Research on infrared feature recognition algorithm for water leakage in highway tunnels

Jian Liu; Chengshun Lv; Zhiyaun Zhao; Yunfeng Ding; Quanyi Xie

doi:10.1117/12.2658365

22 December 2022 Research on infrared feature recognition algorithm for water leakage in highway tunnels

Jian Liu, Chengshun Lv, Zhiyaun Zhao, Yunfeng Ding, Quanyi Xie

Proceedings Volume 12460, International Conference on Smart Transportation and City Engineering (STCE 2022); 124603V (2022) https://doi.org/10.1117/12.2658365
Event: International Conference on Smart Transportation and City Engineering (STCE 2022), 2022, Chongqing, China

Abstract

With the rapid development of the world economy, the number and scale of road transportation infrastructure have grown rapidly. In recent years, a large number of highway tunnels have been put into use. The prevalence of water seepage diseases in road tunnels poses a major hazard to the safety of personnel and vehicles. Water seepage detection has been one of the high-priority research topics for tunnel inspection. Previous studies have mainly used a single visible camera as a sensor to detect water leakage areas in images, which is extremely sensitive to insufficient lighting in the tunnel. Considering the existence of temperature difference between the water leakage area and the normal area, we used an infrared camera to collect tunnel lining images and constructed a water leakage area identification algorithm based on the temperature difference between the water leakage area and the normal area using K-means clustering algorithm and low-pass filtering algorithm based on the temperature field distribution of infrared images. This study can provide a new idea for the rapid identification of tunnel water leakage.

Citation Download Citation

Jian Liu, Chengshun Lv, Zhiyaun Zhao, Yunfeng Ding, and Quanyi Xie "Research on infrared feature recognition algorithm for water leakage in highway tunnels", Proc. SPIE 12460, International Conference on Smart Transportation and City Engineering (STCE 2022), 124603V (22 December 2022); https://doi.org/10.1117/12.2658365

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