Moving Objects Tracking Using Statistical Models

Object detection plays an important role in successfulness of a wide range ofapplications that involve images as input data. In this paper we have presented anew approach for background modeling by nonconsecutive frames differencing.Direction and velocity of moving objects have been extracted in order to get anappropriate sequence of frames to perform frame subtraction. Stationary parts ofbackground are extracted from differenced frames and joined as patches tocomplete the background model. There is also a special stage to handle changingregions of dynamic scenes. During the detection phase, the modeled background isupdated for every new frame. Since it's not necessary to estimate each pixel grayvalue like the most common statistical methods, modeling process is not timeconsuming.Different experiments show successful results even for challengingphenomena like environmental changes.

Keywords:

Object tracking , Background modeling , Frame subtraction