Vision-based Moving Object Detection And Gesture Recognition

Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications. A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model. There are many challenges in developing a good background subtraction algorithm. First, it must be robust against changes in illumination. Second, it should avoid detecting non-stationary background objects such as swinging leaves, rain, snow,and shadow cast by moving objects. Based on the study of existing methods, I propose several modified methods to overcome these problems.This paper combines HSV shadow suppression into the background model to deal with shadows, highlights and illumination changes. To deal with moving backgrounds, this paper propose a new background update strategy which include the foreground information in the model. we propose a method that combines pixel-based and block-based approaches into a single framework. We show that efficient hierarchical backgrounds can be built by considering that these two approaches are complementary to each other. In addition, a novel descriptor is proposed for block-based background modeling in the coarse level of the hierarchy. Quantitative evaluations show that the proposed hierarchical method can provide better results than existing single-level approaches.Based on the accurate detection of foreground moving people, in this thesis, we address the issue of detecting and recognizing hand gesture in video sequences. First, hand is extracted using skin model. Second, Extended finite state machine is used to segment motion sequence in video sequences. Hausdorff distance is used for motion classification of invariant scale and translation.