Abstract
Evaluation of traffic and environmental impact on pavements using digital images has become increasingly popular in recent years because of the improved efficiency it brings to pavement management. Meanwhile, significant leaps have been made in the sciences of computer vision and image processing. Although automated pavement distress evaluation using digital images has benefitted from the advances in image processing, innovative techniques used in computer vision, such as image characterization using quantification of optical texture properties of images, has not been exploited adequately in pavement evaluation. Several widely used optical texture techniques for characterization of digital images are introduced in this paper, and their useful applications in pavement evaluation are highlighted. Automated and accurate detection of correspondences in progressive images of the same pavement captured during different times is essential for close monitoring of cracks or wear at the project level. Two reliable methods for determining correspondences among pavement images irrespective of the illumination at capture are (a) texture masking and minimum texture distance method, applicable to locations with no significant distress, and (b) homogeneous coordinate geometrical matching and the maximum texture distance to detect the locations of distress. Scaled scattering index, which is a parameter ideal for estimating the size of texture primitives required for texture analysis and characterization of the pavement surface composition, is also introduced. Finally, texture characterization is applied to detection of exact locations of crack propagation and excessive pavement wear.
Get full access to this article
View all access options for this article.