Light-YOLOv8-Flame: A Lightweight High-Performance Flame Detection Algorithm
Authors:
- Jiawei LanJLJiawei Lan
- Ye TaoYTYe Tao
- Zhibiao WangZWZhibiao Wang
- Haoyang YuHYHaoyang Yu
- Wenhua CuiWCWenhua Cui
Preprint
Abstract
Fire detection algorithms, particularly those based on computer vision, encounter significant challenges such as high computational costs and delayed response times, which hinder their application in real-time systems. To address these limitations, this paper introduces Light-YOLOv8-Flame, a lightweight flame detection algorithm specifically designed for fast and efficient real-time deployment. The proposed model enhances the YOLOv8 architecture through the substitution of the original C2f module with the FasterNet Block module. This new block combines Partial Convolution (PConv) and Convolution (Conv) layers, reducing both computational complexity and model size. A dataset comprising 7,431 images, representing both flame and non-flame scenarios, was collected and augmented for training purposes. Experimental findings indicate that the modified YOLOv8 model achieves a 0.78% gain in mean average precision (mAP) and a 2.05% boost in recall, while reducing the parameter count by 25.34%, with only a marginal decrease in precision by 0.82%. These findings highlight that Light-YOLOv8-Flame offers enhanced detection performance and speed, making it well-suited for real-time fire detection on resource-constrained devices.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- Focal and efficient IOU loss for accurate bounding box regressionNeurocomputing, 2022
- Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance SegmentationIEEE Transactions on Cybernetics, 2021
- Fire Detection Using Multi Color Space and Background ModelingFire Technology, 2020