Abstract
We present a closed form solution to the problem of segmenting multiple 3D motion models from straight-line optical flow. We introduce the multibody line optical flow constraint(MLOFC), a polynomial equation relating motion models and line parameters. We show that the motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences are also presented.
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
Preview
Unable to display preview. Download preview PDF.
References
Rittscher, J., Tu, P.H., Krahnstoever, N.: Simultaneous estimation of segmentation and shape. In: IEEE Conference on Computr Vision and Pattern Recognition (2005)
Torr, P.H.S.: Geometric motion segmentation and model selection Phil. Trans. Royal Society of London A (1998)
Feng, X., Perona, P.: Scene segmentation from 3d motion (1998)
Torr, P., Szeliski, R., Anandan, P.: An integrated bayesian approach to layer extraction from image sequences. IEEE Trans. on Pattern Analysis and Machine Intelligence 23, 297–303 (2001)
Vidal, R., Ma, Y., Sastry, S.: Generalized principal component analysis (gpca). In: IEEE Conference on Computr Vision and Pattern Recognition, pp. 621–628 (2003)
Vidal, R., Ma, Y.: A unified algebraic approach to 2-d and 3-d motion segmentation. In: European Conference on Computer Vision, pp. 1–15 (2004)
Singaraju, D., Vidal, R.: A bottom up algebraic approach to motion segmentation. In: Asian Conference on Computer Vision, pp. 286–296 (2006)
Vidal, R., Singaraju, D.: A closed-form solution to direct motion segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 510–515 (2005)
Vidal, R., Ravichandran, A.: Optical flow estimation and segmentation of multiple moving dynamic textures. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)
Fan, X., Vidal, R.: The space of multibody fundamental matrices: Rank, geometry and projection. In: IEEE International Conference on Computer Vision (2005)
Yan, J., Pollefeys, M.: Articulated motion segmentation using ransac with priors. In: IEEE International Conference on Computer Vision (2005)
Hajder, L., Chetverikov, D.: Robust 3d segmentation of multiple moving objects underweak perspective. In: IEEE International Conference on Computer Vision (2005)
Shi, F., Wang, J., Zhang, J., Liu, Y.: Motion segmentation of multiple translating objects using line correspondences. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 315–320 (2005)
Zhang, J., Shi, F., Liu, Y.: Motion segmentation by multibody trifocal tensor using line correspondence. In: International Conference on Pattern Recognition (2006)
Faugeras, O., Navab, N., Deriche, R.: On the information contained in the motion field of lines and the cooperation between motion and stereo. International Journal of Imaging Systems and Technology (1991)
Jiang, S.F., Chen, Z., Yang, S.H.: Reconstructing 3d rotation motion parameters from 2d image straight-line optical flow. Journal of Nanchang Institute of Aeronautical Technology(Natural Science) (2005)
Hartley, R., Vidal, R.: The multibody trifocal tensor: Motion segmentation from 3 perspective views. In: IEEE Conference on Computer Vision and Pattern Recognition (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Zhang, J., Shi, F., Wang, J., Liu, Y. (2007). 3D Motion Segmentation from Straight-Line Optical Flow. In: Sebe, N., Liu, Y., Zhuang, Y., Huang, T.S. (eds) Multimedia Content Analysis and Mining. MCAM 2007. Lecture Notes in Computer Science, vol 4577. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73417-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-540-73417-8_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73416-1
Online ISBN: 978-3-540-73417-8
eBook Packages: Computer ScienceComputer Science (R0)