All Issue

2023 Vol.19, Issue 4 Preview Page

Original Article

31 December 2023. pp. 968-975
Abstract
Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.
연구목적: 화재 탐지시 불꽃/연기의 오탐지율이 높은 것을 확인하고 오탐지율을 낮추기 위해 화재 상황을 인식하여 분류하는 방법과 데이터셋을 제안하고자 한다. 연구방법: 동영상을 학습데이터로 활용하여 화재 상황의 특징을 추출하여 분류모델에 적용하고, 평가는 한국정보화진흥원(NIA)에서 진행하는 화재 데이터셋을 이용하여 Yolov8, Slowfast의 모델 성능을 비교 및 분석하였다. 연구결과: YOLO는 배경의 영향에 따라 탐지 성능이 민감하게 변화하며, 화재의 규모가 너무 크거나 작을 때에도 화재를 제대로 감지하지 못했다. SlowFast는 동영상의 시간 축을 같이 학습하기 때문에 비정형 객체에 대해 주변이 흐리거나 밝아 형상을 명확하게 유추할 수 없는 상황에서도 우수하게 화재를 탐지하는 것을 확인했다. 결론: 화재 탐지율은 이미지 데이터 방식보다는 동영상 기반의 인공지능 인식(Detection) 모델을 활용했을 때 더 적절했음을 확인했다.
References
  1. Ang G. Aritejh Kr Goil, Henryk Chan, Jieyi Jeric Lew, Xin Chun Lee, Raihan Bin Ahmad Mustaffa, Timotius Jason, Ze Ting Woon, Bingquan Shen. (2023). "A novel application for real-time arrhythmia detection using YOLOv8." arXiv preprint arXiv:2305.16727.
  2. Feichtengofer, C, Haoqi Fan Jitendra Malik Kaiming He. (2019). "SlowFast networks for video recognition." Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1-10. 10.1109/ICCV.2019.00630
  3. Hu C., Tang, P., Jin, W., He, Z., Li, W. (2018). "Real-time fire detection based on deep convolutional long-recurrent networks and optical flow method." Proceedings of the 37th Chinese Control Conference. pp. 9061-9066. 10.23919/ChiCC.2018.8483118
  4. Huo, Y., Zhang, Q., Zhang, Y., Zhu, J., Wang, J. (2022). "3DVSD: An end-to-end 3D convolutional object detection network for video smoke detection." Fire Safety Journal, Vol. 134, pp. 1-11. 10.1016/j.firesaf.2022.103690
  5. Kim, K.-J., Jang, I.-S., Lim, K.-T. (2021a). "Construction of wild-fire smoke data-set and comparative analysis of detection method based on deep neural network." Electronics and Telecommunications Research Institute Winter Conference, pp. 1172-1173.
  6. Jeong, Y.-S., Kim, Y.-W., Yim, J.-I. (2023). "A study on the development of an automatic classification system for life safety prevention service reporting images through the development of AI learning model and AI model serving server." Journal of the Society of Disaster Information, Vol. 19, No. 2, pp. 432-438.
  7. Jin, C., Wang, T., Alhusaini, N., Zhao, S., Liu, H., Xu, K., Zhang, J. (2023). "Video fire detection methods based on deep learning : dataset, methods, and future directions." Fire, Vol. 6, No. 8, pp. 3-15. 10.3390/fire6080315
  8. Jocher, G. (2023). YOLO by Ultralytics (Version 8.0.0). https://github.com/ultralytics/ultralytics
  9. Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, A., Suleyman, M., Zisserman, A. (2017) "The kinetics human action video dataset." arXiv preprint.
  10. Khan, F., Xu, Z., Sun, J., Khan, F.M., Ahmed, A., Zhao, Y. (2022). "Recent advances in sensors for fire detection." Sensors, Vol. 22, No. 9, pp. 3-10. 10.3390/s22093310 35590999 PMC9100504
  11. Kim, C.Y., Lee, H.-S., Lee, K.Y. (2022). "Implementation of a deep learning based realtime fire alarm system using a data augmentation" Journal of IKEEE, Vol. 26, No. 3, pp. 468-474.
  12. Kim, J.-S., Park, S.-M., Hong, C.-H., Park, S.-H., Lee, J.-W. (2022). "Development of AI detection model based on CCTV image for underground utility tunnel." Journal of the Society of Disaster Information, Vol. 18, No. 2, pp. 364-373.
  13. Kim, K.-J., Jang, I.-S., Lim, K.-T. (2021b). "Analysis of video-based fire detection learning model".Electronics and Telecommunications Research Institute Summer Conference, pp. 240-241.
  14. Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Dollár, P. (2014). "Miscrosoft COCO common objects in context." European Conference on Computer Vision. pp. 740-755. 10.1007/978-3-319-10602-1_48
  15. Na, Y.-M., Hyun, D.-H., Park, D.-H., Hwang, S.-H., Lee, S.-H. (2020). "AI fire detection & notification system." The Korea Society of Computer and Information, Vol. 25, No. 12, pp. 63-71.
  16. Nam, G.-T., Seo, K.-J., Choi, D.-C. (2022). "A study on the development of AI-based fire fighting facility design technology through image recognition." Journal of the Society of Disaster Information, Vol. 18, No. 4, pp. 883-890.
  17. Park, J., Cho, Y.K, Kim, S. (2022). "Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic." International-Journal-of-Applied-Earth-Observation-and-Geoinformation, Vol. 115, 103111. 10.1016/j.jag.2022.103111
  18. Yan, C., Wang, Q., Zhao, Y., Zhang, X. (2023). "YOLOv5-CSF: An improved deep convolutional neural network for flame detection." Application of Soft Computing, Vol. 27, pp. 19013-19023. 10.1007/s00500-023-08136-6
Information
  • Publisher :The Korean Society of Disaster Information
  • Publisher(Ko) :한국재난정보학회
  • Journal Title :Journal of the Society of Disaster Information
  • Journal Title(Ko) :한국재난정보학회논문집
  • Volume : 19
  • No :4
  • Pages :968-975