Journal of the Korean Institute of Electrical and Electronic Material Engineers (한국전기전자재료학회논문지)

The Korean Institute of Electrical and Electronic Material Engineers (한국전기전자재료학회)
권호 표지
DOI QR코드

DOI QR Code

Research on Improving the Performance of YOLO-Based Object Detection Models for Smoke and Flames from Different Materials

다양한 재료에서 발생되는 연기 및 불꽃에 대한 YOLO 기반 객체 탐지 모델 성능 개선에 관한 연구

  • Heejun Kwon (Department of Fire and Disaster Prevention, Semyung University) ;
  • Bohee Lee (Department of Electrical Engineering, Semyung University) ;
  • Haiyoung Jung (Department of Fire and Disaster Prevention, Semyung University)
  • Received : 2023.12.05
  • Accepted : 2024.01.06
  • Published : 2024.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

Keywords

Acknowledgement

이 논문은 2023학년도 세명대학교 교내학술연구비 지원에 의해 수행된 연구임.

References

  1. T. Kim, M. Yoon, and J. Lee, J. Korean Soc. Hazard Mitigation, 19, 1 (2019). doi: https://doi.org/10.9798/KOSHAM.2019.19.2.1 
  2. J. S. You, K. S. Kang, J. S. Lee, and Y. J. Chung, Appl. Chem. Eng., 34, 421 (2023). doi: https://doi.org/10.14478/ace.2023.1056 
  3. J. You and Y. J. Chung, Fire Sci. Eng., 33, 69 (2019). doi: https://doi.org/10.7731/KIFSE.2019.33.1.069 
  4. A. H. Awad, R. E. Gamasy, A.A.E. Wahab, and M. H. Abdellatif, Eng. Sci., 4, 34 (2019). doi: https://doi.org/10.11648/j.es.20190402.12 
  5. J. G. Kim, C. I. Park, J. W. Jung, and S. G. Kim, J. Soc. Disaster Inf., 17, 60 (2021). doi: https://doi.org/10.15683/kosdi.2021.3.31.060 
  6. S. K. Kim, S. G. Choi, and C. H. Lee, Fire Sci. Eng., 31, 42 (2017). doi: https://doi.org/10.7731/KIFSE.2017.31.1.042 
  7. C. S. Park and T. H. Oh, Korean J. Secur. Convergence Manage., 10, 249 (2021). doi: https://doi.org/10.24826/kscs.10.6.16 
  8. S. M. Park and S. K. Kim, Fire Sci. Eng., 31, 111 (2017). doi: https://doi.org/10.7731/KIFSE.2017.31.4.111 
  9. S. K. Kim, D. S. Gum, and C. H. Lee, Fire Sci. Eng., 29, 57 (2015). doi: https://doi.org/10.7731/KIFSE.2015.29.5.057 
  10. S. Choi, S. Kim, and H. Jung, Electronics, 12, 2579 (2023). doi: https://doi.org/10.3390/electronics12122579 
  11. K. M. Shong, Y. S. Roh, and H. R. Kwak, J. Korean Inst. Illum. Electr. Install. Eng., 20, 71 (2006). doi: https://doi.org/10.5207/JIEIE.2006.20.8.071 
  12. M. S. Park and C. S. Choi, Fire Sci. Eng., 34, 101 (2020). doi: https://doi.org/10.7731/KIFSE.96dca8eb 
  13. B. S. Koo, G. H. Jung, A. H. Kim, and H. J. Lee, Proc. Korea Information Processing Society Conference (2020) p. 312. doi: https://doi.org/10.3745/PKIPS.y2020m11a.312 
  14. J. S. Park, H. T. Kim, and Y. S. Yu, J. Korea Inst. Electron. Commun. Sci., 6, 206 (2011). doi: https://doi.org/10.13067/JKIECS.2011.6.2.206 
  15. H. J. Kim, D. H. Lee, A. Niaz, C. Y. Kim, A. A. Memon, and K. N. Choi, IEEE Access, 9, 11694 (2021). doi: https://doi.org/10.1109/ACCESS.2021.3051424 
  16. R. Girshick, J. Donahue, T. Darrell, and J. Malik, 2014 IEEE Conference on Computer Vision and Pattern Recognition (IEEE, Columbus, USA, 2014) p. 580. doi: https://doi.org/10.1109/cvpr.2014.81 
  17. Q. Zhang, J. Xu, L. Xu, and H. Guo, Proc. 2016 International Forum on Management, Education and Information Technology Application (Atlantis Press, 2016). doi: https://doi.org/10.2991/ifmeita-16.2016.105 
  18. P. Li and W. Zhao, Case Stud. Therm. Eng., 19, 100625 (2020). doi: https://doi.org/10.1016/j.csite.2020.100625 
  19. R. Girshick, Proc. 2015 IEEE International Conference on Computer Vision (ICCV) (IEEE, Santiago, Chile, 2015) p. 1440. doi: https://doi.org/10.1109/ICCV.2015.169 
  20. S. Ren, K. He, R. Girshick, and J. Sun, IEEE Trans. Pattern Anal. Mach. Intell., 39, 1137 (2017). doi: https://doi.org/10.1109/tpami.2016.2577031 
  21. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Las Vegas, USA, 2016) p. 779. doi: https://doi.org/10.1109/CVPR.2016.91 
  22. B. V. Kumar, S. Abirami, R. J. Bharathi Lakshmi, R. Lohitha, and R. B. Udhaya, IOP Conference Series: Materials Science and Engineering (IOP Publishing Ltd, Tamil Nadu, India, 2019). doi: https://doi.org/10.1088/1757-899X/590/1/012062 
  23. G. Jocher, A. Chaurasia, A. Stoken, J. Borovec, NanoCode012, Y. Kwon, T. Xie, K. Michael, J. Fang, imyhxy, Lorna, C. Wong, Y. Zeng, V. Abhiram, D. Montes, Z. Wang, C. Fati, J. Nadar, Laughing, UnglvKitDe, tkianai, yxNONG, P. Skalski, A. Hogan, M. Strobel, M. Jain, L. Mammana, and xylieong, Zenodo, Ultralytics/yolov5: v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai Integrations, (2022). https://zenodo.org/records/7002879 
  24. K. M. Ting, Confusion Matrix, Encyclopedia of Machine Learning and Data Mining (2017) p. 260. doi: https://doi.org/10.1007/978-1-4899-7687-1_50 
  25. R. Padilla, S. L. Netto, and E.A.B. da Silva, Proc. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP) (IEEE, Niteroi, Brazil, 2020) p. 237. doi: https://doi.org/10.1109/IWSSIP48289.2020.9145130