The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.01 - January (2011 vol.33)
pp: 144-157
Nicolas Papadakis , Image Group, Barcelona Media, Barcelona
Aurélie Bugeau , Image Group, Barcelona Media, Barcelona
ABSTRACT
This work presents a new method for tracking and segmenting along time-interacting objects within an image sequence. One major contribution of the paper is the formalization of the notion of visible and occluded parts. For each object, we aim at tracking these two parts. Assuming that the velocity of each object is driven by a dynamical law, predictions can be used to guide the successive estimations. Separating these predicted areas into good and bad parts with respect to the final segmentation and representing the objects with their visible and occluded parts permit handling partial and complete occlusions. To achieve this tracking, a label is assigned to each object and an energy function representing the multilabel problem is minimized via a graph cuts optimization. This energy contains terms based on image intensities which enable segmenting and regularizing the visible parts of the objects. It also includes terms dedicated to the management of the occluded and disappearing areas, which are defined on the areas of prediction of the objects. The results on several challenging sequences prove the strength of the proposed approach.
INDEX TERMS
Tracking, interacting objects, occlusions, graph cuts optimization.
CITATION
Nicolas Papadakis, Aurélie Bugeau, "Tracking with Occlusions via Graph Cuts", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 1, pp. 144-157, January 2011, doi:10.1109/TPAMI.2010.56
REFERENCES
[1] Y. Boykov and M.P. Jolly, "Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in n-d Images," Proc. IEEE Int'l Conf. Computer Vision, vol. 1, pp. 105-112, 2001.
[2] Y. Boykov and V. Kolmogorov, "An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1124-1137, Sept. 2004.
[3] Y. Boykov, O. Veksler, and R. Zabih, "Fast Approximate Energy Minimization via Graph Cuts," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001.
[4] M. Bray, P. Kohli, and P. Torr, "Posecut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic Graph-Cuts," Proc. European Conf. Computer Vision, 2006.
[5] A. Bugeau and P. Pérez, "Track and Cut: Simultaneous Tracking and Segmentation of Multiple Objects with Graph Cuts," Proc. Int'l Conf. Computer Vision Theory and Applications, vol. 2, pp. 447-454, 2008.
[6] A. Bugeau and P. Pérez, "Track and Cut: Simultaneous Tracking and Segmentation of Multiple Objects with Graph Cuts," EURASIP J. Image and Video Processing, vol. 2008, pp. 1-14, 2008.
[7] T. Corpetti, E. Mémin, and P. Pérez, "Dense Estimation of Fluid Flows," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 365-380, Mar. 2002.
[8] I.J. Cox, S.L. Hingorani, S.B. Rao, and B.M. Maggs, "A Maximum Likelihood Stereo Algorithm," Computer Vision and Image Understanding, vol. 63, no. 3, pp. 542-567, 1996.
[9] D. Cremers, "Dynamical Statistical Shape Priors for Level Set-Based Tracking," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 8, pp. 1262-1273, Aug. 2006.
[10] A. Criminisi, A. Blake, C. Rother, J. Shotton, and P.H. Torr, "Efficient Dense Stereo with Occlusions for New View-Synthesis by Four-State Dynamic Programming," Int'l J. Computer Vision, vol. 71, no. 1, pp. 89-110, 2007.
[11] A. Criminisi, G. Cross, A. Blake, and V. Kolmogorov, "Bilayer Segmentation of Live Video," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 53-60, 2006.
[12] S. Dambreville, Y. Rathi, and A. Tannenbaum, "Tracking Deformable Objects with Unscented Kalman Filtering and Geometric Active Contours," Proc. Am. Control Conf., 2006.
[13] L.R. Ford and D.R. Fulkerson, "Maximal Flow through a Network," Canadian J. Math., vol. 8, pp. 399-404, 1956.
[14] D. Freedman and M. Turek, "Illumination Invariant Tracking via Graph Cuts," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 10-17, 2005.
[15] D. Freedman and T. Zhang, "Motion Detection and Estimation— Active Contours for Tracking Distributions," IEEE Trans. Image Processing, vol. 13, no. 4, pp. 518-526, 2004.
[16] C. Harris and M. Stephens, "A Combined Corner and Edge Detection," Proc. Fourth Alvey Vision Conf., pp. 147-151, 1988.
[17] M. Isard and A. Blake, "Condensation—Conditional Density Propagation for Visual Tracking," Int'l J. Computer Vision, vol. 29, no. 1, pp. 5-28, 1998.
[18] V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, and C. Rother, "Bi-Layer Segmentation of Binocular Stereo Video," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 407-414, 2005.
[19] V. Kolmogorov and R. Zabih, "Computing Visual Correspondence with Occlusions via Graph Cuts," Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp. 508-515, 2001.
[20] V. Kolmogorov and R. Zabih, "What Energy Functions Can Be Minimized via Graph Cuts?" IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 2, pp. 147-159, Feb. 2004.
[21] B. Lucas and T. Kanade, "An Iterative Image Registration Technique with an Application to Stereovision," Proc. Int'l Joint Conf. Artificial Intelligence, pp. 674-679, 1981.
[22] J. Malcolm, Y. Rathi, and A. Tannenbaum, "Multi-Object Tracking through Clutter Using Graph Cuts," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[23] J. Malcolm, Y. Rathi, and A. Tannenbaum, "Tracking through Clutter Using Graph Cuts," Proc. British Machine Vision Conf., 2007.
[24] C. Mota, I. Stuke, T. Aach, and E. Barth, "Spatial and Spectral Analysis of Occluded Motions," Signal Processing: Image Comm., vol. 20, pp. 529-536, 2005.
[25] H.T. Nguyen and A.W.M. Smeulders, "Fast Occluded Object Tracking by a Robust Appearance Filter," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1099-1104, Aug. 2004.
[26] M. Niethammer and A. Tannenbaum, "Dynamic Geodesic Snakes for Visual Tracking," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 660-667, 2004.
[27] N. Papadakis and E. Mémin, "A Variational Method for the Tracking of Curve and Motion," J. Math. Imaging and Vision, vol. 31, no. 1, pp. 81-103, 2008.
[28] D. Ramanan, "Using Segmentation to Verify Object Hypotheses," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[29] Y. Rathi, N. Vaswani, A. Tannenbaum, and A.J. Yezzi, "Particle Filtering for Geometric Active Contours with Application to Tracking Moving and Deforming Objects," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 8, pp. 1470-1475, Aug. 2007.
[30] F. Schmidt, E. Aarts, D. Cremers, and Y. Boykov, "Efficient Shape Matching via Graph Cuts," Proc. Conf. Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 39-54, 2007.
[31] D. Terzopoulos and R. Szeliski, "Tracking with Kalman Snakes," Active Vision, pp. 3-20, MIT Press, 1993.
[32] N. Xu, R. Bansal, and N. Ahuja, "Object Segmentation Using Graph Cuts Based Active Contours," Computer Vision and Image Understanding, vol. 107, no. 3, pp. 210-224, 2007.
[33] A. Yilmaz, O. Javed, and M. Shah, "Object Tracking: A Survey," ACM Computing Surveys, vol. 38, no. 4, 2006.
[34] W. Yu, G. Sommer, S. Beauchemin, and K. Daniilidis, "Oriented Structure of the Occlusion Distortion: Is It Reliable?" IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 9, pp. 1286-1290, Sept. 2002.
[35] L. Zhao and L.S. Davis, "Closely Coupled Object Detection and Segmentation," Proc. IEEE Int'l Conf. Computer Vision, 2005.
5 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool