A method segments a video into objects, without user assistance. An MPEG compressed video is converted to a structure called a pseudo spatial/temporal data using DCT coefficients and motion vectors. The compressed video is first parsed and the pseudo spatial/temporal data are formed. Seeds macro-blocks are identified using, e.g., the DCT coefficients and changes in the motion vector of macro-blocks.
A video volume is “grown” around each seed macro-block using the DCT coefficients and motion distance criteria. Self-descriptors are assigned to the volume, and mutual descriptors are assigned to pairs of similar volumes. These descriptors capture motion and spatial information of the volumes. Similarity scores are determined for each possible pair-wise combination of volumes. The pair of volumes that gives the largest score is combined iteratively. In the combining stage, volumes are classified and represented in a multi-resolution coarse-to-fine hierarchy of video objects.