Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n

To address the challenges in underground unmanned locomotive image feature extraction—such as poor lighting, high noise, and motion blur, which result in the loss of image details and difficulty in identifying small targets—a multi-object detection model for underground unmanned locomotives based on...

Full description

Saved in:
Bibliographic Details
Main Authors: XU Jinhui, WANG Wenshan, WANG Shuang, WANG Wenyue, ZHAO Tingting
Format: Article
Language:zho
Published: Editorial Department of Industry and Mine Automation 2025-04-01
Series:Gong-kuang zidonghua
Subjects:
Online Access:http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414810173702144
author XU Jinhui
WANG Wenshan
WANG Shuang
WANG Wenyue
ZHAO Tingting
author_facet XU Jinhui
WANG Wenshan
WANG Shuang
WANG Wenyue
ZHAO Tingting
author_sort XU Jinhui
collection DOAJ
description To address the challenges in underground unmanned locomotive image feature extraction—such as poor lighting, high noise, and motion blur, which result in the loss of image details and difficulty in identifying small targets—a multi-object detection model for underground unmanned locomotives based on DYCS-YOLOv8n was proposed. Based on YOLOv8n, the Convolutional Block Attention Module (CBAM) was introduced, enhancing the extraction of key features through spatial and channel attention mechanisms. A small-object detection layer was added, increasing the original three layers to four, thereby improving the extraction of fine features and enhancing detection performance for small-sized targets. The dynamic upsampling operator DySample was employed to adaptively adjust the sampling strategy according to the input features, better preserving edges and local details in the images and avoiding the loss of critical information. Experiments conducted on a self-constructed underground unmanned locomotive dataset showed that: ① The DYCS-YOLOv8n model achieved a mean Average Precision (mAP@0.5) of 97.5%, an improvement of 3.4% over the YOLOv8n model, with a detection speed of 46.35 frames per second, meeting the requirements for real-time detection. ② Compared with mainstream YOLO series object detection models, DYCS-YOLOv8n achieved the optimal mAP@0.5, maintaining a lightweight structure while ensuring high computational speed. ③ In complex underground scenarios with noise and low illumination, the DYCS-YOLOv8n model exhibited high average detection confidence for pedestrians, tracks, and signal lights, with no cases of missed or false detections.
format Article
id doaj-art-d2f2dee69c144fe583b4eb2b67d72b4f
institution Kabale University
issn 1671-251X
language zho
publishDate 2025-04-01
publisher Editorial Department of Industry and Mine Automation
record_format Article
series Gong-kuang zidonghua
spelling doaj-art-d2f2dee69c144fe583b4eb2b67d72b4f2025-08-20T03:33:42ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2025-04-015148692, 13010.13272/j.issn.1671-251x.2024100036Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8nXU JinhuiWANG WenshanWANG ShuangWANG WenyueZHAO TingtingTo address the challenges in underground unmanned locomotive image feature extraction—such as poor lighting, high noise, and motion blur, which result in the loss of image details and difficulty in identifying small targets—a multi-object detection model for underground unmanned locomotives based on DYCS-YOLOv8n was proposed. Based on YOLOv8n, the Convolutional Block Attention Module (CBAM) was introduced, enhancing the extraction of key features through spatial and channel attention mechanisms. A small-object detection layer was added, increasing the original three layers to four, thereby improving the extraction of fine features and enhancing detection performance for small-sized targets. The dynamic upsampling operator DySample was employed to adaptively adjust the sampling strategy according to the input features, better preserving edges and local details in the images and avoiding the loss of critical information. Experiments conducted on a self-constructed underground unmanned locomotive dataset showed that: ① The DYCS-YOLOv8n model achieved a mean Average Precision (mAP@0.5) of 97.5%, an improvement of 3.4% over the YOLOv8n model, with a detection speed of 46.35 frames per second, meeting the requirements for real-time detection. ② Compared with mainstream YOLO series object detection models, DYCS-YOLOv8n achieved the optimal mAP@0.5, maintaining a lightweight structure while ensuring high computational speed. ③ In complex underground scenarios with noise and low illumination, the DYCS-YOLOv8n model exhibited high average detection confidence for pedestrians, tracks, and signal lights, with no cases of missed or false detections.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100036underground unmanned drivinglocomotivemulti-object detectionyolov8nconvolutional attention mechanismsmall-object detectiondynamic upsampling
spellingShingle XU Jinhui
WANG Wenshan
WANG Shuang
WANG Wenyue
ZHAO Tingting
Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
Gong-kuang zidonghua
underground unmanned driving
locomotive
multi-object detection
yolov8n
convolutional attention mechanism
small-object detection
dynamic upsampling
title Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
title_full Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
title_fullStr Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
title_full_unstemmed Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
title_short Multi-object detection for underground unmanned locomotives based on DYCS-YOLOv8n
title_sort multi object detection for underground unmanned locomotives based on dycs yolov8n
topic underground unmanned driving
locomotive
multi-object detection
yolov8n
convolutional attention mechanism
small-object detection
dynamic upsampling
url http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100036
work_keys_str_mv AT xujinhui multiobjectdetectionforundergroundunmannedlocomotivesbasedondycsyolov8n
AT wangwenshan multiobjectdetectionforundergroundunmannedlocomotivesbasedondycsyolov8n
AT wangshuang multiobjectdetectionforundergroundunmannedlocomotivesbasedondycsyolov8n
AT wangwenyue multiobjectdetectionforundergroundunmannedlocomotivesbasedondycsyolov8n
AT zhaotingting multiobjectdetectionforundergroundunmannedlocomotivesbasedondycsyolov8n