iccv iccv2013 iccv2013-160 iccv2013-160-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Anestis Papazoglou, Vittorio Ferrari
Abstract: We present a technique for separating foreground objects from the background in a video. Our method isfast, , fully automatic, and makes minimal assumptions about the video. This enables handling essentially unconstrained settings, including rapidly moving background, arbitrary object motion and appearance, and non-rigid deformations and articulations. In experiments on two datasets containing over 1400 video shots, our method outperforms a state-of-theart background subtraction technique [4] as well as methods based on clustering point tracks [6, 18, 19]. Moreover, it performs comparably to recent video object segmentation methods based on objectproposals [14, 16, 27], while being orders of magnitude faster.
[1] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Ssstrunk. Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. on PAMI, 34(1 1), 2012.
[2] B. Alexe, T. Deselaers, and V. Ferrari. What is an object? In CVPR, 2010.
[3] X. Bai, J. Wang, D. Simons, and G. Sapiro. Video snapcut: robust video object cutout using localized classifiers. In SIGGRAPH, 2009.
[4] O. Barnichm and M. Van Droogenbroeck. Vibe: A universal background subtraction algorithm for video sequences. IEEE Trans. Image Processing, 2011.
[5] M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri. Actions as space-time shapes. In ICCV, 2005.
[6] T. Brox and J. Malik. Object segmentation by long term analysis of point trajectories. In ECCV, 2010.
[7] S. Brutzer, B. Hoeferlin, and G. Heidemann. Evaluation of background subtraction techniques for video surveillance. In CVPR, 2011. 11778833 to bottom: monkeydog, cheetah, birdfall, parachute, girl. (Right) YouTube-Objects. Top to bottom: cat, dog, motorbike, bird, horse. We include example result videos in the supplementary material.
[8] P. Chockalingam, S. N. Pradeep, and S. Birchfield. Adaptive fragments-based tracking of non-rigid objects using level sets. In ICCV, 2009.
[9] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati. Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans. on PAMI, 2003.
[10] I. Endres and D. Hoiem. Category independent object proposals. In ECCV, 2010.
[11] M. Everingham et al. The PASCAL Visual Object Classes Challenge 2010 Results, 2010.
[12] J. Foley, A. van Dam, S. Feiner, and J. Hughes. Computer Graphics: Principles and Practice, 2nd Edition. AddisonWesley, 1990.
[13] M. Grundmann, V. Kwatra, M. Han, and I. Essa. Efficient hierarchical graph-based video segmentation. In CVPR, 2010.
[14] Y. J. Lee, J. Kim, and K. Grauman. Key-segments for video object segmentation. In ICCV, 2011.
[15] A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, and K. Siddiqi. ”TurboPixels: Fast Superpixels Using Geometric Flows. IEEE Trans. on PAMI, 2009.
[16] T. Ma and L. J. Latecki. Maximum weight cliques with mutex constraints for video object segmentation. In CVPR, 2012.
[17] P. Ochs and T. Brox. Object segmentation in video: A hierarchical variational approach for turning pont trajectories into dense regions. In ICCV, 2011.
[18] P. Ochs and T. Brox. Higher order motion models and spectral clustering. In CVPR, 2012.
[19] A. Prest, C. Leistner, J. Civera, C. Schmid, and V. Ferrari. Learning object class detectors from weakly annotated video. In CVPR, 2012.
[20] B. L. Price, B. S. Morse, and S. Cohen. Livecut: Learningbased interactive video segmentation by evaluation of multiple propagated cues. In ICCV, 2009.
[21] C. Rother, V. Kolmogorov, and A. Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. In SIGGRAPH, 2004.
[22] N. Sundaram, T. Brox, and K. Keutzer. Dense point trajectories by gpu-accelerated large displacement optical flow. In ECCV, 2010.
[23] P. Sundberg, T. Brox, M. Maire, P. Arbelaez, and J. Malik. Occlusion boundary detection and figure/ground assignment from optical flow. In CVPR, 2011.
[24] D. Tsai, M. Flagg, and J. Rehg. Motion coherent tracking with multi-label mrf optimization. In BMVC, 2010.
[25] P. Viola and M. Jones. Robust real-time object detection. In IJCV, 2001.
[26] T. Wang and J. Collomosse. Probabilistic motion diffusion of labeling priors for coherent video segmentation. IEEE Trans. Multimedia, 2012.
[27] J. O. Zhang, D. and M. Shah. Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In CVPR, 2013. 11778844