iccv iccv2013 iccv2013-361 iccv2013-361-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Feng Shi, Zhong Zhou, Jiangjian Xiao, Wei Wu
Abstract: Due to occlusions and objects ’ non-rigid deformation in the scene, the obtained motion trajectories from common trackers may contain a number of missing or mis-associated entries. To cluster such corrupted point based trajectories into multiple motions is still a hard problem. In this paper, we present an approach that exploits temporal and spatial characteristics from tracked points to facilitate segmentation of incomplete and corrupted trajectories, thereby obtain highly robust results against severe data missing and noises. Our method first uses the Discrete Cosine Transform (DCT) bases as a temporal smoothness constraint on trajectory projection to ensure the validity of resulting components to repair pathological trajectories. Then, based on an observation that the trajectories of foreground and background in a scene may have different spatial distributions, we propose a two-stage clustering strategy that first performs foreground-background separation then segments remaining foreground trajectories. We show that, with this new clustering strategy, sequences with complex motions can be accurately segmented by even using a simple trans- lational model. Finally, a series of experiments on Hopkins 155 dataset andBerkeley motion segmentation dataset show the advantage of our method over other state-of-the-art motion segmentation algorithms in terms of both effectiveness and robustness.
[1] I. Akhter, Y. Sheikh, S. Khan, and T. Kanade. Trajectory space: a dual representation for nonrigid structure from motion. IEEE Trans. on PAMI, 33(7): 1442–1456, July 2011.
[2] I. Akhter, T. Simon, S. Khan, T. Simon, and Y. Sheikh. Bilinear spatiotemporal basis models. ACM Trans. Graph, 3 1(2), April 2012.
[3] T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. In Proc. ECCV, volume 63 15, pages 282–295, 2010.
[4] A. M. Cheriyadat and R. J. Radke. Non-negative matrix factorization of partial track data for motion segmentation. In Proc. ICCV, pages 865–872. IEEE, 2009.
[5] J. Costeira and T. Kanade. A multibody factorization method for independently moving objects. IJCV, 29(3): 159–179, September 1998.
[6] R. Dragon, B. Rosenhahn, and J. Ostermann. Multi-scale clustering of frame-to-frame correspondences for motion segmentation. In Proc. ECCV, 2012.
[7] E. Elhamifar and R. Vidal. Sparse subspace clustering. In Proc. CVPR, pages 2790–2797. IEEE, 2009.
[8] M. Fradet, P. Robert, and P. Perez. Clustering point trajectories with various life-spans. In Proc. CVMP, pages 7–14. IEEE, 2009.
[9] K. Fragkiadaki and J. Shi. Detection free tracking: exploiting motion and topology for segmenting and tracking under entanglement. In Proc. CVPR, pages 2073–2080. IEEE, 2011.
[10] G. Liu, Z. Lin, and Y. Yu. Robust subspace segmentation by
[11]
[12]
[13]
[14]
[15]
[16]
[17] low-rank representation. In Proc. ICML, 2010. Q. Mo and B. A. Draper. Semi-nonnegative matrix factorization for motion segmentation with missing data. In Proc. ECCV, volume 7578, pages 402–415, 2012. P. Ochs and T. Brox. Higher order motion models and spectral clustering. In Proc. CVPR, pages 614–621. IEEE, 2012. S. R. Rao, R. Tron, R. Vidal, and Y. Ma. Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories. In Proc. CVPR, pages 1–8. IEEE, 2008. J. Shi and C. Tomasi. Good features to track. In Proc. CVPR, pages 593–600. IEEE, 1994. N. Sundaram, T. Brox, and K. Keutzer. Dense point trajectories by gpu-accelerated large displacement optical flow. In Proc. ECCV, volume 6311, pages 438–451, 2010. R. Tron and R. Vidal. A benchmark for the comparison of 3d motion segmentation algorithms. In Proc. CVPR, pages 1–8. IEEE, 2007. J. Yan and M. Pollefeys. A general framework for motion segmentation: Independent, articulated, rigid, nonrigid, degenerate and non-degenerate. In Proc. ECCV, volume 3954, pages 94–106, 2006. 33008958