文献类型：期刊文献

中文题名：Research on Traffic Sign Detection Based on Improved YOLOv8

英文题名：Research on Traffic Sign Detection Based on Improved YOLOv8

作者：Zhongjie Huang[1];Lintao Li[1];Gerd Christian Krizek[2];Linhao Sun[1]

第一作者：Zhongjie Huang

机构：[1]School of Computer and Information Engineering, Xinxiang University, Xinxiang, China;[2]Department of Applied Mathematics and Physics, UAS Technikum Wien, Vienna, Austria

第一机构：新乡学院计算机与信息工程学院

年份：2023

卷号：11

期号：7

起止页码：226-232

中文期刊名：电脑和通信(英文)

外文期刊名：Journal of Computer and Communications

语种：英文

中文关键词：Traffic Sign Detection;Small Object Detection;YOLOv8;Feature Fusion

外文关键词：Traffic Sign Detection;Small Object Detection;YOLOv8;Feature Fusion

摘要：Aiming at solving the problem of missed detection and low accuracy in detecting traffic signs in the wild, an improved method of YOLOv8 is proposed. Firstly, combined with the characteristics of small target objects in the actual scene, this paper further adds blur and noise operation. Then, the asymptotic feature pyramid network (AFPN) is introduced to highlight the influence of key layer features after feature fusion, and simultaneously solve the direct interaction of non-adjacent layers. Experimental results on the TT100K dataset show that compared with the YOLOv8, the detection accuracy and recall are higher. .
Aiming at solving the problem of missed detection and low accuracy in detecting traffic signs in the wild, an improved method of YOLOv8 is proposed. Firstly, combined with the characteristics of small target objects in the actual scene, this paper further adds blur and noise operation. Then, the asymptotic feature pyramid network (AFPN) is introduced to highlight the influence of key layer features after feature fusion, and simultaneously solve the direct interaction of non-adjacent layers. Experimental results on the TT100K dataset show that compared with the YOLOv8, the detection accuracy and recall are higher. .