Similar articles

Abstract: Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal constraints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).

[1] Gunawardana, A., Mahajan, M., Acero, A., Platt, J.C., 2005. Hidden Conditional Random Fields for Phone Classification. Proc. 9th International Conference on Speech Communication and Technology. Lisbon, Portugal, p.1117-1120.

[2] Kumar, S., Hebert, M., 2003. Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification. ICCV’03. Nice, France, 2:1150-1157.

[3] Kumar, S., Hebert, M., 2005. A Hierarchical Field Framework for Unified Context-based Classification. ICCV’05. Beijing, China, 2:1284-1291.

[4] Lafferty, J., McCallum, A., Pereira, F., 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proc. Int’l Conf. Machine Learning, p.282-289.

[5] Martel-Brisson, N., Zaccarin, A., 2005. Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model. Proc. CVPR’05. IEEE Computer Society, Washington DC, 2:643-648.

[6] Migdal, J., Grimson, E., 2005. Background Subtraction Using Markov Thresholds. IEEE Workshop on Motion and Video Computing. Washington DC, USA, p.58-65.

[7] Porikli, F., Thornton, J., 2005. Shadow Flow: A Recursive Method to Learn Moving Cast Shadows. ICCV’05, 1:891-898.

[8] Quattoni, A., Collins, M., Darrell, T., 2004. Conditional Random Fields for Object Recognition. Advances in Neural Information Processing Systems. Canada.

[9] Sha, F., Pereira, F., 2003. Shallow Parsing with Conditional Random Fields. Proc. Human Language Technology-NAACL. Edmonton, Canada, p.213-220.

[10] Sheikh, Y., Shah, M., 2005. Bayesian modeling of dynamic scenes for object detection. IEEE Trans. Pattern Anal. Machine Intell., 27(11):1778-1792.

[11] Stauffer, C., Grimson, W., 2000. Learning patterns of activity using real-time tracking. IEEE Trans. Pattern Anal. Machine Intell., 22(8):747-757.

[12] Stenger, B., Ramesh, V., Paragios, N., Coetzee, F., Buhmann, J.M., 2001. Topology Free Hidden Markov Models: Application to Background Modeling. Proc. Int’l Conf. Computer Vision, 1:294-301.

[13] Wang, Y., Ji, Q., 2005. A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences. CVPR’05. San Diego, CA, p.264-270.

[14] Wang, Y., Loe, K.F., Wu, J.K., 2006. A dynamic conditional random field model for foreground and shadow segmentation. IEEE Trans. Pattern Anal. Machine Intell., 28(2):279-289.

[15] Wang, S., Quattoni, A., Morency, L., Demirdjian, D., Darrell, T., 2006. Hidden Conditional Random Fields for Gesture Recognition. CVPR’06. New York, 2:1521-1527.

[16] Yang, T., Li, S.Z., Pan, Q., Li, J., 2004. Real-Time and Accurate Segmentation of Moving Objects in Dynamic Scene. ACM_VSSN’04. New York, p.10-16.

[17] Zhou, Y., Xu, W., Tao, H., Gong, Y.H., 2005. Background Segmentation Using Spatial-Temporal Multi-Resolution MRF. IEEE Workshop on Motion and Video Computing, 2:8-13.

[18] Zivkovic, Z., 2004. Improved Adaptive Gaussian Mixture Model for Background Subtraction. ICPR’04. Cambridge, United Kingdom, 2:28-31.