This paper describes how image sequences taken by a moving video camera may be processed to detect and track moving objects against a moving background in real-time. The motion segmentation and shape tracking system is known as ASSET-2 -- A Scene Segmenter Establishing Tracking, Version 2.
The work has been conducted using as a typical real life situation, a vehicle travelling along a road, taking video pictures of what is in front of it. If other vehicles can be seen, they must be ``segmented'' from the background of the rest of the scene so that their motion can be estimated and the necessary evasive action taken. This situation provides a testbed for the developed program which is quite general, and ASSET-2 has been tested on other types of sequence containing independent motion.
This paper gives a brief review of current image sequence segmentation methods followed by an overview of the ASSET-2 system. Next, short descriptions of each of the sections of ASSET-2 are given. Finally, results of using the ASSET-2 system are shown and discussed.
ASSET-2 supersedes ASSET [29], which matched features only from one frame to the next (as opposed to tracking them over many frames) and segmented the resulting flow vectors into clusters assuming constant flow within clusters (now improved with the allowance of linear flow variations).