Dam surface crack detection based on SE-YOLOv7

Qian Feng; Cuimei Li

doi:10.1117/12.3033192

5 July 2024 Dam surface crack detection based on SE-YOLOv7

Qian Feng, Cuimei Li

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131846C (2024) https://doi.org/10.1117/12.3033192
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference and noise, complex and changeable shape and unbalanced pixels, which results in poor crack detection effect on the dam surface. We propose a dam surface crack detection method based on SE-YOLO and verify it through multiple scenarios. Crack detection on the dam surface is the key link of the safety inspection of the hydropower station, but the complex environment has problems such as large interference noise, complex and changeable shape, and pixel imbalance, which results in poor crack detection effect on the dam surface. A dam surface crack detection method based on SE-YOLO is proposed and validated through a variety of scenarios. By adding the attention mechanism SE between the large backbone of the YOLOv7 model and the Head, the feature extraction ability of the backbone network is enhanced to achieve a better detection effect. Experimental validation analysis was performed on the same dataset using FCN, U-Net, YOLOv7, SE-YOLOv7, and the method presented here. The experimental results show that the two-stage dam surface crack detection method based on SE-YOLO v7 can accurately detect the cracks, and effectively avoid the negative effects. Our mAP method and F1 method can reach 83.81% and 79.98%, respectively, and FPS reaches 77.86Hz, with a significant improvement compared with other models

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Qian Feng and Cuimei Li "Dam surface crack detection based on SE-YOLOv7", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131846C (5 July 2024); https://doi.org/10.1117/12.3033192

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Convolution

Object detection

Education and training

Feature fusion

Image fusion

Performance modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years