International Journal of Advanced Culture Technology

  • 제10권4호
  • /
  • Pages.536-546
  • /
  • 2022
  • /
  • 2288-7202(pISSN)
  • /
  • 2288-7318(eISSN)
국제문화기술진흥원 (The International Promotion Agency of Culture Technology)
권호 표지
DOI QR코드

DOI QR Code

Implementation of YOLOv5-based Forest Fire Smoke Monitoring Model with Increased Recognition of Unstructured Objects by Increasing Self-learning data

  • Gun-wo, Do (Dept. of Computer Engineering, Dong-eui Univ.) ;
  • Minyoung, Kim (Research Institute of ICT Fusion and Convergence, Dong-eui Univ.) ;
  • Si-woong, Jang (Dept. of Computer Engineering, Dong-eui Univ.)
  • 투고 : 2022.11.26
  • 심사 : 2022.12.09
  • 발행 : 2022.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

키워드

과제정보

This Work was supported by Dong-eui University Foundation Grant (2021). Also, This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program(IITP-2022-2020-0-01791) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation). Finally, Thank you to Donggyu Choi (dgchoi @deu.ac.kr) senior researcher who helped me a lot when I wrote this paper.

참고문헌

  1. M. N. Jang and Y. J. Lee, "Selecting Forest Fire Vulnerable Regions Based on Biophysical and Socioeconomic Factors in Gangwon Province," Crisisonomy (KRCEM), Vol. 16, No. 3, pp.133-144, 2022. DOI : http://doi.org/10.14251/crisisonomy.2020.16.3.133 
  2. S. J. Oh, "Database Design for Growth Prediction of Forest using Drone Photo," The Journal of the Convergence on Culture Technology (JCCT), Vol. 6, No. 4, pp.709-714, 2020. DOI: http://koreascience.or.kr/article/JAKO202034965718305.page  https://doi.org/10.17703/JCCT.2020.6.4.709
  3. B. C. Ko, "IoT technology for wildfire disaster monitoring," Broadcasting and Media Magazine, Vol. 20, No. 3, pp.91-98, 2015. DOI: https://koreascience.kr/article/JAKO201524848982493.page 
  4. YOLOv5, https://github.com/ultralytics/yolov5 
  5. S. Lee, B. Shin, B. Song, S. Song, S. An, J. Kim and H. Lee, "Wild Fire Monitoring System using the Image Matching," The Journal of the Korea Contents Association, Vol.13, No. 6, pp.40-47, 2013. DOI: https://doi.org/10.5392/JKCA.2013.13.06.040 
  6. YOLO: Real-Time Object Detection, https://pjreddie.com/darknet/yolo/ 
  7. Y. Kim and H. Cho, "Detecting Location of Fire in Video Stream Environment using Deep Learning," The Transactions of the Korean Institute of Electrical Engineers, Vol.69, No. 3, pp.474-479, 2020. DOI: http://doi.org/10.5370/KIEE.2020.69.3.474 
  8. J. Pack and D. Kang, "RFDSys: Real-time Fire Detection System using AIoT-based K-NN and Motion Detection," Journal of Korean Institute of Information Technology (JKIIT), Vol. 19, No. 10, pp.115-123, 2021. DOI: http://dx.doi.org/10.14801/jkiit.2021.19.10.115 
  9. Y. Lee and J. Shim, "Deep Learning and Color Histogram based Fire and Smoke Detection Research," International Journal of Advanced Smart Convergence(IJASC), Vol. 8, No. 2, pp.116-125, 2019. DOI: https://doi.org/10.7236/IJASC.2019.8.2.116 
  10. J. Park, Y. Kim, "A Study on Deep Learning Performance Improvement Based on YOLOv5," in Proc. 78th the Korean Institute of Communication Sciences Conference, pp. 1592-1593, Jun. 22-24, 2022. 
  11. C. Wang, H. M. Liao, I. Yeh, Y. Wu, P. Chen and J. Hsieh, "CSPNet: A New Backbone that can Enhance Learning Capability of CNN," in Proc. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.1-10, Jun.14-19, 2020. 
  12. Y. H. Jeon, I. S. Kim and M. G. Lee, "Analysis of Results according to the YOLOv5 Model," in Proc. Korean Society for Precision Engineering 2021 Autumn Conference, pp.508, Nov.24-26, 2021. 
  13. About mAP(mean Average Precision), https://ctkim.tistory.com/79 
  14. T. Wang, S. Oh, H. Lee, D. Choi, J. Jang and M. Kim, "A Study on the Implementation of Real-Time Marine Deposited Waste Detection AI System and Performance Improvement Method by Data Screening and Class Segmentation," The Journal of the Convergence on Culture Technology (JCCT), Vol. 8, No. 3, pp. 571-580, 2022. DOI: http://dx.doi.org/10.17703/JCCT.2022.8.3.571 
  15. J. S. Kim and I. Y. Hong, "Analysis of Building Object Detection Based on the YOLO Neural Network Using UAV Images", Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vo1.39, No. 6, pp. 381-392, 2021. DOI: https://doi.org/10.7848/ksgpc.2021.39.6.381 
  16. Roboflow, https://roboflow.com/