cvpr cvpr2013 cvpr2013-334 cvpr2013-334-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Katerina Fragkiadaki, Han Hu, Jianbo Shi
Abstract: Human pose detectors, although successful in localising faces and torsos of people, often fail with lower arms. Motion estimation is often inaccurate under fast movements of body parts. We build a segmentation-detection algorithm that mediates the information between body parts recognition, and multi-frame motion grouping to improve both pose detection and tracking. Motion of body parts, though not accurate, is often sufficient to segment them from their backgrounds. Such segmentations are crucialfor extracting hard to detect body parts out of their interior body clutter. By matching these segments to exemplars we obtain pose labeled body segments. The pose labeled segments and corresponding articulated joints are used to improve the motion flow fields by proposing kinematically constrained affine displacements on body parts. The pose-based articulated motion model is shown to handle large limb rotations and displacements. Our algorithm can detect people under rare poses, frequently missed by pose detectors, showing the benefits of jointly reasoning about pose, segmentation and motion in videos.
[1] P. Arbelaez, M. Maire, C. C. Fowlkes, and J. Malik. From contours to regions: An empirical evaluation. In CVPR, 2009.
[2] L. Bourdev, S. Maji, T. Brox, and J. Malik. Detecting people using mutually consistent poselet activations. In ECCV, 2010.
[3] C. Bregler and J. Malik. Tracking people with twists and exponential maps. In CVPR, 1998.
[4] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. In ECCV, 2004.
[5] T. Brox and J. Malik. Large displacement optical flow: Descriptor matching in variational motion estimation. TPAMI, 2010.
[6] T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. In ECCV. 2010.
[7] T. Brox, B. Rosenhahn, D. Cremers, and H.-P. Seidel. High accuracy optical flow serves 3-D pose tracking: exploiting contour and flow based constraints. In ECCV, 2006.
[8] A. Datta, Y. A. Sheikh, and T. Kanade. Linear motion estimation for systems of articulated planes. In CVPR, 2008.
[9] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (VOC) challenge. IJCV, 88, 2010.
[10] R. Fablet and M. J. Black. Automatic detection and tracking of human motion with a view-based representation. In ECCV, 2002.
[11] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained partbased models. TPAMI, 32, 2010.
[12] V. Ferrari, M. Marn-Jimnez, and A. Zisserman. 2D human pose estimation in TV shows. In D. C. et al., editor, Statistical and Geometrical Approaches to Visual Motion Analysis, LNCS, pages 128–147. Springer, 1st edition, 2009.
[13] K. Fragkiadaki and J. Shi. Exploiting motion and topology for segmenting and tracking under entanglement. In CVPR, 2011.
[14] K. Fragkiadaki, W. Zhang, G. Zhang, and J. Shi. Twogranularity tracking: Mediating trajectory and detection graphs for tracking under occlusions. In ECCV, 2012.
[15] H. Jiang. Human pose estimation using consistent maxcovering. In ICCV, 2009.
[16] S. Johnson and M. Everingham. Learning effective human pose estimation from inaccurate annotation. In CVPR, 2011.
[17] S. X. Ju, M. J. Black, and Y. Yacoob. Cardboard people: A parameterized model of articulated image motion. In FG, 1996.
[18] L. Karlinsky, M. Dinerstein, D. Harari, and S. Ullman. The chains model for detecting parts by their context. In CVPR, 2010.
[19] G. Mori, X. Ren, A. A. Efros, and J. Malik. Recovering human body configurations: combining segmentation and recognition. In CVPR, 2004.
[20] D. Park and D. Ramanan. N-best maximal decoders for part models. In ICCV, 2011.
[21] D. Ramanan, D. A. Forsyth, and A. Zisserman. Strike a pose: Tracking people by finding stylized poses. CVPR, 2005.
[22] J. M. Rehg and T. Kanade. Model-based tracking of selfoccluding articulated objects. In ICCV, 1995.
[23] B. C. Russell, A. Efros, J. Sivic, W. T. Freeman, and A. Zisserman. Using multiple segmentations to discover objects and their extent in image collections. In CVPR, 2006.
[24] B. Sapp, D. Weiss, and B. Taskar. Parsing human motion with stretchable models. In CVPR, 2011.
[25] E. Sharon, A. Brandt, and R. Basri. Fast multiscale image segmentation. In CVPR, 2000.
[26] N. Sundaram, T. Brox, and K. Keutzer. Dense point trajectories by GPU-accelerated large displacement optical flow. In ECCV. 2010.
[27] L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. TPAMI, 34, 2012.
[28] Y. Yang and D. Ramanan. Articulated pose estimation with flexible mixtures-of-parts. In CVPR, 2011. 222000666644