3D pavement surface reconstruction using an RGB-D sensor

TL;DR

This paper presents a cost-effective method for 3D pavement surface reconstruction using RGB-D sensors, specifically Kinect, enabling pavement distress detection without expensive laser scanners.

Contribution

It introduces a novel, low-cost approach combining Kinect sensors, calibration, SVD correction, and image stitching algorithms for pavement 3D reconstruction and defect detection.

Findings

Successful 3D reconstruction of pavement surfaces

Effective detection of pavement surface defects

Cost reduction compared to laser-based methods

Abstract

A core procedure of pavement management systems is data collection. The modern technologies which are used for this purpose, such as point-based lasers and laser scanners, are too expensive to purchase, operate, and maintain. Thus, it is rarely feasible for city officials in developing countries to conduct data collection using these devices. This paper aims to introduce a cost-effective technology which can be used for pavement distress data collection and 3D pavement surface reconstruction. The applied technology in this research is the Kinect sensor which is not only cost-effective but also sufficiently precise. The Kinect sensor can register both depth and color images simultaneously. A cart is designed to mount an array of Kinect sensors. The cameras are calibrated and the slopes of collected surfaces are corrected via the Singular Value Decomposition (SVD) algorithm. Then, a procedure is proposed for stitching the RGB-D (Red Green Blue Depth) images using SURF (Speeded-up Robust Features) and MSAC (M-estimator SAmple Consensus) algorithms in order to create a 3D-structure of the pavement surface. Finally, transverse profiles are extracted and some field experiments are conducted to evaluate the reliability of the proposed approach for detecting pavement surface defects.