Automatic Pavement Crack Detection Using HMRF-EM Algorithm

Cracks have always been a key issue in road maintenance. The shortage of funds and human resources puts high demands on the automatic detection of cracks. In this paper, we present an efficient and accurate crack detection method. There are two main contributions. First, the combination of the adaptive line detector and the hidden Markov random field model and its expectation-maximization (HMRF-EM) algorithm improves precision. Second, the quantitative description of crack region’s credibility and conditional connection increase the integrity and continuity of the crack. The experimental results demonstrate that this method is effective and accurate. And the crack obtained by this method has higher integrity and continuity compared with other existing crack detection methods.