DOI QR코드

DOI QR Code

Development of Weather Information Acquisition Technology using CCTV Video and Deep Learning for Low-Altitude Aircraft Pilots

저고도 항공기 조종사를 위한 CCTV 영상과 딥러닝 기반의 기상정보획득기술 개발

  • 함조환 (국립공주대학교 군사과학정보학과) ;
  • 윤성철 (국립공주대학교 군사과학정보학과) ;
  • 윤천열 (국립공주대학교 군사과학정보학과) ;
  • 박종철 (국립공주대학교 군사과학정보학과)
  • Received : 2025.07.17
  • Accepted : 2025.09.05
  • Published : 2025.09.30

Abstract

The safe operation of aircraft is closely related to weather conditions. Aircraft operating at low altitudes, in particular, are highly susceptible to rapidly changing local weather phenomena occurring near the ground surface. Aviation accidents related to adverse weather conditions occur consistently each year. Furthermore, the frequency of such accidents is expected to rise even further due to the anticipated rapid growth in the aviation transportation market. This study proposes a method for providing accurate and timely real-time weather information to pilots operating at low altitudes. To achieve this, we developed a real-time weather classification model based on a convolutional neural network (CNN), utilizing CCTV video footage originally intended for road surveillance. The developed model is expected to effectively deliver weather-condition information to pilots, thereby practically contributing to enhanced aviation safety in low-altitude flight operations.

Keywords

References

  1. Kwon, B. H., and Kim, C. Y., "Correlation between weather conditions and aviation accidents", 2006 Fall Conference of the Korean Society for Aviation and Aeronautics, Korean Society for Aviation and Aeronautics, Seoul, Korea, 2006, pp. 47-54.
  2. Aviation and Railway Accident Investigation Board, "Casebook of Aviation and Railway Accidents", Ministry of Land, Infrastructure and Transport, 2023, pp. 21-69.
  3. Jo, Y. J., and Kim, S. R., "A study on the necessity of meteorological information for low-altitude aircraft," Journal of the Korean Society for Aviation and Aeronautics, 28(1), 2020, pp. 45-57. https://doi.org/10.12985/ksaa.2020.28.1.045
  4. Kim, N. K., Park, S. H., and Jeong, M. J., "Study on sea fog detection technique using CCTV images and convolutional neural networks", Journal of the Korean Institute of Electronic Communication Sciences, 15(6), 2020, pp. 1081-1087.
  5. Kim, M. S., Lee, M. R.,Park, I. C., and Choi,W. J., "A study on the cause analysis of urban flooding using CCTV images: Focusing on Gangnam Station", 2012 Annual Conference of the Korean Society of Civil Engineers, Korean Society of Civil Engineers, 2012, pp. 624-627.
  6. Byun, J., Jun, C., Lee, J., Kim, H., and Cha, H., "A study on data pre-processing for rainfall estimation from CCTV videos", 2022 Conference of the Korean Water Resources Association, Korean Water Resources Association, 2022.
  7. Naufal, M. F., and Kusuma, S. F., "Weather image classification using convolutional neural network with transfer learning", AIP Conference Proceedings, AIP Publishing, New York, USA, 2470(1), 2022, p. 050004.
  8. Li, J., and Luo, X., "A study of weather-image classification combining ViT and a dual enhanced-attention module," Electronics, 12(5), 2023, p. 1213.
  9. Heo, B. D., Kim, D. W., and Park, M. H., "Automatic highway weather detection technology using traffic surveillance CCTV images", Journal of the Institute of Electronics Engineers of Korea, 46(11), 2019, pp. 42-52.
  10. Krizhevsky, A., Sutskever, I., and Hinton, G. E., "ImageNet classification with deep convolutional neural networks", Advances in Neural Information Processing Systems, 25, 2012, pp. 1097-1105.
  11. He, K.,Zhang, X., Ren, S.,and Sun, J., "Deep residual learning for image recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016, pp. 770-778.
  12. Jung, I., Lee, S., Ha, J., Jeon, H., Jo, Y., and Son, J., "Diagnosis of forecast errors according to data assimilation improvement in the Korea Integrated Model (KIM)", The 60th Anniversary of the Korean Meteorological Society and 2023 Spring Conference, Korean Meteorological Society, 2023. pp. 355.
  13. Park, S. H., Kim, N. K., Jeong, M. J., Hwang, D. H., Enkhjargl, U., Kim, B. R., Park, M. S., Yoon, H. J., and Seo, W. C., "Study on detection technique for coastal debris by using unmanned aerial vehicle remote sensing and object detection algorithm based on deep learning", Journal of the Korea Institute of Electronic Communication Sciences, 15(6), 2020, pp. 1209-1216. https://doi.org/10.13067/JKIECS.2020.15.6.1209
  14. Park, S. J., Cho, G., and Lim, J. H., "A method for tracking and visualizing dynamic objects using CCTV images", Journal of the Korea Land and Geospatial Informatix Corporation, 51(1), 2021, pp. 53-65.
  15. Shin, D. H., and Baek, J. H., "Abnormal vehicle detection using deep learning based on road CCTV data", Journal of the Korea Convergence Society, 12(2), 2021, pp. 1-6. https://doi.org/10.15207/JKCS.2021.12.2.001
  16. Lee, Y. J., "A design of anomaly behavior detection system based on deep learning model using CCTV", Journal of the Korea Institute of Information and Knowledge Technology, 17(2), 2022, pp. 183-191.
  17. Hwang, J. B., Jang, S. C., Jang, J. W., Kim, K. H., and Ha, J. C., "Anomaly detection in industrial control systems using deep learning", Journal of the Korea Academia-Industrial Cooperation Society, 23(1), 2022, pp. 24-32. https://doi.org/10.5762/KAIS.2022.23.1.24
  18. Kim, D. H., Lee, J. H., and Park, S. S., "Fire detection system using deep learning based on CCTV images", 2017 Fall Conference of the Korean Institute of Broadcast and Media Engineers, Korean Institute of Broadcast and Media Engineers, 2017, pp. 139-141.
  19. Kwon, S. H., Ha, C. Y.,and Lee, S. Y., "A study on the application of the agricultural reservoir water level recognition model using CCTV image data", Journal of Korea Water Resources Association, 56(4), 2023, pp. 245-259.
  20. Baek, J. H., Yoon, S. H., Min, J. Y., and Namkoong, S., "An in-tunnel traffic accident detection algorithm using CCTV image processing", Journal of the Korea Information Processing Society, 4(2), 2015, pp. 83-90. https://doi.org/10.3745/KTSDE.2015.4.2.83
  21. Jung, S. W., Kim, E. C.,and Yoo, J. H., "Autonomous deep learning-based child abuse detection system using CCTV images", Journal of Institute of Control, Robotics and Systems, 27(12), 2021, pp. 1029-1037. https://doi.org/10.5302/J.ICROS.2021.21.0134
  22. Splitt, M., Caldwell, B. S., Sharma, V., and Houghton, N., "Scales and attributes of weather information representativeness for pre-flight and en-route advisories for pilots in low altitude operations", AIAA AVIATION 2022 Forum, AIAA, 2022, AIAA 2022-3779.
  23. Wang, X., Zhao, K., Huang, H., Zhou, A., and Chen, H., "Surveillance camera-based deep learning framework for high-resolution precipitation classification", Atmospheric Measurement Techniques Discussions, 2025.
  24. Choi, W., Sung, H., and Chong, K., "AI-driven particulate matter estimation using urban CCTV: A comparative analysis under various experimental conditions", Applied Sciences, 14(21), 2024, pp. 9629.
  25. Li, S., Fu, H., and Lo, W. L., "Meteorological visibility evaluation on webcam weather image using deep learning features", International Journal of Computer Theory and Engineering, 9(6), 2017, pp.455-461. https://doi.org/10.7763/IJCTE.2017.V9.1186
  26. Arkin, E., Yadikar, N., Muhtar, Y., andUbul, K., "Object detection in real-time video surveillance using attention mechanism and transformer-based detection head", Alexandria Engineering Journal, 64, 2025, pp. 3779.
  27. Park, J. H., and Lee, S. H., "Aviation weather service by using the spatial information system", Proceedings of the 24th Fall Conference of the Korea Information Processing Society, Korea, 12(2), 2005, pp. 541-544.
  28. Kim, K. W., "Crisis level measurement of road fog intensity using CCTV cameras on Yeongdong expressway", Proceedings of the 85th Conference of the Korean Society of Transportation, Korean Society of Transportation, Korea, 2021, pp. 203-204.
  29. Byun, J., Kim, H. J., Hwang, S., Baik, J., and Jun, C., "Snowfall intensity estimation based on CNNs using CCTV data," Journal of Korea Water Resources Association, 58(4), 2025, pp. 313-327. https://doi.org/10.3741/JKWRA.2025.58.4.313