Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7

Dongzhu Jiang; Keyan Liu; Limin Jia; Yong Qin; Yaopeng Jiang; Zhipeng Wang

doi:10.1016/j.ifacol.2023.10.672

Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7

Dongzhu Jiang^*
, Keyan Liu^*
, Limin Jia^*
, Yong Qin^*
, Yaopeng Jiang^*
, Zhipeng Wang^*

^*此作品的通讯作者

Beijing Jiaotong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

5 引用（Scopus）

摘要

In recent years, UAV(Unmanned Aerial Vehicle) has shown great vitality and potential in automated railway inspection operations. The catenary support device is an important infrastructure on the high-speed railway, which guarantees for the electric power system when the high-speed railway is running. However, the current inspection by UAV cannot automatically obtain multi-scale and standardized image data of the catenary support devices. It presents a serious challenge to the faulty diagnosis of the catenary support devices. Concerning this issue, an automatic multi-scale image capture strategy of catenary support device based on improved YOLOv7 is proposed. Due to the characteristics of less foreground and more background in the image detection of catenary support device, the Focal Loss is introduced. Experimental results show that the convergence speed of the model is improved with high detection accuracy. Furthermore, multi-scale and standardized capture strategies for catenary support device data are proposed. In the deployment experiment, improved YOLOv7 achieves 81.3% mAP, the multi-scale, standardized and normalized image data of catenary support device is captured.

源语言	英语
主期刊名	IFAC-PapersOnLine
编辑	Hideaki Ishii, Yoshio Ebihara, Jun-ichi Imura, Masaki Yamakita
出版商	Elsevier B.V.
页	7597-7602
页数	6
版本	2
ISBN（电子版）	9781713872344
DOI	https://doi.org/10.1016/j.ifacol.2023.10.672
出版状态	已出版 - 1 7月 2023
已对外发布	是
活动	22nd IFAC World Congress - Yokohama, 日本期限: 9 7月 2023 → 14 7月 2023

出版系列

姓名	IFAC-PapersOnLine
编号	2
卷	56
ISSN（电子版）	2405-8963

会议

会议	22nd IFAC World Congress
国家/地区	日本
市	Yokohama
时期	9/07/23 → 14/07/23

访问文件

10.1016/j.ifacol.2023.10.672

其它文件与链接

链接到 Scopus 的出版物

引用此

@inproceedings{a144563ce27b46b5bfaa6e27815fa8d1,

title = "Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7",

abstract = "In recent years, UAV(Unmanned Aerial Vehicle) has shown great vitality and potential in automated railway inspection operations. The catenary support device is an important infrastructure on the high-speed railway, which guarantees for the electric power system when the high-speed railway is running. However, the current inspection by UAV cannot automatically obtain multi-scale and standardized image data of the catenary support devices. It presents a serious challenge to the faulty diagnosis of the catenary support devices. Concerning this issue, an automatic multi-scale image capture strategy of catenary support device based on improved YOLOv7 is proposed. Due to the characteristics of less foreground and more background in the image detection of catenary support device, the Focal Loss is introduced. Experimental results show that the convergence speed of the model is improved with high detection accuracy. Furthermore, multi-scale and standardized capture strategies for catenary support device data are proposed. In the deployment experiment, improved YOLOv7 achieves 81.3\% mAP, the multi-scale, standardized and normalized image data of catenary support device is captured.",

keywords = "Catenary support device, Improved YOLOv7, Multiscale capture strategy, UAV automatic inspection",

author = "Dongzhu Jiang and Keyan Liu and Limin Jia and Yong Qin and Yaopeng Jiang and Zhipeng Wang",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/); 22nd IFAC World Congress ; Conference date: 09-07-2023 Through 14-07-2023",

year = "2023",

month = jul,

day = "1",

doi = "10.1016/j.ifacol.2023.10.672",

language = "英语",

series = "IFAC-PapersOnLine",

publisher = "Elsevier B.V.",

number = "2",

pages = "7597--7602",

editor = "Hideaki Ishii and Yoshio Ebihara and Jun-ichi Imura and Masaki Yamakita",

booktitle = "IFAC-PapersOnLine",

address = "荷兰",

edition = "2",

}

Jiang, D, Liu, K, Jia, L, Qin, Y, Jiang, Y & Wang, Z 2023, Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7. 在 H Ishii, Y Ebihara, J Imura & M Yamakita (编辑), IFAC-PapersOnLine. 2 编辑, IFAC-PapersOnLine, 号码 2, 卷 56, Elsevier B.V., 页码 7597-7602, 22nd IFAC World Congress, Yokohama, 日本, 9/07/23. https://doi.org/10.1016/j.ifacol.2023.10.672

Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7. / Jiang, Dongzhu; Liu, Keyan; Jia, Limin 等.
IFAC-PapersOnLine. 编辑 / Hideaki Ishii; Yoshio Ebihara; Jun-ichi Imura; Masaki Yamakita. 2. 编辑 Elsevier B.V., 2023. 页码 7597-7602 (IFAC-PapersOnLine; 卷 56, 号码 2).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7

AU - Jiang, Dongzhu

AU - Liu, Keyan

AU - Jia, Limin

AU - Qin, Yong

AU - Jiang, Yaopeng

AU - Wang, Zhipeng

PY - 2023/7/1

Y1 - 2023/7/1

N2 - In recent years, UAV(Unmanned Aerial Vehicle) has shown great vitality and potential in automated railway inspection operations. The catenary support device is an important infrastructure on the high-speed railway, which guarantees for the electric power system when the high-speed railway is running. However, the current inspection by UAV cannot automatically obtain multi-scale and standardized image data of the catenary support devices. It presents a serious challenge to the faulty diagnosis of the catenary support devices. Concerning this issue, an automatic multi-scale image capture strategy of catenary support device based on improved YOLOv7 is proposed. Due to the characteristics of less foreground and more background in the image detection of catenary support device, the Focal Loss is introduced. Experimental results show that the convergence speed of the model is improved with high detection accuracy. Furthermore, multi-scale and standardized capture strategies for catenary support device data are proposed. In the deployment experiment, improved YOLOv7 achieves 81.3% mAP, the multi-scale, standardized and normalized image data of catenary support device is captured.

AB - In recent years, UAV(Unmanned Aerial Vehicle) has shown great vitality and potential in automated railway inspection operations. The catenary support device is an important infrastructure on the high-speed railway, which guarantees for the electric power system when the high-speed railway is running. However, the current inspection by UAV cannot automatically obtain multi-scale and standardized image data of the catenary support devices. It presents a serious challenge to the faulty diagnosis of the catenary support devices. Concerning this issue, an automatic multi-scale image capture strategy of catenary support device based on improved YOLOv7 is proposed. Due to the characteristics of less foreground and more background in the image detection of catenary support device, the Focal Loss is introduced. Experimental results show that the convergence speed of the model is improved with high detection accuracy. Furthermore, multi-scale and standardized capture strategies for catenary support device data are proposed. In the deployment experiment, improved YOLOv7 achieves 81.3% mAP, the multi-scale, standardized and normalized image data of catenary support device is captured.

KW - Catenary support device

KW - Improved YOLOv7

KW - Multiscale capture strategy

KW - UAV automatic inspection

UR - https://www.scopus.com/pages/publications/85184959005

U2 - 10.1016/j.ifacol.2023.10.672

DO - 10.1016/j.ifacol.2023.10.672

M3 - 会议稿件

AN - SCOPUS:85184959005

T3 - IFAC-PapersOnLine

SP - 7597

EP - 7602

BT - IFAC-PapersOnLine

A2 - Ishii, Hideaki

A2 - Ebihara, Yoshio

A2 - Imura, Jun-ichi

A2 - Yamakita, Masaki

PB - Elsevier B.V.

T2 - 22nd IFAC World Congress

Y2 - 9 July 2023 through 14 July 2023

ER -

Automatic Detection Strategy of Multi-Scale Catenary Support Device Based on Improved YOLOv7

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此