High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target

Traffic sign detection is one of essential foundations in intelligent transportation and intelligent driving systems. For autonomous driving, traffic signs captured by cameras are usually small, and detecting low resolution imagines of traffic signs at long distances is still a big challenge. To imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengxia Hu, Shengwen Pi, Jinying Zhou, Xinming Wan, Qiaoshou Liu
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10786195/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850121987947495424
author Mengxia Hu
Shengwen Pi
Jinying Zhou
Xinming Wan
Qiaoshou Liu
author_facet Mengxia Hu
Shengwen Pi
Jinying Zhou
Xinming Wan
Qiaoshou Liu
author_sort Mengxia Hu
collection DOAJ
description Traffic sign detection is one of essential foundations in intelligent transportation and intelligent driving systems. For autonomous driving, traffic signs captured by cameras are usually small, and detecting low resolution imagines of traffic signs at long distances is still a big challenge. To improve the accuracy of small traffic sign detection, this paper proposes an improved lightweight model based on you only look once version 5 small (YOLOv5s). Firstly, a dense connection is employed to reduce the number of parameters in the main network, facilitating multiple reuses of large-scale feature maps to strengthen the ability for extracting information from small targets. Secondly, a new C3 module is constructed by combining the receptive-field attention convolution operation (RFCAConv) mechanism for feature fusion in the neck network to make the network more focused on details of small targets in feature maps. Finally, we replace the original corrected intersection over union (CIOU) loss function with inner-shape intersection over union (Inner-SIOU) loss function, which improves both the training speed and accuracy of the model. Testing results on public traffic signs datasets of CCTSDB2021 and TT100K indicate that the proposed mode reduces the parameter count by 30%, increases mAP0.5 by 4-5%, and boosts FPS by 16% comparing with the original YOLOv5s model.
format Article
id doaj-art-72647a040a944ff692a2e3601b84877d
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-72647a040a944ff692a2e3601b84877d2025-08-20T02:34:56ZengIEEEIEEE Access2169-35362024-01-011219152719153610.1109/ACCESS.2024.351344510786195High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small TargetMengxia Hu0Shengwen Pi1https://orcid.org/0009-0004-9469-5890Jinying Zhou2Xinming Wan3Qiaoshou Liu4https://orcid.org/0000-0002-4065-0919State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaTraffic sign detection is one of essential foundations in intelligent transportation and intelligent driving systems. For autonomous driving, traffic signs captured by cameras are usually small, and detecting low resolution imagines of traffic signs at long distances is still a big challenge. To improve the accuracy of small traffic sign detection, this paper proposes an improved lightweight model based on you only look once version 5 small (YOLOv5s). Firstly, a dense connection is employed to reduce the number of parameters in the main network, facilitating multiple reuses of large-scale feature maps to strengthen the ability for extracting information from small targets. Secondly, a new C3 module is constructed by combining the receptive-field attention convolution operation (RFCAConv) mechanism for feature fusion in the neck network to make the network more focused on details of small targets in feature maps. Finally, we replace the original corrected intersection over union (CIOU) loss function with inner-shape intersection over union (Inner-SIOU) loss function, which improves both the training speed and accuracy of the model. Testing results on public traffic signs datasets of CCTSDB2021 and TT100K indicate that the proposed mode reduces the parameter count by 30%, increases mAP0.5 by 4-5%, and boosts FPS by 16% comparing with the original YOLOv5s model.https://ieeexplore.ieee.org/document/10786195/Traffic sign detectionsmall target detectionYOLOv5dense connectionattention mechanism
spellingShingle Mengxia Hu
Shengwen Pi
Jinying Zhou
Xinming Wan
Qiaoshou Liu
High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
IEEE Access
Traffic sign detection
small target detection
YOLOv5
dense connection
attention mechanism
title High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
title_full High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
title_fullStr High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
title_full_unstemmed High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
title_short High-Performance YOLOv5s: Traffic Sign Detection Algorithm for Small Target
title_sort high performance yolov5s traffic sign detection algorithm for small target
topic Traffic sign detection
small target detection
YOLOv5
dense connection
attention mechanism
url https://ieeexplore.ieee.org/document/10786195/
work_keys_str_mv AT mengxiahu highperformanceyolov5strafficsigndetectionalgorithmforsmalltarget
AT shengwenpi highperformanceyolov5strafficsigndetectionalgorithmforsmalltarget
AT jinyingzhou highperformanceyolov5strafficsigndetectionalgorithmforsmalltarget
AT xinmingwan highperformanceyolov5strafficsigndetectionalgorithmforsmalltarget
AT qiaoshouliu highperformanceyolov5strafficsigndetectionalgorithmforsmalltarget