A Multi-Layer MRF Model for Video Object Segmentation
A novel video object segmentation method is proposed which aims at combining color and motion information. The model has a multi-layer structure: Each feature has its own layer, called feature layer, where a classical Markov random field (MRF) image segmentation model is defined using only the corresponding feature. A special layer is assigned to the combined MRF model, called combined layer, which interacts with each feature layer and provides the segmentation based on the combination of different features. Unlike previous methods, our approach doesn’t assume motion boundaries being part of spatial ones. Therefore a very important property of the proposed method is the ability to detect boundaries that are visible only in the motion feature as well as those visible only in the color one. The method is validated on synthetic and real video sequences.
KeywordsMarkov Random Field Feature Layer Color Layer Motion Segmentation Markov Random Field Model
Unable to display preview. Download preview PDF.
- 1.Odobez, J.M., Bouthemy, P.: Direct model-based image motion segmentation for dynamic scene analysis. In: Proceedings of Asian Conference on Computer Vision (1995)Google Scholar
- 2.Weiss, Y., Adelson, E.H.: A unified mixture framework for motion segmentation: Incorporating spatial coherence and estimating the number of models. In: Proceedings of International Conference on Computer Vision and Pattern Recognition (1996)Google Scholar
- 3.Khan, S., Shah, M.: Object based segmentation of video using color, motion and spatial information. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, vol. II, pp. 746–751. IEEE, Los Alamitos (2001)Google Scholar
- 7.Besag, J.: On the statistical analysis of dirty pictures. J. Roy. Statist. Soc., ser. B (1986)Google Scholar
- 8.Proesmans, M., Gool, L.V., Pauwels, E., Oosterlinck, A.: Determination of optical flow and its discontinuities using non-linear diffusion. In: Proceedings of Eurpoean Conference on Computer Vision, vol. 2, pp. 295–304 (1994)Google Scholar
- 11.Comaniciu, D., Meer, P.: Mean shift: A robust approach towards feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence (2001)Google Scholar
- 12.Kato, Z., Pong, T.C., Song, G.Q.: Unsupervised segmentation of color textured images using a multi-layer MRF model. In: Proceedings of International Conference on Image Processing, Barcelona, Spain, vol. I, pp. 961–964. IEEE, Los Alamitos (2003)Google Scholar