Using Convolution Neural Network for flooding detection in CCTV images in urban areas

被引：0

作者：

Su, Yaun-Fong ^{[1
]}

Chien, Ta-Chun ^{[2
]}

Lin, Yi-Ting ^{[2
]}

机构：

[1] National Taiwan Ocean University, Department of Harbor and River Engineering, Taiwan

[2] National Taiwan Ocean University, Geographic Information System Research Center, Taiwan

来源：

Journal of Taiwan Agricultural Engineering | 2024年 / 70卷 / 02期

关键词：

Convolution neural network (CNN) has been proved to be very useful in many research fields. However, there are still many possible applications in disaster monitoring and emergency operations. In Taiwan, CCTV also plays an important role for providing real-time situation in the field. Due to its importance, there are more than 20,000 CCTV working in Taiwan to provide real-time information. During flooding events, however, operation agency still needs manpower to check every CCTV footage and it is time and labor consuming. To address this issue, we collected 52,941 CCTV images during typhoon and storm events in 2023. From these images, we selected 3,540 images within urban area during daytime as the training dataset of the CNN model for flooding detection in CCTV image in urban areas. The developed CNN model has 2.4 million parameters to train and the training time costs about 1 hour. The trained CNN model shows a good performance with overall accuracy reaching 98 % while the accuracy for flooding detection for training and testing datasets reaches 85 %. This model may be further improved by considering two-stages CNN model and hopefully may make flooding detection using CCTV in a more efficient way. © 2024, Taiwan Agricultural Engineers Society. All rights reserved;

D O I：

10.29974/JTAE.202406_70(2).0003

中图分类号：

学科分类号：

摘要：

引用

页码：30 / 39

共 50 条

[21] Detection of Lung Cancer Using Convolution Neural Network
Shankara C.
Hariprasad S.A.
Latha D.U.
SN Computer Science, 4 (3)
[22] URBAN AREAS DETECTION USING POLARIMETRIC SAR IMAGES
Azmedroub, Boussad
Ouarzeddine, Mounira
2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 3227 - 3230
[23] Coherent convolution neural network based retinal disease detection using optical coherence tomographic images
Upadhyay, Pawan Kumar
Rastogi, Somil
Kumar, K. Vimal
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (10) : 9688 - 9695
[24] Stingray Detection of Aerial Images with Region-based Convolution Neural Network
Chen, Chien-Hung
Liu, Keng-Hao
2017 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW), 2017,
[25] Salient Target Detection Method of Video Images Based on Convolution Neural Network
Yao, Zhuo
Guo, Li
TRAITEMENT DU SIGNAL, 2022, 39 (06) : 2157 - 2163
[26] Aircraft detection in remote sensing images based on saliency and convolution neural network
Hu, Guoxiong
Yang, Zhong
Han, Jiaming
Huang, Li
Gong, Jun
Xiong, Naixue
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2018,
[27] Aircraft detection in remote sensing images based on saliency and convolution neural network
Guoxiong Hu
Zhong Yang
Jiaming Han
Li Huang
Jun Gong
Naixue Xiong
EURASIP Journal on Wireless Communications and Networking, 2018
[28] Convolution neural network model for an intelligent solution for crack detection in pavement images
Rababaah, Aaron Rasheed
Wolfer, James
INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2022, 68 (04) : 389 - 396
[29] Classification of breast cancer mammogram images using convolution neural network
Albalawi, Umar
Manimurugan, S.
Varatharajan, R.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 34 (13):
[30] Classification of Woven Fabric Faulty Images Using Convolution Neural Network
Ashraf, Rehan
Ijaz, Yasir
Asif, Muhammad
Haider, Khurram Zeeshan
Mahmood, Toqeer
Owais, Muhammad
MATHEMATICAL PROBLEMS IN ENGINEERING, 2022, 2022

← 1 2 3 4 5 →