All Issue

2024 Vol.57, Issue 11 Preview Page

Research Article

Development of a water body segmentation model for water level estimation in agricultural reservoirs

농업용 저수지 수위 추정을 위한 수체 분할 모델 개발

Suhyun Lima
,
Soon Ho Kwonb
,
Seungyub Leec*
임 수현a
,
권 순호b
,
이 승엽c*
aMaster Student, Department of Civil and Environmental Engineering, Hannam University, Daejeon, Korea
bPostdoctoral Researcher, Department of Civil and Environmental Engineering, Hannam University, Daejeon, Korea
cAssistant Professor, Department of Civil and Environmental Engineering, Hannam University, Daejeon, Korea
a한남대학교 건설시스템공학과 석사과정
b한남대학교 토목환경공학과 박사후연구원
c한남대학교 토목환경공학과 조교수
*Corresponding Author
30 November 2024. pp. 935-944
PDF XML Citation
Abstract

Agricultural reservoirs are a key infrastructure, supplying 60% of the agricultural water in Korea. Recently, they have been increasingly exposed, either directly or indirectly, to natural disasters such as droughts and floods. Real-time estimation of the reservoir's storage volume (or water level) is crucial for sustainable operational decision-making under these risks, but budget constraints pose significant challenges. In this study, we propose a water body segmentation model for agricultural reservoirs to predict water levels using CCTV image, originally installed for security purposes. Image segmentation refers to the process of distinguishing water from the background in the original CCTV images. This study utilizes transfer learning based on V-FloodNet, a model suited for water segmentation. The proposed model was validated using data from four agricultural reservoirs in Korea, and the results showed that it could distinguish between water and background with an accuracy of approximately 90% when using around 1,000 images. The methodology presented in this study can be effectively applied to the management of agricultural reservoirs using existing infrastructure without incurring additional costs or requiring new data collection.

Keywords
CCTV image
Agricultural reservoir
Water level classification
Image segmentation
Transfer learning

농업용 저수지는 우리나라 농업용수의 60%를 공급하는 주요 기반 시설로, 최근에는 가뭄 및 홍수와 같은 자연재해에 직간접적으로 노출되고 있다. 이러한 위험으로부터 지속 가능한 운영 의사결정을 위한 농업용 저수지의 실시간 저수량(혹은 저수위) 추정이 중요하지만, 한정된 예산으로 인한 한계가 있다. 본 연구에서는 기존 보안목적으로 저수지에 설치된 CCTV 이미지를 활용하여 저수위 예측을 위한 농업용 저수지 수체 분할 모델을 제시하였다. 이미지 분할은 CCTV 원본 이미지를 물과 배경으로 구분하는 과정이며, 본 연구에서는 수체 분할에 적합한 모델인 V-FloodNet을 활용한 전이학습에 기반하여 구성하였다. 제안한 모델은 국내 4개 농업용 저수지의 데이터를 활용하여 검증하였으며, 적용 결과 1,000장 정도의 이미지를 사용하였을 때 90% 수준의 높은 정확도로 물과 배경을 구분할 수 있음을 확인하였다. 본 연구에서 제시한 방법론은 추가적인 비용 및 데이터 확보하지 않고도 기존 인프라를 활용하여 농업용 저수지의 효과적인 운영에 활용할 수 있을 것이다.

키워드
CCTV 이미지
농업용 저수지
수위 분류
이미지 분할
전이학습
References
1

Abbasi, M., Shah-Hosseini, R., and Aghdami-Nia, M. (2023). "Sentinel-1 polarization comparison for flood segmentation using deep learning." Proceedings, Vol. 87, No. 1, 14.

10.3390/IECG2022-14069
2

Chaudhary, P., D'Aronco, S., Moy de Virty, M., Leitao, J.P., and Wegner, J.D. (2019). "Flood-water level estimation from social media images." The International Archives of the Photogrammetry, RSSIS, Vol. IV-2/W5, pp. 5-12.

10.5194/isprs-annals-IV-2-W5-5-2019
3

Cheng, B., Girshick, R., Dollár, P., Berg, A.C., and Kirillov, A. (2021). "Boundary IoU: Improving object-centric image segmentation evaluation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, TN, U.S., pp. 15334-15342.

10.1109/CVPR46437.2021.01508
4

De Albuquerque Teixeira, A.M., Batista, L.V., da Silva, R.M., Freitas, L.M.T., and Santos, C.A.G. (2024). "Dynamic monitoring of surface area and water volume of reservoirs using satellite imagery, computer vision and deep learning." Remote Sensing Applications: Society and Environment, Vol. 35, No.5, 101205.

10.1016/j.rsase.2024.101205
5

Eltner, A., Bressan, P.O., Akiyama, T., Gonçalves, W.N., and Marcato Junior, J. (2021). "Using deep learning for automatic water stage measurements." Water Resources Research, Vol. 57, No. 3, e2020WR027608.

10.1029/2020WR027608
6

Ghosh, B., Garg, S., Motagh, M., and Martinis, S. (2024). "Automatic flood detection from Sentinel-1 data using a nested UNet model and a NASA benchmark dataset." PFG - Journal of Photogrammetry, RSGIS, Vol. 92, No. 1, pp. 1-18.

10.1007/s41064-024-00275-1
7

Jenks, G.F. (1967). "The data model concept in statistical mapping." International Yearbook of Cartography, Vol. 7, pp. 186-190.

8

Joo, D.H., Lee, S.H., Choi, G.H., Yoo, S.H., Na, R., Kim, H.Y., Oh, C.J., and Yoon, K.S. (2023). "Development of methodology for measuring water level in agricultural water reservoir through deep learning anlaysis of CCTV images." Journal of the Korean Society of Agricultural Engineers, Vol. 65, No. 1, pp. 15-26.

9

Joo, D.H., Na, R., Kim, H.Y., Choi, G.H., Kwon, J.H., and Yoo, S.H. (2022). "Analysis of the optimal window size of hampel filter for calibration of real-time water level in agricultural reservoirs." Journal of The Korean Society of Agricultural Engineers, Vol. 64, No. 3, pp. 9-24.

10

Kim, K.H., Kim, M.G., Yoon, P.R., Bang, J.H., Myoung, W.H., Choi, J.Y., and Choi, G.H. (2022). "Application of CCTV image and semantic segmentation model for water level estimation of irrigation channel." Journal of The Korean Society of Agricultural Engineers, Vol. 64, No. 3, pp. 63-73.

11

Korea Rural Community Corporation (KRC) (2024) Rural agricultural water resource information system, accessed on 17 October 2024, <https://rawris-am.ekr.or.kr/wrms/>.

12

Korea Water Resources Corporation (K-water) (2020) A study on the efficient use of water through improving the agricultural water use estimation.

13

Kusudo, T., Yamamoto, A., Kimura, M., and Matsuno, Y. (2021). "Development and assessment of water-level prediction models for small reservoirs using a deep learning algorithm." Water, Vol. 14, No. 1, 55.

10.3390/w14010055
14

Kwon, S.H., and Kim, J.H. (2021). "Machine learning and urban drainage systems: State-of-the-art review." Water, Vol. 13, No. 24, 3545.

10.3390/w13243545
15

Kwon, S.H., and Lee, S. (2024). "Deep learning to recognize water level for agriculture reservoir using CCTV imagery." Water Resources Management, Vol. 38, No. 3, pp. 1165-1180.

10.1007/s11269-023-03714-7
16

Kwon, S.H., Ha, C., and Lee, S. (2023). "A study on the application of the agricultural reservoir water level recognition model using CCTV image data." Journal of Korea Water Resources Association, Vol. 56, No. 4, pp. 245-259.

17

Liang, Y., Li, X., Tsai, B., Chen, Q., and Jafari, N. (2023). "V- FloodNet: A video segmentation system for urban flood detection and quantification." Environmental Modelling & Software, Vol. 160, 105586.

10.1016/j.envsoft.2022.105586
18

Ministry of Environment (ME) (2021) The 1st national water management master plan (2021-2030).

19

Moy de Vitry, M., Kramer, S., Wegner, J.D., and Leitão, J.P. (2019). "Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network." Hydrology and Earth System Sciences, Vol. 23, No. 11, pp. 4621-4634.

10.5194/hess-23-4621-2019
20

Muhadi, N.A., Abdullah, A.F., Bejo, S.K., Mahadi, M.R., and Mijic, A. (2021). "Deep learning semantic segmentation for water level estimation using surveillance camera." Applied Sciences, Vol. 11, No. 20, 9691.

10.3390/app11209691
21

Qiao, G., Yang, M., and Wang, H. (2022). "A water level measurement approach based on YOLOv5s." Sensors, Vol. 22, No. 10, 3714.

10.3390/s2210371435632123PMC9147151
22

Vandaele, R., Dance, S.L., and Ojha, V. (2021). "Deep learning for automated river-level monitoring through river-camera images: An approach based on water segmentation and transfer learning." Hydrology and Earth System Sciences, Vol. 25, No. 8, pp. 4435-4453.

10.5194/hess-25-4435-2021
23

Wang, Z., Wang, E., and Zhu, Y. (2020). "Image segmentation evaluation: A survey of methods." Artificial Intelligence Review, Springer Nature, Vol. 53, No. 8, pp. 5637-5674.

10.1007/s10462-020-09830-9
24

Wu, J., Huang, X., Xu, N., Zhu, Q., Zorn, C., Guo, W., Wang, J., Wang, B., Shao, S., and Yu, C. (2023). "Combining satellite imagery and a deep learning algorithm to retrieve the water levels of small reservoirs." Remote Sensing, Vol. 15, No. 24, 5740.

10.3390/rs15245740
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 57
  • No :11
  • Pages :935-944
  • Received Date : 2024-10-17
  • Revised Date : 2024-11-01
  • Accepted Date : 2024-11-04
  • DOI :https://doi.org/10.3741/JKWRA.2024.57.11.935
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close