Drainage pipe defect identification based on convolutional neural 
network

Dong Zhou; Feifei Liu; Xiangfei Dou; Jie Chen; Zhexin Wen

doi:10.1117/12.2671480

16 March 2023 Drainage pipe defect identification based on convolutional neural network

Dong Zhou, Feifei Liu, Xiangfei Dou, Jie Chen, Zhexin Wen

Proceedings Volume 12593, Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022); 125930X (2023) https://doi.org/10.1117/12.2671480
Event: 2nd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022), 2022, Guangzhou, China

Abstract

At present, the detection of drainage pipe defects adopts manual frame-by-frame naked eye discrimination, which has low detection efficiency and high cost, so a two-path multi-receptive convolutional neural network is designed, which also takes into account a certain small volume on the basis of obtaining the highest classification index. The experimental results show that the volume accuracy of the designed model is 92.3%, the recall rate is 91.1%, the F1 score is 91.7%, the model volume is 30.7M, the parameter quantity is 8.97M, and the calculation amount is 2.25G. Compared with other networks, this model is more suitable for automatic identification of drainage pipes.

Citation Download Citation

Dong Zhou, Feifei Liu, Xiangfei Dou, Jie Chen, and Zhexin Wen "Drainage pipe defect identification based on convolutional neural network", Proc. SPIE 12593, Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022), 125930X (16 March 2023); https://doi.org/10.1117/12.2671480

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