Paper Info
Title
Pose from Flow and Flow from Pose
Abstract
Human pose detectors, although successful in localising faces and torsos of people, often fail with lower arms. With fast movements body motion estimation is often inaccurate. 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 crucial 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.
Year
DOI
Venue
2013
10.1109/CVPR.2013.268
Computer Vision and Pattern Recognition
Keywords
Field
DocType
face recognition,image segmentation,object detection,pose estimation,video signal processing,face localisation,flow from pose,human pose detectors,pose from flow,segmentation-detection algorithm,torso localisation,video,motion segmentation,optical flow,pose estimation,tracking
Computer vision,Object detection,Pattern recognition,Computer science,Segmentation,3D pose estimation,Image segmentation,Pose,Artificial intelligence,Motion estimation,Articulated body pose estimation,Optical flow
Conference
Volume
Issue
ISSN
2013
1
1063-6919
Citations 
PageRank 
References 
28
0.76
22
Authors
3
Name
Order
Citations
PageRank
Katerina Fragkiadaki142421.57
Han Hu2331.20
Jianbo Shi3102071031.66