Machine learning algorithms application to road defects classification

Issue title: Proceedings from COMPSE 2016: Current Trends in Optimization Technology

Guest editors: Pandian Vasant and Utku Kose

Article type: Research Article

Authors: Nguyen, T.H.^{a; *} | Nguyen, T.L.^a | Sidorov, D.N.^{a; c} | Dreglea, A.I.^b

Affiliations: [a] Irkutsk National Research Technical University, Irkutsk, Russia | [b] Vinogradov Institute of Geochemistry SB RAS, Irkutsk, Russia | [c] Energy Systems Institute SB RAS, Irkutsk, Russia

Correspondence: [*] Corresponding author: T.H. Nguyen, Irkutsk National Research Technical University, Irkutsk, Russia. E-mail: [email protected].

Abstract: The novel approach for automatic detection and classification of road defects is proposed based on shape and texture features analysis. The system includes three main steps: defects position detection, feature contour extraction followed by classification of defects. The proposed approach is implemented in Matlab for automatic detection and classification of defects based on digital images analysis combined with machine learning algorithms such as the random forest algorithm and boosting. Segmentation is implemented using graph-cuts method and Markov random fields. The efficiency of proposed approach is demonstrated on the real data set.

Keywords: Road defects, pavement condition, Markov random fields, graph-cuts method, a random forest algorithm, boosting algorithm

DOI: 10.3233/IDT-170323

Journal: Intelligent Decision Technologies, vol. 12, no. 1, pp. 59-66, 2018