摘要
在自动驾驶领域,现有的交通标志检测方法在检测复杂背景中的标志时存在着漏检或误检的问题,降低了智能汽车的可靠性。对此,提出了一种改进YOLOv5-S的实时交通标志检测算法。在特征提取网络中融合坐标注意力机制,通过构建目标的长范围依赖来捕获物体的位置感知,使得算法聚焦于重点的特征区域;引入Focal-EIoU损失函数来取代CIoU,使其更关注高质量的分类样本,提高对难分类样本的学习能力,减少漏检或者误检的问题;在网络中融合轻量级卷积技术GSConv,降低模型的计算量。增加新的小目标检测层,通过更丰富的特征信息提高小尺寸标志的检测效果。实验结果表明,改进方法的mAP@0.5和mAP@0.5:0.95分别为88.1%和68.5%,检测速度达到了83 FPS,能够满足实时可靠的检测需求。
In the field of autonomous driving,existing traffic sign detection methods have problems with missed or incor-rect sign detection in complex backgrounds,reducing the reliability of intelligent vehicles.To address this issue,a real-time traffic sign detection algorithm is proposed to enhance YOLOv5-S.Firstly,the coordinate attention mechanism is inte-grated into the feature extraction network to perceive the location of the object by establishing long-term dependencies on the target,making the algorithm focus on high-priority regions.Secondly,the Focal-EIoU loss function is used to replace the CIoU,allowing the network to focus more on high-quality classification samples,improving the network’s ability to learn from difficult samples and reducing the occurrence of missed or false detections.Next,the lightweight convolution technique GSConv is integrated into the network to reduce the complexity of the model.Finally,a new small target detec-tion layer is added to improve the algorithm’s detection of small-sized signs by using richer feature information.The experi-mental results show that the improves algorithm achieves 88.1%for mAP@0.5 and 68.5%for mAP@0.5:0.95,with a detection speed of 83 FPS,which can meet the requirements of real-time and reliable detection.
作者
刘海斌
张友兵
周奎
张宇丰
吕圣
LIU Haibin;ZHANG Youbing;ZHOU Kui;ZHANG Yufeng;LYU Sheng(Joint Laboratory of Sharing-X Mobile Service Technology,School of Automotive Engineers,Hubei University of Automotive Technology,Shiyan,Hubei 442000,China)
出处
《计算机工程与应用》
CSCD
北大核心
2024年第5期200-209,共10页
Computer Engineering and Applications
基金
湖北省科技重大专项(2020AAA001)
湖北省重点研发计划项目(2021BED004,2023BAB169)。
作者简介
刘海斌(1995-),男,硕士研究生,CCF会员,研究方向为智能驾驶环境感知;通信作者:张友兵(1972-),男,硕士,教授,研究方向为智能驾驶,E-mail:zhangyb@huat.edu.cn;周奎(1980-),男,硕士,讲师,研究方向为智能驾驶。
