Output details
15 - General Engineering
University of Oxford
Output title
Progressive search space reduction for human pose estimation
Type
E - Conference contribution
Name of conference/published proceedings
2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12
Volume number
-
Issue number
-
First page of article
976
ISSN of proceedings
1063-6919
Year of publication
2008
URL
-
Number of additional authors
2
Additional information
The objective here is to estimate 2D human pose as a spatial configuration of body parts in an image. Apart from the novelty of the approach (which combines detection, segmentation and tree graphical models), the paper was one of the first to successfully estimate human pose in very visually challenging (for a computer) images from TV and film. It also introduced a benchmark data set and evaluation procedure for assessing the performance of human pose estimation algorithms, see http://www.robots.ox.ac.uk/~vgg/data/stickmen/. This data set and evaluation protocol have been used extensively by other researchers. A journal version was published in 2012.
Interdisciplinary
-
Cross-referral requested
-
Research group
D - Information, Vision and Control
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
