基于YOLOv7的交通目标检测算法研究  

Research on Traffic Object Detection Algorithm Based on YOLOv7

作　　者：王沛雪 张富春[1] 董晨乐 WANG Peixue;ZHANG Fuchun;DONG Chenle(School of Physics and Electronic Information,Yan an University,Yan an 716000,China)

机构地区：[1]延安大学物理与电子信息学院,陕西延安716000

出　　处：《计算机测量与控制》2024年第4期74-80,共7页Computer Measurement &Control

基　　金：国家自然科学基金(62264015);延安市科技创新项目(2017CXTD-01)。

摘　　要：针对交通场景中,由于光照、遮挡、目标小以及背景复杂等因素导致目标检测精度低,易出现漏检和误检问题的情况,提出了一种基于YOLOv7的交通目标检测算法;该算法在主干网络中融入多头注意力机制,以增强网络特征学习能力,从而更好地捕获数据和特征内部的相关性;在YOLOv7颈部网络引入协调注意力模块(CA),将位置信息嵌入到注意力机制中,忽略无关信息的干扰,以增强网络的特征提取能力;增加一个多尺度检测网络,以增强模型对不同尺度目标的检测能力;将CIoU损失函数更改为SIoU函数,以减少模型收敛不稳定问题,提高模型的鲁棒性;实验结果表明,改进的算法在BDD100K公开数据集上的检测精度和速度分别达到了59.8%mAP和96.2 FPS,相比原算法检测精度提高了2.5%;这表明改进的算法在满足实时性要求的同时,具备良好的检测精度,适用于复杂情况下的交通目标检测任务。Aiming at the factors of lighting,occlusion,small target and complex background in complex traffic scenes,it leads to low target detection accuracy and is prone to cause missed and false detections,a traffic target detection algorithm based on YOLOv7 is proposed.To better capture the internal correlation within the data and features,the algorithm incorporates the multi-head attention mechanism into the backbone network to enhance the network feature learning ability.The coordinated attention(CA)module is introduced into the YOLOv7 neck network,and the position information is embedded into the attention mechanism,which can ignore the interference of irrelevant information and enhance the feature extraction ability of the network.A multi-scale detection network is added to enhance the detection capability of the model for different scale targets.The CIoU loss function is modified to the SIoU function to reduce the convergence and instability of the model,and improve the robustness of the model.The expermental results show that the mean average precision(mAP)and dectection speed of the improved algorithm on the BDD100K public dataset reach up to 59.8%and 96.2 frames per second(FPS),respectively,with an increase of 2.5%compared to that of the original algorithm.It shows that the improved algorithm has a good detection accuracy while meeting the real-time requirements,which is suitable for traffic target detections in complex situations.

关 键 词：交通目标检测 YOLOv7网络 注意力机制 浅层网络检测层 SIoU损失函数 

分 类 号：TP83[自动化与计算机技术—检测技术与自动化装置]