Road crack detection based on faster R-CNN

Liangliang Zhu; Juan Qin; Zhiling Guo; Xiaobing Zhang; Shuo Feng; Honglin Liu

doi:10.1117/12.2620322

22 December 2021 Road crack detection based on faster R-CNN

Liangliang Zhu, Juan Qin, Zhiling Guo, Xiaobing Zhang, Shuo Feng, Honglin Liu

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 1205844 (2021) https://doi.org/10.1117/12.2620322
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

Road crack is an important factor that causes highway damage. There are three main types of road cracks: longitudinal crack, transverse crack and chapped crack. Road crack detection has developed from manual detection to semi-automatic detection based on image processing and full-automatic detection based on the combination of image processing and deep learning technology. This project is dedicating to detect road cracks by using Faster R-CNN (Faster Region-based Convolution Network). In the project, VGG16 is chosen as the backbone network architecture. The fully-connected layer and the pooling operation of the last layer are not used, only the convolution layer, pooling layer and ReLU layer of VGG16 are used. According to the characteristics of cracks, it generates the proportion size of the bounding box. The accuracy and recall rates are 90%, 95% and 98%, 97% respectively, on the self-made data set and on the open data set. The problem that the road crack identification algorithm is affected by the environment is improved.

Citation Download Citation

Liangliang Zhu, Juan Qin, Zhiling Guo, Xiaobing Zhang, Shuo Feng, and Honglin Liu "Road crack detection based on faster R-CNN", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 1205844 (22 December 2021); https://doi.org/10.1117/12.2620322

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
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Roads

Detection and tracking algorithms

3D modeling

Data modeling

Convolution

Network architectures

Visual process modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years