«Automation and Informatization of the fuel and energy complex»

Fire recognition in panoramic images using convolutional neural network

UDC: 004.896
DOI: 10.33285/2782-604X-2023-12(605)-5-10

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: convolutional neural networks, computer vision, fire detection, machine learning, panoramic image

Annotation:

The article considers a new approach to detecting fires at technological facilities. Its essence lies in using a panoramic CCTV camera and recognizing flame and smoke using a convolutional neural network. The panoramic camera allows covering a larger area with fewer installation points. The article overviews the existing methods of fires visual detection of such as the use of infrared cameras and analyzes the color spectrum of the image. The convolutional neural network of the YOLOv5 architecture, which is used in the work to recognize fires is discussed as well. For a convolutional neural network to work accurately, distortions in a panoramic image should be straightened. To do this, the method of stereoscopic projection, according to which the panoramic image is divided into four projected smaller images with intersection, which are used for recognition by a convolutional neural network is discussed. The use of this method allows identifying fires in the high distortion zone as well as small fires located far from the camera.

Bibliography:

1. Smart City and fire detection using thermal imaging / M. Mazur-Milecka, N. Głowacka, M. Kaczmarek [et al.] // 14th Int. Conf. on Human System Interaction (HSI), Gdańsk, Poland, July 08–10. – 2021. – P. 1–7. – DOI: 10.1109/HSI52170.2021.9538699
2. Chacon-Murguia M.I., Perez-Vargas F.J. Thermal Video Analysis for Fire Detection Using Shape Regularity and Intensity Saturation Features // Lecture Notes in Computer Science. – 2011. – Vol. 6718. Pattern Recognition: Proc. of Third Mexican Conf., Cancun, Mexico, June 29 – July 2, 2011. – P. 118–126. – DOI: 10.1007/978-3-642-21587-2_13
3. Fire Detection Using Computer Vision / T. Zaman, M. Hasan, S. Ahmed, S. Ashfaq // IEEE 61st Int. Midwest Symp. on Circuits and Systems (MWSCAS), Windsor, ON, Canada, Aug. 05–08. – 2018. – P. 356–359. – DOI: 10.1109/MWSCAS.2018.8623842
4. Manjunatha K.C., Mohana H.S., Vijaya P.A. Implementation of Computer Vision Based Industrial Fire Safety Automation by Using Neuro-Fuzzy Algorithms // Int. J. of Information Technology and Computer Science. – 2015. – Vol. 7, No. 4. – P. 14–27. – DOI: 10.5815/ijitcs.2015.04.02
5. Automating Fire Detection and Suppression with Computer Vision: A Multi-Layered Filtering Approach to Enhanced Fire Safety and Rapid Response / S. Mondal, V. Prasad, R. Kumar [et al.] // Fire Technology. – 2023. – Vol. 59, Issue 4. – P. 1555–1583. – DOI: 10.1007/s10694-023-01392-w
6. Convolutional Neural Networks Based Fire Detection in Surveillance Videos / K. Muhammad, J. Ahmad, I. Mehmood [et al.] // IEEE Access. – 2018. – Vol. 6. – P. 18174–18183. – DOI: 10.1109/ACCESS.2018.2812835
7. Flame detection using deep learning / Dongqing Shen, Xin Chen, Minh Nguyen, Wei Qi Yan // 4th Int. Conf. on Control, Automation and Robotics (ICCAR), Auckland, New Zealand, Apr. 20–23. – 2018. – P. 416–420. – DOI: 10.1109/ICCAR.2018.8384711
8. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation / R. Girshick, J. Donahue, T. Darrell, J. Malik // 2014 IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, June 23–28. – 2014. – P. 580–587. – DOI: 10.1109/CVPR.2014.81
9. Mask R-CNN / Kaiming He, G. Gkioxari, P. Dollár, R. Girshick // 2017 IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, Oct. 22–29. – 2017. – P. 2980–2988. – DOI: 10.1109/ICCV.2017.322
10. You Only Look Once: Unified, Real-Time Object Detection / J. Redmon, S. Divvala, R. Girshick, A. Farhadi // 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 27–30. – 2016. – P. 779–788. – DOI: 10.1109/CVPR.2016.91
11. SSD: Single Shot MultiBox Detector / Wei Liu, D. Anguelov, D. Erhan [et al.] // Lecture Notes in Computer Science. – 2016. – Vol. 9905. European Conf. on Computer Vision (ECCV 2016). – Cham: Springer, 2016. – P. 21–37. – DOI: 10.1007/978-3-319-46448-0_2
12. Focal Loss for Dense Object Detection / Tsung-Yi Lin, P. Goyal, R. Girshick [et al.] // 2020 IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2020. – Vol. 42, Issue 2. – P. 318–327. – DOI: 10.1109/TPAMI.2018.2858826
13. Object Detection in Equirectangular Panorama / Wenyan Yang, Yanlin Qian, J.K. Kämäräinen [et al.] // 24th Int. Conf. on Pattern Recognition (ICPR), Beijing, China, Aug. 20–24. – 2018. – P. 2190–2195. – DOI: 10.1109/ICPR.2018.8546070
14. Fucheng Deng, Xiaorui Zhu, Jiamin Ren. Object detection on panoramic images based on deep learning // 3rd Int. Conf. on Control, Automation and Robotics (ICCAR), Nagoya, Japan, Apr. 24–26. – 2017. – P. 375–380. – DOI: 10.1109/ICCAR.2017.7942721
15. Chien-Yao Wang, Bochkovskiy A., Hong-Yuan Mark Liao. Scaled-YOLOv4: Scaling Cross Stage Partial Network // 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, June 20–25. – 2021. – P. 13024–13033. – DOI: 10.1109/CVPR46437.2021.01283