| 注册
首页|期刊导航|液晶与显示|基于YOLOv8s改进的自动驾驶目标检测

基于YOLOv8s改进的自动驾驶目标检测

王龙春 方巍 张丽娟 李东明

液晶与显示2025,Vol.40Issue(5):773-784,12.
液晶与显示2025,Vol.40Issue(5):773-784,12.DOI:10.37188/CJLCD.2024-0290

基于YOLOv8s改进的自动驾驶目标检测

Improved autonomous driving object detection based on YOLOv8s

王龙春 1方巍 2张丽娟 3李东明3

作者信息

  • 1. 南京信息工程大学 计算机学院,江苏 南京 210044||无锡学院 物联网工程学院,江苏 无锡 214105
  • 2. 南京信息工程大学 计算机学院,江苏 南京 210044
  • 3. 无锡学院 物联网工程学院,江苏 无锡 214105
  • 折叠

摘要

Abstract

Aimed at overcoming issues like limited object types,missed detection,and false positives in existing models,an improved object detection algorithm for autonomous driving based on YOLOv8s is proposed.Ordinary convolutions in the YOLOv8s backbone are replaced with RepConv(Re-parameterization Convolution)to enhance target perception while reducing computational load and memory consumption,thereby improving model efficiency.Additionally,an efficient multi-scale attention(EMA)mechanism is introduced after the neck's C2f block to strengthen feature attention and accelerate model convergence.A P2 detection head is also added to improve small object detection capabilities.Finally,the WIoU(Wise-IoU)loss function,featuring a dynamic non-monotonic focusing mechanism and gradient gain allocation strategy,is employed to boost overall detector performance.On a manually labeled Car dataset,the improved model achieved mAP50 and mAP(50-95)scores of 81.2%and 58.4%,respectively,1.5%and 1.2%higher than the original YOLOv8s model.Precision and recall are improved by 1.9%and 0.8%,and the parameter count is decreased from 11.14M to 10.87M.The proposed modules increase detection accuracy while reducing parameter count,making the model more suitable for autonomous driving applications.

关键词

自动驾驶/目标检测/YOLOv8s/EMA/Wise-IoU

Key words

autonomous driving/object detection/YOLOv8s/efficient multi-scale attention/wise-IoU

分类

计算机与自动化

引用本文复制引用

王龙春,方巍,张丽娟,李东明..基于YOLOv8s改进的自动驾驶目标检测[J].液晶与显示,2025,40(5):773-784,12.

基金项目

国家自然科学基金(No.61801439) (No.61801439)

吉林省科技发展计划重点研发项目(No.20210204050YY) (No.20210204050YY)

吉林省生态环境厅科研项目(吉环科字第2021-07号) (吉环科字第2021-07号)

无锡学院引进人才科研启动专项经费(No.2023R004,No.2023R006) Supported by National Natural Science Foundation of China project(No.61801439) (No.2023R004,No.2023R006)

Key R&D Project of Jilin Province Science and Technology Development Plan(No.20210204050YY) (No.20210204050YY)

Research Project of Jilin Provincial Department of Ecology and Environment(Jihuan Kezi No.2021-07) (Jihuan Kezi No.2021-07)

Wuxi University's Special Fund for Talent Introduction and Scientific Research Launch(No.2023R004,No.2023R006) (No.2023R004,No.2023R006)

液晶与显示

OA北大核心

1007-2780

访问量0
|
下载量0
段落导航相关论文