Comparison between Optical and Computer Vision Estimates of Visibility in Daytime Fog
Abstract
The estimation of conspicuity is of importance for engineers who aim at making traffic signs
conspicuous enough to attract attention regardless of drivers' preoccupation. Unfortunately,
conspicuity remains a poorly understood attribute due to the relatively limited - although growing -
knowledge about the human visual processing system. Our goal is to develop a system which
estimates the conspicuity of traffic signs based on the processing of images acquired with a
camera onboard a vehicle, in order to be able to make a diagnosis regarding their conspicuity.
Aside from specific feature known to be of importance for road signs, there is currently no
complete model for conspicuity. However, a computational model for attentional conspicuity was
proposed in computer science. This model is based on vision science knowledge of the low levels
of the human visual processing system, and we show that it is not suitable for sign detection
tasks. We thus propose a new paradigm for conspicuity estimation in search tasks based on
statistical learning of the features of the searched object.
Reference
@inproceedings{jpt-cie15,
author = {Tarel, J.-P. and Br\'emond, R. and Dumont, E. and Joulan, K.},
title = {Comparison between Optical and Computer Vision Estimates of Visibility in Daytime Fog},
booktitle = {Proceedings of the International Conference of the 28th session of the CIE (CIE'15)},
date = {June 28-July 4},
address = {Manchester, UK},
year = {2015},
pages = {610-617},
volume = {1},
note = {http://perso.lcpc.fr/tarel.jean-philippe/publis/cie15.html}
}
Pdf file (1040 Kb)
(c) CIE