Title :
Hybrid body representation for integrated pose recognition, localization and segmentation
Author :
Chen, Cheng ; Fan, Guoliang
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK
Abstract :
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body part as well as the whole body are represented by an off-line learned shape model where both region-based and edge-based priors are combined in a coupled shape representation. Part-based spatial priors are represented by a ldquostarrdquo graphical model. This hybrid body representation can synergistically integrate pose recognition, localization and segmentation into one computational flow. Moreover, as an important step for feature extraction and model inference, segmentation is involved in the low-level, mid-level and high-level vision stages, where top-down prior knowledge and bottom-up data processing is well integrated via the proposed hybrid body representation.
Keywords :
computer vision; feature extraction; image representation; image segmentation; pose estimation; computational flow; coupled shape representation; data processing; feature extraction; hybrid body representation; integrated pose recognition; model inference; off-line learned shape model; part-based structural information; pose localization; pose segmentation; star graphical model; template-like view information; Biological system modeling; Data processing; Deformable models; Feature extraction; Graphical models; Humans; Image recognition; Image segmentation; Object recognition; Shape;
Conference_Titel :
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4244-2242-5
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2008.4587459