Abstract
This paper presents an algorithm for finding the dense motion flow of deformable objects from RGB-D images. We introduce a 3D deformable spatial pyramid model by reformulating the previous 2D deformable spatial pyramid model [1] with depth information. Our algorithm recasts the problem of estimating 3D motion of deformable objects as a problem of estimating 2D motions of a set of grid cells where each pixel contains a viewpoint-invariant feature vector. These grid cells are controlled by a pyramid graph model. Our approach significantly reduces the computational cost through a 2D correspondence search and efficiently handles even large deformations with the pyramid graph model. As demonstrated in the experimental results, the proposed algorithm shows robustness in various deformation scenarios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Kim, J., Liu, C., Sha, F., Grauman, K.: Deformable spatial pyramid matching for fast dense correspondences. In: CVPR (2013)
Li, K., Dai, Q., Xu, W.: Markerless shape and motion capture from multiview video sequences. IEEE Trans. CSVT 21, 320–334 (2011)
Geiger, A., Lauer, M., Wojek, C., Stiller, C., Urtasun, R.: 3d traffic scene understanding from movable platforms. IEEE Trans. PAMI (2014)
Lenz, P., Ziegler, J., Geiger, A., Roser, M.: Sparse scene flow segmentation for moving object detection in urban environments. In: Intelligent Vehicles Symposium (IV) (2011)
Herbst, E., Ren, X., Fox, D.: Rgb-d flow: Dense 3-d motion estimation using color and depth. In: ICRA (2013)
Quiroga, J., Devernay, F., Crowley, J.L.: Local/Global Scene Flow Estimation. In: ICIP (2013)
Hornacek, M., Fitzgibbon, A., Rother, C.: Sphereflow: 6 dof scene flow from rgb-d pairs. In: CVPR (2013)
Shaji, A., Varol, A., Torresani, L., Fua, P.: Simultaneous point matching and 3d deformable surface reconstruction. In: CVPR (2010)
Schulman, J., Lee, A., Ho, J., Abbeel, P.: Tracking deformable objects with point clouds. In: ICRA (2013)
Gossow, D., Weikersdorfer, D., Beetz, M.: Distinctive texture features from perspective-invariant keypoints. In: ICPR (2012)
Diebel, J., Thrun, S.: An application of markov random fields to range sensing. In: Proceedings of Conference on Neural Information Processing Systems (NIPS). MIT Press, Cambridge (2005)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110, 346–359 (2008)
Li, S.Z., Singh, S.: Markov random field modeling in image analysis, vol. 26. Springer (2009)
Murphy, K.P., Weiss, Y., Jordan, M.I.: Loopy belief propagation for approximate inference: An empirical study. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, UAI 1999 (1999)
Weiss, Y.: Correctness of local probability propagation in graphical models with loops. Neural. Comput. 12, 1–41 (2000)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. International Journal of Computer Vision 70, 41–54 (2006)
Liu, C., Yuen, J., Torralba, A.: Sift flow: Dense correspondence across scenes and its applications. IEEE Trans. PAMI 33, 978–994 (2011)
Liu, L., Low, K.L., Lin, W.Y.: Dense image correspondence under large appearance variations. In: ICIP, pp. 770–774 (2013)
Rother, C., Kolmogorov, V., Blake, A.: “grabcut”: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Hur, J., Lim, H., Ahn, S.C. (2014). 3D Deformable Spatial Pyramid for Dense 3D Motion Flow of Deformable Object. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2014. Lecture Notes in Computer Science, vol 8887. Springer, Cham. https://doi.org/10.1007/978-3-319-14249-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-14249-4_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14248-7
Online ISBN: 978-3-319-14249-4
eBook Packages: Computer ScienceComputer Science (R0)