cvpr cvpr2013 cvpr2013-362 cvpr2013-362-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Koichiro Yamaguchi, David McAllester, Raquel Urtasun
Abstract: We consider the problem of computing optical flow in monocular video taken from a moving vehicle. In this setting, the vast majority of image flow is due to the vehicle ’s ego-motion. We propose to take advantage of this fact and estimate flow along the epipolar lines of the egomotion. Towards this goal, we derive a slanted-plane MRF model which explicitly reasons about the ordering of planes and their physical validity at junctions. Furthermore, we present a bottom-up grouping algorithm which produces over-segmentations that respect flow boundaries. We demonstrate the effectiveness of our approach in the challenging KITTI flow benchmark [11] achieving half the error of the best competing general flow algorithm and one third of the error of the best epipolar flow algorithm.
[1] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. S ¨usstrunk. SLIC superpixels. Tech rep., 2010. 1, 4, 7
[2] M. Bleyer, C. Rother, and P. Kohli. Surface stereo with soft segmentation. In CVPR, 2010. 1, 5
[3] J.-Y. Bouguet. Pyramidal implementation of the lucas kanade feature tracker. Intel, 2000. 5
[4] G. Bradski. The OpenCV library. Dr. Dobb’s Journal of Software Tools, 2000. 5, 8
[5] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. In ECCV, 2004. 1, 2, 5
[6] T. Brox and J. Malik. Large displacement optical flow: Descriptor matching in variational motion estimation. PAMI, 2011. 2, 5
[7] J. Cech, J. Sanchez-Riera, and R. P. Horaud. Scene flow estimation by growing correspondence seeds. In CVPR, 2011. 5, 8
[8] J. Cech and R. Sara. Efficient sampling of disparity space for fast and accurate matching. In BenCOS, 2007. 8
[9] N. Einecke and J. Eggert. A two-stage correlation method for stereoscopic depth estimation. In DICTA, 2010. 8
[10] G. Farneback. Two-frame motion estimation based on polynomial expansion. In SCIA, 2003. 5 111888666866
[11] A. Geiger, P. Lenz, and R. Urtasun. Are we ready for autonomous driving? In CVPR, 2012. 1, 5, 6, 7, 8
[12] A. Geiger, M. Roser, and R. Urtasun. Efficient large-scale stereo matching. In ACCV, 2010. 8
[13] P. Ghosh and B. Manjunath. Robust simultaneous registration and segmentation with sparse error reconstruction. PAMI, 2012. 5
[14] B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. In CVPR, 2008. 1, 2
[15] R. Hartley. In defense of the eight-point algorithm. PAMI, 1997. 2
[16] T. Hazan and A. Shashua. Norm-product belief propagation: Primal-dual message-passing for approximate inference. IEEE Trans. Information Theory, 2010. 6
[17] T. Hazan and R. Urtasun. A primal-dual message-passing algorithm for approximated large scale structured prediction. NIPS, 2010. 6
[18] S. Hermann and R. Klette. Hierarchical scan line dynamic programming for optical flow using semi-global matching. In Intelligent Mobile Vision, ACCV-Workshop, 2012. 5
[19] S. Hermann and R. Klette. Iterative semi-global matching for robust driver assistance systems. In ACCV, 2012. 8
[20] H. Hirschmueller. Stereo processing by semiglobal matching and mutual information. PAMI, 2008. 1, 2, 3, 8
[21] B. K. P. Horn and B. G. Schunck. Determining optical flow: A retrospective. AI, 1993. 1, 2, 5
[22] B. Kitt and H. Lategahn. Trinocular optical flow estimation for intelligent vehicle applications. In ITSC, 2012. 1, 2, 5, 6
[23] V. Kolmogorov and R. Zabih. Computing visual correspondence with occlusions using graph cuts. In ICCV, 2001 . 8
[24] J. Kostkova. Stratified dense matching for stereopsis in complex scenes. In BMVC, 2003. 8
[25] C. Lei and Y. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. In ICCV, 2009. 1, 2
[26] V. Lempitsky, S. Roth, and C. Rother. FusionFlow: Discretecontinuous optimization for optical flow estimation. In CVPR, 2008. 2
[27] H. Longuet-Higgins and K. Prazdny. The interpretation of a moving retinal image. In Proc. R. Soc. Lond. B, 1980. 2
[28] D. G. Lowe. Distinctive image features from scale-invariant
[29]
[30] [3 1]
[32]
[33]
[34]
[35]
[36]
[37]
[38]
[39] keypoints. IJCV, 2004. 2 J. Peng, T. Hazan, D. McAllester, and R. Urtasun. Convex max-product algorithms for continuous MRFs with applications to protein folding. In ICML, 2011. 6 R. Ranftl, S. Gehrig, T. Pock, and H. Bischof. Pushing the Limits of Stereo Using Variational Stereo Estimation. In IEEE Intelligent Vehicles Symposium, 2012. 8 C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. In CVPR, 2011. 8 A. Schwing, T. Hazan, M. Pollefeys, and R. Urtasun. Distributed message passing for large scale graphical models. In CVPR, 2011. 6, 7 N. Slesareva, A. Bruhn, and J. Weickert. Optic flow goes stereo: a variational method for estimating discontinuitypreserving dense disparity maps. In DAGM, 2005. 2 D. Sun, S. Roth, and M. J. Black. Secrets of optical flow estimation and their principles. In CVPR, 2010. 5 W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. In ECCV, 2008. 2 L. Valgaerts, A. Bruhn, and J. Weickert. A variational model for the joint recovery of the fundamental matrix and the optical flow. In DAGM, 2008. 2 A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structureand motion-adaptive regularization for high accuracy optic flow. In ICCV, 2009. 2 M. Werlberger. Convex Approaches for High Performance Video Processing. Phdthesis, 2012. 5 K. Yamaguchi, T. Hazan, D. McAllester, and R. Urtasun. Continuous markov random fields for robust stereo estima- tion. In ECCV, 2012. 1, 5, 6, 7, 8
[40] R. Zabih and J. Woodfill. Non-parametric local transforms for computing visual correspondence. In ECCV, 1994. 3
[41] C. Zach, T. Pock, and H. Bischof. A duality based approach for realtime TV-L1 optical flow. In DAGM, 2007. 1, 2, 5 111888666977