딥러닝 기법을 이용한 농업용저수지 CCTV 영상 기반의 수위계측 방법 개발
Development of Methodology for Measuring Water Level in Agricultural Water Reservoir through Deep Learning anlaysis of CCTV Images
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
This study aimed to evaluate the performance of water level classification from CCTV images in agricultural facilities such as reservoirs. Recently, theCCTV system, widely used for facility monitor or disaster detection, can automatically detect and identify people and objects from the images bydeveloping new technologies such as a deep learning system. Accordingly, we applied the ResNet-50 deep learning system based on ConvolutionalNeural Network and analyzed the water level of the agricultural reservoir from CCTV images obtained from TOMS (Total Operation ManagementSystem) of the Korea Rural Community Corporation. As a result, the accuracy of water level detection was improved by excluding night and rainfallCCTV images and applying measures. For example, the error rate significantly decreased from 24.39 % to 1.43 % in the Bakseok reservoir. We believethat the utilization of CCTVs should be further improved when calculating the amount of water supply and establishing a supply plan according tothe integrated water management policy.
Abstract
This study aimed to evaluate the performance of water level classification from CCTV images in agricultural facilities such as reservoirs. Recently, theCCTV system, widely used for facility monitor or disaster detection, can automatically detect and identify people and objects from the images bydeveloping new technologies such as a deep learning system. Accordingly, we applied the ResNet-50 deep learning system based on ConvolutionalNeural Network and analyzed the water level of the agricultural reservoir from CCTV images obtained from TOMS (Total Operation ManagementSystem) of the Korea Rural Community Corporation. As a result, the accuracy of water level detection was improved by excluding night and rainfallCCTV images and applying measures. For example, the error rate significantly decreased from 24.39 % to 1.43 % in the Bakseok reservoir. We believethat the utilization of CCTVs should be further improved when calculating the amount of water supply and establishing a supply plan according tothe integrated water management policy.
참고문헌 (21)
- Bruhn, A., "Real-time optic flow computation with variational methods", Computer Analysis of Images and Patterns, pp.222~229 (2003)
- Cengil, E., "Image classification with caffe deep learning framework", 2017International Conference on Computer Science and Engineering (UBMK), pp.440~444 (2017)
- Ko, K. E., "Trend of object recognition and detection technology using deep learning", Journal of the Institute of Control, Robotics and Systems, 23(3), pp.17~24 (2017)
- Hwang, U., "Computer Vision based Water-level Detection", Proceedings of the Korean Society of Broadcast Engineers Conference, pp.303~306 (2013)
- 홍상완, "지능형 CCTV를 이용한 수위감지 경보시스템에 대한 실험 및 해석적 연구", 한국재난정보학회 논문집, 10(1), pp.105~115 (2014), 한국재난정보학회
- Mukti, I. Z., "Transfer Learning Based Plant Diseases Detection Using ResNet50", 4th International Conference on Electrical Information and Communication Technology (EICT), pp.1~6 (2019)
- Torres, J., "First Contact with Tensorflow", pp.117~ (2016), Hanbit Media, Inc
- Water level analysis using cctv video informations, "Korea Rural Community Corporation (KRC)", ~ (2020)
- 김옥주, "Region growing 기법을 적용한 영상기반 수위감지 알고리즘 개선에 대한 연구", 대한원격탐사학회지, 36(5), pp.1245~1254 (2020), 대한원격탐사학회[DOI]
- 김낙우, "광패턴을 이용한 능동형 수위 및 거리 측정 기법", 전자공학회논문지, 52(4), pp.156~163 (2015), 대한전자공학회
- 김재도, "목자판 표면 상태에 적응적인 영상 기반 수위 계측 기법", 한국컴퓨터정보학회논문지, 15(9), pp.67~76 (2010), 한국컴퓨터정보학회
- 이남주, "시공간 영상 분석을 이용한 하천 수위 측정", 한국방재학회논문집, 17(2), pp.461~469 (2017), 한국방재학회[DOI]
- Lee, J. M., "The importance of safety management and subsequent damage management of agricultural production infrastructure in response to changes", Magazine of the Korean Society of Agricultural Engineers, 56(3), pp.38~46 (2014)
- 이은주, "랜덤 포레스트 분류기 기반의 컨벌루션 뉴럴 네트워크를 이용한 속도 제한 표지판 인식", 방송공학회 논문지, 20(6), pp.938~949 (2015), 한국방송∙미디어공학회[DOI]
- The practical study of flood forecasting and warning system with auto water level detection process using intellingent CCTV, "National Disaster Management Research Institute(NDMI)", ~ (2012)
- 서명배, "시차가 있는 수위표 이미지의 상관분석을 통한 수면측정기법", 한국산학기술학회논문지, 14(1), pp.470~477 (2013), 한국산학기술학회[DOI]
- Saito, A., "Water level detection algorithm based on synchronous frame addition and filtering", Proceedings of the 19th Workshop on Circuits and Systems in Karuizawa, pp.525~530 (2006)
- Takagi, Y., "The geometrical and optical analysis concerning the feature of the water surface interface of an inclined plate which is used the water level measuring", J. of EICA, 4(4), pp.9~18 (2000)
- 김태완, "합성곱 신경망 기반의 헬기 기종 분류 모형 연구", 제어.로봇.시스템학회 논문지, 26(6), pp.479~486 (2020), 제어·로봇·시스템학회[DOI]
- Wei, Y., "Effective Waterline Detection of Unmanned Surface Vehicles Based on Optical Images", Sensors, 16(10) (2016)
- Yu, J., "Remote detection and monitoring of a water level using narrow band channel", Journal of Information Science and Engineering, 26(1), pp.71~82 (2010)