Partitioning of video objects into temporal segments using local motion information

Abstract

We propose an algorithm to partition MPEG-4 video objects into temporal segments with uniform activity levels. These segments can be used for efficient summarization of video objects and/or retrieval of video objects by their motion. The proposed algorithm is based on the shape and texture coding modes of inter coded video object planes. Because the employed filtering techniques are simple and full decoding of the MPEG-4 bitstream is not required, the algorithm is computationally efficient.