Abstract:
The goal of this work is to detect a human figure image and localize his joints and limbs along with their associated pixel masks. In this work we attempt to tackle this ...Show MoreMetadata
Abstract:
The goal of this work is to detect a human figure image and localize his joints and limbs along with their associated pixel masks. In this work we attempt to tackle this problem in a general setting. The dataset we use is a collection of sports news photographs of baseball players, varying dramatically in pose and clothing. The approach that we take is to use segmentation to guide our recognition algorithm to salient bits of the image. We use this segmentation approach to build limb and torso detectors, the outputs of which are assembled into human figures. We present quantitative results on torso localization, in addition to shortlisted full body configurations.
Published in: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
Date of Conference: 27 June 2004 - 02 July 2004
Date Added to IEEE Xplore: 19 July 2004
Print ISBN:0-7695-2158-4
Print ISSN: 1063-6919
Computer Science Division, University of California Berkeley, Berkeley, CA, USA
Computer Science Division, University of California Berkeley, Berkeley, CA, USA
Robotics Research Group, University of Oxford, Oxford, UK
Computer Science Division, University of California Berkeley, Berkeley, CA, USA
Contents Computer Science Division, University of California Berkeley, Berkeley, CA, USA
Computer Science Division, University of California Berkeley, Berkeley, CA, USA
Robotics Research Group, University of Oxford, Oxford, UK
Computer Science Division, University of California Berkeley, Berkeley, CA, USA
