测绘通报 ›› 2024, Vol. 0 ›› Issue (12): 106-110.doi: 10.13474/j.cnki.11-2246.2024.1217

• 工程测量分会年会优选论文 • 上一篇    下一篇

基于改进YOLOv8的交通标识检测方法

李玉婷1,2, 袁振超1,2, 张丽1,2   

  1. 1. 上海市测绘院, 上海 200063;
    2. 自然资源部超大城市自然资源时空大数据分析应用重点实验室, 上海 200063
  • 收稿日期:2024-07-24 发布日期:2024-12-27
  • 作者简介:李玉婷(1996-),女,硕士,助理工程师,主要从事智能化全息测绘、新型基础测绘等方面的工作。E-mail:1529487123@qq.com

Traffic signs detection algorithm based on improved YOLOv8

LI Yuting1,2, YUAN Zhenchao1,2, ZHANG Li1,2   

  1. 1. Shanghai Surveying and Mapping Institute, Shanghai 200063, China;
    2. Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities, Ministry of Natural Resources, Shanghai 200063, China
  • Received:2024-07-24 Published:2024-12-27

摘要: 近年来,上海开展新型基础测绘试点工作,已完成全市上万千米的全息道路,覆盖了上海城市主要道路。随着智能驾驶的快速发展,准确地检测和识别道路交通标识是构建智能驾驶道路框架数据的重要一环。在实际场景中很多因素会给影像中交通标识的检测带来挑战,如运动模糊、日照条件及拍摄角度等。针对此问题,本文提出了一种基于 YOLOv8改进的交通标识检测算法。在模型的Neck部分融合GAM注意力机制,增强了交通标识的特征信息;使用Wise_IoU损失函数代替原有的损失函数,提升了数据集的训练性能。与未作任何优化的模型相比,优化后的模型在交通标识检测上的精确度和平均精度均值分别提升了6.5%、4.1%,具有实际应用价值。

关键词: 高精地图, 智能驾驶, YOLOv8, 注意力机制, 损失函数, 交通标识检测

Abstract: It has carried out pilot work on new fundamental surveying and mapping,and has completed more than 10000 km of holographic roads in the city in recent year,covering the main roads in Shanghai.With the rapid development of intelligent driving,accurate detection and identification of road traffic signs is essential in constructing intelligent driving road framework data.In actual scenarios,many factors will bring challenges to the detection and recognition of traffic signs,such as motion blur,sunlight conditions,and shooting angles.So,the paper proposes an improved traffic signs detection algorithm based on YOLOv8.The GAM attention mechanism is introduced in the Neck part of the model to enhance the characteristic information of traffic signs.The Wise_IoU loss function has improved the training performance of the dataset compared to the original loss function.Compared with the model without any optimization,the accuracy and mean average precision increased by 6.5% and 4.1% respectively,which has practical application value.

Key words: high-precision map, intelligent driving, YOLOv8, attention mechanism, loss function, traffic sign detection

中图分类号: