Human Detection and Pose Estimation in aMulti-camera System : Using a 3D version of Pictorial Structures
Abstract: Multi-view 3D human pose estimation is still a challenging task in uncontrolled environments. Many related approaches are still dependent on silhouettes of the subject obtained by background subtraction. Background subtraction is difficult if the cameras are moving or the background is dynamic. Our solution is to do body part detections both on the foreground and the background, similar to some 2D pose estimation algorithms. We introduce a novel approach to combine 2D body part detections from multiple views to obtain a unified space of detection scores employing the constraints of the 3D space. This combination of detections helps to remove the false positive detection scores suggested by the 2D detectors. We also propose a new human pose estimation algorithm that performs the pose inference directly in the 3D configuration space, taking advantage of the unified detections. This algorithm is a modified version of the well known pictorial structures method and uses distance transform in solving the optimization. Repulsion between joints is also considered in our algorithm which is very helpful for estimating some specific poses. Qualitative results are presented to show the potential strength of our approach.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)