3D Video-based Motion Capture using Convolutional Neural Networks

This paper considers the problem of estimating three-dimensional motion of human actors from single view video sequences. This problem has received considerable attention in the recent past, since the motion capture data obtained from video sequences find applications in several domains of character animation. The problem becomes increasingly challenging when both the camera and the background are non-stationary. We propose a framework based on state-of-the-art Convolutional Neural Networks for object detection, estimation of positions of 2D anatomical landmarks and the reconstruction of 3D joint positions. Experimental results and analysis showing the effectiveness of the proposed framework in capturing motion from single-view video sequences are presented.