Efficient Multi-Person Hierarchical 3D Pose Estimation for Autonomous Driving

With increasing need of analyzing human poses for autonomous driving, multi-person 3D pose estimation using monocular dash camera in real world scenarios is of great concern. Existing 3D human pose estimation features either large scale training data, or high computation complexity due to the high degrees of freedom in 3D human poses. We propose a novel scheme to hierarchically estimate 3D human poses in natural videos by static or moving cameras in an efficient fashion. Without the need of 3D training data, we formulate torso estimation as a Perspective N Point (PNP) problem, formulate limb pose estimation as an optimization problem, and hierarchically structure the high dimensional poses to address the challenge efficiently. Experiments show good performance and high efficiency of our proposed multi-person 3D pose estimation on real world street scenario videos, resulting in great new opportunities to understand and predict human behaviors for autonomous driving.