湖北汽车工业学院学报2026，Vol.40Issue(1)：1-7,7.DOI:10.3969/j.issn.1008-5483.2026.01.001
基于改进YOLOv7的复杂道路目标检测算法
Complex Road Target Detection Algorithm Based on Improved YOLOv7
摘要
Abstract
To address the challenges of low detection accuracy for dense targets in complex autonomous driving road scenarios,which often lead to missed detections and false alarms,an improved YOLOv7 target detection algorithm was proposed.The algorithm introduced a small-target detection layer to the basic model architecture,enhancing the receptive field and improving feature learning for small targets.The K-means++algorithm was employed for dataset clustering,ensuring that anchor boxes better align with actual targets.A two-level routing mechanism was integrated into the SPPCSPC module,enabling dynamic querying and sparse perception capabilities of the model.Additionally,the original CIoU loss function was replaced with the EIoU loss function to accelerate model convergence.Experimental re-sults demonstrate that the proposed method achieves an mAP@0.5 of 94.9%on the KITTI dataset,rep-resenting a 3.1 percentage point improvement over the original algorithm.On the SODA10M dataset,it attains an mAP@0.5 of 67.8%,a 5.6 percentage point increase.This approach effectively mitigates small-target detection challenges in complex autonomous driving road environments.关键词
YOLOv7/自动驾驶/小目标检测头/K-means++/双层路由注意力/EIOU函数Key words
YOLOv7/autonomous driving/small target detection head/K-means++/two-level routing attention/EIOU function分类
交通工程引用本文复制引用
唐海,张彬,吴文欢,徐洪胜,饶宇锋,冯立..基于改进YOLOv7的复杂道路目标检测算法[J].湖北汽车工业学院学报,2026,40(1):1-7,7.基金项目
湖北省自然科学基金(2025AFD239) （2025AFD239）
湖北省重点研发计划项目(2023EHA018) （2023EHA018）
湖北省教育科学规划课题(2020GA045,2022GA049) （2020GA045,2022GA049）
