Foreground and Shadow Detection Based on Conditional Random Field
This paper presents a conditional random field (CRF) approach to integrate spatial and temporal constraints for moving object detection and cast shadow removal in image sequences. Interactions among both detection (foreground/background/shadow) labels and observed data are unified by a probabilistic framework based on the conditional random field, where the interaction strength can be adaptively adjusted in terms of data similarity of neighboring sites. Experimental results show that the proposed approach effectively fuses contextual dependencies in video sequences and significantly improves the accuracy of object detection.
KeywordsConditional random field contextual constraint object detection shadow removal
Unable to display preview. Download preview PDF.
- 2.Jabri, S., Duric, Z., Wechsler, H., Rosenfeld, A.: Detection and location of people in video images using adaptive fusion of color and edge information. In: Proc. Int’l. Conf. Pattern Recognition, vol. 4, pp. 627–630 (2000)Google Scholar
- 3.Kumar, S., Hebert, M.: Discriminative fields for modeling spatial dependencies in natural images. Advances in Neural Information Processing Systems, 1351–1358 (2004)Google Scholar
- 4.Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. Int’l. Conf. Machine Learning, pp. 282–289 (2001)Google Scholar
- 6.Paragios, N., Ramesh, V.: A MRF-based approach for real-time subway monitoring. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 1034–1040 (2001)Google Scholar
- 8.Rittscher, J., Kato, J., Joga, S., Blake, A.: A probabilistic background model for tracking. Proc. European Conf. Computer Vision 2, 336–350 (2000)Google Scholar
- 9.Seki, M., Wada, T., Fujiwara, H., Sumi, K.: Background subtraction based on cooccurrence of image variations. Proc. IEEE Conf. Computer Vision and Pattern Recognition 2, 65–72 (2003)Google Scholar