Adaboost-based Crack Detection Method for Pavement

2018 International Conference on Civil and Hydraulic Engineering

土木建筑工程;水利工程

Wang, Shibing^1 ; Yang, Fan^1 ; Cheng, Yunmei^1 ; Yang, Yuanyuan^2 ; Wang, Yuzeng^2

School of Mechanical Engineering, University of Jinan, Jinan, Shandong

250022, China^1

School of Electrical Engineering, University of Jinan, Jinan, Shandong

250022, China^2

关键词: AdaBoost algorithm;    Detection methods;    Highway pavement;    Pavement cracks;    Road quality;    Texture feature extraction;    Texture features;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/189/2/022005/pdf
DOI  :  10.1088/1755-1315/189/2/022005

学科分类：土木及结构工程学

来源: IOP

【 摘 要 】

In highway pavement, pavement crack is the most common and harmful disease, which has seriously affected road quality. This article reviews the current texture feature processing algorithms and analyses the principle of Adaboost algorithm from aspects of image processing, texture feature extraction and recognition. And we use OpenCV to train classifiers and identify cracks in cement pavements and asphalt pavements from a software perspective. Finally, this paper uses Adaboost algorithm to detect the cracks on cement pavement and asphalt pavement and achieve the desired effect.