Proceedings of the 5th International Conference on Information Engineering for Mechanics and Materials

A Novel Visual Attention Framework using Unsupervised Feature Learning for Road Scene Understanding

Authors
Yanfen Mao, Qingyu Meng, Ming Chen
Corresponding Author
Yanfen Mao
Available Online July 2015.
DOI
10.2991/icimm-15.2015.215How to use a DOI?
Keywords
Visual attention; Road Scene Understanding; Deep Learning; Bayesian Framework
Abstract

Road scene understanding plays a key role in autonomous driving for intelligent vehicle. For the problem making semantic labeling with equivalent priority results in confliction between huge amounts of data and limited computation resource, this paper proposes a novel framework that efficiently fuses selective visual attention mechanism into the solution to scene perception task. Incorporating top-down and bottom-up two kinds of attention effect into an integrated Bayesian framework, total saliency map can be obtained taking use of implicit feature representation by unsupervised feature learning from natural images.

Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 5th International Conference on Information Engineering for Mechanics and Materials
Series
Advances in Engineering Research
Publication Date
July 2015
ISBN
978-94-62520-88-2
ISSN
2352-5401
DOI
10.2991/icimm-15.2015.215How to use a DOI?
Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Yanfen Mao
AU  - Qingyu Meng
AU  - Ming Chen
PY  - 2015/07
DA  - 2015/07
TI  - A Novel Visual Attention Framework using Unsupervised Feature Learning for Road Scene Understanding
BT  - Proceedings of the 5th International Conference on Information Engineering for Mechanics and Materials
PB  - Atlantis Press
SP  - 1201
EP  - 1204
SN  - 2352-5401
UR  - https://doi.org/10.2991/icimm-15.2015.215
DO  - 10.2991/icimm-15.2015.215
ID  - Mao2015/07
ER  -