cvpr cvpr2013 cvpr2013-203 cvpr2013-203-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Guillem Palou, Philippe Salembier
Abstract: As early stage of video processing, we introduce an iterative trajectory merging algorithm that produces a regionbased and hierarchical representation of the video sequence, called the Trajectory Binary Partition Tree (BPT). From this representation, many analysis and graph cut techniques can be used to extract partitions or objects that are useful in the context of specific applications. In order to define trajectories and to create a precise merging algorithm, color and motion cues have to be used. Both types of informations are very useful to characterize objects but present strong differences of behavior in the spatial and the temporal dimensions. On the one hand, scenes and objects are rich in their spatial color distributions, but these distributions are rather stable over time. Object motion, on the other hand, presents simple structures and low spatial variability but may change from frame to frame. The proposed algorithm takes into account this key difference and relies on different models and associated metrics to deal with color and motion information. We show that the proposed algorithm outperforms existing hierarchical video segmentation algorithms and provides more stable and precise regions.
[1] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. IEEE TPAMI, 33:898–916, 2011.
[2] T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. In ECCV, ECCV’ 10, pages 282–295, Berlin, Heidelberg, 2010. Springer-Verlag.
[3] T. Brox and J. Malik. Large displacement optical flow: Descriptor matching in variational motion estimation. IEEE TPAMI, 33(3):500 –513, march 2011.
[4] F. Calderero and F. Marques. Region merging techniques using information theory statistical measures. IEEE Transactions on Image Processing, 19(6): 1567 –1586, june 2010.
[5] A. Chen and J. Corso. Propagating multi-class pixel labels throughout video frames. In Image Processing Workshop (WNYIPW), pages 14 –17, nov. 2010.
[6] J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha, and A. Yuille. Efficient multilevel brain tumor segmentation with integrated bayesian model classification. IEEE Transactions on Medical Imaging, 27(5):629 –640, may 2008.
[7] A. J. Davison, I. D. Reid, N. D. Molton, and O. Stasse. Monoslam: Real-time single camera slam. IEEE TPAMI, 29(6): 1052–1067, June 2007.
[8] P. F. Felzenszwalb and D. P. Huttenlocher. Efficient graphbased image segmentation. IJCV, 59(2): 167–181, Sept. 2004.
[9] C. Fowlkes, S. Belongie, F. Chung, and J. Malik. Spectral grouping using the nystrom method. IEEE TPAMI, 26(2):214 –225, feb. 2004.
[10] M. Grundmann, V. Kwatra, M. Han, and I. A. Essa. Efficient hierarchical graph-based video segmentation. In CVPR, pages 2141–2148. IEEE, 2010.
[11] C. Harris and M. Stephens. A combined corner and edge detector. In Alvey Vision Conference, pages 147–15 1, 1988.
[12] J. Lezama, K. Alahari, J. Sivic, and I. Laptev. Track to the future: Spatio-temporal video segmentation with long-range motion cues. In CVPR, 2011.
[13] P. Ochs and T. Brox. Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions. In ICCV, ICCV ’ 11, pages 1583–1590, Washington, DC, USA, 2011. IEEE Computer Society.
[14] G. Palou and P. Salembier. 2.1 depth estimation of frames in image sequences using motion occlusions. In A. Fusiello, V. Murino, and R. Cucchiara, editors, ECCV Workshops, volume 7585 of Lecture Notes in Computer Science, pages 5 16– 525. Springer, 2012.
[15] N. Papenberg, A. Bruhn, T. Brox, S. Didas, and J. Weickert. Highly accurate optic flow computation with theoretically justified warping. IJCV, 67(2): 141–158, Apr. 2006.
[16] S. Paris. Edge-preserving smoothing and mean-shift segmentation of video streams. In ECCV, volume 5303 of Lecture Notes in Computer Science, pages 460–473. Springer Berlin Heidelberg, 2008.
[17] S. Paris and F. Durand. A topological approach to hierarchical segmentation using mean shift. In CVPR, pages 1–8, june 2007.
[18] J. Pont-Tuset and F. Marqu ´es. Supervised assessment of segmentation hierarchies. In ECCV, 01/2012 2012.
[19] S. Rao, R. Tron, R. Vidal, and Y. Ma. Motion segmentation in the presence of outlying, incomplete, or corrupted trajectories. IEEE TPAMI, 32(10): 1832–1845, Oct. 2010.
[20] Y. Rubner, C. Tomasi, and L. Guibas. A metric for distributions with applications to image databases. In ICCV, pages 59 –66, jan 1998.
[21] P. Salembier and L. Garrido. Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE Transactions on Image Processing, 9(4):561 –576, apr 2000.
[22] J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE TPAMI, 22(8):888–905, Aug. 2000.
[23] A. N. Stein and M. Hebert. Occlusion boundaries from motion: Low-level detection and mid-level reasoning. IJCV,
[24]
[25]
[26]
[27]
[28]
[29]
[30] [3 1] 82(3):325–357, May 2009. N. Sundaram, T. Brox, and K. Keutzer. Dense point trajectories by gpu-accelerated large displacement optical flow. In ECCV, Lecture Notes in Computer Science. Springer, Sept. 2010. N. Sundaram and K. Keutzer. Long term video segmentation through pixel level spectral clustering on gpus. In ICCV Workshops, pages 475–482. IEEE, 2011. P. Sundberg, T. Brox, M. Maire, P. Arbelaez, and J. Malik. Occlusion boundary detection and figure/ground assignment from optical flow. In CVPR, CVPR ’ 11, pages 2233–2240, Washington, DC, USA, 2011. IEEE Computer Society. V. Vilaplana, F. Marques, and P. Salembier. Binary partition trees for object detection. IEEE Transactions on Image Processing, 17(1 1):2201–2216, Nov. 2008. A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. Statistical and geometrical approaches to visual motion analysis. chapter An Improved Algorithm for TV-L1 Optical Flow, pages 23–45. Springer-Verlag, Berlin, Heidelberg, 2009. O. Wirjadi. Survey of 3D image segmentation methods. Technical Report 123, Fraunhofer Institut fur Techno und Wirtschaftsmathematik, 2007. C. Xu and J. Corso. Evaluation of super-voxel methods for early video processing. In CVPR, pages 1202 –1209, june 2012. C. Xu, C. Xiong, and J. J. Corso. Streaming hierarchical video segmentation. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid, editors, ECCV, volume 7577 of Lecture Notes in Computer Science, pages 626–639. Springer, 2012.
[32] L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. In CVPR, pages 1293 –1300, june 2010. 222111000644