Stereo-Based 3D Reconstruction of Potholes by a Hybrid, Dense Matching Scheme

Abstract

Automated condition monitoring of pavements is seeing a paradigm shift in the twenty-first century, as the focus is increasingly shifting from visual to 3D imaging. The 3D measurement represents the ground truth, within the bounds of discretization of the imager. Hence, working with the 3D data and interpreting it is a lot easier. The 3D laser scanners are the current norm for range imaging. Laser scanners, although technically versatile and extremely accurate, are very expensive. Therefore, the need for alternative 3D imaging technologies is imperative, especially in the developing world context. The coming decade will see alternative technologies first target large pavement distresses, like potholes, before moving onto smaller defect types. In this regard, this is the first study that treats the stereo imaging of roads from a moving vehicle, for any distresses, and especially for pothole measurements. A fast stereo matching procedure is proposed. A preliminary keypoint matching estimates the global disparity between the stereo pair. The estimated disparity is used toward further keypoint and block matching procedure, by concentrating on smaller image regions. Images obtained from a moving vehicle are preprocessed to reduce the effects of image blur. Furthermore, algorithms to determine key critical metrological parameters, such as the area, depth, and volume, of a pothole are also developed. A benchmarking of the proposed system shows that the 3D measurements are within 3 mm for static situations and 5 mm when imaged from a moving vehicle. At 10-km/h vehicle speed, potholes are imaged to accuracies of -20% for volume, -15% for area, and -4% for depth, when compared to static imagery.