Automatic road crack detection and classification using image processing techniques, machine learning and integrated models in urban areas: A novel image binarization technique

The quality of the road pavement has always been one of the major concerns for governments around the world. Cracks in the asphalt are one of the most common road tensions that generally threaten the safety of roads and highways. In recent years, automated inspection methods such as image and video processing have been considered due to the high cost and error of manual methods. For this purpose, different image processing techniques and classification methods have been developed by many researchers. In this study, we propose an integrated model includes a heuristic image segmentation technique for crack detection. Furthermore, the accuracy of various classification models such as KNN, decision tree and SVM will be compared. Finally, 5-fold cross validation shows that Subspace KNN method will be more accurate than other classification models which is used in this study. On the other hand, we also simulate the depth and density of different segment of crack by utilizing density matrix values.

Automatic road crack detection and classification using image processing techniques, machine learning and integrated models in urban areas: A novel image binarization technique Keywords:

crack detection , classification , machine learning , integrated model , segmentation