Home Journals Articles Updates About
CN
image
收藏切换
Water Level Identification Method of Rivers and Lakes Based on Mask RCNN
收藏切换
Zhi XU1, Kai GAO2, Xi-chao GAO2, Li-li LIANG1, Pan YI3
Water Resources and Power | 2023, 41(7) : 22 - 26
Less
收藏切换
Water Resources and Power | 2023, 41(7): 22-26
• HYDROLOGY，WATER RESOURCES AND ENVIRONMENT •
Water Level Identification Method of Rivers and Lakes Based on Mask RCNN
Full
Zhi XU1, Kai GAO2, Xi-chao GAO2, Li-li LIANG1, Pan YI3
Affiliations
  • 1.Science and Technology Research Inst., China Three Gorges Corporation, Beijing 100038, China
  • 2.China Institute of Water Resources and Hydropower Research, Beijing 100038, China
  • 3.Beijing Hydrology Center, Beijing 100089, China
Published: 2023-07-25 doi: 10.20040/j.cnki.1000-7709.2023.20222376
Outline
收藏切换

With the development of deep learning and image recognition technology, monitoring the water level of urban rivers and lakes through video has become a hot research topic in recent years. In order to realize the comprehensiveness of urban river and lake water level monitoring, a method of river and lake water level identification based on Mask RCNN was proposed. The water level was obtained by the water level characters and their position relations in the video images, and it was verified by the monitoring video of the real water level station in Dongying City, Shandong Province. The results show that the probability that the comparison error between the water level identification result and the measured data was less than 2 cm was 68.5%, the probability of error less than 3 cm is 76.9%, the probability of error less than 5 cm is 93.5%, the average error is 2.1 cm, and the root mean square error (RMSE) is 3.0 cm, which meets the recognition accuracy requirements of video water gauge level in Technical Outline of Digital Twin Watershed Construction (Trial). Therefore, the model has a good recognition effect and a certain application prospect.

water level identification  /  image recognition  /  deep learning  /  Mask RCNN
徐志, 高凯, 高希超, 梁犁丽, 易攀. 基于Mask RCNN的河湖水位识别方法. 水电能源科学, 2023 , 41 (7) : 22 -26 . DOI: 10.20040/j.cnki.1000-7709.2023.20222376
Zhi XU, Kai GAO, Xi-chao GAO, Li-li LIANG, Pan YI. Water Level Identification Method of Rivers and Lakes Based on Mask RCNN[J]. Water Resources and Power, 2023 , 41 (7) : 22 -26 . DOI: 10.20040/j.cnki.1000-7709.2023.20222376
Appendix
Less
Year 2023 volume 41 Issue 7
457
106
Cite this Article
BibTeX
Article Info
doi: 10.20040/j.cnki.1000-7709.2023.20222376
  • Receive Date：2022-11-11
  • Online Date：2026-01-28
  • Published：2023-07-25
Article Data
Affiliations
History
  • Received：2022-11-11
  • Revised：2023-02-07
Funding
Affiliations
    1.Science and Technology Research Inst., China Three Gorges Corporation, Beijing 100038, China
    2.China Institute of Water Resources and Hydropower Research, Beijing 100038, China
    3.Beijing Hydrology Center, Beijing 100089, China
References
Share
https://castjournals.cast.org.cn/joweb/sdnykx/EN/10.20040/j.cnki.1000-7709.2023.20222376
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House