• SATEESH KUMAR
• MR. RUPESH MAHAMUNE

The detection of moving object is important and critical task in Real -Time video signal. This becomes more critical under the circumstances such as luminance changed, weaving leaves, rainy weather, under heavy snow fall weather. In this paper we studies background subtraction algorithm for foreground detection. Foreground detection is mainly with help of two approaches these approaches pixel to pixel or frame to frame. But in real-time video sequence pixel to pixel foreground detection is complex because it has more time for processing because in this method compares pixel value. And in frame to frame comparison method compare two consecutive frames. In this paper by using GMM Algorithm improves result in case of less illumination as well as the images having moving objet of the background. In this paper, many soft computing techniques is used such as filtering, mean square error, recall , precision etc. will used for identifying foreground.

soft computing, filtering, , recall, precision, MSE, GMM, BG, FG.

"Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition video: A review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 4, page no.1092-1096, April-2015, Available :http://www.jetir.org/papers/JETIR1504045.pdf

"Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition video: A review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 4, page no. pp1092-1096, April-2015, Available at : http://www.jetir.org/papers/JETIR1504045.pdf