo (ICME). Chengdu China:IEEE, 2014. 1-6
[10]	Grabner H, Matas J, Van Gool L, Cattin P. Tracking the invisible:learning where the object might be. In:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA, USA:IEEE, 2010. 1285-1292
[11]	Dinh T B, Vo N, Medioni G. Context tracker:exploring supporters and distracters in unconstrained environments. In:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO, USA:IEEE, 2011. 1177-1184
[12]	Wen L Y, Cai Z W, Zhen L, Dong Y, Li S Z. Online spatio-temporal structural context learning for visual tracking. In:Proceedings of the 2012 European Conference on Computer Vision (ECCV). Florence, Italy:Springer, 2012. 716-729
[13]	Yang M, Wu Y, Hua G. Context-aware visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(7):1195-1209
[14]	Zhang K H, Zhang L, Liu Q S, Zhang D, Yang M H. Fast visual tracking via dense spatio-temporal context learning. In:Proceedings of the 2014 European Conference on Computer Vision (ECCV). Czech Republic:Springer, 2014. 127-141
[15]	Sundaram N, Brox T, Keutzer K. Dense point trajectories by GPU-accelerated large displacement optical flow. In:Proceedings of the 2010 European Conference on Computer Vision (ECCV). Florence, Italy:Springer, 2010. 438-451
[16]	Nourani-Vatani N, Borges P V K, Roberts J M. A study of feature extraction algorithms for optical flow tracking. In:Proceedings of the 2012 Australasian Conference on Robotics and Automation. Victoria University of Wellington, New Zealand, 2012.
[17]	Kalal Z, Mikolajczyk K, Matas J. Forward-backward error:automatic detection of tracking failures. In:Proceedings of the 2012 International Conference on Pattern Recognition (ICPR). Istanbul Turkey:IEEE, 2010. 2756-2759
[18]	Wu Y, Lim J, Yang M H. Online object tracking:a benchmark. In:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, OR, USA:IEEE, 2013. 2411-2418
[19]	Zhang K H, Zhang L, Yang M H. Real-time compressive tracking. In:Proceedings of the 2012 European Conference on Computer Vision (ECCV). Florence, Italy:Springer, 2012. 864-877
[20]	Zhang T X, Ghanem B, Liu S, Ahuja N. Robust visual tracking via multi-task sparse learning. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA:IEEE, 2012. 2042-2049
[21]	Laura S L, Erik L M. Distribution fields for tracking. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA:IEEE, 2012. 1910-1917
[22]	Grabner H, Grabner M, Bischof H. Real-time tracking via on-line boosting. In:Proceedings of the 2006 British Machine Vision Conference. 2006, 47-56
[23]	Oron S, Bar-Hillel A, Levi D, Avidan S. Locally orderless tracking. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA:IEEE, 2012. 1940-1947
[24]	Adam A, Rivlin E, Shimshoni I. Robust fragments-based tracking using the integral histogram. In:Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2006. 798-805
[25]	Bao C L, Wu Y, Ling H B, Ji H. Real time robust L1 tracker using accelerated proximal gradient approach. In:Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA:IEEE, 2012. 1830-1837