Monocular 3D Reconstruction of Human Motion in Long Action Sequences

Abstract. A novel algorithm is presented for the 3D reconstruction of human action in long (> 30 second) monocular image sequences.A sequence is represented by a small set of automatically found representative keyframes. The skeletal joint positions are manually located in each keyframe and mapped to all other frames in the sequence. For each keyframe a 3D key pose is created, and interpolation between these 3D body poses, together with the incorporation of limb length and symmetry constraints, provides a smooth initial approximation of the 3D motion. This is then fitted to the image data to generate a realistic 3D reconstruction. The degree of manual input required is controlled by the diversity of the sequence's content. Sports' footage is ideally suited to this approach as it frequently contains a limited number of repeated actions. Our method is demonstrated on a long (36 second) sequence of a woman playing tennis filmed with a non-stationary

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Gareth Loy, Martin Eriksson, Josephine Sullivan, Stefan Carlsson
• Keywords: Computer Vision, ECCV 2004, Image Sequences.A Sequence, Realistic 3D Reconstruction, Skeletal Joint Positions, Smooth Initial Approximation, Woman Playing Tennis