计算机工程与应用2025，Vol.61Issue(21)：81-93,13.DOI:10.3778/j.issn.1002-8331.2503-0397
LFDS-YOLO:多尺度特征融合的轻量化航拍路面病害检测算法
LFDS-YOLO:Lightweight Aerial Pavement Damage Detection Algorithm with Multi-Scale Fea-ture Fusion
摘要
Abstract
Current aerial pavement distress detection algorithms suffer from redundant feature extraction,high computa-tional complexity,inefficient global attention mechanisms,and limited multi-dimensional feature extraction in convolu-tional attention,leading to constrained detection accuracy and real-time performance.To address these issues,this paper proposes LFDS-YOLO,a lightweight detection network based on multi-scale feature fusion and enhanced attention mech-anisms.This paper reconstructs a feature pyramid structure(LF_PANet)by removing large-scale feature branches,designs a dynamic feature extraction block(DFEB)for adaptive resource allocation.A multi-head column attention mech-anism(MHCol-Attn)is introduced,accelerated by FlashAttention to optimize training efficiency.A superior lightweight coordinate attention(SLCA)is proposed to enhance multi-dimensional feature extraction.Unstructured pruning is employed to compress model size and boost inference speed.Experimental results on the UAV-PDD2023 dataset demon-strate that LFDS-YOLO achieves a 3.5 percentage points higher mAP than YOLOv11s,while reducing parameters,com-putational complexity,and model size by 53.2%,6.5%,and 52.2%,respectively,with a detection speed of 95 FPS,vali-dating its effectiveness in aerial pavement distress detection.关键词
路面病害检测/YOLOv11s/特征融合/注意力机制/轻量化Key words
pavement defect detection/YOLOv11s/feature fusion/attention mechanism/lightweight分类
计算机与自动化引用本文复制引用
李勇,沈坚..LFDS-YOLO:多尺度特征融合的轻量化航拍路面病害检测算法[J].计算机工程与应用,2025,61(21):81-93,13.基金项目
重庆市技术创新与应用发展专项重点项目(CSTB2024TIAD-KPX0027) （CSTB2024TIAD-KPX0027）
重庆市建设科技计划项目(城科字2018(1-1-7)). （城科字2018(1-1-7）
