Hand Tracking Using Kernel Density Approximation

Abstract-In this paper, a new method is proposed for hand tracking based on a density approximation and optimization method. Considering tracking as a classification problem, we train an approximator to recognize hands from its background. This procedure is done by extracting feature vector of every pixel in the first frame and then building an approximator to construct a virtual optimized surface of pixels for similarity of the frames which belong to the hand of those frames related to the movie. Received a new video frame, approximator is employed to test the pixels and build a surface. In this method, the features we use is color RGB corresponding to the feature space. Conducting simulations, it is demonstrated that hand tracking based on this method result in acceptable and efficient performance. The experimental results agree with the theoretical results.