Pose from Flow and Flow from Pose

Katerina Fragkiadaki, Han Hu, Jianbo Shi
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Human pose detectors, although successful in localising faces and torsos of people, often fail with lower arms. Motion estimation is often inaccurate under fast movements of body parts. We build a segmentation-detection algorithm that mediates the information between body parts recognition, and multi-frame motion grouping to improve both pose detection and tracking. Motion of body parts, though not accurate, is often sufficient to segment them from their backgrounds. Such segmentations are
more » ... al for extracting hard to detect body parts out of their interior body clutter. By matching these segments to exemplars we obtain pose labeled body segments. The pose labeled segments and corresponding articulated joints are used to improve the motion flow fields by proposing kinematically constrained affine displacements on body parts. The pose-based articulated motion model is shown to handle large limb rotations and displacements. Our algorithm can detect people under rare poses, frequently missed by pose detectors, showing the benefits of jointly reasoning about pose, segmentation and motion in videos. Part detections change motion affinities Region clusters index into pose exemplars Body pose induces kinematic constraints Pose propagates with articulated flow
doi:10.1109/cvpr.2013.268 dblp:conf/cvpr/FragkiadakiHS13 fatcat:4gtj5d2fxfdgfl5jw3pd7fbnha