Research and Design of Industrial Transportation Oxygen Cylinder Detection and Tracking Based on Deep Learning.

Saved in:

Bibliographic Details
Title:	Research and Design of Industrial Transportation Oxygen Cylinder Detection and Tracking Based on Deep Learning.
Authors:	Minghao Ma¹ mmh13591920408@163.com, Shaochuan Xu² shaochuanxu1@163.com, Dehua Liu³ liudehua0527@163.com
Source:	IAENG International Journal of Computer Science. Mar2025, Vol. 52 Issue 3, p589-597. 9p.
Subjects:	Factory safety, Inspection & review, Deep learning, Industrial workers, Labor costs
Abstract:	To enhance the detection capabilities for identifying illegal operations by oxygen factory workers and abnormal conditions of oxygen cylinders, this paper proposes an algorithm based on YOLOv7 to improve target detection. The algorithm specifically addresses the need to check whether sufficient rubber rings are installed on the oxygen cylinders and to detect whether the oxygen cylinders are rolling on the ground. A small object detection layer was introduced to enhance the capture of shallow features. Additionally, the accuracy was improved by incorporating the CBAM Attention Mechanism module. The actual field dataset was utilized for ablation and comparison tests. Safety inspections were conducted through target detection and tracking to timely identify illegal and abnormal operations, thereby avoiding repeated alarms for the same target. The issues of misjudgment and missed detection of small targets, such as rubber rings, were resolved. This significantly improved detection accuracy, reduced labor costs, and provided assurance for the safety of the factory production process. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	To enhance the detection capabilities for identifying illegal operations by oxygen factory workers and abnormal conditions of oxygen cylinders, this paper proposes an algorithm based on YOLOv7 to improve target detection. The algorithm specifically addresses the need to check whether sufficient rubber rings are installed on the oxygen cylinders and to detect whether the oxygen cylinders are rolling on the ground. A small object detection layer was introduced to enhance the capture of shallow features. Additionally, the accuracy was improved by incorporating the CBAM Attention Mechanism module. The actual field dataset was utilized for ablation and comparison tests. Safety inspections were conducted through target detection and tracking to timely identify illegal and abnormal operations, thereby avoiding repeated alarms for the same target. The issues of misjudgment and missed detection of small targets, such as rubber rings, were resolved. This significantly improved detection accuracy, reduced labor costs, and provided assurance for the safety of the factory production process. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X