This paper presents two techniques for improving human body tracking within the particle filtering scheme. Both techniques explore the use of auxiliary measurements. The first technique uses optical flow cues to improve the sampling distribution. The second technique involves the detection of individual body parts, namely the hand, head and torso; and using these detection results to provide additional inference on subsets of state parameters. This method enables the automatic initialization of state vector and allows recovering from tracking failures. These two methods improve the overall accuracy, efficiency and robustness of human body tracking as illustrated by the experimental results.