Multi-target detection of underground personnel based on an improved YOLOv8n model

This study aims to address the complex challenges in monitoring underground personnel in hazardous areas, including uneven lighting, target scale inconsistency, and occlusion. An innovative multi-target detection algorithm, YOLOv8n-MSMLAS, was proposed based on the YOLOv8n network structure. The alg...

Full description

Saved in:
Bibliographic Details
Main Authors: WEN Yongzhong, JIA Pengtao, XIA Mingao, ZHANG Longgang, WANG Weifeng
Format: Article
Language:zho
Published: Editorial Department of Industry and Mine Automation 2025-01-01
Series:Gong-kuang zidonghua
Subjects:
Online Access:http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024110035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197693671931904
author WEN Yongzhong
JIA Pengtao
XIA Mingao
ZHANG Longgang
WANG Weifeng
author_facet WEN Yongzhong
JIA Pengtao
XIA Mingao
ZHANG Longgang
WANG Weifeng
author_sort WEN Yongzhong
collection DOAJ
description This study aims to address the complex challenges in monitoring underground personnel in hazardous areas, including uneven lighting, target scale inconsistency, and occlusion. An innovative multi-target detection algorithm, YOLOv8n-MSMLAS, was proposed based on the YOLOv8n network structure. The algorithm modified the Neck layer by incorporating a Multi-Scale Spatially Enhanced Attention Mechanism (MultiSEAM) to enhance the detection of occluded targets. Furthermore, a Hybrid Local Channel Attention (MLCA) mechanism was introduced into the C2f module to create the C2f-MLCA module, which fused local and global feature information, thereby improving feature representation. An Adaptive Spatial Feature Fusion (ASFF) module was embedded in the Head layer to boost detection performance for small-scale targets. Experimental results demonstrated that YOLOv8n-ASAM outperformed mainstream models such as Faster R-CNN, SSD, RT-DETR, YOLOv5s, and YOLOv7 in terms of overall performance, achieving mAP@0.5 and mAP@0.5: 0.95 of 93.4% and 60.1%, respectively,with a speed of 80.0 frames per second,the parameter is 5.80×106, effectively balancing accuracy and complexity. Moreover, YOLOv8n-ASAM exhibited superior performance under uneven lighting, target scale inconsistency, and occlusion, making it well-suited for real-world applications.
format Article
id doaj-art-e4dea7c52d594cf9b1e321e196336373
institution OA Journals
issn 1671-251X
language zho
publishDate 2025-01-01
publisher Editorial Department of Industry and Mine Automation
record_format Article
series Gong-kuang zidonghua
spelling doaj-art-e4dea7c52d594cf9b1e321e1963363732025-08-20T02:13:03ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2025-01-015113137, 7710.13272/j.issn.1671-251x.2024110035Multi-target detection of underground personnel based on an improved YOLOv8n modelWEN Yongzhong0JIA Pengtao1XIA Mingao2ZHANG Longgang3WANG Weifeng4Shaanxi Shanmei Pubai Mining Co., Ltd., Weinan 715517, ChinaCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, ChinaCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, ChinaShaanxi Shanmei Pubai Mining Co., Ltd., Weinan 715517, ChinaCollege of Safety Science and Engineering, Xi'an University of Science and Technology, Xi'an 710054, ChinaThis study aims to address the complex challenges in monitoring underground personnel in hazardous areas, including uneven lighting, target scale inconsistency, and occlusion. An innovative multi-target detection algorithm, YOLOv8n-MSMLAS, was proposed based on the YOLOv8n network structure. The algorithm modified the Neck layer by incorporating a Multi-Scale Spatially Enhanced Attention Mechanism (MultiSEAM) to enhance the detection of occluded targets. Furthermore, a Hybrid Local Channel Attention (MLCA) mechanism was introduced into the C2f module to create the C2f-MLCA module, which fused local and global feature information, thereby improving feature representation. An Adaptive Spatial Feature Fusion (ASFF) module was embedded in the Head layer to boost detection performance for small-scale targets. Experimental results demonstrated that YOLOv8n-ASAM outperformed mainstream models such as Faster R-CNN, SSD, RT-DETR, YOLOv5s, and YOLOv7 in terms of overall performance, achieving mAP@0.5 and mAP@0.5: 0.95 of 93.4% and 60.1%, respectively,with a speed of 80.0 frames per second,the parameter is 5.80×106, effectively balancing accuracy and complexity. Moreover, YOLOv8n-ASAM exhibited superior performance under uneven lighting, target scale inconsistency, and occlusion, making it well-suited for real-world applications.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024110035underground hazardous areas in coal minesmulti-target detection of underground personnelyolov8nmulti-scale spatially enhanced attention mechanismadaptive spatial feature fusionlightweight hybrid local channel attention mechanism
spellingShingle WEN Yongzhong
JIA Pengtao
XIA Mingao
ZHANG Longgang
WANG Weifeng
Multi-target detection of underground personnel based on an improved YOLOv8n model
Gong-kuang zidonghua
underground hazardous areas in coal mines
multi-target detection of underground personnel
yolov8n
multi-scale spatially enhanced attention mechanism
adaptive spatial feature fusion
lightweight hybrid local channel attention mechanism
title Multi-target detection of underground personnel based on an improved YOLOv8n model
title_full Multi-target detection of underground personnel based on an improved YOLOv8n model
title_fullStr Multi-target detection of underground personnel based on an improved YOLOv8n model
title_full_unstemmed Multi-target detection of underground personnel based on an improved YOLOv8n model
title_short Multi-target detection of underground personnel based on an improved YOLOv8n model
title_sort multi target detection of underground personnel based on an improved yolov8n model
topic underground hazardous areas in coal mines
multi-target detection of underground personnel
yolov8n
multi-scale spatially enhanced attention mechanism
adaptive spatial feature fusion
lightweight hybrid local channel attention mechanism
url http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024110035
work_keys_str_mv AT wenyongzhong multitargetdetectionofundergroundpersonnelbasedonanimprovedyolov8nmodel
AT jiapengtao multitargetdetectionofundergroundpersonnelbasedonanimprovedyolov8nmodel
AT xiamingao multitargetdetectionofundergroundpersonnelbasedonanimprovedyolov8nmodel
AT zhanglonggang multitargetdetectionofundergroundpersonnelbasedonanimprovedyolov8nmodel
AT wangweifeng multitargetdetectionofundergroundpersonnelbasedonanimprovedyolov8nmodel