Genetic programming for detecting target motions

This study presents a selective motion detection methodology which is based on genetic programming (GP), an evolutionary search strategy. By this approach, motion detection programs can be automatically evolved instead of manually coded. This study investigates the suitable GP representation for motion detection as well as explores the advantages of this method. Unlike conventional methods, this evolutionary approach can generate programs which are able to mark target motions. The stationary background and the uninteresting or irrelevant motions such as swaying trees, noises are all ignored. Furthermore, programs can be trained to detect target motions from a moving background. They are capable of distinguishing different kinds of motions. Such differentiation can be based on the type of motions as well, for example, fast moving targets are captured, while slow moving targets are ignored. One of the characteristics of this method is that no modification or additional process is required when different types of motions are introduced. Moreover, real-time performance can be achieved by this GP motion detection method