Abstract
Motion segmentation is a well studied problem in computer vision. Most approaches assume a priori knowledge of the number of moving objects in the scene. In the absence of such information, motion segmentation is generally achieved through brute force search, e.g., searching over all possible priors or iterating over a search for the most prominent motion. In this paper, we propose an efficient method that achieves motion segmentation over a sequence of frames while estimating the number of moving segments; no prior assumption is made about the structure of scene. We utilize metric embedding to map a complex graph of image features and their relations into hierarchically well-separated tree, yielding a simplified topology over which the motions are segmented. Moreover, the method provides a hierarchical decomposition of motion for objects with moving parts.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bartal, Y.: Probabilistic approximation of metric spaces and its algorithmic applications. In: Proceedings of the 37th Annual Symposium on Foundations of Computer Science, FOCS 1996, pp. 184–193. IEEE Computer Society, Washington, DC (1996)
Bartal, Y.: On approximating arbitrary metrices by tree metrics. In: Proceedings of the 30th Annual ACM Symposium on Theory of Computing, STOC 1998, pp. 161–168. ACM, New York (1998)
Charikar, M., Chekuri, C., Goel, A., Guha, S., Plotkin, S.: Approximating a finite metric by a small number of tree metrics. In: Proceedings of the 39th Annual Symposium on Foundations of Computer Science, FOCS 1998, pp. 379–388. IEEE Computer Society, Washington, DC (1998)
Colombari, A., Fusiello, A., Murino, V.: Segmentation and tracking of multiple video objects. Pattern Recogn. 40(4), 1307–1317 (2007)
Dahlhaus, E., Johnson, D.S., Papadimitriou, C.H., Seymour, P.D., Yannakakis, M.: The complexity of multiway cuts (extended abstract). In: Proceedings of the 24th Annual ACM Symposium on Theory of Computing, STOC 1992, pp. 241–251. ACM, New York (1992)
Demirci, M.F., Osmanlioglu, Y., Shokoufandeh, A., Dickinson, S.: Efficient many-to-many feature matching under the l1 norm. Comput. Vis. Image Underst. 115(7), 976–983 (2011)
Endlessreference. Animation reference - athletic male standard walk - realtime [Video file], 12 January 2015. https://www.youtube.com/watch?v=GBkJY86tZRE
Fakcharoenphol, J., Rao, S., Talwar, K.: A tight bound on approximating arbitrary metrics by tree metrics. In: Proceedings of the 35th Annual ACM Symposium on Theory of Computing, STOC 2003, pp. 448–455. ACM, New York (2003)
Flores-Mangas, F., Jepson, A.D.: Fast rigid motion segmentation via incrementally-complex local models. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2259–2266. IEEE (2013)
Goemans, M.X., Williamson, D.P.: The primal-dual method for approximation algorithms and its application to network design problems. In: Hochbaum, D.S. (ed.) Approximation Algorithms for NP-hard Problems, pp. 144–191. PWS Publishing Co., Boston (1997)
Julià, C., Sappa, A.D., Lumbreras, F., Serrat, J., López, A.: Motion segmentation from feature trajectories with missing data. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds.) IbPRIA 2007. LNCS, vol. 4477, pp. 483–490. Springer, Heidelberg (2007)
Karp, R.M.: A 2k-competitive algorithm for the circle. Manuscript, 5 August 1989
Karzanov, A.V.: Minimum 0-extensions of graph metrics. Eur. J. Comb. 19(1), 71–101 (1998)
Kleinberg, J., Tardos, É.: Approximation algorithms for classification problems with pairwise relationships: metric labeling and Markov random fields. J. ACM 49(5), 616–639 (2002)
Kong, M., Leduc, J.P., Ghosh, B.K., Wickerhauser, V.M.: Spatio-temporal continuous wavelet transforms for motion-based segmentation in real image sequences. In: Proceedings of the 1998 International Conference on Image Processing, ICIP 1998, vol. 2, pp. 662–666. IEEE (1998)
Konjevod, G., Ravi, R., Salman, F.S.: On approximating planar metrics by tree metrics. Inf. Process. Lett. 80(4), 213–219 (2001)
Kumar, M.P., Torr, P.H., Zisserman, A.: Learning layered motion segmentations of video. Int. J. Comput. Vis. 76(3), 301–319 (2008)
Li, R., Songyu, Y., Yang, X.: Efficient spatio-temporal segmentation for extracting moving objects in video sequences. IEEE Trans. Consum. Electron. 53(3), 1161–1167 (2007)
Osmanlıoğlu, Y., Shokoufandeh, A.: Multi-layer tree matching using HSTs. In: Liu, C.-L., Luo, B., Kropatsch, W.G., Cheng, J. (eds.) GbRPR 2015. LNCS, vol. 9069, pp. 198–207. Springer, Heidelberg (2015)
Rathi, Y., Vaswani, N., Tannenbaum, A., Yezzi, A.: Tracking deforming objects using particle filtering for geometric active contours. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1470–1475 (2007)
Shen, H., Zhang, L., Huang, B., Li, P.: A map approach for joint motion estimation, segmentation, and super resolution. IEEE Trans. Image Process. 16(2), 479–490 (2007)
Stolkin, R., Greig, A., Hodgetts, M., Gilby, J.: An EM/E-MRF algorithm for adaptive model based tracking in extremely poor visibility. Image Vis. Comput. 26(4), 480–495 (2008)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vis. 9(2), 137–154 (1992)
Vazirani, V.V.: Approximation Algorithms. Springer, Heidelberg (2003)
Zhang, J., Shi, F., Wang, J., Liu, Y.: 3D motion segmentation from straight-line optical flow. In: Sebe, N., Liu, Y., Zhuang, Y., Huang, T.S. (eds.) MCAM 2007. LNCS, vol. 4577, pp. 85–94. Springer, Heidelberg (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Osmanlıoğlu, Y., Dickinson, S., Shokoufandeh, A. (2015). Unsupervised Motion Segmentation Using Metric Embedding of Features. In: Feragen, A., Pelillo, M., Loog, M. (eds) Similarity-Based Pattern Recognition. SIMBAD 2015. Lecture Notes in Computer Science(), vol 9370. Springer, Cham. https://doi.org/10.1007/978-3-319-24261-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-24261-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24260-6
Online ISBN: 978-3-319-24261-3
eBook Packages: Computer ScienceComputer Science (R0)