DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition

The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates models that demonstrate exceptional accuracy, computational efficiency, and real-time processing capabilities. Traditionally Convolutional Ne...

Full description

Saved in:
Bibliographic Details
Published inSN computer science Vol. 5; no. 6; p. 770
Main Authors Shianios, Demetris, Kolios, Panayiotis S., Kyrkou, Christos
Format Journal Article
LanguageEnglish
Published Singapore Springer Nature Singapore 08.08.2024
Springer Nature B.V
Subjects
Artificial intelligence
Artificial neural networks
Building failures
Classification
Computer Analysis of Images and Patterns in the Deep Learning Era
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Context
Data collection
Data Structures and Information Theory
Datasets
Deep learning
Disasters
Earthquakes
Efficiency
Embedded systems
Emergency preparedness
Feature extraction
Floods
Forest & brush fires
Frames per second
Information Systems and Communication Service
Labels
Original Research
Pattern Recognition and Graphics
Performance evaluation
R&D
Real time
Research & development
Satellites
Seismic engineering
Social networks
Software Engineering/Programming and Operating Systems
Test sets
Unmanned aerial vehicles
Vision
Convolutional Neural Networks
Vision Transformers
Natural disaster recognition
UAV (Unmanned Aerial Vehicle)
Multi-label classification
Image classification
Online AccessGet full text

Cover

Abstract The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates models that demonstrate exceptional accuracy, computational efficiency, and real-time processing capabilities. Traditionally Convolutional Neural Networks (CNNs), demonstrate efficiency in local feature extraction but are limited by their potential for global context interpretation. On the other hand, Vision Transformers (ViTs) show promise for improved global context interpretation through the use of attention mechanisms, although they still remain underinvestigated in UAV-based disaster response applications. Bridging this research gap, we introduce DiRecNetV2, an improved hybrid model that utilizes convolutional and transformer layers. It merges the inductive biases of CNNs for robust feature extraction with the global context understanding of Transformers, maintaining a low computational load ideal for UAV applications. Additionally, we introduce a new, compact multi-label dataset of disasters, to set an initial benchmark for future research, exploring how models trained on single-label data perform in a multi-label test set. The study assesses lightweight CNNs and ViTs on the AIDERSv2 dataset, based on the frames per second (FPS) for efficiency and the weighted F1 scores for classification performance. DiRecNetV2 not only achieves a weighted F1 score of 0.964 on a single-label test set but also demonstrates adaptability, with a score of 0.614 on a complex multi-label test set, while functioning at 176.13 FPS on the Nvidia Orin Jetson device.
AbstractList The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates models that demonstrate exceptional accuracy, computational efficiency, and real-time processing capabilities. Traditionally Convolutional Neural Networks (CNNs), demonstrate efficiency in local feature extraction but are limited by their potential for global context interpretation. On the other hand, Vision Transformers (ViTs) show promise for improved global context interpretation through the use of attention mechanisms, although they still remain underinvestigated in UAV-based disaster response applications. Bridging this research gap, we introduce DiRecNetV2, an improved hybrid model that utilizes convolutional and transformer layers. It merges the inductive biases of CNNs for robust feature extraction with the global context understanding of Transformers, maintaining a low computational load ideal for UAV applications. Additionally, we introduce a new, compact multi-label dataset of disasters, to set an initial benchmark for future research, exploring how models trained on single-label data perform in a multi-label test set. The study assesses lightweight CNNs and ViTs on the AIDERSv2 dataset, based on the frames per second (FPS) for efficiency and the weighted F1 scores for classification performance. DiRecNetV2 not only achieves a weighted F1 score of 0.964 on a single-label test set but also demonstrates adaptability, with a score of 0.614 on a complex multi-label test set, while functioning at 176.13 FPS on the Nvidia Orin Jetson device.
Abstract The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates models that demonstrate exceptional accuracy, computational efficiency, and real-time processing capabilities. Traditionally Convolutional Neural Networks (CNNs), demonstrate efficiency in local feature extraction but are limited by their potential for global context interpretation. On the other hand, Vision Transformers (ViTs) show promise for improved global context interpretation through the use of attention mechanisms, although they still remain underinvestigated in UAV-based disaster response applications. Bridging this research gap, we introduce DiRecNetV2, an improved hybrid model that utilizes convolutional and transformer layers. It merges the inductive biases of CNNs for robust feature extraction with the global context understanding of Transformers, maintaining a low computational load ideal for UAV applications. Additionally, we introduce a new, compact multi-label dataset of disasters, to set an initial benchmark for future research, exploring how models trained on single-label data perform in a multi-label test set. The study assesses lightweight CNNs and ViTs on the AIDERSv2 dataset, based on the frames per second (FPS) for efficiency and the weighted F1 scores for classification performance. DiRecNetV2 not only achieves a weighted F1 score of 0.964 on a single-label test set but also demonstrates adaptability, with a score of 0.614 on a complex multi-label test set, while functioning at 176.13 FPS on the Nvidia Orin Jetson device.
ArticleNumber 770
Author Kyrkou, Christos
Shianios, Demetris
Kolios, Panayiotis S.
Author_xml – sequence: 1
  givenname: Demetris
  orcidid: 0009-0005-8266-0727
  surname: Shianios
  fullname: Shianios, Demetris
  organization: KIOS Research and Innovation Center of Excellence, University of Cyprus
– sequence: 2
  givenname: Panayiotis S.
  orcidid: 0000-0003-3981-993X
  surname: Kolios
  fullname: Kolios, Panayiotis S.
  organization: KIOS Research and Innovation Center of Excellence, University of Cyprus, Department of Computer Science, University of Cyprus
– sequence: 3
  givenname: Christos
  orcidid: 0000-0002-7926-7642
  surname: Kyrkou
  fullname: Kyrkou, Christos
  email: kyrkou.christos@ucy.ac.cy
  organization: KIOS Research and Innovation Center of Excellence, University of Cyprus
BookMark eNp9kE9PAyEQxYmpibX2C3jaxDMKLLDgrWnrvzSamOqVsCxbt7ZQYRuz317qmujJ00xm3u9N5p2CgfPOAnCO0SVGqLiKlMhCQkQoRDniHHZHYEg4x1BIVAz-9CdgHOMaIUQYopSzIXiYNc_WPNr2lVxnk2wZtIu1D1sb4Ny9aWdslaXtpw_vWZpnExsavclmTdSxtSFLsF-5pm28OwPHtd5EO_6pI_ByM19O7-Di6fZ-OllAgzHrIKs1wzVhmpdI5kQya02lNSqqknJuGBZE1KXIGRdUS2xKIW0laFkSXBTMsHwELnrfXfAfextbtfb74NJJlaP0JJW5OKhIrzLBxxhsrXah2erQKYzUITbVx6ZSbOo7NtUlKO-hmMRuZcOv9T_UFx0ZcTc
Cites_doi 10.1109/ASONAM49781.2020.9381294
10.1080/10095020.2023.2183145
10.1109/CVPRW53098.2021.00289
10.1016/j.comnet.2021.108001
10.1007/s00138-023-01430-1
10.3389/fenvs.2022.1095986
10.1109/EUVIP53989.2022.9922799
10.3390/rs15041085
10.3390/rs13030504
10.1109/CVPR52688.2022.01167
10.1109/ICAIS53314.2022.9743035
10.3390/app13158583
10.3390/rs12010044
10.3390/app10020602
10.1109/5.726791
10.1145/3065386
10.1109/JSTARS.2020.2969809
10.1007/978-3-031-06794-5_4
10.3390/rs13173527
10.1109/ICCV.2019.00140
10.1007/s00521-022-07717-0
10.1016/j.compeleceng.2022.108401
10.1109/ICSES52305.2021.9633803
10.1109/ICIAI.2019.8850811
10.1109/ICIBA56860.2023.10165349
10.1109/INISTA49547.2020.9194655
10.1007/978-981-16-5987-4_49
10.1016/j.jhydrol.2023.129236
10.1109/JPROC.2022.3223186
10.3390/s19071486
10.3390/rs14112577
10.1016/S0140-6736(23)00326-4
10.1109/ACCESS.2021.3090981
10.1007/978-3-030-01264-9_8
10.1109/HPEC43674.2020.9286248
10.1109/CCDC49329.2020.9163816
10.3390/rs12020260
10.3390/rs13214213
10.1109/ICESIT53460.2021.9696599
10.1088/1742-5468/ac9830
10.1109/CVPR.2018.00474
10.1007/978-3-031-44240-7_24
10.1029/2021JB023657
10.1109/CVPR.2019.00293
10.1109/CVPRW.2019.00077
10.31449/inf.v46i7.4280
10.1016/j.envsoft.2021.105285
10.3390/su13147547
10.1109/TKDE.2013.39
10.20473/jisebi.8.1.31-41
10.1109/ACCESS.2019.2958983
10.1049/ipr2.12046
ContentType Journal Article
Copyright The Author(s) 2024
The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2024
– notice: The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
JQ2
DOI 10.1007/s42979-024-03066-y
DatabaseName SpringerOpen
CrossRef
ProQuest Computer Science Collection
DatabaseTitle CrossRef
ProQuest Computer Science Collection
DatabaseTitleList
CrossRef
ProQuest Computer Science Collection
Database_xml – sequence: 1
  dbid: C6C
  name: SpringerOpen
  url: http://www.springeropen.com/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2661-8907
ExternalDocumentID 10_1007_s42979_024_03066_y
GrantInformation_xml – fundername: HORIZON EUROPE Widening participation and spreading excellence
  grantid: 739551
  funderid: http://dx.doi.org/10.13039/100018706
– fundername: University of Cyprus
GroupedDBID 0R~
406
AACDK
AAHNG
AAJBT
AASML
AATNV
AAUYE
ABAKF
ABECU
ABFGW
ABHQN
ABJNI
ABMQK
ABTEG
ABTKH
ABWNU
ACAOD
ACDTI
ACHSB
ACIPQ
ACOKC
ACWMK
ACZOJ
ADKNI
ADTPH
ADYFF
AEFQL
AEMSY
AESKC
AESTI
AEVTX
AFBBN
AFQWF
AGMZJ
AGQEE
AGRTI
AIGIU
AILAN
AIMYW
AJZVZ
AKQUC
ALMA_UNASSIGNED_HOLDINGS
AMXSW
AMYLF
BAPOH
C6C
DPUIP
EBLON
EBS
FIGPU
FNLPD
GGCAI
GNWQR
IKXTQ
IWAJR
JZLTJ
LLZTM
NPVJJ
NQJWS
OK1
PT4
ROL
RSV
SNE
SOJ
SRMVM
SSLCW
UOJIU
UTJUX
ZMTXR
AAYXX
CITATION
SJYHP
JQ2
ID FETCH-LOGICAL-c115y-5fa51f25a6b093295eecdaa07db466c51828fb835684a91cb89ed84bb21775c53
IEDL.DBID C6C
ISSN 2661-8907
2662-995X
IngestDate Thu Oct 17 05:00:53 EDT 2024
Thu Sep 12 20:38:21 EDT 2024
Fri Aug 09 01:10:28 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords Convolutional Neural Networks
Vision Transformers
Natural disaster recognition
UAV (Unmanned Aerial Vehicle)
Multi-label classification
Image classification
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c115y-5fa51f25a6b093295eecdaa07db466c51828fb835684a91cb89ed84bb21775c53
ORCID 0000-0002-7926-7642
0009-0005-8266-0727
0000-0003-3981-993X
OpenAccessLink https://doi.org/10.1007/s42979-024-03066-y
PQID 3090749385
PQPubID 6623307
ParticipantIDs proquest_journals_3090749385
crossref_primary_10_1007_s42979_024_03066_y
springer_journals_10_1007_s42979_024_03066_y
PublicationCentury 2000
PublicationDate 8-8-2024
PublicationDateYYYYMMDD 2024-08-08
PublicationDate_xml – month: 08
  year: 2024
  text: 8-8-2024
  day: 08
PublicationDecade 2020
PublicationPlace Singapore
PublicationPlace_xml – name: Singapore
– name: Kolkata
PublicationTitle SN computer science
PublicationTitleAbbrev SN COMPUT. SCI
PublicationYear 2024
Publisher Springer Nature Singapore
Springer Nature B.V
Publisher_xml – name: Springer Nature Singapore
– name: Springer Nature B.V
References LeCunYBottouLBengioYHaffnerPGradient-based learning applied to document recognitionProc IEEE199886112278232410.1109/5.726791
YuanJDingXLiuFCaiXDisaster cassification net: a disaster classification algorithm on remote sensing imageryFront Environ Sci202310269010.3389/fenvs.2022.1095986
Mehta S, Rastegari M. Separable self-attention for mobile vision transformers. arxiv; 2022. arXiv preprint arXiv:2206.02680.
Alam F, Alam T, Hasan M, Hasnat A, Imran M, Ofli F, et al. Medic: A multi-task learning dataset for disaster image classification; 2021. arXiv preprint arXiv:2108.12828
ElangovanASasikalaSA multi-label classification of disaster-related tweets with enhanced word embedding ensemble convolutional neural network modelInformatica.202246713114410.31449/inf.v46i7.4280
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on computer vision and pattern recognition; 2018. p. 4510–4520.
AnggraeniSRRanggiantoNAGhozaliIFatichahCPurwitasariDDeep learning approaches for multi-label incidents classification from twitter textual informationJ Inform Syst Eng Bus Intell.202281314110.20473/jisebi.8.1.31-41
ChenJShiXGuLWuGSuTWangHMKimJSZhangLXiongLImpacts of climate warming on global floods and their implication to current flood defense standardsJ Hydrol202361812923610.1016/j.jhydrol.2023.129236
Gadhavi VB, Degadwala S, Vyas D. Transfer learning approach for recognizing natural disasters video. In: 2022 Second International Conference on artificial intelligence and smart energy (ICAIS). IEEE; 2022. p. 793–798.
GebrehiwotAHashemi-BeniLThompsonGKordjamshidiPLanganTEDeep convolutional neural network for flood extent mapping using unmanned aerial vehicles dataSensors2019197148610.3390/s19071486
MaHLiuYRenYWangDYuLYuJImproved cnn classification method for groups of buildings damaged by earthquake, based on high resolution remote sensing imagesRemote Sens202012226010.3390/rs12020260
Shianios D, Kyrkou C, Kolios PS. A benchmark and investigation of deep-learning-based techniques for detecting natural disasters in aerial images. In: International Conference on computer analysis of images and patterns. Springer; 2023. p. 244–254.
Yang NTS, Tham ML, Chua SY, Lee YL, Owada Y, Poomrittigul S. Efficient device-edge inference for disaster classification. In: 2022 Thirteenth International Conference on ubiquitous and future networks (ICUFN). IEEE; 2022. p. 314–319.
MunawarHSUllahFQayyumSKhanSIMojtahediMUavs in disaster management: application of integrated aerial imagery and convolutional neural network for flood detectionSustainability20211314754710.3390/su13147547
Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on machine learning. PMLR; 2019. p. 6105–6114.
Alam F, Ofli F, Imran M, Alam T, Qazi U. Deep learning benchmarks and datasets for social media image classification for disaster response. In: 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). IEEE; 2020. p. 151–158.
SainiNChattopadhyayCDasDE2alertnet: an explainable, efficient, and lightweight model for emergency alert from aerial imageryRemote Sens Appl Soc Environ202329100896
XieSHouCYuHZhangZLuoXZhuNMulti-label disaster text classification via supervised contrastive learning for social media dataComput Electr Eng202210410840110.1016/j.compeleceng.2022.108401
Roy R, Kulkarni SS, Soni V, Chittora A, et al. Transformer-based flood scene segmentation for developing countries; 2022. arXiv preprint arXiv:2210.04218.
RahnemoonfarMChowdhuryTSarkarAVarshneyDYariMMurphyRRFloodnet: a high resolution aerial imagery dataset for post flood scene understandingIEEE Access20219896448965410.1109/ACCESS.2021.3090981
YangWZhangXLuoPTransferability of convolutional neural network models for identifying damaged buildings due to earthquakeRemote Sens202113350410.3390/rs13030504
Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S. A convnet for the 2020s. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition; 2022. p. 11976–11986.
PallyRSamadiSApplication of image processing and convolutional neural networks for flood image classification and semantic segmentationEnviron Model Softw202214810528510.1016/j.envsoft.2021.105285
Hatamizadeh A, Yin H, Heinrich G, Kautz J, Molchanov P. Global context vision transformers. In: International Conference on machine learning. PMLR; 2023. p. 12633–12646.
Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV. Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition; 2019. p. 2820–2828.
Singh S, Ghosh S, Maity A, Bag BC, Koley C, Maity HK. Disasternet: a multi-label disaster aftermath image classification model. In: ICT Systems and Sustainability: Proceedings of ICT4SD 2021, vol. 1. Springer; 2022. p. 481–490.
Jadon A, Omama M, Varshney A, Ansari MS, Sharma R. Firenet: a specialized lightweight fire & smoke detection model for real-time iot applications; 2019. arXiv preprint arXiv:1905.11922.
ZhangMLZhouZHA review on multi-label learning algorithmsIEEE Trans Knowl Data Eng20132681819183710.1109/TKDE.2013.39
Doshi J, Basu S, Pang G. From satellite imagery to disaster insights; 2018. arXiv preprint arXiv:1812.07033.
Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, et al. Searching for mobilenetv3. In: Proceedings of the IEEE/CVF International Conference on computer vision; 2019. p. 1314–1324.
Hossain FA, Zhang Y, Yuan C, Su CY. Wildfire flame and smoke detection using static image features and artificial neural network. In: 2019 1st International Conference on industrial artificial intelligence (iai). IEEE; 2019. p. 1–6.
Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer; 2021. arXiv preprint arXiv:2110.02178.
KyrkouCTheocharidesTEmergencynet: efficient aerial image classification for drone-based emergency monitoring using Atrous convolutional feature fusionIEEE J Sel Top Appl Earth Observ Remote Sens2020131687169910.1109/JSTARS.2020.2969809
FrizziSBouchouichaMGinouxJMMoreauESayadiMConvolutional neural network for smoke and fire semantic segmentationIET Image Proc202115363464710.1049/ipr2.12046
Xiong C, Yu A, Rong L, Huang J, Wang B, Liu H. Fire detection system based on unmanned aerial vehicle. In: 2021 IEEE International Conference on emergency science and information technology (ICESIT). IEEE; 2021. p. 302–306
Steiner A, Kolesnikov A, Zhai X, Wightman R, Uszkoreit J, Beyer L. How to train your vit? data, augmentation, and regularization in vision transformers; 2021. arXiv preprint arXiv:2106.10270.
UwishemaOAddressing the effects of the earthquakes on Türkiye’s health-care systemThe Lancet20234011037872710.1016/S0140-6736(23)00326-4
Kyrkou C, Theocharides T. Deep-learning-based aerial image classification for emergency response applications using unmanned aerial vehicles. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); 2019. p. 517–525. https://doi.org/10.1109/CVPRW.2019.00077
Yuan J, Ma X, Zhang Z, Xu Q, Han G, Li S, Gong W, Liu F, Cai X. EFFC-net: lightweight fully convolutional neural networks in remote sensing disaster images. Geo-spatial Inform Sci. 2023;1–12. https://doi.org/10.1080/10095020.2023.2183145.
Agrawal T, Meleet M, et al. Classification of natural disaster using satellite & drone images with cnn using transfer learning. In: 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES). IEEE; 2021. p. 1–5.
Munawar HS, Hammad A, Ullah F, Ali TH. After the flood: a novel application of image processing and machine learning for post-flood disaster management. In: Proceedings of the 2nd International Conference on sustainable development in civil engineering (ICSDC 2019), Jamshoro, Pakistan; 2019. p. 5–7.
SaadOMChenYSavvaidisAFomelSChenYReal-time earthquake detection and magnitude estimation using vision transformerJ Geophys Res Solid Earth20221275e2021JB02365710.1029/2021JB023657
Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$< 0.5$$\end{document} mb model size; 2016. arXiv preprint arXiv:1602.07360
KrizhevskyASutskeverIHintonGEImagenet classification with deep convolutional neural networksCommun ACM2017606849010.1145/3065386
Sarp S, Kuzlu M, Cetin M, Sazara C, Guler O. Detecting floodwater on roadways from image data using mask-r-cnn. In: 2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA). IEEE; 2020. p. 1–6.
JiMLiuLZhangRF BuchroithnerMDiscrimination of earthquake-induced building destruction from space using a pretrained cnn modelAppl Sci202010260210.3390/app10020602
Mao J, Harris K, Chang NR, Pennell C, Ren Y. Train and deploy an image classifier for disaster response. In: 2020 IEEE High Performance Extreme Computing Conference (HPEC). IEEE; 2020. p. 1–5.
YuanJMaXHanGLiSGongWResearch on lightweight disaster classification based on high-resolution remote sensing imagesRemote Sens20221411257710.3390/rs14112577
MaHLiuYRenYYuJDetection of collapsed buildings in post-earthquake remote sensing images based on the improved yolov3Remote Sens20191214410.3390/rs12010044
Munsif M, Afridi H, Ullah M, Khan SD, Cheikh FA, Sajjad M. A lightweight convolution neural network for automatic disasters recognition. In: 2022 10th European Workshop on Visual Information Processing (EUVIP). IEEE; 2022. p. 1–6.
Ma N, Zhang X, Zheng HT, Sun J. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European
P Bhadra (3066_CR6) 2023; 34
3066_CR53
3066_CR52
GY Lee (3066_CR33) 2023; 20
SR Anggraeni (3066_CR5) 2022; 8
ML Zhang (3066_CR70) 2013; 26
3066_CR2
3066_CR1
3066_CR4
3066_CR19
3066_CR3
3066_CR7
3066_CR57
3066_CR12
3066_CR56
3066_CR11
3066_CR10
OM Saad (3066_CR50) 2022; 127
S Frizzi (3066_CR14) 2021; 15
3066_CR15
3066_CR59
H Ma (3066_CR36) 2020; 12
3066_CR58
L Shi (3066_CR55) 2021; 13
3066_CR42
3066_CR41
3066_CR40
J Chen (3066_CR9) 2023; 618
A Elangovan (3066_CR13) 2022; 46
A Gebrehiwot (3066_CR17) 2019; 19
A Shamsoshoara (3066_CR54) 2021; 193
3066_CR46
3066_CR44
3066_CR49
N Saini (3066_CR51) 2023; 29
J Yuan (3066_CR67) 2023; 10
A Krizhevsky (3066_CR28) 2017; 60
3066_CR30
M Ji (3066_CR25) 2020; 10
C Kyrkou (3066_CR31) 2020; 13
C Kyrkou (3066_CR29) 2023; 111
F Chen (3066_CR8) 2019; 7
J Yuan (3066_CR68) 2022; 14
X Ge (3066_CR16) 2023; 15
3066_CR35
3066_CR34
O Uwishema (3066_CR61) 2023; 401
3066_CR39
3066_CR38
3066_CR60
3066_CR20
3066_CR64
3066_CR62
R Ghali (3066_CR18) 2021; 13
HS Munawar (3066_CR45) 2021; 13
R Pally (3066_CR47) 2022; 148
H Ma (3066_CR37) 2019; 12
Y LeCun (3066_CR32) 1998; 86
P Mo (3066_CR43) 2023; 13
S Xie (3066_CR63) 2022; 104
3066_CR24
W Yang (3066_CR66) 2021; 13
3066_CR23
3066_CR22
3066_CR21
3066_CR65
M Rahnemoonfar (3066_CR48) 2021; 9
3066_CR27
3066_CR26
3066_CR69
References_xml – ident: 3066_CR4
  doi: 10.1109/ASONAM49781.2020.9381294
– ident: 3066_CR69
  doi: 10.1080/10095020.2023.2183145
– ident: 3066_CR23
  doi: 10.1109/CVPRW53098.2021.00289
– volume: 193
  start-page: 108001
  year: 2021
  ident: 3066_CR54
  publication-title: Comput Netw
  doi: 10.1016/j.comnet.2021.108001
  contributor:
    fullname: A Shamsoshoara
– volume: 34
  start-page: 76
  issue: 5
  year: 2023
  ident: 3066_CR6
  publication-title: Mach Vis Appl
  doi: 10.1007/s00138-023-01430-1
  contributor:
    fullname: P Bhadra
– volume: 29
  start-page: 100896
  year: 2023
  ident: 3066_CR51
  publication-title: Remote Sens Appl Soc Environ
  contributor:
    fullname: N Saini
– ident: 3066_CR22
– volume: 10
  start-page: 2690
  year: 2023
  ident: 3066_CR67
  publication-title: Front Environ Sci
  doi: 10.3389/fenvs.2022.1095986
  contributor:
    fullname: J Yuan
– ident: 3066_CR46
  doi: 10.1109/EUVIP53989.2022.9922799
– ident: 3066_CR41
– volume: 15
  start-page: 1085
  issue: 4
  year: 2023
  ident: 3066_CR16
  publication-title: Remote Sens
  doi: 10.3390/rs15041085
  contributor:
    fullname: X Ge
– ident: 3066_CR60
– volume: 13
  start-page: 504
  issue: 3
  year: 2021
  ident: 3066_CR66
  publication-title: Remote Sens
  doi: 10.3390/rs13030504
  contributor:
    fullname: W Yang
– ident: 3066_CR35
  doi: 10.1109/CVPR52688.2022.01167
– ident: 3066_CR15
  doi: 10.1109/ICAIS53314.2022.9743035
– volume: 13
  start-page: 8583
  issue: 15
  year: 2023
  ident: 3066_CR43
  publication-title: Appl Sci
  doi: 10.3390/app13158583
  contributor:
    fullname: P Mo
– ident: 3066_CR19
– volume: 12
  start-page: 44
  issue: 1
  year: 2019
  ident: 3066_CR37
  publication-title: Remote Sens
  doi: 10.3390/rs12010044
  contributor:
    fullname: H Ma
– ident: 3066_CR2
– volume: 10
  start-page: 602
  issue: 2
  year: 2020
  ident: 3066_CR25
  publication-title: Appl Sci
  doi: 10.3390/app10020602
  contributor:
    fullname: M Ji
– volume: 86
  start-page: 2278
  issue: 11
  year: 1998
  ident: 3066_CR32
  publication-title: Proc IEEE
  doi: 10.1109/5.726791
  contributor:
    fullname: Y LeCun
– volume: 60
  start-page: 84
  issue: 6
  year: 2017
  ident: 3066_CR28
  publication-title: Commun ACM
  doi: 10.1145/3065386
  contributor:
    fullname: A Krizhevsky
– volume: 13
  start-page: 1687
  year: 2020
  ident: 3066_CR31
  publication-title: IEEE J Sel Top Appl Earth Observ Remote Sens
  doi: 10.1109/JSTARS.2020.2969809
  contributor:
    fullname: C Kyrkou
– ident: 3066_CR27
  doi: 10.1007/978-3-031-06794-5_4
– ident: 3066_CR42
– volume: 13
  start-page: 3527
  issue: 17
  year: 2021
  ident: 3066_CR18
  publication-title: Remote Sens
  doi: 10.3390/rs13173527
  contributor:
    fullname: R Ghali
– ident: 3066_CR49
– ident: 3066_CR21
  doi: 10.1109/ICCV.2019.00140
– ident: 3066_CR3
  doi: 10.1007/s00521-022-07717-0
– volume: 104
  start-page: 108401
  year: 2022
  ident: 3066_CR63
  publication-title: Comput Electr Eng
  doi: 10.1016/j.compeleceng.2022.108401
  contributor:
    fullname: S Xie
– ident: 3066_CR1
  doi: 10.1109/ICSES52305.2021.9633803
– ident: 3066_CR10
– ident: 3066_CR20
  doi: 10.1109/ICIAI.2019.8850811
– ident: 3066_CR7
  doi: 10.1109/ICIBA56860.2023.10165349
– ident: 3066_CR53
  doi: 10.1109/INISTA49547.2020.9194655
– ident: 3066_CR57
  doi: 10.1007/978-981-16-5987-4_49
– volume: 618
  start-page: 129236
  year: 2023
  ident: 3066_CR9
  publication-title: J Hydrol
  doi: 10.1016/j.jhydrol.2023.129236
  contributor:
    fullname: J Chen
– volume: 111
  start-page: 19
  issue: 1
  year: 2023
  ident: 3066_CR29
  publication-title: Proc IEEE
  doi: 10.1109/JPROC.2022.3223186
  contributor:
    fullname: C Kyrkou
– volume: 19
  start-page: 1486
  issue: 7
  year: 2019
  ident: 3066_CR17
  publication-title: Sensors
  doi: 10.3390/s19071486
  contributor:
    fullname: A Gebrehiwot
– ident: 3066_CR24
– ident: 3066_CR62
– volume: 14
  start-page: 2577
  issue: 11
  year: 2022
  ident: 3066_CR68
  publication-title: Remote Sens
  doi: 10.3390/rs14112577
  contributor:
    fullname: J Yuan
– volume: 401
  start-page: 727
  issue: 10378
  year: 2023
  ident: 3066_CR61
  publication-title: The Lancet
  doi: 10.1016/S0140-6736(23)00326-4
  contributor:
    fullname: O Uwishema
– volume: 9
  start-page: 89644
  year: 2021
  ident: 3066_CR48
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3090981
  contributor:
    fullname: M Rahnemoonfar
– ident: 3066_CR38
  doi: 10.1007/978-3-030-01264-9_8
– ident: 3066_CR34
  doi: 10.1109/CVPR52688.2022.01167
– ident: 3066_CR39
  doi: 10.1109/HPEC43674.2020.9286248
– ident: 3066_CR26
  doi: 10.1109/CCDC49329.2020.9163816
– volume: 12
  start-page: 260
  issue: 2
  year: 2020
  ident: 3066_CR36
  publication-title: Remote Sens
  doi: 10.3390/rs12020260
  contributor:
    fullname: H Ma
– volume: 13
  start-page: 4213
  issue: 21
  year: 2021
  ident: 3066_CR55
  publication-title: Remote Sens
  doi: 10.3390/rs13214213
  contributor:
    fullname: L Shi
– ident: 3066_CR64
  doi: 10.1109/ICESIT53460.2021.9696599
– ident: 3066_CR11
– ident: 3066_CR12
  doi: 10.1088/1742-5468/ac9830
– ident: 3066_CR52
  doi: 10.1109/CVPR.2018.00474
– ident: 3066_CR56
  doi: 10.1007/978-3-031-44240-7_24
– ident: 3066_CR40
– volume: 127
  start-page: e2021JB023657
  issue: 5
  year: 2022
  ident: 3066_CR50
  publication-title: J Geophys Res Solid Earth
  doi: 10.1029/2021JB023657
  contributor:
    fullname: OM Saad
– ident: 3066_CR65
– ident: 3066_CR59
  doi: 10.1109/CVPR.2019.00293
– volume: 20
  start-page: 1
  year: 2023
  ident: 3066_CR33
  publication-title: IEEE Geosci Remote Sens Lett.
  contributor:
    fullname: GY Lee
– ident: 3066_CR30
  doi: 10.1109/CVPRW.2019.00077
– volume: 46
  start-page: 131
  issue: 7
  year: 2022
  ident: 3066_CR13
  publication-title: Informatica.
  doi: 10.31449/inf.v46i7.4280
  contributor:
    fullname: A Elangovan
– volume: 148
  start-page: 105285
  year: 2022
  ident: 3066_CR47
  publication-title: Environ Model Softw
  doi: 10.1016/j.envsoft.2021.105285
  contributor:
    fullname: R Pally
– volume: 13
  start-page: 7547
  issue: 14
  year: 2021
  ident: 3066_CR45
  publication-title: Sustainability
  doi: 10.3390/su13147547
  contributor:
    fullname: HS Munawar
– ident: 3066_CR44
– volume: 26
  start-page: 1819
  issue: 8
  year: 2013
  ident: 3066_CR70
  publication-title: IEEE Trans Knowl Data Eng
  doi: 10.1109/TKDE.2013.39
  contributor:
    fullname: ML Zhang
– volume: 8
  start-page: 31
  issue: 1
  year: 2022
  ident: 3066_CR5
  publication-title: J Inform Syst Eng Bus Intell.
  doi: 10.20473/jisebi.8.1.31-41
  contributor:
    fullname: SR Anggraeni
– volume: 7
  start-page: 181396
  year: 2019
  ident: 3066_CR8
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2958983
  contributor:
    fullname: F Chen
– ident: 3066_CR58
– volume: 15
  start-page: 634
  issue: 3
  year: 2021
  ident: 3066_CR14
  publication-title: IET Image Proc
  doi: 10.1049/ipr2.12046
  contributor:
    fullname: S Frizzi
SSID ssj0002504465
Score 2.3178356
Snippet The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates...
Abstract The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment,...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Publisher
StartPage 770
SubjectTerms Artificial intelligence
Artificial neural networks
Building failures
Classification
Computer Analysis of Images and Patterns in the Deep Learning Era
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Context
Data collection
Data Structures and Information Theory
Datasets
Deep learning
Disasters
Earthquakes
Efficiency
Embedded systems
Emergency preparedness
Feature extraction
Floods
Forest & brush fires
Frames per second
Information Systems and Communication Service
Labels
Original Research
Pattern Recognition and Graphics
Performance evaluation
R&D
Real time
Research & development
Satellites
Seismic engineering
Social networks
Software Engineering/Programming and Operating Systems
Test sets
Unmanned aerial vehicles
Vision
Title DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition
URI https://link.springer.com/article/10.1007/s42979-024-03066-y
https://www.proquest.com/docview/3090749385
Volume 5
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED1Bu7DwjSiUygMbWCSu7cRs_VRViQyoRd0iO3ZElxS1Zei_x3YTKioYWOPEw_M5987newdwn5ksEpHKcRBojmkYGBxnUYBjSaQMZaalP8x5SfhoSsczNitlclwtzF7-_mll_5eRwNaTYMduOd4cQt35YNemocd73-cpToqLclbWxfz-6U_fsyOUezlQ71qGp3BcckLU2S7iGRyY4hxOqn4LqNx-FzDuzy3LS8z6jTyjDppUnNMs8aB496l8lGyvdSP7HHW8daH-fCWdHAJ6rS4LLYpLmA4Hk94Il70QcGY52wazXLIwJ0xyFVjKJZgxFkcZRFpRzjNmw4Q4V5ZO8ZhKEWYqFkbHVCkbckQsY-0rqBWLwlwDIkyHubZhTCQFJUQLklNXykEcW6C5bsBDhVL6sZW8SL_FjT2mqcU09ZimmwY0KyDT0vxXaTtwMbdox6wBjxW4u-G_Z7v53-u3cET8-jqV7SbU1stPc2dJwlq1oN4ZdrtJy1vJF7g3tTA
link.rule.ids 315,783,787,27938,27939,41134,42203,51590
linkProvider Springer Nature
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgDLDwjSgU8MAGFo5rOzFb1Q-V0mZALeoW2bEjuqSoLUP_PbabtKKCgdVxMjyfc-98d88A3KcmDUWoMoSx5ogG2KAoDTGKJJEykKmW_jBnEPPuiPbGbFzI5LhemK38_dPc_i9DgawnQY7dcrTcBXuUEOwTs7y5Pk9xUlyUs6Iv5vdXf_qeDaHcyoF619I5BocFJ4SN1SKegB2Tn4Kj8r4FWGy_M9BrTSzLi83inTzDBhyWnNPMUDv_8Kl8GK_KuqEdhw1vXbA1mUsnhwDfymKhaX4ORp32sNlFxV0IKLWcbYlYJlmQESa5wpZyCWaMxVHiUCvKecpsmBBlytIpHlEpglRFwuiIKmVDjpClrH4BKvk0N5cAEqaDTNswJpTCIqkFyahr5SCOLdBMV8FDiVLyuZK8SNbixh7TxGKaeEyTZRXUSiCTwvznSR27mFvUI1YFjyW4m8d_f-3qf9PvwH53OOgn_Zf49RocEL_WTnG7BiqL2Ze5sYRhoW69pXwDjlq2lQ
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwGG0UE-PF30YUtQdv2rB1bbd6IyBBVGIMGG5Lt7aRyyAwD_z3tt0GavTgdb8Or-2-9_X73isA16lKQx4mGnmeZIj4nkJRGnooElgIX6RSuM2c5wHrjUh_TMdfVPyu270qSRaaBuvSlOXNmdTNlfDN_EVDjkx8QZbzMrTcBFvE9wPrnt9m7dUuizXoIoyWapnfX_0ekdY080dl1AWc7j7YLZkibBVDewA2VHYI9qpTGGC5KI9AvzMx3G-g8jd8B1twWDFRNUf32bsr8MNB0ewNzXXYcnMOdiYLYU0S4GvVQjTNjsGoez9s91B5QgJKDZNbIqoF9TWmgiWeIWKcKmXQFV4oE8JYSk3yEOnEkCwWEcH9NIm4khFJEpOIhDSlwQmoZdNMnQKIqfS1NMlNKDjBWHKsiRV4YMshiJZ1cFOhFM8KI4x4ZXnsMI0NprHDNF7WQaMCMi4XxSIOPJuJ8yCidXBbgbu-_ffXzv73-BXYful046eHweM52MFuqK0NdwPU8vmHujAsIk8u3UT5BPOYvuU
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DiRecNetV2%3A+A+Transformer-Enhanced+Network+for+Aerial+Disaster+Recognition&rft.jtitle=SN+computer+science&rft.au=Shianios%2C+Demetris&rft.au=Kolios%2C+Panayiotis+S.&rft.au=Kyrkou%2C+Christos&rft.date=2024-08-08&rft.issn=2661-8907&rft.eissn=2661-8907&rft.volume=5&rft.issue=6&rft_id=info:doi/10.1007%2Fs42979-024-03066-y&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s42979_024_03066_y
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2661-8907&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2661-8907&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2661-8907&client=summon