There are a number of different algorithms for object motion estimation in image sequences. Almost every algorithm is based on one of three different mathematical methods. An overview of these methods is given, together with some published application examples on object tracking.
A method for tracking of multiple moving objects has been developed on a GOP 300 image processing system. This method works on image sequences with a stationary background, and can be divided into the following steps:
These steps are repeated for every sample of the sequence. As an output from every processed sample in a test sequence, both a resulting image and a record in a datafile have been generated. The resulting image is a copy of the actual sample with the active object identities overlayed at the corresponding positions. The resulting images have been stored on a video tape.