Cracks are one type of pavement surface damages, whose assessment is very important for developing road network maintenance strategies, which aims to ensure the functioning of the road and driving safety. Existing methods for automatic crack detection depend mostly on expensive equipment and high maintenance and cannot divide the crack segments accurately. This paper discusses an automation method of classification and segmentation of asphalt pavement cracks. The goal of the research is to classify asphalt pavement cracks using the classification method of the Support Vector Machine (SVM) algorithm and segmentation method of the OTSU algorithm. The OTSU algorithm for segmentation has advantages in choosing the optimal threshold that is stable. This algorithm is proven to be more effective and stronger than conventional segmentation algorithms. For detection results, the proposed method achieves overall accuracy.
Road Crack Detection using Support Vector Machine (SVM) and OTSU Algorithm
2019-11-01
348698 byte
Conference paper
Electronic Resource
English
An Improved Otsu Image Segmentation Algorithm for Path Mark Detection under Variable Illumination
British Library Conference Proceedings | 2005
|Traffic Sign Recognition Using Ridge Regression and OTSU Method
British Library Conference Proceedings | 2011
|