Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (4): 630-637    DOI: 10.3785/j.issn.1008-973X.2013.04.010
    
Primal-dual method for spatiotemporal tracking model with moving background
WANG Shi-yan, YU Hui-min
Department of Information and Electronics Engineering, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A new method for multi-target segmentation and tracking with a moving viewing system was proposed. The active contour model was used for integrating motion estimation and segmentation into a variational framework throughout the spatiotemporal domain. A global convex minimization method was applied to the spatiotemporal tracking model, overcoming the limitation of the level set method that is sensitive to the initial condition. The primal-dual algorithm was designed for the proposed model in order to improve the computation efficiency. Experimental results illustrated the validity and improvements provided by the proposed spatiotemporal tracking model.

Published: 01 April 2013
CLC:  TP 391.7  
  TP 317.4  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

WANG Shi-yan, YU Hui-min. Primal-dual method for spatiotemporal tracking model with moving background. J4, 2013, 47(4): 630-637.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2013.04.010     OR     http://www.zjujournals.com/eng/Y2013/V47/I4/630


运动场景下的时空域跟踪模型及原始-对偶算法

针对摄像机运动的情况,提出多目标分割和跟踪的新方法.利用主动轮廓模型,将运动估计和运动分割融合在同一基于时空域的能量泛函中.为了克服传统的活动轮廓模型和水平集方法存在的局部最小值问题,对时空分割模型进行凸优化,避免了初始化轮廓对分割结果的影响,保证了能量函数对分割的全局最优性.提出相应的快速原始-对偶算法,提高了计算效率.实验表明,该方法能够有效地实现运动场景下的时空域运动分割与跟踪.

［1］ SUDIPTA N S, FRAHM J M, POLLEFEYS M, et al. Feature tracking and matching in video using programmable graphics hardware ［J］. Machine Vision and Applications, 2011, 22(1): 207-217.

［2］ HAYAKAWA H, SHIBATA T. Block-matching-based motion field generation utilizing directional edge displacement ［J］. Computer and Electronic Engineering, 2010, 36(4): 617-625.

［3］ SUNDARAM N, BROX T, KEUTZER K. Dense point trajectories by GPU-accelerated large displacement optical flow ［J］. Lecture Notes in Computer Science, 2010, 6311: 438-451.

［4］ BROX T, MALIK J. Large displacement optical flow: descriptor matching in variational motion estimation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2011, 33(3): 500-513.

［5］ DUFAUX F, MOCCAGATTA I, MOSCHENI F, et al. Vector quantization-based motion field segmentation under the entropy criterion ［J］. Journal of Vision Communication and Image Representation, 1994, 5(4): 356-369.

［6］ PARAGIOS N, DERICHE R. Geodesic active regions and level set methods for motion estimation and tracking ［J］. Computer Vision and Image Understanding, 2005, 97(3): 259-282.

［7］ M＇EMIN E, P＇EREZ P. Hierarchical estimation and segmentation of dense motion fields ［J］. International Journal of Computer Vision, 2002, 46(2): 129-155.

［8］ FEGHALI R, MITICHE A. Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera: a level sets PDEs approach with concurrent camera motion compensation ［J］. IEEE Transactions on Image Processing, 2004, 13(11): 1473-1490.

［9］ CASELLES V, KIMMELI R, SAPRIRO G. Geodesic active contours ［J］.International Journal of Computational Vision,1997,22(1)： 61-79.

［10］ CHAN T, VESE L. Active contours without edges ［J］.IEEE Transactions on Image Processing, 2001, 10(2)： 266-277.

［11］ BERTALMIO M, SAPIRO G, RANDALL G. Morphing active contour ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(7): 733-737.

［12］ BESSON S J, BARLAUD M, AUBERT G. Detection and tracking of moving objects using a new level set based method ［C］∥ Proceedings of International Conference on Pattern Recognition. Barcelona: ［s.n.］, 2000: 1100-1105.

［13］ OSHER S, SETHIAN J. Fronts propagating with curvature dependent speed: algorithms based on the Hamilton-Jacobi formulation ［J］. Journal of Computational Physics,1988,79(1)： 1249.

［14］ CHAN T F, ESEDO GLU S, NIKOLOVA M. Algorithms for finding global minimizers of image segmentation and denoising models ［J］. SIAM Journal of Applied Mathematics, 2006, 66(5): 1632-1648.

［15］ BRESSON X, ESEDOGLU S, VANDERGHEYNST P, et al. Fast global minimization of the active contour/snake models ［J］. Journal of Mathematical Imaging and Vision, 2007, 28(2): 151-167.

［16］ GOLDSTEIN T, BRESSON X, OSHER S. Geometric applications of the split Bregman method: segmentation and surface reconstruction \
[J\]. Journal of Scientific Computing, 2010,45: 272-293.

［17］ BOYKOV Y, FUNKA-LEA G. Graph cuts and ecient N-D image segmentation ［J］. International Journal of Computer Vision (IJCV), 2006, 70(2): 109-131.

［18］ BOYKOV Y, KOLMOGOROV V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137.

［19］ RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms ［J］. Physica D: Nonlinear Phenomena, 1992, 60(1/2/3/4): 259-268.

［20］ CHAMBOLLE A. An algorithm for total variation minimization and applications ［J］. Journal of Mathematical Imaging and Vision, 2004, 20(1/2): 89-97.

［21］ TONY C, GOLUB G H, MULET P. A nonlinear primal-dual method for total variation-based image restoration ［J］. SIAM Journal on Scientific Computing, 1999, 20: 1964-1977.

［22］ WANG S Y, YU H M, ROLAND H. 3D Video based segentation and motion estimation with active surface evolution ［J］. Journal of Signal Processing Systems, 2013, 71(1): 21-34.

［23］ WANG S Y, YU H M. A variational approach for ego-motion estimation and segmentation based on 3D TOF camera ［C］∥4th International Congress on Image and Signal Processing. Shanghai: IEEE, 2011: 1174-1178.
No related articles found!