IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Deep-Learning-Based Water Shield Automation System by Predicting River Overflow and Vehicle Flooding Possibility

하천 범람 및 차량 침수 가능성 예측을 통한 딥러닝 기반 차수막 자동화 시스템

  • Received : 2023.03.13
  • Accepted : 2023.05.02
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

Keywords

Acknowledgement

본 논문은 정부 (과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구 (NRF-2020R1A2C1014768)이고, 국방부 재원으로 정보통신기획평가원 지원을 받아 수행된 "이동형 모바일 환경 인공지능을 활용한 경계 감시 시스템 기술개발 (A)" 연구 결과 중 일부입니다.

References

  1. 최병성, "포항 참사 진짜 원인, 처참한 현장에 남은 결정적 증거," 오마이뉴스, 2022년 9월 30일 자.
  2. J. W. Jung, H. L. Mo, J. H. Lee, Y. H. Yoo, H. S. Kim, "Flood Stage Forecasting at the Gurye-Gyo Station in Sumjin River Using LSTM-Based Deep Learning Models," Journal of the Korean Society of Hazard Mitigation, Vol. 21, No. 3, pp. 193-201, 2021 (in Korean). https://doi.org/10.9798/KOSHAM.2021.21.3.193
  3. S. H. Jung, H. S. Cho, J. G. Kim, G. H. Lee, "Prediction of Water Level in a Tidal River Using a Deep-learning Based LSTM Model," Journal of Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216, 2018 (in Korean).
  4. Y. Bengio, P. Frasconi, P. Simard, "The Problem of Learning Long-term Dependencies in Recurrent Networks," In IEEE International Conference on Neural Networks, Vol. 3, pp. 1183-1188, 1993.
  5. S. Hochreiter, J. Schmidhuber, "Long Short-Term Memory," Neural Computation, Vol. 9, No. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  6. J. J. Jung, J. Y. Kim, "A Performance Analysis by Adjusting Learning Methods in Stock Price Prediction Model Using LSTM," Journal of Digital Convergence, Vol. 18, No. 11, pp. 259-266, 2020 (in Korean). https://doi.org/10.14400/JDC.2020.18.11.259
  7. B. K. Jeon, K. H. Lee, E. J. Kim, "Development of a Prediction Model of Solar Irradiances Using LSTM for Use in Building Predictive Control," Journal of the Korean Solar Energy Society, Vol. 39, No. 5, pp. 41-52, 2019 (in Korean). https://doi.org/10.7836/kses.2019.39.5.041
  8. E. H. Kim, A. Oh, "Automated Vehicle Research by Recognizing Maneuvering Modes Using LSTM Model," The Journal of the Korea Institute of Intelligent Transportation Systems, Vol. 16, No. 4, pp. 153-163, 2017 (in Korean). https://doi.org/10.12815/kits.2017.16.4.153
  9. J. H. Choi, G. T. Hwang, S. J. Lee, "Behavior Pattern Prediction Algorithm Based on 2D Pose Estimation and LSTM from Videos," IEMEK J. Embed. Sys. Appl., Vol. 17, No. 4, pp. 191-197, 2022 (in Korean).
  10. A. Dai, K. E. Trenberth, T. R. Karl, "Effects of Clouds Soil Moisture, Precipitation, and Water Vapor on Diurnal Temperature Range," Journal of Climate, Vol. 12, No. 8, pp. 2451-2473, 1999. https://doi.org/10.1175/1520-0442(1999)012<2451:EOCSMP>2.0.CO;2
  11. S. K. Min, S. W. Son, K. H. Seo, J. S. Kug, S. I. An, Y. S. Choi, J. H. Jeong, B. M. Kim, J. W. Kim, Y. H. Kim, J. Y. Lee, M. I. Lee, "Erratum to: Changes in Weather and Climate Extremes over Korea and Possible Causes: A Review," Asia-Pacific Journal of Atmospheric Sciences, Vol. 51, No. 3, pp. 291-291, 2015 (in Korean). https://doi.org/10.1007/s13143-015-0072-7
  12. 이호근, "[이호근 교수의 자동차이야기]'카 히스토리' 통해 침수차인지 반드시 확인해야," 소비자경제, 2022년 8월 30일 자.
  13. Ultralytics, YOLOv5 [Internet] https://github.com/ultralytics/yolov5
  14. 공공데이터포털, 한국수자원공사_우량수위 관측정보, https://data.go.kr/data/3074802/openapi.do