A comparison chart of the detection effect.

<div><p>The improved YOLOv8n algorithm is proposed for the existing target detection algorithms to solve the issues of insufficient detection accuracy and leakage due to the target scale variability and complex background interference during road surface crack detection. This algorithm i...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Wenyuan Xu (2553028) (author)
مؤلفون آخرون: Jianbo Xu (1824238) (author), Yongcheng Ji (5628128) (author), Guodong Li (1525873) (author), Hao Li (31608) (author), Zhen Zang (684900) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852016965381521408
author Wenyuan Xu (2553028)
author2 Jianbo Xu (1824238)
Yongcheng Ji (5628128)
Guodong Li (1525873)
Hao Li (31608)
Zhen Zang (684900)
author2_role author
author
author
author
author
author_facet Wenyuan Xu (2553028)
Jianbo Xu (1824238)
Yongcheng Ji (5628128)
Guodong Li (1525873)
Hao Li (31608)
Zhen Zang (684900)
author_role author
dc.creator.none.fl_str_mv Wenyuan Xu (2553028)
Jianbo Xu (1824238)
Yongcheng Ji (5628128)
Guodong Li (1525873)
Hao Li (31608)
Zhen Zang (684900)
dc.date.none.fl_str_mv 2025-09-04T17:38:01Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0330218.g019
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/A_comparison_chart_of_the_detection_effect_/30055545
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biochemistry
Biotechnology
Cancer
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
spatial pyramid pooling
efficiently extracts multi
detrimental gradients produced
complex background interference
50 &# 8211
8 %, respectively
target scale variability
stage partial convolution
stage partial channel
insufficient detection accuracy
improved yolov8n algorithm
benchmark model yolov8n
8 %, 1
stage partial
detection accuracy
enhanced yolov8n
7 %,
scale features
enhanced algorithm
algorithm introduces
xlink ">
weighted intersection
significantly enhanced
road fractures
quality pictures
neck paradigm
model parameters
loss function
learning capability
leakage due
fine slim
feature fusion
experimental outcomes
employed instead
effectively reducing
effectively accommodate
complete intersection
average precision
attention mechanism
aforementioned enhancements
95 ),
dc.title.none.fl_str_mv A comparison chart of the detection effect.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>The improved YOLOv8n algorithm is proposed for the existing target detection algorithms to solve the issues of insufficient detection accuracy and leakage due to the target scale variability and complex background interference during road surface crack detection. This algorithm introduces the convolutional block attention module (CBAM) attention mechanism and integrates it with the cross-stage partial-feature fusion (C2f) module in the backbone network. The spatial pyramid pooling faster cross-stage partial channel (SPPFCSPC) module is introduced by integrating the spatial pyramid pooling (SPP) module with the Fully Cross-Stage Partial Convolution (FCSPC) module, which efficiently extracts multi-scale features. Then, the fine Slim-Neck paradigm is adopted to enhance the learning capability of the model while effectively reducing the number of model parameters. Ultimately, to mitigate the detrimental gradients produced by low-quality pictures, the weighted intersection over union (WIOU) loss function is employed instead of the complete intersection over union (CIOU), hence augmenting the bounding box regression efficacy of the network. After the aforementioned enhancements, the experimental outcomes on the road apparent crack dataset indicate that in comparison to the benchmark model YOLOv8n, the average precision (mAP@50), mean average precision (mAP@50–95), and recall of the enhanced algorithm have risen by 1.8%, 1.7%, and 1.8%, respectively. This indicates that the detection accuracy of road fractures is significantly enhanced by the enhanced YOLOv8n, which can more effectively accommodate the requirements of road maintenance.</p></div>
eu_rights_str_mv openAccess
id Manara_bc919444fea042fa76321dd4616b2ec9
identifier_str_mv 10.1371/journal.pone.0330218.g019
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30055545
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A comparison chart of the detection effect.Wenyuan Xu (2553028)Jianbo Xu (1824238)Yongcheng Ji (5628128)Guodong Li (1525873)Hao Li (31608)Zhen Zang (684900)BiochemistryBiotechnologyCancerSpace ScienceBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedspatial pyramid poolingefficiently extracts multidetrimental gradients producedcomplex background interference50 &# 82118 %, respectivelytarget scale variabilitystage partial convolutionstage partial channelinsufficient detection accuracyimproved yolov8n algorithmbenchmark model yolov8n8 %, 1stage partialdetection accuracyenhanced yolov8n7 %,scale featuresenhanced algorithmalgorithm introducesxlink ">weighted intersectionsignificantly enhancedroad fracturesquality picturesneck paradigmmodel parametersloss functionlearning capabilityleakage duefine slimfeature fusionexperimental outcomesemployed insteadeffectively reducingeffectively accommodatecomplete intersectionaverage precisionattention mechanismaforementioned enhancements95 ),<div><p>The improved YOLOv8n algorithm is proposed for the existing target detection algorithms to solve the issues of insufficient detection accuracy and leakage due to the target scale variability and complex background interference during road surface crack detection. This algorithm introduces the convolutional block attention module (CBAM) attention mechanism and integrates it with the cross-stage partial-feature fusion (C2f) module in the backbone network. The spatial pyramid pooling faster cross-stage partial channel (SPPFCSPC) module is introduced by integrating the spatial pyramid pooling (SPP) module with the Fully Cross-Stage Partial Convolution (FCSPC) module, which efficiently extracts multi-scale features. Then, the fine Slim-Neck paradigm is adopted to enhance the learning capability of the model while effectively reducing the number of model parameters. Ultimately, to mitigate the detrimental gradients produced by low-quality pictures, the weighted intersection over union (WIOU) loss function is employed instead of the complete intersection over union (CIOU), hence augmenting the bounding box regression efficacy of the network. After the aforementioned enhancements, the experimental outcomes on the road apparent crack dataset indicate that in comparison to the benchmark model YOLOv8n, the average precision (mAP@50), mean average precision (mAP@50–95), and recall of the enhanced algorithm have risen by 1.8%, 1.7%, and 1.8%, respectively. This indicates that the detection accuracy of road fractures is significantly enhanced by the enhanced YOLOv8n, which can more effectively accommodate the requirements of road maintenance.</p></div>2025-09-04T17:38:01ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0330218.g019https://figshare.com/articles/figure/A_comparison_chart_of_the_detection_effect_/30055545CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300555452025-09-04T17:38:01Z
spellingShingle A comparison chart of the detection effect.
Wenyuan Xu (2553028)
Biochemistry
Biotechnology
Cancer
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
spatial pyramid pooling
efficiently extracts multi
detrimental gradients produced
complex background interference
50 &# 8211
8 %, respectively
target scale variability
stage partial convolution
stage partial channel
insufficient detection accuracy
improved yolov8n algorithm
benchmark model yolov8n
8 %, 1
stage partial
detection accuracy
enhanced yolov8n
7 %,
scale features
enhanced algorithm
algorithm introduces
xlink ">
weighted intersection
significantly enhanced
road fractures
quality pictures
neck paradigm
model parameters
loss function
learning capability
leakage due
fine slim
feature fusion
experimental outcomes
employed instead
effectively reducing
effectively accommodate
complete intersection
average precision
attention mechanism
aforementioned enhancements
95 ),
status_str publishedVersion
title A comparison chart of the detection effect.
title_full A comparison chart of the detection effect.
title_fullStr A comparison chart of the detection effect.
title_full_unstemmed A comparison chart of the detection effect.
title_short A comparison chart of the detection effect.
title_sort A comparison chart of the detection effect.
topic Biochemistry
Biotechnology
Cancer
Space Science
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
spatial pyramid pooling
efficiently extracts multi
detrimental gradients produced
complex background interference
50 &# 8211
8 %, respectively
target scale variability
stage partial convolution
stage partial channel
insufficient detection accuracy
improved yolov8n algorithm
benchmark model yolov8n
8 %, 1
stage partial
detection accuracy
enhanced yolov8n
7 %,
scale features
enhanced algorithm
algorithm introduces
xlink ">
weighted intersection
significantly enhanced
road fractures
quality pictures
neck paradigm
model parameters
loss function
learning capability
leakage due
fine slim
feature fusion
experimental outcomes
employed instead
effectively reducing
effectively accommodate
complete intersection
average precision
attention mechanism
aforementioned enhancements
95 ),