Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/30407
Title: | Estimating ambient visibility in the presence of fog: a deep convolutional neural network approach | Authors: | Outay, Fatma Taha, Bilal Chaabani, Hazar Kamoun, Faouzi Werghi, Naoufel YASAR, Ansar |
Issue Date: | 2021 | Publisher: | SPRINGER LONDON LTD | Source: | PERSONAL AND UBIQUITOUS COMPUTING, 25, p. 51-62 | Abstract: | Next-generation intelligent transportation systems are based on the acquisition of ambient data that influence traffic flow and safety. Among these, is the ambient visibility range whose estimation, in the presence of fog, is extremely useful for next-generation intelligent transportation systems. However, existing camera-based approaches are based on "engineered features" extraction methods that use computer algorithms and procedures from the image processing field. In this contribution, a novel approach to estimate visibility range under foggy weather conditions is proposed which is based on "learned features" instead. More precisely, we use AlexNet deep convolutional neural network (DCNN), trained with raw image data, for feature extraction and a support vector machine (SVM) for visibility range estimation. Our quantitative analysis showed that the proposed approach is very promising in estimating the visibility range with very good accuracy. The proposed solution can pave the way towards intelligent driveway assistance systems to enhance awareness of driving weather conditions and hence mitigate the safety risks emanating from fog-induced low visibility conditions. | Notes: | Kamoun, F (reprint author), ESPRIT Sch Engn, Tunis, Tunisia. Fatma.outay@zu.ac.ae; bilal.taha@mail.utoronto.ca; hazar.chaabani@esprit.tn; faouzi.kammoun@esprit.tn; Naoufel.Werghi@ku.ac.ae; ansar.yasar@uhasselt.be |
Other: | Kamoun, F (reprint author), ESPRIT Sch Engn, Tunis, Tunisia. Fatma.outay@zu.ac.ae; bilal.taha@mail.utoronto.ca; hazar.chaabani@esprit.tn; faouzi.kammoun@esprit.tn; Naoufel.Werghi@ku.ac.ae; ansar.yasar@uhasselt.be | Keywords: | Intelligenttransportation systems;Ubiquitoustechnologies;Atmospheric visibility;Road safety;Deepconvolutional neural networks;Ambient intelligence | Document URI: | http://hdl.handle.net/1942/30407 | ISSN: | 1617-4909 | e-ISSN: | 1617-4917 | DOI: | 10.1007/s00779-019-01334-w | ISI #: | WOS:000494801100002 | Rights: | Springer-Verlag London Ltd., part of Springer Nature 2019 | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2020 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
s00779-019-01334-w.pdf Restricted Access | Published version | 1.95 MB | Adobe PDF | View/Open Request a copy |
WEB OF SCIENCETM
Citations
11
checked on Apr 23, 2024
Page view(s)
52
checked on Sep 7, 2022
Download(s)
4
checked on Sep 7, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.