Abstract:

We introduce an automatic segmentation framework that blends the advantages of color, texture, shape, and motion based segmentation methods in a computationally feasible way. A spatiotemporal data structure is first constructed for each group of video frames, in which each pixel is assigned a feature vector based on low-level visual information. Then, the smallest homogeneous components, so called as volumes, are expanded from selected marker points using an adaptive, three dimensional, centroid-linkage method. Self descriptors that characterize each volume, and relational descriptors that capture the mutual properties between pairs of volumes are determined by evaluating the boundary, trajectory, and motion of the volumes. These descriptors are used to measure the similarity between volumes based on which volumes are further grouped into objects. A fine-to-coarse clustering algorithm yields a multi-resolution object tree representation as an output of the segmentation.