Abstract
Motion segmentation is the task of classifying the feature trajectories in an image sequence to different motions. Hypergraph based approaches use a specific graph to incorporate higher order similarities for the estimation of motion clusters. They follow the concept of hypothesis generation and validation. For the sampling of hypotheses, a high probability of selecting clean samples, i.e. samples consisting of points from the same cluster, is desired. Many approaches use spatial proximity to build an auxiliary graph for the sampling. But, spatial proximity is often not sufficient to capture the main affinities for motion segmentation. Thus, we introduce a simple but effective model for incorporating motion-coherent affinities into the auxiliary graph. The evaluation on two state of the art benchmarks shows that the hypotheses generated from the resulting hypergraphs lead to a significant decrease of the segmentation error. Additionally, less computation time is required due to a reduced hypergraph complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33(3), 500–513 (2011)
Brox, T.: Higher order motion models and spectral clustering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 614–621. IEEE Computer Society (2012)
Chen, G., Lerman, G.: Spectral curvature clustering (SCC). Int. J. Comput. Vision (IJCV) 81(3), 317–330 (2008)
Chin, T.J., Yu, J., Suter, D.: Accelerated hypothesis generation for multistructure data via preference analysis. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 34(4), 625–638 (2012)
Cordes, K., Hockner, M., Ackermann, H., Rosenhahn, B., Ostermann, J.: WM-SBA: weighted multibody sparse bundle adjustment. In: 14th IAPR International Conference on Machine Vision Applications (MVA), pp. 162–165 (2015)
Delong, A., Osokin, A., Isack, H.N., Boykov, Y.: Fast approximate energy minimization with label costs. Int. J. Comput. Vision (IJCV) 96(1), 1–27 (2012)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 23(6), 643–660 (2001)
Li, Z., Guo, J., Cheong, L.F., Zhou, S.: Perspective motion segmentation via collaborative clustering. In: IEEE International Conference on Computer Vision (ICCV), pp. 1369–1376 (2013)
Li, Z., Cheong, L.-F., Yang, S., Toh, K.C.: Simultaneous clustering and model selection for tensor affinities. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Liu, H., Yan, S.: Efficient structure detection via random consensus graph. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 574–581 (2012)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision (IJCV) 60(2), 91–110 (2004)
MacKay, D.J.: The Swendson-Wang method. In: Information Theory, Inference and Learning Algorithms. Cambridge University Press (2003)
Ozden, K., Schindler, K., Van Gool, L.: Simultaneous segmentation and 3D reconstruction of monocular image sequences. In: IEEE International Conference on Computer Vision (ICCV), pp. 1–8 (2007)
Pham, T.T., Chin, T.J., Yu, J., Suter, D.: The random cluster model for robust geometric fitting. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 36(8), 1658–1671 (2014)
Poling, B., Lerman, G.: A new approach to two-view motion segmentation using global dimension minimization. Int. J. Comput. Vision (IJCV) 108(3), 165–185 (2014)
Purkait, P., Chin, T.-J., Ackermann, H., Suter, D.: Clustering with hypergraphs: the case for large hyperedges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 672–687. Springer, Cham (2014). doi:10.1007/978-3-319-10593-2_44
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 22(8), 888–905 (2000)
Swendsen, R.H., Wang, J.S.: Nonuniversal critical dynamics in Monte Carlo simulations. Phys. Rev. Lett. 58, 86–88 (1987)
Tron, R., Vidal, R.: A benchmark for the comparison of 3D motion segmentation algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2007)
Vidal, R., Ma, Y., Soatto, S., Sastry, S.: Two-view multibody structure from motion. Int. J. Comput. Vision (IJCV) 68(1), 7–25 (2006)
Wang, H., Xiao, G., Yan, Y., Suter, D.: Mode-seeking on hypergraphs for robust geometric model fitting. In: The IEEE International Conference on Computer Vision (ICCV), pp. 2902–2910 (2015)
Xiao, G., Wang, H., Lai, T., Suter, D.: Hypergraph modelling for geometric model fitting. Pattern Recogn. 60, 748–760 (2016)
Zhou, D., Huang, J., Schölkopf, B.: Learning with hypergraphs: clustering, classification, and embedding. In: Advances in Neural Information Processing Systems (NIPS), vol. 19. MIT Press (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cordes, K., Ray’onaldo, C., Broszio, H. (2017). Motion-Coherent Affinities for Hypergraph Based Motion Segmentation. In: Felsberg, M., Heyden, A., Krüger, N. (eds) Computer Analysis of Images and Patterns. CAIP 2017. Lecture Notes in Computer Science(), vol 10424. Springer, Cham. https://doi.org/10.1007/978-3-319-64689-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-64689-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64688-6
Online ISBN: 978-3-319-64689-3
eBook Packages: Computer ScienceComputer Science (R0)