基于改进YOLOv5s的无人驾驶夜间车辆目标检测算法

Algorithm on nighttime target detection for unmanned vehicles based on an improved YOLOv5s

夜间车辆检测对无人驾驶车辆行驶安全具有重要意义。但是,夜间光照强度低,车辆几何特征呈现不明显,尤其远处车辆由于目标小而特征视认难,导致检测难度大幅提升。基于此,提出了一种基于改进YOLOv5s的无人驾驶夜间车辆检测算法。首先,采集榆林市部分道路夜间场景自构建数据集,并通过Retinex算法实现数据增强处理;在此基础上,进一步通过以下3个措施对传统YOLOv5s网络进行改进:将深度可分离卷积引入Backbone结构,减少网络参数量;将多种注意力机制与FPN融合,提升网络的特征提取能力;在PAN中引入空洞卷积,在感受野不变和特征信息损失较少的同时,减少网络参数量。最终实验结果显示:夜间车辆的平均检测精度可达84.8%,相较改进前提升了5.2%;对应检测速度可达48 fps,提升了9.1%。研究成果可为提升无人驾驶车辆在事故多发夜间时段的行车安全性奠定理论基础。

Nighttime vehicle detection is of great significance to the safety of unmanned vehicles.At night,low light intensity makes the geometric characteristics of a vehicle inconspicuous.Moreover,a remote vehicle is even difficult to be recognized due to its small size,thus resulting in a significant increase of difficulty in its detection.In this context,this paper proposes an algorithm on nighttime target detection for unmanned vehicles based on an improved YOLOv5s model.To begin with,some night scenes concerning roads in Yulin City are collected for dataset construction.The data is then enhanced by Retinex algorithm.On this basis,the following three measures are made to improve the traditional YOLOv5s network:introducing depthwise separable convolution into the Backbone structure to reduce the number of network parameters;combining multiple attention mechanisms with the FPN structure to improve the ability of feature extraction of the network;embedding dilated convolution into the PAN structure to reduce the number of network parameters,as well as the loss of feature information,while keeping the receptive field unchanged at the same time.The final experimental results demonstrate that the average accuracy of nighttime vehicle detection reaches 84.8%,which is 5.2%higher than before.The corresponding detection speed is up to 48 frames per second,an increase of 9.1%.The research results can lay a theoretical foundation for improving the driving safety of unmanned vehicles during accident-prone nights.