Video object plane segmentation using a morphological motion filter and Hausdorff object tracking

This paper considers the decomposition of video sequences into so-called video object planes, which is required for the content-based representation of visual objects in MPEG-4. A new segmentation algorithm is described that identifies physical objects using a morphological motion filter. For the object of interest, a two-dimensional binary model is derived based on areas in the scene that are moving differently from the background. This model is updated each frame to pick up possible rotation and changes in shape of the object. Temporal correspondence is established by a Hausdorff object tracker: The binary model sequences guide the actual video object plane extraction. Since the model points correspond to edges detected by the Canny operator; a high object boundary location is achieved. Experimental results demonstrate that our proposed technique can successfully extract the physical object from video sequences