Development of Methodology for Measuring Water Level in Agricultural Water Reservoir through Deep Learning anlaysis of CCTV Images

Donghyuk Joo; Sang-Hyun Lee; Gyu-Hoon Choi; Seung-Hwan Yoo; Ra Na; Hayoung Kim; Chang-Jo Oh; Kwang-Sik Yoon

doi:10.5389/KSAE.2023.65.1.015

All Issue

2023 Vol.65, Issue 1 Preview Page Next Page

Development of Methodology for Measuring Water Level in Agricultural Water Reservoir through Deep Learning anlaysis of CCTV Images 딥러닝 기법을 이용한 농업용저수지 CCTV 영상 기반의 수위계측 방법 개발

2023. pp. 15-26

PDF XML

Abstract

This study aimed to evaluate the performance of water level classification from CCTV images in agricultural facilities such as reservoirs. Recently, the CCTV system, widely used for facility monitor or disaster detection, can automatically detect and identify people and objects from the images by developing new technologies such as a deep learning system. Accordingly, we applied the ResNet-50 deep learning system based on Convolutional Neural Network and analyzed the water level of the agricultural reservoir from CCTV images obtained from TOMS (Total Operation Management System) of the Korea Rural Community Corporation. As a result, the accuracy of water level detection was improved by excluding night and rainfall CCTV images and applying measures. For example, the error rate significantly decreased from 24.39 % to 1.43 % in the Bakseok reservoir. We believe that the utilization of CCTVs should be further improved when calculating the amount of water supply and establishing a supply plan according to the integrated water management policy.

Keywords

CCTV

deep learning

ResNet-50

water level

References

REFERENCES

A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger and C. Schnorr, Computer Analysis of Images and Patterns, Groningen, The Netherlands, Aug. 25-Aug. 27, LNCS 2756, Real-time optic flow computation with variational methods; 222-229 (2003)10.1007/978-3-540-45179-2_28

E. Cengil, A. Çınar and E. Özbay, 2017 International Conference on Computer Science and Engineering (UBMK), Image classification with caffe deep learning framework; 440-444 (2017)10.1109/ubmk.2017.8093433

K. E. Ko and K. B. Sim, Journal of the Institute of Control, Robotics and Systems, Trend of object recognition and detection technology using deep learning, 23(3); 17-24, (in Korean) (2017)

U. Hwang, J. S. Yoo and J. C. Jeong, Proceedings of the Korean Society of Broadcast Engineers Conference, Computer Vision based Water-level Detection; 303-306, (in Korean) (2013)

S. W. Hong, Y. G. Park and H. C. Lee, Journal of the Korea Society of Disaster Information, Experimental and Analytical Study on the Water Level Detection and Early Warning System with Intelligent CCTV, 10(1); 105-115, (in Korean) (2014)10.15683/kosd.2014.10.1.105

I. Z. Mukti and D. Biswas, 4th International Conference on Electrical Information and Communication Technology (EICT), Transfer Learning Based Plant Diseases Detection Using ResNet50; 1-6 (2019)10.1109/eict48899.2019.9068805

J. Torres and Haeseon Park, First Contact with Tensorflow; 117, Hanbit Media, Inc. (2016)

Korea Rural Community Corporation (KRC), Water level analysis using cctv video informations, (in Korean) (2020)

O. J. Kim, J. W. Lee, J. Y. Park and M. H. Cho, Korean Journal of Remote Sensing, A Study on the Improvement of Image-Based Water Level Detection Algorithm Using the Region growing, 36(5-4); 1245-1254, (in Korean) (2020)10.7780/kjrs.2020.36.5.4.9

N. W. Kim, S. C. Son, M. S. Lee, G. H. Min and B. T. Lee, Journal of the Institute of Electronics and Information Engineers, Active Water-Level and Distance Measurement Algorithmusing Light Beam Pattern, 52(4); 156-163, (in Korean) (2015)10.5573/ieie.2015.52.4.156

J. D. Kim, Y. G. Han and H. S. Hahn, Journal of the Korea Society of Computer and Information, Image-based Water Level Measurement Method Adapting to Ruler’s Surface Condition, 15(9); 67-76, (in Korean) (2010)10.9708/jksci.2010.15.9.067

N. J. Lee and K. K. Yu, Journal of the Korea Society of Hazerd Mitigation, A Novel Method to Measure River Water Stage by Using Spatio-Temporal Image Analyses, 17(2); 461-469, (in Korean) (2017)10.9798/kosham.2017.17.2.461

J. M. Lee, Magazine of the Korean Society of Agricultural Engineers, The importance of safety management and subsequent damage management of agricultural production infrastructure in response to changes, 56(3); 38-46, (in Korean) (2014)

E. H. Lee, J. Y. Nam and B. C. Ko, Journal of Broadcast Engineering, Speed-limit Sign Recognition Using Convolutional Neural Network Based on Random Forest, 20(6); 938-949, (in Korean) (2015)10.5909/jbe.2015.20.6.938

National Disaster Management Research Institute (NDMI), The practical study of flood forecasting and warning system with auto water level detection process using intellingent CCTV, (in Korean) (2012)

M. B. Seo, C. J. Lee and D. G. Kim, Journal of the Korea Academia-Industrial Cooperation Society, A Water Surface Detection Method by Correlation Analysis of Watermark Images with Time Interval, 14(1); 470-477, (in Korean) (2013)10.5762/kais.2013.14.1.470

A. Saito and M. Iwahashi, Proceedings of the 19th Workshop on Circuits and Systems in Karuizawa, Water level detection algorithm based on synchronous frame addition and filtering; 525-530, (in Japanese) (2006)

Y. Takagi, H. Mori, A. Tsujikawa, T. Saito and K. Karube, J. of EICA, The geometrical and optical analysis concerning the feature of the water surface interface of an inclined plate which is used the water level measuring, 4(4); 9-18, (in Japanese) (2000)

T. W. Kim, H. S. Moon and J. H. Kim, Journal of Institute of Control, Robotics and Systems, The Study on CNN based Helicopter Type Classification Model, 26(6); 479-486, (in Korean) (2020)10.5302/j.icros.2020.20.0017

Y. Wei and Y. Zhang, Sensors, Effective Waterline Detection of Unmanned Surface Vehicles Based on Optical Images, 16(10), (in Chinese) (2016)10.3390/s16101590

J. Yu and H. Hahn, Journal of Information Science and Engineering, Remote detection and monitoring of a water level using narrow band channel, 26(1); 71-82, (in Korean) (2010)10.6688/JISE.2010.26.1.6

Information

Publisher :The Korean Society of Agricultural Engineers
Publisher(Ko) :한국농공학회
Journal Title :Journal of Korean Society of Agricultural Engineers
Journal Title(Ko) :한국농공학회논문집
Volume : 65
No :1
Pages :15-26
Received Date : 2022-04-22
Revised Date : 2022-10-04
Accepted Date : 2022-10-26
DOI :https://doi.org/10.5389/KSAE.2023.65.1.015

Journal of Korean Society of Agricultural Engineers ISSN:1738-3692(Print) 2093-7709(Online) 한국농공학회논문집

All Issue

REFERENCES