基于Y0L0v8n的轻量化森林火灾烟雾检测算法研究

打开文本图片集

中图分类号：TP391.4 文献标识码：A 文章编号：2096-4706（2026）04-0055-05

Research on a Lightweight Forest Fire Smoke Detection Algorithm Based on YOLOv8n

WANGXiaojing，WU Junjie，GUO Ruicheng，XI Chenran （Taiyuan Normal University， Jinzhong，Shanxi 030619）

Abstract： To solve the deployment challenge of the forest fire detection model，a lightweight algorithm for enhancing YOLOv8n isputforward：employing GhostConvlightweightconvolution tosubstitutesome traditionalconvolutions;introducing the C2f-Faster module tooptimizethe feature fusion process，thereby enhancing adaptabilitytocomplexscenarios by integrating multi-scalefeatures;combiing teC2f-Faster-EMAmoduletostrengthenthemodel'sabilitytocapturefeaturesoffaintadblred smoke and earlytiyflames;utilizing theEficient Detect module tosimplifythestructureof thedetection head.Expermental outcomes demonstrate that the optimized model reduces the parameter quantity by 36.7% ，lowers GFLOPs by 51.9% ，and raises the mean average precision by1.4 percentage points，enhancing the detection accuracy on the basis ofbeing lightweight.

Keywords： fire smoke detection; YOLOv8n; lightweighting;Attention Mechanism

0 引言

森林是陆地生态系统的核心，承担着涵养水源、固碳释氧、维护生物多样性等重要生态功能。（剩余6255字）