基于YOLOv5的雾霾天气下交通标志识别模型  

Traffic sign recognition model in haze weather based on YOLOv5

作　　者：尹靖涵 瞿绍军 姚泽楷[1,2] 胡玄烨 秦晓雨 华璞靖 YIN Jinghan;QU Shaojun;YAO Zekai;HU Xuanye;QIN Xiaoyu;HUA Pujing(College of Information Science and Engineering,Hunan Normal University,Changsha Hunan 410081,China;College of Xiangjiang Artificial Intelligence,Hunan Normal University,Changsha Hunan 410081,China)

机构地区：[1]湖南师范大学信息科学与工程学院,长沙410081 [2]湖南师范大学湘江人工智能学院,长沙410081

出　　处：《计算机应用》2022年第9期2876-2884,共9页journal of Computer Applications

基　　金：国家自然科学基金资助项目(12071126);湖南省教育厅科学研究项目(19C1149);湖南师范大学湘江人工智能学院科研创新项目(202031A12)。

摘　　要：针对雾霾、雨雪等恶劣天气下小型交通标志识别精度低、漏检严重的问题,提出一种基于YOLOv5的雾霾天气下交通标志识别模型。首先,对YOLOv5的结构进行优化,采用逆向思维,通过削减特征金字塔深度、限制最高下采样倍数来解决小目标难以识别的问题,并通过调整残差模块的特征传递深度来抑制背景特征的重复叠加;其次,引入数据增强、K-means先验框、全局非极大值抑制(GNMS)等机制到模型;最后,在中国交通标志数据集TT100K上验证改进YOLOv5模型在面对恶劣天气时的检测能力,并对精度下降最显著的雾霾天气下的交通标志识别展开了重点研究。实验结果表明,改进YOLOv5模型的F1-score达0.92150,平均精度均值@0.5(mAP@0.5)达95.3%,平均精度均值@0.5:0.95(mAP@0.5:0.95)达75.2%,且所提模型在恶劣天气下仍能进行交通标志的高精度识别,每秒检测帧数(FPS)达到50,满足实时检测的需求。Aiming at the problem of poor recognition precision and serious missed detection of small traffic signs in bad weather such as haze,rain and snow,a traffic sign recognition model in haze weather based on YOLOv5(You Only Look Once version 5)was proposed. Firstly,the structure of YOLOv5 was optimized. By using contrary thinking,the problem of small object recognition difficulty was solved by reducing the depth of feature pyramid and limiting the maximum down sampling multiple. By adjusting the depth of residual module,the repeated overlapping of background features was suppressed. Secondly,the mechanisms such as data augmentation,K-means anchor and Global Non-Maximum Suppression(GNMS)were introduced into the model. Finally,the detection ability of the improved YOLOv5 facing the bad weather was verified on the Chinese traffic sign dataset TT100K,and the study on traffic sign recognition in the haze weather with the most obvious precision decline was focused on. Experimental results show that the F1-score,mean Average Precision @0. 5(mAP@0. 5),mean Average Precision @0. 5:0. 95(mAP@0. 5:0. 95)of the improved YOLOv5 model reach 0. 921 50,95. 3% and 75. 2%,respectively. The proposed model can maintain high-precision recognition of traffic sign in bad weather,and has Frames Per Second(FPS)up to 50,meeting the requirement of real-time detection.

关 键 词：深度学习 目标检测 YOLOv5 特征金字塔 雾霾天气 交通标志识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]