Fusing complementary images for pavement cracking measurements

Abstract

Cracking is a major pavement distress that jeopardizes road serviceability and traffic safety. Automated pavement distress survey (APDS) systems have been developed using digital imaging technology to replace human surveys for more timely and accurate inspections. Most APDS systems require special lighting devices to illuminate pavements and prevent shadows of roadside objects that distort cracks in the image. Most artificial lighting devices are laser based, and are either hazardous to unprotected people or require dedicated power supplies on the vehicle. This study was aimed to develop a new imaging system that can scan pavement surface at highway speed and determine the level of severity of pavement cracking without using any artificial lighting. The new system consists of dual line-scan cameras that are installed side by side to scan the same pavement area as the vehicle moves. Cameras are controlled with different exposure settings so that both sunlit and shadowed areas can be visible in two separate images. The paired images contain complementary details useful for reconstructing an image in which the shadows are eliminated. This paper intends to present (1) the design of the dual line-scan camera system, (2) a new calibration method for line-scan cameras to rectify and register paired images, (3) a customized image-fusion algorithm that merges the multi-exposure images into one shadow-free image for crack detection, and (4) the results of the field tests on a selected road over a long period.

Revisión de métodos para la clasificación de fallas superficiales en pavimentos flexibles

“…Los sistemas comerciales, [50] -[54], usan una combinación de cámaras digitales apoyada por varios sensores, lo que los hace más robustos y al mismo tiempo costosos. Las imágenes digitales 2D se utilizan con frecuencia, como se observa en [15] - [30] y [34] - [36]; sin embargo, los métodos 2D no pueden detectar algunos tipos de falla debido a la falta de información de profundidad y pueden tener dificultad para discriminar áreas oscuras, como sombras e iluminación deficiente. Para hacer frente a estas desventajas, se propusieron sistemas que obtienen modelos 3D partiendo de imágenes 2D, [31] - [33], y también se incorporan los sistemas de escaneo láser que pueden recopilar perfiles 3D para construir superficies de pavimento [5] - [6], [9] - [13].…”

“…Triangulación [5] [6] [7] [8] Tiempo de vuelo [9] Luz estructurada [10] [11] [12] [13] Cámaras digitales Cámaras de escaneo Lineal [15] [16] [17] [18] [19] Cámaras de escaneo por área [20]…”

“…[15] - [19] usan cámaras de escaneo lineal para adquirir los datos del pavimento. Para mejorar las condiciones de iluminación, [16] y [19] utilizan módulos de iluminación láser; en [15], se eliminan las sombras reconstruyendo la imagen a partir de imágenes complementarias capturadas con dos cámaras.…”

Active solution of homography for pavement crack recovery with four laser lines

“…The accuracy of the pavement image system is evaluated on different lighting conditions. The detection system named the automated pavement distress survey (APDS) is designed by Yao M. 22 to achieve the automatic inspection of pavement cracks. The developed system consists of two line-scan cameras.…”

Measuring fiber orientations in nonwoven web images using corner detection by Bézier fitting curves

“…Image fusion is a process of combining information from multiple images into a single composite image. 8 Wang and colleagues proposed a multi-focus image fusion technique to generate a sharp image from sequential images focused at different depths for measuring fiber orientations in thick nonwovens. 9 However, most of these existing image-analysis algorithms regarded a nonwoven web as a single structure without dissecting fibers that were bonded or intersected with others before calculating fiber orientations.…”