Title: FlameNet: a lightweight convolutional neural network for flame detection and localisation
Authors: Xing Hu; Mei Li; Dawei Zhang
Addresses: School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China ' School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China ' School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China
Abstract: Accurately and efficiently detecting and localising the flame is critical for preventing fire disasters. However, most high-performance deep models require high hardware resources, making them hard to deploy on edge or mobile intelligent devices. This paper proposes a lightweight deep convolutional neural network, called FlameNet, for flame detection and localisation. The proposed FlameNet is derived from YOLOv4 with the following modifications: First, MobileNetV2 replaces the CSPDarknet53 as the new backbone network of YOLOv4; Second, the Coordinate Attention module is added to the inverted residual linear bottleneck of MobileNetV2; Third, the Depthwise Separable Convolutions is used in PANet of YOLOv4. There is no large-scale public dataset available, and we produced a real-world flame (RWF) dataset containing 13,129 images. Qualitative and quantitative analysis and comparisons of experimental results demonstrate that the accuracy and efficiency of the proposed FlameNet for flame detection out-perform the original YOLOv4 and the other relative models.
Keywords: deep learning; flame detection and localisation; FlameNet; lightweight model; MobileNetV2; PANet.
International Journal of Vehicle Design, 2023 Vol.91 No.1/2/3, pp.87 - 106
Received: 03 Oct 2021
Accepted: 10 Jan 2022
Published online: 22 May 2023 *