Robust video segmentation employing variable bandwidth object boundary

A pixel-wise accurate and interactive video segmentation technique is proposed in this paper to generate a binary mask of moving objects optimized for MPEG-4 object-based video coding. The initial object mask is tracked temporally, and three regions are classified as background region, object region, and uncertain region where the pixel is within a certain distance from the tracked object boundary. We exploit the color feature in the L?u?v? space, and use a non-parametric gradient-based iterative color clustering algorithm, called the mean shift algorithm to generate the region marker in the background and object region. We use watershed technique to classify the pixels in the uncertain region into background and object. In addition, by employing a variable bandwidth region boundary, the final mask for moving objects, i:e: shape is optimized for MPEG-4 coding efficiency. In fact, the shape coding efficiency can be improved up to 30% with negligible loss of perceptual quality.