Moving Object detection using RunningAverage Discrete Wavelet Transform
Ravi M. Kamble · 2014
Object detection is the first important step in video surveillance. This paper presents a new approach to automatic segmentation of foreground objects from an image sequence by integrating techniques of background subtraction and noise filter. Here, moving objects are detectedusing background subtraction methods. In this background module we cangenerated from the video sequence by using Running average Discrete-Wavelet-Transform. After this moving objects aredetected by comparing current and background frame. Manybackground subtraction approaches are available but most ofthem are not illumination sensitive. The current status of thebackground with sudden illumination change is updated here.In order to produce higher accuracy the proposed method used a noise filter for motion detection. This generates binary motion detection mask. This proposed method shows better result as compared to the existing methods.