Detection of TBM tunnel surrounding rock debris based on attention mechanism YOLOv5

Lijie Jiang; Yongliang Wen; Heng Wang; Pei Zhang; Mingze Li; Ruoyu Wang; Lianhui Jia

doi:10.1117/12.2684774

19 October 2023 Detection of TBM tunnel surrounding rock debris based on attention mechanism YOLOv5

Lijie Jiang, Yongliang Wen, Heng Wang, Pei Zhang, Mingze Li, Ruoyu Wang, Lianhui Jia

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 127094P (2023) https://doi.org/10.1117/12.2684774
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

There is background interference, random size, overlapping accumulation and other problems in the detection of surrounding rock debris pieces generated during tunnel boring machine excavation. The traditional manual detection method is highly dependent on the experience and subjective judgment of the detection personnel, and has shortcomings such as high energy consumption and hysteresis. This paper proposes a visual detection method of surrounding rock debris sheet based on YOLOv5-SE model. First, homomorphic filtering and limited contrast adaptive histogram equalization method are used for preprocessing to improve the light intensity and contrast of the debris sheet image; secondly, based on the YOLOv5s model, an attention mechanism is added to the feature channel to selectively emphasize the features of the debris; the SIOU function is used as the loss function, and the detection accuracy is further improved by considering the overlapping area, the center point distance and the true difference; the small target detection layer is added to improve the detection effect of small targets. The experimental results show that the recognition rate of the YOLOv5-SE model reaches 93.7%, which can effectively avoid missed detection and false detection, and the detection speed reaches 30 FPS, which can meet the real-time requirements.

Citation Download Citation

Lijie Jiang, Yongliang Wen, Heng Wang, Pei Zhang, Mingze Li, Ruoyu Wang, and Lianhui Jia "Detection of TBM tunnel surrounding rock debris based on attention mechanism YOLOv5", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 127094P (19 October 2023); https://doi.org/10.1117/12.2684774

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
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Target detection

Small targets

Object detection

Image filtering

Tunable filters

Histograms

Image segmentation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years