3D hand tracking in recent years has become a hot spot in Human Computer Interaction(HCI), and it also exists many difficulties. Our research roots in the observation model which is used to measure similarity between hand image and hand model for hand tracking. Firstly, using edge feature extracted from hand image and hand model projection contour to get a probability function, which measures the similarity between hand model and hand image according their chamfer distance. Secondly, using skin color segmentation algorithm to get binary hand image, at the same time we can get hand model silhouette from hand model projection points. After getting the binary hand image and hand model silhouette we then build another probability function based silhouette feature. Finally we combine the two functions to build the observation model to evaluate the probability of hand state according current observation. Applying the observation model into the weight calculation stage of particle filter can effectively increase calculation accuracy. On the other hand, we introduce hand constraints to hand model, utilize these constraints in sampling stage not only can reduce sampling degree of freedom(DOF) but also can revise the incorrect samples. 

No abstract

To confront the ISI caused by multipath in spread spectrum system,we proposed a hardware architecture of LMS equalizer based on FPGA using parallel processing, which greatly increased the number of iterations in a limited period, and accelerated the convergence of the algorithm. At the same time, the multiplier and the divider was optimized by using the internal hardware multiplier. Simulation results proved that the scheme almost had the same performance compared with the software result with high speed and less hardware consumption.Keywords-least mean square(LMS), field programmable gate array(FPGA), parallel processing. I. INTRODUCTIONAs the time diffusing of mobile wireless environment, if the channel's coherence bandwidth is less than the signal bandwidth, the channel will show frequency selective fading, which cause the overlap between the transmitted symbols, which is called inter-symbol interference (ISI) [1]. The effective way to improve channel is the equalization technique. In this paper, we proposed a new hardware architecture of least mean square (LMS) equalizer that adaptively compensate for ISI of the time variable channel. It takes full use of the correlation among successive channel and the characteristic of the structure of the algorithm, and taking the advantages of parallel processing of FPGA, which greatly improve the speed of precessing and convergence of the algorithm, while ensure the performance of the algorithm. Simulations are presented in the end of the paper.

No abstract