A Robust Fire Detection Model via Convolution Neural Networks for Intelligent Robot Vision Sensing

• Main Authors: An, Q. (Author), Chen, X. (Author), Huang, W. (Author), Shi, R. (Author), Yang, Y. (Author), Zhang, J. (Author)
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: Clustering algorithms; Computer vision; Convolution; Convolution neural network; deep learning; Deep learning; detection; Detection; Detection models; dynamic convolution; Dynamic convolution; F1 scores; Fire detection; Fire detectors; Fire-detection method; Fires; Intelligent robots; Learning methods; Smoke; YOLOv5
• Online Access: View Fulltext in Publisher

 Accurate fire identification can help to control fires. Traditional fire detection methods are mainly based on temperature or smoke detectors. These detectors are susceptible to damage or in-terference from the outside environment. Meanwhile, most of the current deep learning methods are less discriminative with respect to dynamic fire and have lower detection precision when a fire changes. Therefore, we propose a dynamic convolution YOLOv5 fire detection method using a video sequence. Our method first uses the K‐mean++ algorithm to optimize anchor box clustering; this significantly reduces the rate of classification error. Then, the dynamic convolution is intro-duced into the convolution layer of YOLOv5. Finally, pruning of the network heads of YOLOv5’s neck and head is carried out to improve the detection speed. Experimental results verify that the proposed dynamic convolution YOLOv5 fire detection method demonstrates better performance than the YOLOv5 method in recall, precision and F1‐score. In particular, compared with three other deep learning methods, the precision of the proposed algorithm is improved by 13.7%, 10.8% and 6.1%, respectively, while the F1‐score is improved by 15.8%, 12% and 3.8%, respectively. The method described in this paper is applicable not only to short‐range indoor fire identification but also to long‐range outdoor fire detection. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.