-Pavement crack detection using computer vision techniques has been studied widely over the past several years. However, these techniques have faced several limitations when applied to real world situations due to for example changes of lightning conditions or variation in textures. But the recent advancements in the field of artificial neural networks, especially in deep learning, have paved a new way for applying computer vision methods to pavement crack detection. Even though deep learning has been used before for crack detection, the network used is rather shallow when compared to the current networks used for other applications. In this paper we demonstrate the effectiveness of using deeper networks in computer vision based pavement crack detection for improved accuracy. We also show how variations in location of training and testing datasets affect the performance of the deep learning based pavement crack detection method.

No abstract

Detection of road pavement cracks is important and needed at an early stage to repair the road and extend its lifetime for maintaining city roads. Cracks are hard to detect from images taken with visible spectrum cameras due to noise and ambiguity with background textures besides the lack of distinct features in cracks. Hyperspectral images are sensitive to surface material changes and their potential for road crack detection is explored here. The key observation is that road cracks reveal the interior material that is different from the worn surface material. A novel asphalt crack index is introduced here as an additional clue that is sensitive to the spectra in the range 450–550 nm. The crack index is computed and found to be strongly correlated with the appearance of fresh asphalt cracks. The new index is then used to differentiate cracks from road surfaces. Several experiments have been made, which confirmed that the proposed index is effective for crack detection. The recall-precision analysis showed an increase in the associated F1-score by an average of 21.37% compared to the VIS2 metric in the literature (a metric used to classify pavement condition from hyperspectral data).

-This paper presents the use of off-the-shelf products as a low cost solution to bridge bearing inspection. A commercial product, known as a DiddyBorg, is a robot designed for use with a Raspberry Pi as the on-board computer. The DiddyBorg is used as a robotic platform to make a photogrammetric survey of the bearing area of a bridge. The images collected from this survey are then used to make a 3D reconstruction using Structurefrom-Motion (SfM) and software 3DFlow Zephyr Aerial (Zephyr). The quality of the 3D reconstruction had an accuracy of +/-30 mm when compared to the known dimensions of the area. The resulting point cloud was then used as a map that the robot can use for navigation purposes. In particular we present a simple localization algorithm based on distance three readings measured from the robot.

a b s t r a c tA multi-physics computational method is presented to model the effect of internally and externally-carried fuel on aeroelastic behaviour of a pitch-plunge aerofoil model through the transonic regime. The model comprises three strongly coupled solvers: a compressible finite-volume Euler code for the external flow, a two-degree of freedom spring model and a smoothed particle hydrodynamics solver for the fuel. The smoothed particle hydrodynamics technique was selected as this brings the benefit that nonlinear behaviour such as wave breaking and tank wall impacts may be included. Coupling is accomplished using an iterative method with subcycling of the fuel solver to resolve the differing timestep requirements. Results from the fuel-structural system are validated experimentally, and internally and externally-carried fuel is considered using time marching analysis. Results show that the influence of the fuel, ignoring the added mass effect, is to raise the flutter boundary at transonic speeds, but that this effect is less pronounced at lower Mach numbers. The stability boundary crossing is also found to be less abrupt when the effect of fuel is included and limit cycles often appear. An external fuel tank is seen to exhibit a lower stability boundary, while the response shows a beating effect symptomatic of two similar frequency components, potentially due to interaction between vertical and horizontal fuel motion.