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
收藏
页码：30 / 39
相关论文
共 50 条
  • [41] Tomato Leaf Disease Detection Using Convolution Neural Network
    Kibriya, Hareem
    Rafique, Rimsha
    Ahmad, Wakeel
    Adnan, S. M.
    PROCEEDINGS OF 2021 INTERNATIONAL BHURBAN CONFERENCE ON APPLIED SCIENCES AND TECHNOLOGIES (IBCAST), 2021, : 346 - 351
  • [42] A Retinal Verssel Detection Approach Using Convolution Neural Network
    Sengur, Abdulkadir
    Guo, Yanhui
    Budak, Umit
    Vespa, Lucas J.
    2017 INTERNATIONAL ARTIFICIAL INTELLIGENCE AND DATA PROCESSING SYMPOSIUM (IDAP), 2017,
  • [43] Fabric Defect Detection Using Deep Convolution Neural Network
    Fan, Junjun
    Wong, Wai Keung
    Wen, Jiajun
    Gao, Can
    Mo, Dongmei
    Lai, Zhihui
    AATCC JOURNAL OF RESEARCH, 2021, 8 (1_SUPPL) : 144 - 151
  • [44] Forest Change Detection Using an Optimized Convolution Neural Network
    Senthilkumar, Radha
    Srinidhi, V.
    Neelavathi, S.
    Renuga Devi, S.
    IETE TECHNICAL REVIEW, 2022, 39 (01) : 135 - 142
  • [45] Detection of Disease in Tea Leaves Using Convolution Neural Network
    Bhowmik, Shyamtanu
    Talukdar, Anjan Kumar
    Sarma, Kandarpa Kumar
    2020 ADVANCED COMMUNICATION TECHNOLOGIES AND SIGNAL PROCESSING (IEEE ACTS), 2020,
  • [46] BRECNET: Breast Cancer Network for Histopathology Images Classification using Convolution Neural Network
    Yogapriya, J.
    Saravanabhavan, C.
    Elakkiya, B.
    Chandran, V. V.
    JOURNAL OF ALGEBRAIC STATISTICS, 2022, 13 (02) : 329 - 342
  • [47] Detection of Air Pollution in Urban Areas Using Monitoring Images
    Chu, Ying
    Chen, Fan
    Fu, Hong
    Yu, Hengyong
    ATMOSPHERE, 2023, 14 (05)
  • [48] Convolution Neural Network Based Multi-Label Disease Detection Using Smartphone Captured Tongue Images
    Bhatnagar, Vibha
    Bansod, Prashant P.
    APPLIED SCIENCES-BASEL, 2024, 14 (10):
  • [49] Automatic detection of non-proliferative diabetic retinopathy in retinal fundus images using convolution neural network
    Saranya, P.
    Prabakaran, S.
    JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2020,
  • [50] Detecting Lung Cancer from Histopathological Images using Convolution Neural Network
    Karim, Dewan Ziaul
    Bushra, Tasfia Anika
    2021 IEEE REGION 10 CONFERENCE (TENCON 2021), 2021, : 626 - 631
12345