Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n

To address challenges in the detection of air duct clamps due to factors such as dim environments and small objects in train detection, such as insufficient detection accuracy and low detection efficiency, this paper proposes a RSA-YOLOv10n-based detection algorithm, developed utilizing a dataset of...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Dairong, ZHAO Yuhong, QU Xiaozhang, LIU Yi
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2025-04-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2025.02.100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224626595430400
author WANG Dairong
ZHAO Yuhong
QU Xiaozhang
LIU Yi
author_facet WANG Dairong
ZHAO Yuhong
QU Xiaozhang
LIU Yi
author_sort WANG Dairong
collection DOAJ
description To address challenges in the detection of air duct clamps due to factors such as dim environments and small objects in train detection, such as insufficient detection accuracy and low detection efficiency, this paper proposes a RSA-YOLOv10n-based detection algorithm, developed utilizing a dataset of air duct clamps collected from trains. Firstly, in order to better capture diverse features in images, the Conv convolution is modified to RepConv convolution based on the YOLOv10n model, facilitating adaptive adjustments in the representation ability of the convolution kernel. Secondly, in order to improve the sensitivity of the model to important information, the StokenAttention attention mechanism is introduced at the Neck layer, supporting dynamic focus on key areas during image detection. Experiments conducted using a dataset comprising thousands of self-labeled images of air duct clamps demonstrated that the <italic>mAP</italic>@50%, <italic>mAP</italic>@95%, accuracy, and recall rate of the proposed RSA-YOLOv10n model were 98.7%, 75.1%, 97.3%, and 96.6%, respectively. These results show improvements of 0.2, 0.8, 0.2, and 0.3 percentage points compared to the YOLOv10n model. Furthermore, the RSA-YOLOv10n model proves a great improvement in the FPS value, while maintaining model size, GFLOPs, function loss value, and other parameters equivalent to those of the YOLOv10n model. Through ablation experiments and comparative experiments with other models, including YOLOv3-tiny, YOLOv5n, and YOLOv8n, the analysis and verification showcased the superiority of the proposed detection algorithm in terms of overall accuracy, recall rate and detection time, suggesting its potential for widespread application in the field of detecting air duct clamps on trains. The study findings are of great significance for the technical development of train device and component detection.
format Article
id doaj-art-231015d76548425cb0e20c2c74edca7e
institution Kabale University
issn 2096-5427
language zho
publishDate 2025-04-01
publisher Editorial Office of Control and Information Technology
record_format Article
series Kongzhi Yu Xinxi Jishu
spelling doaj-art-231015d76548425cb0e20c2c74edca7e2025-08-25T06:57:32ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272025-04-01546488832733Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10nWANG DairongZHAO YuhongQU XiaozhangLIU YiTo address challenges in the detection of air duct clamps due to factors such as dim environments and small objects in train detection, such as insufficient detection accuracy and low detection efficiency, this paper proposes a RSA-YOLOv10n-based detection algorithm, developed utilizing a dataset of air duct clamps collected from trains. Firstly, in order to better capture diverse features in images, the Conv convolution is modified to RepConv convolution based on the YOLOv10n model, facilitating adaptive adjustments in the representation ability of the convolution kernel. Secondly, in order to improve the sensitivity of the model to important information, the StokenAttention attention mechanism is introduced at the Neck layer, supporting dynamic focus on key areas during image detection. Experiments conducted using a dataset comprising thousands of self-labeled images of air duct clamps demonstrated that the <italic>mAP</italic>@50%, <italic>mAP</italic>@95%, accuracy, and recall rate of the proposed RSA-YOLOv10n model were 98.7%, 75.1%, 97.3%, and 96.6%, respectively. These results show improvements of 0.2, 0.8, 0.2, and 0.3 percentage points compared to the YOLOv10n model. Furthermore, the RSA-YOLOv10n model proves a great improvement in the FPS value, while maintaining model size, GFLOPs, function loss value, and other parameters equivalent to those of the YOLOv10n model. Through ablation experiments and comparative experiments with other models, including YOLOv3-tiny, YOLOv5n, and YOLOv8n, the analysis and verification showcased the superiority of the proposed detection algorithm in terms of overall accuracy, recall rate and detection time, suggesting its potential for widespread application in the field of detecting air duct clamps on trains. The study findings are of great significance for the technical development of train device and component detection.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2025.02.100object detectionYOLOv10nair duct clampRepConv convolutionStokenAttention attention mechanism
spellingShingle WANG Dairong
ZHAO Yuhong
QU Xiaozhang
LIU Yi
Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
Kongzhi Yu Xinxi Jishu
object detection
YOLOv10n
air duct clamp
RepConv convolution
StokenAttention attention mechanism
title Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
title_full Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
title_fullStr Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
title_full_unstemmed Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
title_short Detection Algorithm for Air Duct Clamp on Trains Based on RSA-YOLOv10n
title_sort detection algorithm for air duct clamp on trains based on rsa yolov10n
topic object detection
YOLOv10n
air duct clamp
RepConv convolution
StokenAttention attention mechanism
url http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2025.02.100
work_keys_str_mv AT wangdairong detectionalgorithmforairductclampontrainsbasedonrsayolov10n
AT zhaoyuhong detectionalgorithmforairductclampontrainsbasedonrsayolov10n
AT quxiaozhang detectionalgorithmforairductclampontrainsbasedonrsayolov10n
AT liuyi detectionalgorithmforairductclampontrainsbasedonrsayolov10n