Camera Placement Considering Occlusion for Robust Motion Capture

摘要: In multi-camera tracking systems, camera placement can have a significant impact on the overall performance. feature-based motion capture degradation come from two major sources, low image resolution and target occlusion. order to achieve better automate process, quantitative metric evaluate quality of configurations is needed. We propose that estimates error caused by both occlusion.. It includes probabilistic occlusion model reflects dynamic self-occlusion target. Using this metric, we show optimal pose analyzing several configurations. Finally, examples demonstrate how be applied toward automatic design more accurate robust systems.