Browse > Article
http://dx.doi.org/10.5389/KSAE.2022.64.3.063

Application of CCTV Image and Semantic Segmentation Model for Water Level Estimation of Irrigation Channel  

Kim, Kwi-Hoon (Department of Rural Systems Engineering, Seoul National University)
Kim, Ma-Ga (Department of Rural Systems Engineering, Seoul National University)
Yoon, Pu-Reun (Department of Rural Systems Engineering, Seoul National University)
Bang, Je-Hong (Department of Rural Systems Engineering, Seoul National University)
Myoung, Woo-Ho (Rural Research Institute, Korea Rural Community Corporation)
Choi, Jin-Yong (Department of Rural Systems Engineering, Research Institute of Agriculture and Life Sciences, Globel Smart Farm Convergence Major, Seoul National University)
Choi, Gyu-Hoon (WeDB Company)
Publication Information
Journal of The Korean Society of Agricultural Engineers / v.64, no.3, 2022 , pp. 63-73 More about this Journal
Abstract
A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R2 of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.
Keywords
Image classification; image segmentation; CCTV images; irrigation canal;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Bang, J., J. Y. Choi, P. Yoon, C. J. Oh, S. J. Maeng, S. J. Bae, M. W. Jang, T. Jang, and M. S. Park, 2021. Assessing irrigation water supply from agricultural reservoir using automatic water level data of irrigation canal. Journal of the Korean Society of Agricultural Engineers 63(1): 27-35. doi:10.5389/KSAE.2021.63.1.027. (in Korean).   DOI
2 Cao, Y., C. Huo, N. Xu, X. Zhang, S. Xiang, and C. Pan, 2022. HENet: head-level ensemble network for very high resolution remote sensing images semantic segmentation. IEEE Geoscience and Remote Sensing Letters 19: 1-5. doi:2.1109/LGRS.2022.3147857.
3 Maehara, H., M. Nagase, and K. Taira, 2016. Water level measurement from CCTV camera images using water gauge images taken at the time of low water level. Journal of the Japan Society of Photogrammetry and Remote Sensing 55(1): 66-68. doi:10.4287/jsprs.55.66. (in Japanese).   DOI
4 Maehara, H., M. Nagase, M. Kuchi, T. Suzuki, and K. Taira, 2019. A deep-learning based water-level measurement method from CCTV camera images. Journal of the Japan Society of Photogrammetry and Remote Sensing 58(1): 28-33. doi:10.4287/jsprs.58.28. (in Japanese).   DOI
5 Li, J., F. Jiang, J. Yang, B. Kong, M. Gogate, K. Dashtipour, and A. Hussain, 2021. Lane-DeepLab: Lane semantic segmentation in automatic driving scenarios for high-definition maps. Neurocomputing 465: 15-25. doi:10.1016/j.neucom.2021.08.105.   DOI
6 Lin, Y. T., Y. C. Lin, and J. Y. Han, 2018. Automatic water-level detection using single-camera images with varied poses. Measurement 127: 167-174. doi:10.1016/j.measurement.2018.05.100.   DOI
7 Singh V. K., H. A. Rashwan, M. Abder-Nasser, M. Sarker, M. Kamal, F. Akram, P. Nidhi, S. Romani, and D. Puig, 2019. An efficient solution for breast tumor segmentation and classification in ultrasound images using deep adversarial learning. arXiv: 1907.00887v1 [eess.IV].
8 Vianna P., R. Farias, W. C. de Albuquerque Pereira, 2021. U-Net and SegNet performances on lesion segmentation of breast ultrasonography images. Research on Biomedical Engineering 37: 171-179. doi:10.1007/s42600-021-00137-4.   DOI
9 Cheong, T. S., 2018. Development of automatic flow measurement technology to enhance disaster-safety codes for small stream, 98-101. Jung-gu, Ulsan: National Disaster Management Research Institute (in Korean).
10 Kim, S. J., H. J. Kwon, I. J. Kim, and P. S. Kim, 2016. Economical design of water level monitoring network for agricultural water quantification. Journal of the Korean Society of Agricultural Engineers 68(5): 19-28. doi:10.5389/KSAE.2016.58.5.019. (in Korean).   DOI
11 Kingma, D. P., and J. Ba, 2014. Adam: a method for stochastic optimization. arXiv:1412.6980v9.
12 Cui, B., X. Chen, and Y. Lu, 2020. Semantic segmentation of remote sensing images using atransfer learning and deep convolutional neural network with dense connection. IEEE Access 8: 116744-116755. doi:10.1109/ACCESS.2020.3003914.   DOI
13 Hong, E. M., W. H. Nam, J. Y. Choi, and J. T. Kim, 2014. Evaluation of water supply adequacy using real-time water level monitoring system in paddy irrigation canals. Journal of the Korean Society of Agricultural Engineers 56(4): 1-8. doi:10.5389/KSAE.2014.56.4.001. (in Korean).   DOI
14 Hua, Y., D. Marcos, L. Mou, X. X. Zhu, and D. Tuia, 2021. Semantic segmentation of remote sensing images with sparse annotations. arXiv: 2101.03492 [cs.CV].
15 Mique E. Jr, and A. Malicdem, 2020. Deep residual U-Net based lung image segmentation for lung disease detection. 2020 IOP Conference Series: Materials Science and Engineering 803: 012004. doi:10.1088/1757-899X/803/1/012004.   DOI
16 Chau dhary, P., S. D'Aronco, M. Moy de Virty, J. P. Leitao, and J. D. Wegner, 2019. Flood-water level estimation from social media images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2/W5. doi:10.5194.isprs-annals-IV-2-W5-5-2019.   DOI
17 He, K., X. Zhang, S. Ren, and J. Sun, 2015. Deep residual learning for image recognition. arXiv: 1512.03385v1.
18 Kim, K. J., S. K. Choi, S. K. Lee, S. W. Park, and W. T. Ahn, 2019. Accuracy improvement of water level measuring method using stereo CCTV system. Crisisonomy 15(4): 83-93. doi:10.14251/crisisonomy.2019.15.4.83. (in Korean).   DOI
19 Lee, J., J. Noh, M. Kang, and H. Shin, 2020. Evaluation of the irrigation water supply of agricultural reservoir based on measurement information from irrigation canal. Journal of the Korean Society of Agricultural Engineers 62(6): 63-72. doi:10.5389/KSAE.2021.62.6.063. (in Korean).   DOI
20 Lopez-Fuentes L., C. Rossi, and H. Skinnemoen, 2017. River segmentation for flood monitoring. 2017 IEEE International Conference on Big Data, 3760-3763. doi:10.1109/BigData.2017.8258373.   DOI
21 Yuan X., J. Shi, and L. Gu, 2021. A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Systems with Applications 169: 114417. doi:10.1016/j/eswa/2020.114417.   DOI