Enhanced YOLO and Scanning Portal System for Vehicle Component Detection

In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of au...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Ye, Mingzhe Yuan, Chen Luo, Shuo Li, Duotao Pan, Wenhong Wang, Feidao Cao, Diwen Chen
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4809
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770575131574272
author Feng Ye
Mingzhe Yuan
Chen Luo
Shuo Li
Duotao Pan
Wenhong Wang
Feidao Cao
Diwen Chen
author_facet Feng Ye
Mingzhe Yuan
Chen Luo
Shuo Li
Duotao Pan
Wenhong Wang
Feidao Cao
Diwen Chen
author_sort Feng Ye
collection DOAJ
description In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry.
format Article
id doaj-art-b712f6974ee7491a87a0850f3ac8c84e
institution DOAJ
issn 1424-8220
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b712f6974ee7491a87a0850f3ac8c84e2025-08-20T03:02:56ZengMDPI AGSensors1424-82202025-08-012515480910.3390/s25154809Enhanced YOLO and Scanning Portal System for Vehicle Component DetectionFeng Ye0Mingzhe Yuan1Chen Luo2Shuo Li3Duotao Pan4Wenhong Wang5Feidao Cao6Diwen Chen7College of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, ChinaGuangzhou Institute of Industrial Intelligence, Guangzhou 511458, ChinaCollege of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, ChinaGuangzhou Institute of Industrial Intelligence, Guangzhou 511458, ChinaCollege of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, ChinaGuangzhou Institute of Industrial Intelligence, Guangzhou 511458, ChinaGuangzhou Institute of Industrial Intelligence, Guangzhou 511458, ChinaGuangzhou Institute of Industrial Intelligence, Guangzhou 511458, ChinaIn this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry.https://www.mdpi.com/1424-8220/25/15/4809target detectionautomobile parts inspectionsystem designYOLOv12n
spellingShingle Feng Ye
Mingzhe Yuan
Chen Luo
Shuo Li
Duotao Pan
Wenhong Wang
Feidao Cao
Diwen Chen
Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
Sensors
target detection
automobile parts inspection
system design
YOLOv12n
title Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
title_full Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
title_fullStr Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
title_full_unstemmed Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
title_short Enhanced YOLO and Scanning Portal System for Vehicle Component Detection
title_sort enhanced yolo and scanning portal system for vehicle component detection
topic target detection
automobile parts inspection
system design
YOLOv12n
url https://www.mdpi.com/1424-8220/25/15/4809
work_keys_str_mv AT fengye enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT mingzheyuan enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT chenluo enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT shuoli enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT duotaopan enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT wenhongwang enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT feidaocao enhancedyoloandscanningportalsystemforvehiclecomponentdetection
AT diwenchen enhancedyoloandscanningportalsystemforvehiclecomponentdetection