Improved YOLOv8s-based foreign object detection method for mine conveyor belts

In low-illumination mine environments, conveyor belt foreign object detection algorithms suffer from insufficient extraction of global image features and an excessive number of model parameters. A method for detecting foreign objects on mine conveyor belts based on an improved version of YOLOv8s was...

Full description

Saved in:
Bibliographic Details
Main Authors: LI Runze, GUO Xingge, YANG Fazhan, ZHAO Peipei, XIE Guolong
Format: Article
Language:zho
Published: Editorial Department of Industry and Mine Automation 2025-06-01
Series:Gong-kuang zidonghua
Subjects:
Online Access:http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025040068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414768229613568
author LI Runze
GUO Xingge
YANG Fazhan
ZHAO Peipei
XIE Guolong
author_facet LI Runze
GUO Xingge
YANG Fazhan
ZHAO Peipei
XIE Guolong
author_sort LI Runze
collection DOAJ
description In low-illumination mine environments, conveyor belt foreign object detection algorithms suffer from insufficient extraction of global image features and an excessive number of model parameters. A method for detecting foreign objects on mine conveyor belts based on an improved version of YOLOv8s was proposed. YOLOv8s was improved using VMamba and MobileNetv4: MobileNetv4 was employed to enhance the backbone network by integrating the Universal Inverted Bottleneck (UIB) module. The efficient inverted residual structure reduced the overall number of model parameters, and a dynamic feature adaptation mechanism was used to strengthen feature robustness in small-object scenarios. The core feature extraction and fusion module C2f was improved by VMamba's Visual State Space (VSS) module, which efficiently captured global contextual information in images through a state space model and four-directional scanning mechanism, enhancing the model’s understanding of global image structure. A parameter-sharing lightweight detection head was designed, using Group Normalization (GN) as the basic convolutional normalization block to compensate for accuracy loss caused by model lightweighting. Experimental results showed that the improved YOLOv8s model achieved an mAP@0.5 of 0.921 and an mAP@0.5:0.95 of 0.601 on a self-built dataset, reduced the number of parameters by 27.7% compared to original YOLOv8s, outperformed mainstream object detection models such as YOLOv11s and YOLOv10s, and met the requirements for foreign object detection on mine conveyor belts.
format Article
id doaj-art-16407d3f33464f12bef6ca912e923762
institution Kabale University
issn 1671-251X
language zho
publishDate 2025-06-01
publisher Editorial Department of Industry and Mine Automation
record_format Article
series Gong-kuang zidonghua
spelling doaj-art-16407d3f33464f12bef6ca912e9237622025-08-20T03:33:43ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2025-06-015169610410.13272/j.issn.1671-251x.2025040068Improved YOLOv8s-based foreign object detection method for mine conveyor beltsLI Runze0GUO Xingge1YANG Fazhan2ZHAO Peipei3XIE Guolong4School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaChangzhou Haitu Information Technology Co., Ltd., Changzhou 213000, ChinaIn low-illumination mine environments, conveyor belt foreign object detection algorithms suffer from insufficient extraction of global image features and an excessive number of model parameters. A method for detecting foreign objects on mine conveyor belts based on an improved version of YOLOv8s was proposed. YOLOv8s was improved using VMamba and MobileNetv4: MobileNetv4 was employed to enhance the backbone network by integrating the Universal Inverted Bottleneck (UIB) module. The efficient inverted residual structure reduced the overall number of model parameters, and a dynamic feature adaptation mechanism was used to strengthen feature robustness in small-object scenarios. The core feature extraction and fusion module C2f was improved by VMamba's Visual State Space (VSS) module, which efficiently captured global contextual information in images through a state space model and four-directional scanning mechanism, enhancing the model’s understanding of global image structure. A parameter-sharing lightweight detection head was designed, using Group Normalization (GN) as the basic convolutional normalization block to compensate for accuracy loss caused by model lightweighting. Experimental results showed that the improved YOLOv8s model achieved an mAP@0.5 of 0.921 and an mAP@0.5:0.95 of 0.601 on a self-built dataset, reduced the number of parameters by 27.7% compared to original YOLOv8s, outperformed mainstream object detection models such as YOLOv11s and YOLOv10s, and met the requirements for foreign object detection on mine conveyor belts.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025040068conveyor belt foreign object detectionyolov8svmambamobilenetv4lightweightgroup normalization
spellingShingle LI Runze
GUO Xingge
YANG Fazhan
ZHAO Peipei
XIE Guolong
Improved YOLOv8s-based foreign object detection method for mine conveyor belts
Gong-kuang zidonghua
conveyor belt foreign object detection
yolov8s
vmamba
mobilenetv4
lightweight
group normalization
title Improved YOLOv8s-based foreign object detection method for mine conveyor belts
title_full Improved YOLOv8s-based foreign object detection method for mine conveyor belts
title_fullStr Improved YOLOv8s-based foreign object detection method for mine conveyor belts
title_full_unstemmed Improved YOLOv8s-based foreign object detection method for mine conveyor belts
title_short Improved YOLOv8s-based foreign object detection method for mine conveyor belts
title_sort improved yolov8s based foreign object detection method for mine conveyor belts
topic conveyor belt foreign object detection
yolov8s
vmamba
mobilenetv4
lightweight
group normalization
url http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025040068
work_keys_str_mv AT lirunze improvedyolov8sbasedforeignobjectdetectionmethodformineconveyorbelts
AT guoxingge improvedyolov8sbasedforeignobjectdetectionmethodformineconveyorbelts
AT yangfazhan improvedyolov8sbasedforeignobjectdetectionmethodformineconveyorbelts
AT zhaopeipei improvedyolov8sbasedforeignobjectdetectionmethodformineconveyorbelts
AT xieguolong improvedyolov8sbasedforeignobjectdetectionmethodformineconveyorbelts