DOI QR코드

DOI QR Code

Study on Detection Technique for Sea Fog by using CCTV Images and Convolutional Neural Network

CCTV 영상과 합성곱 신경망을 활용한 해무 탐지 기법 연구

  • 김나경 (부경대학교 지구환경시스템과학부) ;
  • 박수호 (부경대학교 지구환경시스템과학부) ;
  • 정민지 (부경대학교 지구환경시스템과학부) ;
  • 황도현 (부경대학교 지구환경시스템과학부) ;
  • 앵흐자리갈 운자야 (부경대학교 지구환경시스템과학부) ;
  • 박미소 (부경대학교 지구환경시스템과학부) ;
  • 김보람 (부경대학교 지구환경시스템과학부) ;
  • 윤홍주 (부경대학교 공간정보시스템공학과)
  • Received : 2020.10.26
  • Accepted : 2020.12.15
  • Published : 2020.12.31

Abstract

In this paper, the method of detecting sea fog through CCTV image is proposed based on convolutional neural networks. The study data randomly extracted 1,0004 images, sea-fog and not sea-fog, from a total of 11 ports or beaches (Busan Port, Busan New Port, Pyeongtaek Port, Incheon Port, Gunsan Port, Daesan Port, Mokpo Port, Yeosu Gwangyang Port, Ulsan Port, Pohang Port, and Haeundae Beach) based on 1km of visibility. 80% of the total 1,0004 datasets were extracted and used for learning the convolutional neural network model. The model has 16 convolutional layers and 3 fully connected layers, and a convolutional neural network that performs Softmax classification in the last fully connected layer is used. Model accuracy evaluation was performed using the remaining 20%, and the accuracy evaluation result showed a classification accuracy of about 96%.

본 논문에서는 합성곱 신경망을 기반으로 CCTV 이미지를 통한 해무 탐지 방법을 제안한다. 학습에 필요한 자료로 시정 1km 기준으로 총 11개의 항만 또는 해수욕장(부산항, 부산신항, 평택항, 인천항, 군산항, 대산항, 목포항, 여수광양항, 울산항, 포항항, 해운대해수욕장)에서 수집된 해무와 해무가 아닌 이미지 10004장을 랜덤 추출하였다. 전체 10004장의 데이터셋 중에 80%를 추출하여 합성곱 신경망 모델 학습에 사용하였다. 사용된 모델은 16개의 합성곱층과 3개의 완전 연결층을 가지고 있으며, 마지막 완전 연결층에서 Softmax 분류를 수행하는 합성곱 신경망을 활용하였다. 나머지 20%를 이용하여 모델 정확도 평가를 수행하였고 정확도 평가 결과 약 96%의 분류 정확도를 보였다.

Keywords

References

  1. K. Heo, S. Min, K. Ha, and J. Kim, "Discrimination between Sea Fog and Low Stratus Using Texture Structure of MODIS Satellite Images," Korean J. of Remote Sensing, vol. 24, no. 6, 2008, pp. 571-581.
  2. M. Kim, Characteristics of sea fog distribution around the Korean Peninsula," Master's Thesis, Chonnam National University Graduate School, 1998.
  3. H. Byun, D. Lee, and H. Lee, "Analysis on the Characteristics and Predictablility of the Marine Fog over and near the East Sea," Korean Meteorological Society, vol. 33, no. 1, 1997, pp. 41-62.
  4. D. Wu, B. Lu, T. Zhang, and F.Yan, "A method of detecting sea fogs using CALIOP data and its application to improve MODIS-based sea fog detection," J. of Quantitative Spectroscopy &Radiative Transfer, vol. 153, 2015, pp. 88-94. https://doi.org/10.1016/j.jqsrt.2014.09.021
  5. D. Koracin, C. E. Dorman, J. M. Lewis, J. G. Hudson, E. M. Wilcox, and A. Torregrosa, "Marine fog: A review," Atmospheric Research, vol. 143, 2014, pp. 142-175. https://doi.org/10.1016/j.atmosres.2013.12.012
  6. T. Bae, J. Han, K. Kim, and Y.Kim, "Coastal Visibility Distance Estimation Using Dark Channel Prior and Distance Map Under Sea-Fog: Korean Peninsula Case," Sensors, vol. 19, no. 20, 2019, pp.4432-4447. https://doi.org/10.3390/s19204432
  7. M. Ahn, E. Sohn, and B. Hwang, "A new algorithm for sea fog/stratus detection using GMS-5 IR data," Advances in Atmospheric Sciences, vol. 20, no. 6 , 2003, pp. 899-913. https://doi.org/10.1007/BF02915513
  8. J. Yoo, M. Yun, M. Jeong, and M. Ahn, "Fog Detection over the Korean Peninsula Derived from Satellite Observations of Polar-orbit (MODIS) and Geostationary (GOES-9)," J. of the Korean Earth Science Society, vol. 27, no. 4, 2006, pp. 450-463.
  9. J. Eyre, J. Brownscombe, and R. Allam, "Detection of fog at night using Advanced Very High Resolution Radiometer (AVHRR) imagery," Meteorological Mag, vol. 113, no. 1346, 1984, pp. 266-271.
  10. G. Ellrod, "Advances in the detection and analysis of fog at night using GOES multispectral infrared imagery," Weather and Forecasting, vol. 10, no. 3, 1995, pp. 606-619. https://doi.org/10.1175/1520-0434(1995)010<0606:AITDAA>2.0.CO;2
  11. Y. Yuan, Z. Qiu, D. Sun, S. Wang, and X. Yue, "Daytime sea fog retrieval based on GOCI data: a case study over the Yellow Sea," Optical Society of America, vol. 24, no. 2, 2016, pp. 787-801.
  12. K. Lee, B. Kwon, and H. Yoon, "Sea Fog Detection Algorithm Using Visible and Near Infrared Bands," J. of The Korea Institute of Electronic Communication Sciences, vol. 13, no. 3, 2018, pp. 669-676. https://doi.org/10.13067/JKIECS.2018.13.3.669
  13. D. Kim, M. Park, Y. Park, and W.Kim, "Geostationary Ocean Color Imager (GOCI) Marine Fog Detection in Combination with Himawari-8 Based on the Decision Tree," remote sensing, vol. 12, no. 1, 2020, pp. 149-165. https://doi.org/10.3390/rs12010149
  14. S.B ak, H. Kim, B. Kim, D. Hwang, E. Unuzaya and H. Yoon, "Study on Detection Technique for Cochlodinium polykrikoides Red tide using Logistic Regression Model and Decision Tree Model," J. of the KIECS, vol. 13, no. 4, 2018, pp. 777-786.
  15. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural computation, vol. 1, no. 4, 1989, pp. 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  16. I. Goodfellow, Y. Bengio, and A. courvil, Deep Learning. Massachusetts: MIT Press book, 2016.