www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/28893

Title: Estimating meteorological visibility range under foggy weather conditions: A deep learning approach
Authors: Chaabani, Hazar
Werghi, Naoufel
Kamoun, Faouzi
Taha, Bilal
Outay, Fatma
Yasar, Ansar-Ul-Haque
Issue Date: 2018
Publisher: ELSEVIER SCIENCE BV
Citation: Shakshuki, E Yasar, A (Ed.). 9TH INTERNATIONAL CONFERENCE ON EMERGING UBIQUITOUS SYSTEMS AND PERVASIVE NETWORKS (EUSPN-2018) / 8TH INTERNATIONAL CONFERENCE ON CURRENT AND FUTURE TRENDS OF INFORMATION AND COMMUNICATION TECHNOLOGIES IN HEALTHCARE (ICTH-2018), ELSEVIER SCIENCE BV,p. 478-483
Abstract: Systems capable of estimating visibility distances under foggy weather conditions are extremely useful for next-generation cooperative situational awareness and collision avoidance systems. In this paper, we present a brief review of noticeable approaches for determining visibility distance under foggy weather conditions. We then propose a novel approach based on the combination of a deep learning method for feature extraction and an SVM classifier. We present a quantitative evaluation of the proposed solution and show that our approach provides better performance results compared to an earlier approach that was based on the combination of an ANN model and a set of global feature descriptors. Our experimental results show that the proposed solution presents very promising results in support for next-generation situational awareness and cooperative collision avoidance systems. Hence it can potentially contribute towards safer driving conditions in the presence of fog. (C) 2018 The Authors. Published by Elsevier Ltd.
Notes: [Chaabani, Hazar; Kamoun, Faouzi] ESPRIT Sch Engn, ZI Chotrana 2,POB 160, Tunis, Tunisia. [Werghi, Naoufel; Taha, Bilal] Khalifa Univ, POB 127788, Abu Dhabi, U Arab Emirates. [Outay, Fatma] Zayed Univ, POB 19282, Dubai, U Arab Emirates. [Yasar, Ansar-Ul-Haque] Hasselt Univ, Wetenschapspk 5 Bus 6,POB 3590, Diepenbeek, Belgium.
URI: http://hdl.handle.net/1942/28893
DOI: 10.1016/j.procs.2018.10.139
ISI #: 000471261700062
ISSN: 1877-0509
Category: C1
Type: Proceedings Paper
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version544.98 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.