Intelligent detection of asphalt pavement abrasion status based on laser and mobile images

Cheng Hua; Xie Chenghao; Ma Shaochen; Tang Wen

doi:10.1117/12.3010783

1 November 2023 Intelligent detection of asphalt pavement abrasion status based on laser and mobile images

Cheng Hua, Xie Chenghao, Ma Shaochen, Tang Wen

Proceedings Volume 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023); 129170D (2023) https://doi.org/10.1117/12.3010783
Event: 3rd International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 2023, Shanghai, China

Abstract

In order to improve the convenience and the efficiency of the asphalt pavement surface wear test, we provided a intelligent detection method based on 3D and 2D pavement surface texture information. We collected the actual pavement surface texture data by a handheld laser 3D scanner and a smartphone. With the 3D points data cloud, we calculated the pavement wear index (PWI) to grade the road surface wear status and extracted of several interested parameters. According to the grading of road surface wear status from the 3D data cloud, the corresponding 2D mobile images were labeled and the training set and test set for neural network training were established. Finally we used a improved ResNet50 network to build a classifier, and tested the classifier performance. The result showed that this method could quickly and effectively predict and classify the road wear state with an accuracy of 94.17% which was adequate for road wear detection.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Cheng Hua, Xie Chenghao, Ma Shaochen, and Tang Wen "Intelligent detection of asphalt pavement abrasion status based on laser and mobile images", Proc. SPIE 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 129170D (1 November 2023); https://doi.org/10.1117/12.3010783

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