版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:LUNAM Univ IFSTTAR F-44344 Bouguenais France Univ Toulouse INP ENSEEIHT IRIT F-31071 Toulouse France LUNAM Univ IRCCyN Ecole Cent Nantes CNRSUMR 6597 F-44321 Nantes France
出 版 物:《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 (IEEE Trans. Intell. Transp. Syst.)
年 卷 期:2016年第17卷第10期
页 面:2718-2729页
核心收录:
学科分类:0808[工学-电气工程] 08[工学] 0814[工学-土木工程] 0823[工学-交通运输工程]
基 金:French Region Pays de la Loire
主 题:Crack detection minimal path Dijkstra algorithm non destructive control road surface condition
摘 要:This paper proposes a new algorithm for automatic crack detection from 2D pavement images. It strongly relies on the localization of minimal paths within each image, a path being a series of neighboring pixels and its score being the sum of their intensities. The originality of the approach stems from the proposed way to select a set of minimal paths and the two post-processing steps introduced to improve the quality of the detection. Such an approach is a natural way to take account of both the photometric and geometric characteristics of pavement images. An intensive validation is performed on both synthetic and real images (from five different acquisition systems), with comparisons to five existing methods. The proposed algorithm provides very robust and precise results in a wide range of situations, in a fully unsupervised manner, which is beyond the current state of the art.