The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottom-up using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an integer quadratic programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 hand-labeled images are used to train the low-level part detector and learn the pairwise constraints. We show test results on a variety of images.
Recovering human body configurations using pairwise constraints between parts
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 824-831 Vol. 1
2005-01-01
532307 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Recovering Human Body Configurations Using Pairwise Constraints between Parts
British Library Conference Proceedings | 2005
|Recovering Human Body Configurations: Combining Segmentation and Recognition
British Library Conference Proceedings | 2004
|