Moving Objects Detection from Video Sequences Using Fuzzy Edge Incorporated Markov Random Field Modeling and Local Histogram Matching
In this article, we put forward a novel region matching based motion estimation scheme to detect objects with accurate boundaries from video sequences. We have proposed a fuzzy edge incorporated Markov Random Field (MRF) model based spatial segmentation scheme that is able even to identify the blurred boundaries of objects in a scene. Expectation Maximization (EM) algorithm is used to estimate the MRF model parameters. To reduce the complexity of searching, a new scheme is proposed to get a rough knowledge of maximum possible shift of objects from one frame to another by finding the amount of shift in positions of the centroid. Moving objects in the scene are detected by the proposed χ 2-test based local histogram matching. It is noticed that the proposed scheme provides better results with less object background misclassification as compared to optical flow and label fusion based techniques.
KeywordsVideo Sequence Local Binary Pattern Image Frame Markov Random Field Target Frame
- 7.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of Imaging understanding workshop, pp. 121–130 (1981)Google Scholar
- 9.Subudhi, B.N., Nanda, P.K., Ghosh, A.: Moving object detection using MRF model and entropy based adaptive thresholding. In: Proceedings of IEEE 2nd International Conference on Human Computer Interaction, vol. 1, pp. 155–161. Springer, Heidelberg (2010)Google Scholar