TY - JOUR
T1 - PSO and genetic modeling of deep features for road passibility analysis during floods
AU - Said, Naina
AU - Nayab, Aysha
AU - Ahmad, Kashif
AU - Ullah, Muhib
AU - Gohar, Touqir
AU - Al-Fuqaha, Ala
N1 - Publisher Copyright:
© 2020, Society for Imaging Science and Technology.
PY - 2020/1/26
Y1 - 2020/1/26
N2 - In recent years, social media outlets have been widely exploited for disaster analysis and retrieving relevant information. Social media information can help in several ways, such as finding the mostly affected areas and information on casualties and scope of the damage etc. In this paper, we tackle a specific facet of social media in natural disasters, namely the identification of passable routs in a flooded region. In detail, we propose several solutions for two relevant tasks, namely (i) identification of flooded and non-flooded images in a collection of images retrieved from social media, and (ii) identification of passable roads in a flooded region. To this aim, we mainly rely on existing deep models pre-trained on ImageNet and Places dataset, where the models pre-trained on ImageNet extract object specific and the ones pre-trained on places dataset extract scene-level features. In order to properly utilize the object and scene-level features, we rely on different fusion methods including Particle Swarm Optimization (PSO) and Genetic Modeling of the deep features in a late fusion manner. The evaluation of the proposed methods are carried out on the large-scale datasets provided for MediaEval-2018 benchmarking competition on Multimedia and Satellites. The results demonstrate significant improvement in the performance over the baselines.
AB - In recent years, social media outlets have been widely exploited for disaster analysis and retrieving relevant information. Social media information can help in several ways, such as finding the mostly affected areas and information on casualties and scope of the damage etc. In this paper, we tackle a specific facet of social media in natural disasters, namely the identification of passable routs in a flooded region. In detail, we propose several solutions for two relevant tasks, namely (i) identification of flooded and non-flooded images in a collection of images retrieved from social media, and (ii) identification of passable roads in a flooded region. To this aim, we mainly rely on existing deep models pre-trained on ImageNet and Places dataset, where the models pre-trained on ImageNet extract object specific and the ones pre-trained on places dataset extract scene-level features. In order to properly utilize the object and scene-level features, we rely on different fusion methods including Particle Swarm Optimization (PSO) and Genetic Modeling of the deep features in a late fusion manner. The evaluation of the proposed methods are carried out on the large-scale datasets provided for MediaEval-2018 benchmarking competition on Multimedia and Satellites. The results demonstrate significant improvement in the performance over the baselines.
UR - http://www.scopus.com/inward/record.url?scp=85095110016&partnerID=8YFLogxK
U2 - 10.2352/ISSN.2470-1173.2020.8.IMAWM-270
DO - 10.2352/ISSN.2470-1173.2020.8.IMAWM-270
M3 - Conference article
AN - SCOPUS:85095110016
SN - 2470-1173
VL - 2020
JO - IS and T International Symposium on Electronic Imaging Science and Technology
JF - IS and T International Symposium on Electronic Imaging Science and Technology
IS - 8
T2 - 2020 Imaging and Multimedia Analytics in a Web and Mobile World Conference, IMAWM 2020
Y2 - 26 January 2020 through 30 January 2020
ER -