摘要：According to the modern bridge health assessment and testing methods, compared with the traditional manual test to determine fracture, detection method based on digital image which applies digital image processing and pattern recognition technology to test and assess the bridge surface defect images has the characteristics of non-contact and high precision. Taking the grey-scale feature of the crack, this paper will put forward a kind of crack detection method based on multi-scale and multi-perspective. In view of the interference factors such as the holes, dirties and the others on the concrete pavement, we should analyze the characteristics of collected road surface images, and adopt DWT and NSST to resolve the source images from multi-scale, and then establish grey value similarity function, and withdraw the suspected crack information according to the similarity of contrast; second, remove the false crack use connected component measurement, and transfer the problem into graph theory problem; last, use the approximation coefficient of NSST domain, the fusion approximate coefficient of DWT domain and fusion detail coefficients to inverse, transform and rebuild fusion images so as to extract real crack. Through a lot of tests on the concrete pavement picture, experimental results show that this method can achieve real pavement cracks feature extraction, and enjoys a strong practicability.
关键词：Crack detection; Reachable matrix; Multi-scale decomposition; Active ; measure; Similarity
