Abstract
We present a novel method for the detection of motion boundaries in a video sequence based on differential properties of the spatio-temporal domain. Regarding the video sequence as a 3D spatio-temporal function, we consider the second moment matrix of its gradients (averaged over a local window), and show that the eigenvalues of this matrix can be used to detect occlusions and motion discontinuities. Since these cannot always be determined locally (due to false corners and the aperture problem), a scale-space approach is used for extracting the location of motion boundaries. A closed contour is then constructed from the most salient boundary fragments, to provide the final segmentation. The method is shown to give good results on pairs of real images taken in general motion. We use synthetic data to show its robustness to high levels of noise and illumination changes; we also include cases where no intensity edge exists at the location of the motion boundary, or when no parametric motion model can describe the data.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This research was supported by the EU under the DIRAC integrated project IST-027787.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Black, M.J., Fleet, D.J.: Probabilistic Detection and Tracking of Motion Boundaries. IJCV 38(3), 231–245 (2000)
Gamble, E., Poggio, T.: Visual integration and detection of discontinuities: The key role of intensity edges. AI Lab, MIT, A.I. Memo No. 970 (1987)
Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. of Alvey Vision Conference, pp. 147–151 (1988)
Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Ke, Q., Kanade, T.: A subspace approach to layer extraction. In: Proc. of CVPR’01, pp. 255–262 (2001)
Kolmogorov, V., Zabih, R.: Computing Visual Correspondence with Occlusions using Graph Cuts. In: Proc. of ICCV’01, vol. 2, pp. 508–515 (2001)
Laptev, I., Lindeberg, T.: Space-time Interest Points. In: Proc. of ICCV’03, pp. 432–439 (2003)
Lindeberg, T.: Edge detection and ridge detection with automatic scale selection. IJCV 30(2), 117–154 (1998)
Laptev, I., Lindeberg, T.: Velocity adaption of space-time interest points. In: ICPR’04, vol. 1, pp. 52–56 (2004)
Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proc. of IJCAI’81, pp. 674–679 (1981)
Murray, D.W., Buxton, B.F.: Scene segmentation from visual motion using global optimization. TPAMI 9(2), 220–228 (1987)
Middendorf, M., Nagel, H.-H.: Estimation and Interpretation of Discontinuities in Optical Flow Fields. Proc. of ICCV’01, vol. 1, 178–183 (2001)
Nicolescu, M., Medioni, G.: A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation. TPAMI 27(5), 739–752 (2005)
Odobez, J.M., Bouthemy, P.: MRF-based motion segmentation exploiting a 2D motion model robust estimation. In: Proc. of ICIP’95, vol.3, pp. 628–631 (1995)
Ogale, A.S., Fermüller, C., Aloimonos, Y.: Motion Segmentation Using Occlusions. TPAMI 27(6), 988–992 (2005)
Sawhney, H.S., Ayer, S.: Compact Representations of Videos Through Dominant and Multiple Motion Estimation. TPAMI 18(8), 814–830 (1996)
Shi, J., Malik, J.: Motion Segmentation and Tracking Using Normalized Cuts. In: Proc. of ICCV’98, pp. 1154–1160 (1998)
Tappen, M., Freeman, W.T.: Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters. In: Proc. of ICCV’03, pp. 900–907 (2003)
Weiss, Y.: Smoothness in layers: motion segmentation estimation using nonparametric mixture. In: Proc. of CVPR’97, pp. 520–526 (1997)
Weiss, Y., Adelson, E.H.: A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models. In: Proc. CVPR’96, pp. 321–326 (1996)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Feldman, D., Weinshall, D. (2007). Motion Segmentation Using an Occlusion Detector. In: Vidal, R., Heyden, A., Ma, Y. (eds) Dynamical Vision. WDV WDV 2006 2005. Lecture Notes in Computer Science, vol 4358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70932-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-70932-9_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70931-2
Online ISBN: 978-3-540-70932-9
eBook Packages: Computer ScienceComputer Science (R0)