基于YOLOv7的道路标识符检测  

Road identifier detection based on YOLOv7

作　　者：吴肖 刘佳佳 段平[1] 李佳[1] WU Xiao;LIU Jiajia;DUAN Ping;LI Jia(Faculty of Geography,Yunnan Normal University,Kunming 650500,China;China Energy Engineering Group Yunnan Electric Power Design Institute Co.Ltd.,Kunming 650000,China)

机构地区：[1]云南师范大学地理学部,昆明650500 [2]中国能源建设集团云南省电力设计院有限公司,昆明650000

出　　处：《激光杂志》2024年第6期82-87,共6页Laser Journal

基　　金：国家自然科学基金(No.41961061);云南省基础研究计划项目(No.202001AT070057);云南省院士专家工作站(No.2017IC063);兴滇英才支持计划项目。

摘　　要：面对复杂道路交通场景,智能、快速、准确地检测道路标识符对自动驾驶技术具有重要的意义。YOLOv7算法检测速度快、准确率高,适用于实时复杂的道路标识符检测。中国交通标志检测数据集对YOLOv7模型进行训练,选取了普通、有遮挡和模糊三种不同的道路交通场景图像测试训练模型,并与CenterNet、Faster R-CNN和SSD三种流行的目标检测算法进行对比分析。结果显示,YOLOv7算法检测速度快,平均精度最高,m AP达到89.7%,且在三种场景的图片测试中性能表现最好,即使在存在遮挡和模糊的情况下仍然能够成功检测出图像中的道路标识物目标。In the face of complex road traffic scenes,intelligent,fast and accurate detection of road identifiers is of great significance to automatic driving technology.The YOLOv7 algorithm with fast detection speed and high accura-cy is suitable for real-time complex road identifier detection.In this paper,the YOLOv7 model is trained with the Chi-nese traffic sign detection dataset,and three different road traffic scene images,namely,ordinary,occluded and blurred,are selected to test the training model and compared and analyzed with three popular target detection algo-rithms,namely,CenterNet,Faster R-CNN and SSD.The results show that the YOLOv7 algorithm is fast in detection,has the highest average accuracy with 89.7%mAP,and has the best performance in the image tests of the three sce-narios,successfully detecting road marker targets in the images even in the presence of occlusion and blurring.

关 键 词：深度学习 目标检测 YOLOv7 道路标识符识别 

分 类 号：TN391[电子电信—物理电子学]