Real-time semantic clothing segmentation
Real-time semantic clothing segmentation
Clothing segmentation is a challenging field of research which is rapidly gaining attention. This paper presents a system for semantic segmentation of primarily monochromatic clothing and printed/stitched textures in single images or live video. This is especially appealing to emerging augmented reality applications such as retexturing sports players' shirts with localized adverts or statistics in TV/internet broadcasting. We initialise points on the upper body clothing by body fiducials rather than by applying distance metrics to a detected face. This helps prevent segmentation of the skin rather than clothing. We take advantage of hue and intensity histograms incorporating spatial priors to develop an efficient segmentation method. Evaluated against ground truth on a dataset of 100 people, mostly in groups, the accuracy has an average F-score of 0.97 with an approach which can be over 88% more efficient than the state of the art.
Cushen, George
52f73d41-3ae0-4c11-a50a-86e782c03745
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
July 2012
Cushen, George
52f73d41-3ae0-4c11-a50a-86e782c03745
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Cushen, George and Nixon, Mark S.
(2012)
Real-time semantic clothing segmentation.
International Symposium on Visual Computing, Crete, Greece.
16 - 18 Jul 2012.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Clothing segmentation is a challenging field of research which is rapidly gaining attention. This paper presents a system for semantic segmentation of primarily monochromatic clothing and printed/stitched textures in single images or live video. This is especially appealing to emerging augmented reality applications such as retexturing sports players' shirts with localized adverts or statistics in TV/internet broadcasting. We initialise points on the upper body clothing by body fiducials rather than by applying distance metrics to a detected face. This helps prevent segmentation of the skin rather than clothing. We take advantage of hue and intensity histograms incorporating spatial priors to develop an efficient segmentation method. Evaluated against ground truth on a dataset of 100 people, mostly in groups, the accuracy has an average F-score of 0.97 with an approach which can be over 88% more efficient than the state of the art.
Text
Cushen-ISVC2012.pdf
- Other
More information
Published date: July 2012
Venue - Dates:
International Symposium on Visual Computing, Crete, Greece, 2012-07-16 - 2012-07-18
Organisations:
Vision, Learning and Control
Identifiers
Local EPrints ID: 340202
URI: http://eprints.soton.ac.uk/id/eprint/340202
PURE UUID: 8973db55-f5cf-4f24-b0b6-0028848c2c14
Catalogue record
Date deposited: 14 Jun 2012 12:47
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
George Cushen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
