In the process of road pavement health and safety assessment, crack detection plays a pivotal role in a preventive maintenance strategy. Recently, Convolutional Neural Networks (CNNs) have been applied to automatically identify the cracks on concrete pavements. The effectiveness of a CNN-based road crack detection and measurement method depends on several factors, including the image segmentation of cracks with complex topology, the inference of noises with similar texture to the distress, and the sensitivity to thin cracks. The presence of shadows, strong light reflections, and road markings can also severely affect the accuracy in detection and measurement. In this study, a review of the state-of-the-art CNN methods for crack identification is presented, paying attention to existing limitations. Then, a novel deep residual convolutional neural network (Parallel ResNet) is proposed with the aim of creating a high-performance pavement crack detection and measurement system. The challenge and special feature of Parallel ResNet is to remove the noise inference, identifying even thin and complex cracks correctly. The performance of Parallel ResNet has been investigated on two publicly available datasets (CrackTree200 and CFD), comparing it with that of competing methods suggested in the literature. Parallel ResNet reached the maximum scores in Precision (94.27%), Recall (92.52%), and F1 (93.08%) using the CrackTree200 dataset. Similarly, for the CFD dataset the novel method achieved high values in Precision (96.21%), Recall (95.12%), and F1 (95.63%). Based on the crack detection and image recognition results, mathematical morphology was then used to further minimize noise and accurately segment the road diseases, obtaining the outer contours of the connected domain in crack images. Therefore, crack skeletons have been extracted to measure the distress length, width, and area on images of rigid pavements. The experimental results show that Parallel ResNet can effectively minimize noise to obtain the geometry of cracks. The results of crack characteristic measurements are accurate and Parallel ResNet can be assumed as a reliable method in pavement crack image analysis, in order to plan the best road maintenance strategy.

Road networks are monitored to evaluate their decay level and the performances regarding ride comfort, vehicle rolling noise, fuel consumption, etc. In this study, a novel inertial sensor-based system is proposed using a low-cost inertial measurement unit (IMU) and a global positioning system (GPS) module, which are connected to a Raspberry Pi Zero W board and embedded inside a vehicle to indirectly monitor the road condition. To assess the level of pavement decay, the comfort index a_wz defined by the ISO 2631 standard was used. Considering 21 km of roads with different levels of pavement decay, validation measurements were performed using the novel sensor, a high performance inertial based navigation sensor, and a road surface profiler. Therefore, comparisons between a_wz determined with accelerations measured on the two different inertial sensors are made; in addition, also correlations between a_wz, and typical pavement indicators such as international roughness index, and ride number were also performed. The results showed very good correlations between the a_wz values calculated with the two inertial devices (R² = 0.98). In addition, the correlations between a_wz values and the typical pavement indices showed promising results (R² = 0.83–0.90). The proposed sensor may be assumed as a reliable and easy-to-install method to assess the pavement conditions in urban road networks, since the use of traditional systems is difficult and/or expensive.

Environmental safeguards promote innovative construction technologies for sustainable pavements. On these premises, this study investigated four hot mix asphalt (HMA) mixtures—i.e., A, B, C, and D—for the railway sub-ballast layer with 0%, 10%, 20%, and 30% reclaimed asphalt pavement (RAP) by total aggregate mass and a rejuvenator additive, varying the bitumen content between 3.5% and 5.0%. Both Marshall and gyratory compactor design methods have been performed, matching the stability, indirect tensile strength, and volumetric properties of each mixture. Dynamic stiffness and fatigue resistance tests provided mechanical performances. Laboratory results highlighted that the RAP and the rejuvenator additive increase the mechanical properties of the mixtures. In addition, the comparative analysis of production costs revealed up to 20% savings as the RAP content increased, and the life cycle impact analysis (LCIA) proved a reduction of the environmental impacts (up to 2% for resource use-fossils, up to 7% for climate change, and up to 13% for water use). The experimental results confirm that HMA containing RAP has mechanical performances higher than the reference mixture with only virgin raw materials. These findings could contribute to waste management and reduce the environmental and economic costs, since the use of RAP in the sub-ballast is not, so far, provided in the Italian specifications for railway construction.

Repairing potholes is a task for municipalities to prevent serious road user injuries and vehicle damage. This study presents a low-cost, high-performance pothole monitoring system to maintain urban roads. The authors developed a methodology based on photogrammetry techniques to predict the pothole’s shape and volume. A collection of overlapping 2D images shot by a Raspberry Pi Camera Module 3 connected to a Raspberry Pi 4 Model B has been used to create a pothole 3D model. The Raspberry-based configuration has been mounted on an autonomous and remote-controlled robot (developed in the InfraROB European project) to reduce workers’ exposure to live traffic in survey activities and automate the process. The outputs of photogrammetry processing software have been validated through laboratory tests set as ground truth; the trial has been conducted on a tile made of asphalt mixture, reproducing a real pothole. Global Positioning System (GPS) and Geographical Information System (GIS) technologies allowed visualising potholes on a map with information about their centre, volume, backfill material, and an associated image. Ten on-site tests validated that the system works in an uncontrolled environment and not only in the laboratory. The results showed that the system is a valuable tool for monitoring road potholes taking into account construction workers’ and road users’ health and safety.

Airport pavements should ensure regular and safe movements during their service life; the management body has to monitor the functional and structural characteristics, and schedule maintenance work, balancing the often conflicting goals of safety, economic and technical issues. This paper presents a remote monitoring system to evaluate the structural performance of a runway composed of concrete thresholds and a flexible central runway. Thermometers, strain gauges, and pressure cells will be embedded at different depths to continuously monitor the pavement’s response to traffic and environmental loads. An innovative system allows data acquisition and processing with specific calculation models, in order to inform the infrastructure manager, in real time, about the actual conditions of the pavement. In this way, the authors aim to develop a system that provides useful information for the correct implementation of an airport pavement management system (APMS) based on real-life data. Indeed, it permits comprehensive monitoring functions to be performed, based on the embedded sensing network.

A comprehensive representation of the road pavement state of health is of great interest. In recent years, automated data collection and processing technology has been used for pavement inspection. In this paper, a new signal on graph (SoG) model of road pavement distresses is presented with the aim of improving automatic pavement distress detection systems. A novel nonlinear Bayesian estimator in recovering distress metrics is also derived. The performance of the methodology was evaluated on a large dataset of pavement distress values collected in field tests conducted in Kazakhstan. The application of the proposed methodology is effective in recovering acquisition errors, improving road failure detection. Moreover, the output of the Bayesian estimator can be used to identify sections where the measurement acquired by the 3D laser technology is unreliable. Therefore, the presented model could be used to schedule road section maintenance in a better way.