VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection

In vehicle safety detection, the accurate identification of body markers on medium and large vehicles plays a critical role in ensuring safe road travel. To address the issues of the feature and gradient information loss in previous You Only Look Once (YOLO) series models, a novel Vehicle Body Marke...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Wang, Chao Li, Chao Zhou, Jun Sun
Format: Article
Language:English
Published: PeerJ Inc. 2025-06-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2932.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471811112140800
author Bin Wang
Chao Li
Chao Zhou
Jun Sun
author_facet Bin Wang
Chao Li
Chao Zhou
Jun Sun
author_sort Bin Wang
collection DOAJ
description In vehicle safety detection, the accurate identification of body markers on medium and large vehicles plays a critical role in ensuring safe road travel. To address the issues of the feature and gradient information loss in previous You Only Look Once (YOLO) series models, a novel Vehicle Body Markers YOLO (VBM-YOLO) model has been designed. Firstly, the model integrates the cross-spatial-channel attention (CSCA) mechanism proposed in this study. The CSCA uses cross-dimensional information to address interaction issues during the fusion of spatial and channel dimensions, significantly enhancing the model’s representational capacity. Secondly, we propose a multi-scale selective feature pyramid network (MSSFPN). By a progressive fusion approach and multi-scale feature selection learning, MSSFPN alleviates the issues of feature loss and target layer information confusion caused by traditional top-down and bottom-up feature pyramids. Finally, an auxiliary gradient branch (AGB) is proposed. During training, AGB incorporates feature information from different target layers to help the current layer retain complete gradient information. Additionally, the AGB branch does not participate in model inference, thereby reducing additional overhead. Experimental results demonstrate that VBM-YOLO improves mean average precision (mAP) by 2.3% and 4.3% at intersection over union (IoU) thresholds of 0.5 and 0.5:0.95, respectively, compared to YOLOv8s on the vehicle body markers dataset. VBM-YOLO also achieves a better balance between accuracy and computational resources than other mainstream models, exhibiting good generalization performance on public datasets like PASCAL VOC and D-Fire.
format Article
id doaj-art-011853459d3648aa88df5d21cbed10c8
institution Kabale University
issn 2376-5992
language English
publishDate 2025-06-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-011853459d3648aa88df5d21cbed10c82025-08-20T03:24:42ZengPeerJ Inc.PeerJ Computer Science2376-59922025-06-0111e293210.7717/peerj-cs.2932VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detectionBin WangChao LiChao ZhouJun SunIn vehicle safety detection, the accurate identification of body markers on medium and large vehicles plays a critical role in ensuring safe road travel. To address the issues of the feature and gradient information loss in previous You Only Look Once (YOLO) series models, a novel Vehicle Body Markers YOLO (VBM-YOLO) model has been designed. Firstly, the model integrates the cross-spatial-channel attention (CSCA) mechanism proposed in this study. The CSCA uses cross-dimensional information to address interaction issues during the fusion of spatial and channel dimensions, significantly enhancing the model’s representational capacity. Secondly, we propose a multi-scale selective feature pyramid network (MSSFPN). By a progressive fusion approach and multi-scale feature selection learning, MSSFPN alleviates the issues of feature loss and target layer information confusion caused by traditional top-down and bottom-up feature pyramids. Finally, an auxiliary gradient branch (AGB) is proposed. During training, AGB incorporates feature information from different target layers to help the current layer retain complete gradient information. Additionally, the AGB branch does not participate in model inference, thereby reducing additional overhead. Experimental results demonstrate that VBM-YOLO improves mean average precision (mAP) by 2.3% and 4.3% at intersection over union (IoU) thresholds of 0.5 and 0.5:0.95, respectively, compared to YOLOv8s on the vehicle body markers dataset. VBM-YOLO also achieves a better balance between accuracy and computational resources than other mainstream models, exhibiting good generalization performance on public datasets like PASCAL VOC and D-Fire.https://peerj.com/articles/cs-2932.pdfYOLOVehicle body markers detectionFeature fusionFeature extractionGradient information
spellingShingle Bin Wang
Chao Li
Chao Zhou
Jun Sun
VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
PeerJ Computer Science
YOLO
Vehicle body markers detection
Feature fusion
Feature extraction
Gradient information
title VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
title_full VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
title_fullStr VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
title_full_unstemmed VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
title_short VBM-YOLO: an enhanced YOLO model with reduced information loss for vehicle body markers detection
title_sort vbm yolo an enhanced yolo model with reduced information loss for vehicle body markers detection
topic YOLO
Vehicle body markers detection
Feature fusion
Feature extraction
Gradient information
url https://peerj.com/articles/cs-2932.pdf
work_keys_str_mv AT binwang vbmyoloanenhancedyolomodelwithreducedinformationlossforvehiclebodymarkersdetection
AT chaoli vbmyoloanenhancedyolomodelwithreducedinformationlossforvehiclebodymarkersdetection
AT chaozhou vbmyoloanenhancedyolomodelwithreducedinformationlossforvehiclebodymarkersdetection
AT junsun vbmyoloanenhancedyolomodelwithreducedinformationlossforvehiclebodymarkersdetection