Multiresolution Information Mining for Pavement Crack Image Analysis

Abstract

Empirical mode decomposition (EMD) is a multiresolution data analysis method recently developed to cater to the inherent nonstationarity in real-world signals. A two-dimensional (2D) extension of EMD is used in this paper as a pavement distress image analytical tool. The algorithm decomposes an image into a set of narrow band components (called bidimensional intrinsic mode function, or BIMF) that uniquely reflect the variations in the image. Although some components could have good image edge characteristics, others might hold fidelity to the shape and size of objects or trends in the image. Therefore, the complete spatial and frequency characteristic of a desired image feature might also be divided into the different components, indicating that all attributes of a desired feature might not be found in a single component. An optimal solution requires image mining from the different component resolutions to accurately extract those specific attributes without compromising certain spatial and frequency characteristics. Two major contributions to pavement image analysis are achieved. First, the paper explores pavement image denoising or enhancement by combining the EMD and a weighted reconstruction technique as a tool for background standardization of images acquired under different types of illumination effects. Second, using principal component pursuit (PCP), the authors reconstruct a composite image by selecting salient information from coarse and fine resolution BIMFs useful for accurate extraction of linear patterns in a pavement distress image. Compared with conventional image reconstruction or approximation techniques, the methodology used in this paper yields better results.