| Summary: | 碩士 === 大葉大學 === 資訊管理學系碩士班 === 93 === Background subtraction is a useful and effective method for detecting moving objects in computer-vision applications. However, the variant environments make the detection result to be unsatisfactory. In order to improve the detection accuracy, an appropriate background model must be constructed and maintained to accommodate to the changed environment. In this research, a robust background model maintenance mechanism is proposed and used to implement a moving object detection module.
The proposed mechanism includes three phases: initial background model construction, sustained background model adjustment, rapid background model replacement. In the first phase, an initial background model is constructed from an unfiltered video stream. In the second phase, the background model is adjusted continually according to the gradual change of environment. If a sudden change of environment occurs, the current background model must be replaced rapidly by a new background model in the third phase. The new background model is trained from some video frames collected in the second phase.
Finally, a moving object detection system is performed by applying a background subtraction approach and a shadow elimination technique. By examining in several variant environments, the Fine experimental results illustrate the practicability of the proposed background model maintenance mechanism.
|
|---|
