Abstract
We present a novel approach for segmenting different motions from 3D trajectories. Our approach uses the theory of transformation groups to derive a set of invariants of 3D points located on the same rigid object. These invariants are inexpensive to calculate, involving primarily QR factorizations of small matrices. The invariants are easily converted into a set of robust motion affinities and with the use of a local sampling scheme and spectral clustering, they can be incorporated into a highly efficient motion segmentation algorithm. We have also captured a new multi-object 3D motion dataset, on which we have evaluated our approach, and compared against state-of-the-art competing methods from literature. Our results show that our approach outperforms all methods while being robust to perspective distortions and degenerate configurations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For ease of exposition, we will consider here that \(N\) = 4, but the following construct is similar for any \(N\) \(\ge \)2.
References
Costeira, J.P., Kanade, T.: A multibody factorization method for independently moving objects. IJCV 29(3), 159–179 (1998)
Vidal, R.: Subspace clustering. IEEE Sig. Process. Mag. 28(3), 52–68 (2011)
Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: CVPR (2009)
Liu, G., Lin, Z., and Yu, Y.: Robust subspace segmentation by low-rank representation. In: ICML (2010)
Lu, C.-Y., Min, H., Zhao, Z.-Q., Zhu, L., Huang, D.-S., Yan, S.: Robust and efficient subspace segmentation via least squares regression. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 347–360. Springer, Heidelberg (2012)
Lauer, F., Schnörr, C.: Spectral clustering of linear subspaces for motion segmentation. In: ICCV (2009)
Zografos, V., Ellis, L., Mester, R.: Discriminative subspace clustering. In: CVPR (2013)
Hadfield, S., Bowden, R.: Kinecting the dots: Particle based scene flow from depth sensors. In: ICCV, pp. 2290–2295 (2011)
Quiroga, J., Devernay, F., Crowley, J.: Scene flow by tracking in intensity and depth data. In: CVPR Workshops (2012)
Mateus, D., Horaud, R.: Spectral methods for 3-D motion segmentation of sparse scene-flow. In: WMVC (2007)
Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS, pp. 849–856 (2001)
Perera, S., Barnes, N.: Maximal cliques based rigid body motion segmentation with a RGB-D camera. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part II. LNCS, vol. 7725, pp. 120–133. Springer, Heidelberg (2013)
Lenz, P., Ziegler, J., Geiger, A., Roser, M.: Sparse scene flow segmentation for moving object detection in urban environments. In: Intelligent Vehicles Symposium, pp. 926–932 (2011)
Klappstein, J., Vaudrey, T., Rabe, C., Wedel, A., Klette, R.: Moving object segmentation using optical flow and depth information. In: Wada, T., Huang, F., Lin, S. (eds.) PSIVT 2009. LNCS, vol. 5414, pp. 611–623. Springer, Heidelberg (2009)
Ghuffar, S., Brosch, N., Pfeifer, N., Gelautz, M.: Motion segmentation in videos from time of flight cameras. In: IWSSIP (2012)
Wang, Y., Huang, S.: An effient motion segmentation algorithm for multibody RGB-D SLAM. In: Proceedings of Australasian Conference on Robotics and Automation (2013)
Stuckler, J., Behnke, S.: Efficient dense 3D rigid-body motion segmentation in RGB-D video. In: BMVC (2013)
Teichman, A., Lussier, J., Thrun, S.: Learning to segment and track in RGBD. IEEE Trans. Autom. Sci. Eng. 10(4), 841–852 (2013)
Herbst, E., Ren, X., Fox, D.: Object segmentation from motion with dense feature matching. In: Workshop on Semantic Perception, Mapping and Exploration (ICRA) (2012)
Weiss, I.: Geometric invariants and object recognition. Inter 10(3), 201–231 (1993)
Gool, L.V., Moons, T., Pauwels, E., Oosterlinck, A.: Vision and Lie’s approach to invariance. Image Vis. Comput. 13(4), 259–277 (1995)
Schulz-Mirbach, H.: Anwendung von Invarianzprinzipien zur Merkmalgewinnung in der Mustererkennung, ser. Fortschritt-Berichte VDI : Reihe 10, Informatik, Kommunikation; Nr. 372. VDI-Verl. Dusseldorf (1995) iSBN 3-18-337210-X
Schulz-Mirbach, H.: Invariant features for gray scale images. In: DAGM (1995)
Govindu, V.M.: A tensor decomposition for geometric grouping and segmentation. In: CVPR, vol. 1, pp. 1150–1157 (2005)
Chen, G., Lerman, G.: Spectral curvature clustering (SCC). IJCV 81(3), 317–330 (2009)
Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: IROS (2012)
Spinello, L., Arras, K.O.: People detection in RGB-D data. In: IROS (2011)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. In: ICCV (2007)
Acknowledgements
This work has been supported by Vinnova through a grant for the project iQmatic, by SSF through a grant for the project VPS, by VR through a grant for the project ETT, and through the Strategic Areas for ICT research CADICS and ELLIIT.
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
Zografos, V., Lenz, R., Ringaby, E., Felsberg, M., Nordberg, K. (2015). Fast Segmentation of Sparse 3D Point Trajectories Using Group Theoretical Invariants. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)