| 注册
首页|期刊导航|光学精密工程|复杂天气条件下基于YOLO-CGT的自动驾驶车辆检测

复杂天气条件下基于YOLO-CGT的自动驾驶车辆检测

伍锡如 郝家琦 赵一波 何佳融 葛舒雅 梁诗意 吴思明

光学精密工程2025,Vol.33Issue(19):3135-3149,15.
光学精密工程2025,Vol.33Issue(19):3135-3149,15.DOI:10.37188/OPE.20253319.3135

复杂天气条件下基于YOLO-CGT的自动驾驶车辆检测

Autonomous vehicle detection in complex weather based on YOLO-CGT

伍锡如 1郝家琦 1赵一波 1何佳融 1葛舒雅 1梁诗意 1吴思明1

作者信息

  • 1. 桂林电子科技大学 电子工程与自动化学院,广西 桂林 541004||桂林电子科技大学 智能综合自动化广西高校重点实验室,广西 桂林 541004
  • 折叠

摘要

Abstract

To mitigate the pronounced decline in vehicle detection performance caused by object blur and occlusion under adverse weather conditions,an enhanced YOLOv8-based vehicle detection algorithm,designated YOLO-CGT,is proposed.Tailored for vehicle-mounted camera imagery,the algorithm incor-porates multiple enhancements to the YOLOv8 architecture to substantially improve detection robustness in challenging environments.Specifically,a multi-scale residual aggregation module replaces the original C2f module in the backbone network to increase exploitation of raw feature information and to alleviate gra-dient vanishing associated with greater network depth.A spatial aggregation module is incorporated to in-tegrate global information extraction with local feature perception.Moreover,a lightweight dynamic detec-tion head is developed to balance detection accuracy and computational efficiency.The conventional IoU metric is supplanted by the Inner-Minimum Points Distance Intersection over Union(Inner-MPDIoU)to reduce bounding-box overlap issues.Trained and validated on a vehicle dataset captured under complex weather conditions,the proposed method attains an average detection accuracy of 81.4%-an improvement of 6.3%-with 3.259×106 model parameters and a computational cost of 9.7 GFLOPs,demonstrating suitability for lightweight deployment while delivering substantial accuracy gains.These results provide a robust foundation for the safe and reliable operation of autonomous driving systems.

关键词

自动驾驶/车辆检测/YOLOv8/复杂天气/多尺度特征

Key words

intelligent driving/vehide detection/YOLOv8/complex weather/multi-scale features

分类

计算机与自动化

引用本文复制引用

伍锡如,郝家琦,赵一波,何佳融,葛舒雅,梁诗意,吴思明..复杂天气条件下基于YOLO-CGT的自动驾驶车辆检测[J].光学精密工程,2025,33(19):3135-3149,15.

基金项目

国家自然科学基金地区科学基金资助项目(No.62263005) (No.62263005)

广西高校人工智能与信息处理重点实验室开放基金重点项目(No.2024GXZDSY013,No.2022GXZDSY004) (No.2024GXZDSY013,No.2022GXZDSY004)

桂林电子科技大学研究生教育创新计划资助项目(No.2025YCXS138) (No.2025YCXS138)

光学精密工程

OA北大核心

1004-924X

访问量0
|
下载量0
段落导航相关论文