Tracking Human Position and Lower Body Parts Using Kalman and Particle Filters Constrained by Human Biomechanics

In this paper, a novel framework for visual tracking of human body parts is introduced. The approach presented demonstrates the feasibility of recovering human poses with data from a single uncalibrated camera by using a limb-tracking system based on a 2-D articulated model and a double-tracking strategy. Its key contribution is that the 2-D model is only constrained by biomechanical knowledge about human bipedal motion, instead of relying on constraints that are linked to a specific activity or camera view. These characteristics make our approach suitable for real visual surveillance applications. Experiments on a set of indoor and outdoor sequences demonstrate the effectiveness of our method on tracking human lower body parts. Moreover, a detail comparison with current tracking methods is presented.

The effect of human-body shadowing on indoor UWB TOA-based ranging systems

Because of its superior time resolution, ultra-wide bandwidth (UWB) transmission can be a highly accurate technique for ranging in indoor localization systems. Nevertheless, the presence of obstructions may deteriorate the ranging performance of the system. Indoor environments are often densely populated with people. However, t h e effect of the human body presence has been scarcely investigated so far within the UWB ranging context. In this work, we investigate this effect by conducting UWB measurements and analyzing the ranging performance of the system. Two measurement campaigns were performed in the 3-5.5 GHz band, in an anechoic chamber and a laboratory environment. The range estimates were obtained by employing the threshold-based first peak detection technique. Analysis results revealed that the human body significantly attenuates the direct-path signal component. On the other hand, in this study it does not introduce a significant range error since the length difference between the diffracted paths around the body and the direct-path is less than the spatial resolution of the measurement setup. © 2012 IEEE.