A NEW APPROACH FOR TRACKING OBJECT IN VIDEOS

In recent days, capturing images with high quality and good size is so easy because of rapid improvement in quality of capturing device with less costly but superior technology. Videos are a collection of sequential images with a constant time interval. Therefore, manually handling videos are quite impossible. So we need an automated devise to process these videos. Our work is related to the broad subject of automatic motion detection and analysis in video surveillance image sequence. Besides, proposing the new algorithm, some of the previous algorithms are analysed, where some of the approaches are noticeably complementary sometimes. In real time surveillance, detecting and tracking multiple objects and monitoring their activities in both outdoor and indoor environment are challenging task for the video surveillance system. Presence of a good number of real time problems limits scope of our work since the beginning. The problems are namely, illumination changes, moving background and shadow detection. An improved tracking algorithm has been proposed . The algorithm is applied on to a number of practical problems to observe whether it leads us to the expected solution. Test result shows that the proposed algorithm shows the better quality result.