Human tracking in the complicated background by Particle Filter using color-histogram and HOG
Lujun Jin, Jian Cheng, Hu Huang · 2010
Human tracking based on computer vision, is a challenging and crucial problem in intelligent video surveillance system. As is known to all, human motion is usually non-linear and non-Gaussian, many prevalent frameworks are not appropriate, such as Kalman Filter, etc. Nevertheless, the Particle Filter could still have good performance even when the system is nonlinear and non-Gaussian. This paper is based on Particle Filter, too. In many cases, the Particle Filter always uses single-human-feature (such as color-histogram, edge gradient, Histogram of Oriented Gradients (HOG), etc) to track human objects. But using single-human-feature will lose a lot of information in the process of tracking human objects. In order to avoid this drawback, this paper proposes to fuse the information of color-histogram and HOG to track. This method keeps both color and shape information, consequently, it is more robust and steady. Experiment results demonstrate that this method is effective to improve the performance of tracking.