All Issue

2022 Vol.18, Issue 2 Preview Page

Original Article

Development of AI Detection Model based on CCTV Image for Underground Utility Tunnel

지하공동구의 CCTV 영상 기반 AI 연기 감지 모델 개발

김정수1*, 박상미2, 홍창희3, 박승화4, 이재욱4

Jeongsoo Kim1*, Sangmi Park2, Changhee Hong3, Seunghwa Park4, Jaewook Lee4

1Research Specialist, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction, Goyang, Republic of Korea
1Post-doctor Researcher, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction, Goyang, Republic of Korea
3Research Fellow, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction, Goyang, Republic of Korea
4Senior Researcher, Korea Institute of Civil Engineering and Building Technology, Department of Future and Smart Construction, Goyang, Republic of Korea
30 June 2022. pp. 364-373
PDF Citation
Abstract
Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.
Keywords
Underground utility tunnel
Smoke
Deep learning
Object detection
Irregular object
연구목적: 본 논문은 지하공동구의 초기 화재 감지를 위해 CCTV를 활용한 AI 연기 객체 감지 모델을 개발하는데 목적이 있다. 연구방법: 비정형성이 높은 연기 객체의 감지 성능을 제고하기 위해 화재 감지에 특화된 딥러닝 객체 감지 모델을 지하공동구 연기 감지에 특화되도록 학습시켰고, 학습데이터셋의 정제 및 학습 중 Gradient explosion 완화 등 감지 성능 개선을 위한 방법들을 적용해 모델 결과를 비교하였다. 연구결과: 결과는 제안된 방법을 통해 모델 성능을 향상시켰고 mAP 등의 지표를 평가를 통해 개발 모델이 우수한 성능을 보유하고 있음을 보여준다. 최종 모델은 지하공동구 환경의 연기에 대해 미탐이 낮은 반면 오탐이 다수 발견되는 성능을 보였다. 결론: 본 논문의 모델은 지하공동구 관리시스템과 연계를 통해 보완함으로써 지하공동구의 연기 객체 감지에 활용할 수 있을 것으로 판단된다.
키워드
지하공동구
연기
딥러닝
객체 인식
비정형 객체
References
  1. Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014). "Rich feature hierarchies for accurate object detection and semantic segmentation." In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, US, pp. 580-587. 10.1109/CVPR.2014.81
  2. Khan, S., Muhammad, K., Hussain, T., Ser, J. D., Cuzzolin, F., Bhattacharyya, S., Akhtar, Z., de Albuquerque, V. (2021). "DeepSmoke: Deep learning model for smoke detection and segmentation in outdoor environments." Expert Systems with Applications, Vol. 182, No. 15, 115125. 10.1016/j.eswa.2021.115125
  3. Kim, D., Jeong, J., Park, S., Go, J., Yeom, C. (2020). "A study on the application of optimal evacuation route through evacuation simulation system in case of fire." Journal of the Society of Disaster Information, Vol. 16, No. 1, pp. 96-110. (In Korean)
  4. Kim, J., Lee, C.-W., Park, S.-H., Lee, J.-H., Hong, C.-H. (2020). "Development of fire detection model for underground utility facilities using deep learning: Training data supplement and bias optimization." Journal of the Korea Academia-Industrial Cooperation Society , Vol. 21, No. 12, pp.320-330. (In Korean)
  5. Lee, B.-Y. (2017). Deep Learning from Scratch, Hanbit Media, Seoul, Korea (In Korean)
  6. Lee, J.-S., Lee, S.-K., Kim, D.-W., Hong, S.-J., Yang, S.-I. (2018). "Trends on object detection techniques based on deep learning." Electronics and Telecommunications Trends, Vol. 33, No. 4, pp. 23-32. (In Korean)
  7. Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016). "You only look once: Unified, real-time object detection." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, US, pp. 779-788. 10.1109/CVPR.2016.91
  8. Ren, S., He, K., Girshick, R., Sun, J. (2016). "Faster R-CNN: Towards real-time object detection with region proposal networks." Advances in Neural Information Processing Systems, Vol. 28, pp. 1-9.
  9. Ryu, D., Kwak, D. (2020) "A study on flame and smoke detection algorithm using convolutional neural netwrok based on deep learning." Journal of Korean Society of Hazard Mitigation, Vol. 20, No. 1, pp. 223-232. (In Korean) 10.9798/KOSHAM.2020.20.1.223
  10. Saponara, S., Elhanashi, A., Gagliardi, A. (2021). "Real-time video fire/smoke detection based on CNN in antifire surveillance systems." Journal of Real-Time Image Processing, Vol. 18, No. 3, pp. 889-900. 10.1007/s11554-020-01044-0
  11. Son, G., Son, S. (2021). "A study on fire alarm test of Iot multi-fire detector combined smoke/CO and smoke/temperature sensors." Journal of the Society of Disaster Information, Vol. 17, No. 2, pp. 236-244. (In Korean)
  12. Yang, J., Chen, F., Zhang, W. (2008). "Visual-based smoke detection using support vector machine." 2008 in Fourth International Conference on Natural Computation, Jinan, China, pp. 301-305. 10.1109/ICNC.2008.219
  13. Yuan, F. (2008). "A fast accumulative motion orientation model based on integral image for video smoke detection." Pattern Recognition Letter, Vol. 29, No. 7, pp.925-932. 10.1016/j.patrec.2008.01.013
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 : 18
  • No :2
  • Pages :364-373
  • DOI :https://doi.org/10.15683/kosdi.2022.6.30.364
Journal Informaiton Journal of the Society of Disaster Information Journal of the Society of Disaster Information
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close