Title
A robust stereo prior for human segmentation
Abstract
The emergence of affordable depth cameras has enabled significant advances in human segmentation and pose estimation in recent years. While it leads to impressive results in many tasks, the use of infra-red cameras have their drawbacks, in particular the fact that they don't work in direct sunlight. One alternative is to use a stereo pair of cameras to produce a disparity space image. In this work, we propose a robust method of using a disparity space image to create a prior for human segmentation. This new prior leads to greatly improved segmentation results; it can be applied to any task where a stereo pair of cameras is available, and segmentation results are desired. As an application, we show how the prior can be inserted into a dual decomposition formulation for stereo, segmentation and human pose estimation.
Year
DOI
Venue
2012
10.1007/978-3-642-37444-9_8
ACCV
Keywords
DocType
Citations 
impressive result,direct sunlight,robust stereo,segmentation result,improved segmentation result,disparity space image,stereo pair,dual decomposition formulation,new prior lead,affordable depth camera,human segmentation
Conference
5
PageRank 
References 
Authors
0.40
14
4
Name
Order
Citations
PageRank
Glenn Sheasby1131.00
Julien Valentin216311.11
Nigel Crook32537.22
Philip H. S. Torr49140636.18