基于分层弹性运动分析的非刚体跟踪方法

吕峰; 邸慧军; 陆耀; 徐光祐

doi:10.16383/j.aas.2015.c140375

基于分层弹性运动分析的非刚体跟踪方法

doi: 10.16383/j.aas.2015.c140375

吕峰^1,2,
邸慧军^1,2,
陆耀^1,2, ,,
徐光祐³

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;
3.
清华大学计算机科学与技术系北京 100084

基金项目:

国家自然科学基金(61273273,61003098),高等学校博士学科点专项科研基金(2012110110034),北京市教育委员会共建项目资助

详细信息

作者简介:
吕峰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与动作识别. E-mail: lvfeng@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_yl@bit.edu.cn

计量
- 文章访问数: 1415
- HTML全文浏览量: 34
- PDF下载量: 1008
- 被引次数: 0
出版历程
- 收稿日期: 2014-06-25
- 修回日期: 2014-10-13
- 刊出日期: 2015-02-20

Non-rigid Tracking Method Based on Layered Elastic Motion Analysis

LV Feng^1,2,
DI Hui-Jun^1,2,
LU Yao^{1,2
, ,},
XU Guang-You³

1.
School of Computer Science, Beijing Institute of Technology, Beijing 100081;
2.
Beijing Laboratory of Intelligent Information Technology, Beijing 100081;
3.
Department of Computer Science and Technology, Tsinghua University, Beijing 100084

Funds:

Supported by National Natural Science Foundation of China (61273273, 61003098), Research Fund for the Doctoral Program of Higher Education of China (2012110110034), and Specialized Fund for Joint Building Project of Beijing Municipal Education Commission

摘要

摘要: 采用时--空分层的弹性运动跟踪策略, 提出了一种分析长时运动稳定结构与短时运动局部变化的非刚体运动跟踪方法. 首先, 基于序贯形状聚类的分段弹性运动跟踪模型, 将整段图像序列分割成若干子段, 并利用弹性运动分析方法得到子段内各帧边缘点的对应关系和各类的平均形状, 获取短时局部运动变化细节. 然后, 通过基于贝叶斯网的整体搜索算法寻找时序上相邻聚类平均形状之间的对应关系, 进而得到整段运动的公共形状, 用于表示长时运动稳定结构. 通过计算公共形状与各类平均形状之间的变形关系, 可以建立各聚类平均形状之间的对应关系, 实现分段运动的连接. 本方法的特点是不依赖先验模型、通用性好、目标的描述能力强. 实验表明, 本方法与现有不依赖模型的方法相比,具有更好的长时稳定性和更高的跟踪精确度.
- 分层弹性运动跟踪 /
- 序贯形状聚类 /
- 运动分段 /
- 运动连接 /
- 贝叶斯网络
Abstract: In this paper, we present a spatial-temporal layered elastic motion tracking method to estimate long-term stable structures and short-term local motions for non-rigid targets. First, the sequence is segmented into several pieces by sequential shape clustering based a piece-wise elastic motion tracking model, the correspondence among frames in the same segment and the mean shape of all clusters are calculated by piece-wise elastic motion tracking. Then, we use a Bayesian network based global search method to find the correspondence of mean shapes of adjoining clusters and extract the common shape of the entire sequence. The proposed method, which does not require prior shape models, is adaptive to and descriptive for general objects. The experiments on non-rigid targets validate both the long-term stability and the detailed accuracy of our proposed method.
- Layered elastic motion tracking /
- sequential shape clustering /
- motion segmentation /
- motion connection /
- Bayesian network

HTML全文

参考文献(28)

[1]	Gavrila D M. The visual analysis of human movement: a survey. Computer Vision and Image Understanding, 1999, 73(1): 82-98
[2]	[2] Aggarwal J K, Cai Q. Human motion analysis: a review. Computer Vision and Image Understanding, 1999, 73(3): 428-440
[3]	[3] Cootes T F, Taylor C J, Cooper D H, Graham J. Active shape models-their training and application. Computer Vision and Image Understanding, 1995, 61(1): 38-59
[4]	[4] Cootes T F. Deformable object modelling and matching. In: Proceedings of the 10th Asian Conference on Computer Vision. Berlin, Heidelberg: Springer-Verlag, 2010. 1-10
[5]	[5] Huang X L, Zhang S, Wang Y, Metaxas D, Saamaras D. A hierarchical framework for high resolution facial expression tracking. In: Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop. Washington D.C., USA: IEEE, 2004. 22
[6]	[6] Aggarwal J K, Cai Q, Liao W, Sabata B. Nonrigid motion analysis: articulated and elastic motion. Computer Vision and Image Understanding, 1998, 70(2): 142-156
[7]	[7] Sundaram N, Brox T, Keutzer K. Dense point trajectories by GPU-accelerated large displacement optical flow. In: Proceedings of the 11th European Conference on Computer Vision. Berlin, Heidelberg: Springer-Verlag, 2010. 438-451
[8]	[8] Brox T, Malik J. Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 500-513
[9]	[9] Dollar P, Rabaud V, Cottrell G, Belongie S. Behavior recognition via sparse spatio-temporal features. In: Proceedings of the 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Washington D.C., USA: IEEE, 2005. 65-72
[10]	Liu T, Yuan Z J, Sun J, Wang J D, Zheng N N, Tang X O, Shum H Y. Learning to detect a salient object. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 353-367
[11]	Mahadevan V, Vasconcelos N. Saliency-based discriminant tracking. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009. 1007-1013
[12]	Di H J, Tao L M, Xu G Y. A mixture of transformed hidden Markov models for elastic motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10): 1817-1830
[13]	Cheng H T, Ahuja N. Exploiting nonlocal spatiotemporal structure for video segmentation. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2012. 741-748
[14]	Li F X, Kim T, Humayun A, Tsai D, Rehg J. Video segmentation by tracking many Figure-Ground segments. In: Proceedings of the 2013 Computer Vision. Sydney, NSW: IEEE, 2013. 2191-2199
[15]	Shapiro L, Wang H, Brady J. A matching and tracking strategy for independently moving objects. British Machine Vision Conference, 1992.
[16]	Tagare H D. Shape-based nonrigid correspondence with application to heart motion analysis. IEEE Transactions on Medical Imaging, 1999, 18(7): 570-579
[17]	Cootes T F, Edwards G J, Taylor C J. Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685
[18]	Matthews I, Baker S. Active appearance models revisited. International Journal of Computer Vision, 2004, 60(2): 135-164
[19]	Duta N, Jain A K, Dubuisson-Jolly M P. Automatic construction of 2D shape models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(5): 433-446
[20]	Huang X L, Paragios N, Metaxasm D N. Shape registration in implicit spaces using information theory and free form deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(8): 1303-1318
[21]	Paragios N, Rousson M, Ramesh V. Non-rigid registration using distance functions. Computer Vision and Image Understanding, 2003, 89(2-3): 142-165
[22]	Besl P J, McKay N D. A method for registration of 3d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256
[23]	Fitzgibbon A. Robust registration of 2D and 3D point sets. Image and Vision Computing, 2003, 21(13): 1145-1153
[24]	Chui H L, Rangarajan A. A new point matching algorithm for non-rigid registration. Computer Vision and Image Understanding, 2003, 89(2-3): 114-141
[25]	Chui H, Rangarajan A, Zhang J, Leonard C M. Unsupervised learning of an atlas from unlabeled point-sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 160-172
[26]	Qi Y J, Hauptmann A, Liu T. Supervised classification for video shot segmentation. In: Proceedings of the 2003 International Conference on Multimedia and Expo. Washington D.C., USA: IEEE, 2003. 689-692
[27]	Wang Liang, Hu Wei-Ming, Tan Tie-Niu. A survey of visual analysis of human motion. Chinese Journal of Computers, 2002, 25(3): 225-237(王亮, 胡卫明, 谭铁牛. 人运动的视觉分析综述. 计算机学报, 2002, 25(3): 225-237)
[28]	Ye Hang-Jun, Bai Xue-Sheng, Xu Guang-You. Face pose discrimination with support vector machines. Journal of Tsinghua University (Science and Technology), 2003, 43(1): 67-70(叶航军, 白雪生, 徐光祐. 基于支持向量机的人脸姿态判定. 清华大学学报(自然科学版), 2003, 43(1): 67-70)