An Improved Deep Convolutional Neural Network-Based Autonomous Road Inspection Scheme Using Unmanned Aerial Vehicles

Recent advancements in the field of machine learning (ML) provide opportunity to conduct research on autonomous devices for a variety of applications. Intelligent decision-making is a critical task for self-driving systems. An attempt is made in this study to use a deep learning (DL) approach for the early detection of road cracks, potholes, and the yellow lane. The accuracy is not sufficient after training with the default model. To enhance accuracy, a convolutional neural network (CNN) model with 13 convolutional layers, a softmax layer as an output layer, and two fully connected layers (FCN) are constructed. In order to achieve the deeper propagation and to prevent saturation in the training phase, mish activation is employed in the first 12 layers with a rectified linear unit (ReLU) activation function. The upgraded CNN model performs better than the default CNN model in terms of accuracy. For the varied situation, a revised and enriched dataset for road cracks, potholes, and the yellow lane is created. The yellow lane is detected and tracked in order to move the unmanned aerial vehicle (UAV) autonomously by following yellow lane. After identifying a yellow lane, the UAV performs autonomous navigation while concurrently detecting road cracks and potholes using the robot operating system within the UAV. The performance model is benchmarked using performance measures, such as accuracy, sensitivity, F1-score, F2-score, and dice-coefficient, which demonstrate that the suggested technique produces better outcomes.

Improving Traffic Safety By Using Waze User Reports

Road inspection regularity and existing types made by road maintenance crew have not been good enough to be aware what is really happening on the roads. Road users' contribution in road traffic safety is very important to ensure fast reaction on different road hazards. It is important to ensure not only the most common ways to report road hazards on state roads by phone, by email and on social media, but also expand data sources options in modern and user-friendly way. Waze navigation application already had functionality to report road hazards – to warn other application users, but no one acted to solve these road hazards until someone reported them through existing communication channels supported by Latvian State roads or Latvian road maintainer. To ensure better road traffic safety and faster reaction time on road hazards solving, Latvian road maintainer gained access to Waze report feed, and, in corporation with Riga Technical university, made a system for analysing and processing Waze data. As the result - Latvian roads maintainer can improve road safety by faster reaction to road hazards reported by Waze users. Today, up to 70 % from total reports processed by Latvian road maintainer are generated by Waze.

Terrain surveillance system with drone and applied machine vision

Road accidents are a major contribution to the Annual death rates all over the world. India, ranks first globally in the number of fatalities from road accidents. According to the Ministry of Roads & Transportation, India saw over 440,000 road accidents in 2019. As a result, over 150,000 lives were lost. Poor road conditions contribute to these directly and indirectly. In India, safety standards and conditions of roads are maintained by local bodies in a given area of jurisdiction. While there have been several attempts at improving the quality of roads, weren’t instrumental in giving proper results [42]. A recent study suggested that Artificial Intelligence (AI) might help achieve the goals. Some of the AI applications have had better results when powered with Computer Vision. While computer vision has been previously used to identify faults in roads, it is not widely implemented or made available for public use. Road inspection still largely remains a time-consuming manual task, hindering the maintenance process in most cities. Moreover, being unaware of unattended faults on roads is often the cause of road accidents, especially in rough weather conditions that make it impossible for drivers to visually gauge any dangers on their route. The proposed model uses a transfer-learning approach; using Mask R-CNN in identifying the defects at an instance level segmentation. As adding this, it requires less labelling and an additional mask helps in blocking out extra noise around the images. This paper trains a Mask R-CNN architecture-based model to identify potholes, discontinuous roads, blind spots, speed bumps, and the type of road--gravel, concrete, asphalt, tar, or mud--with a dataset of images obtained from a drone. The model is further trained to create depth maps and friction estimates of the roads being surveyed. Once trained, the model is tested on a drone-captured live feed of roads in Chennai, India. The results, once sufficiently accurate, will be implemented in a practical application to help users assess road conditions on their path.

Use of Unmanned Aerial Vehicles (UAVs) and Photogrammetry to Obtain the International Roughness Index (IRI) on Roads

Road inspection and maintenance require a large amount of data collection, where the main limiting factor is the time required to cover long stretches of road, having a negative impact on the optimization of the work. This article aims to identify modern tools for road maintenance and analysis. To carry out the research, recent methodologies are used to guide the work in different stages to adequately justify the processes involved. Using unmanned aerial vehicles (UAVs), cameras, and GPS, three-dimensional virtual models are reconstructed, which are useful for extracting the necessary information since they allow for accurate replication of the captured. In this way, it is possible to obtain longitudinal profiles associated with the road, and with it, the international roughness index (IRI) is calculated, which gives results within 0.1 (m/km) of the certified official results, which shows its potential use and development.

Low-Power Drone-Mountable Real-Time Artificial Intelligence Framework for Road Asset Classification

With the continuous increase in interstate highway traffic and demand for higher safety standards, there is a growing need for rapidly scalable road inspection. Currently, inspection and condition assessment of roadways involve manual operations which increase labor costs and limit the scalability and inspection coverage. Furthermore, manually inspecting highways adds additional safety risks for highway workers and road inspectors. To address these challenges, we envision a fully automated process of highway inspection. This paper presents a novel low-power drone-mountable real-time artificial intelligence (AI) framework for road asset classification through visual sensing, which is the first step toward a fully automated inspection system. We analyzed a state DOT dataset, consisting of 14 different kinds of defected road assets. To this end, we developed our baseline framework using MobileNet-V2, which is a convolutional neural network (CNN) specially developed for mobile and embedded platforms. Since our target dataset was small and CNNs networks require a huge amount of data, we leveraged transfer learning, by pretraining MobileNet-V2 using the ImageNet dataset and then fine-tuned it on our target dataset. This new framework was ported to embedded platforms Nvidia Jetson Nano with the capability to perform on-board drone processing. Overall, our results demonstrate 81.33% accuracy on the test set while processing 7.4 frames per second and occupying a total power of 1.9 W. It achieved a Power Reduction Factor (PRF) of 21.17 over Nvidia TitanV implementation, with only 8.74% impact on the projected drone flight time.

Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems

Prediction models in mobility and transportation maintenance systems have been dramatically improved by using machine learning methods. This paper proposes novel machine learning models for an intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well as their hybrids, i.e., Levenberg–Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE) and standard error (SE). The CMIS model outperforms other models with the promising results of APRE = 2.3303, AAPRE = 11.6768, RMSE = 12.0056 and SD = 0.0210.

Analyzing Road Coverage of Public Vehicles According to Number and Time Period for Installation of Road Inspection Systems

Shortages of engineers and financial resources have made it difficult for municipalities to identify and address problems with aging road infrastructures. To resolve these problems, numerous studies have focused on automating road inspection, including a study in which we developed a smartphone-based road inspection system. For efficient operation of the system, it is necessary to understand the usage of vehicles in which the system will be installed. In this study, we analyzed the usage of public vehicles with long-term global positioning system (GPS) probe data collected from public vehicles operating in Kakogawa city and Fujisawa city in Japan. As a result, we discovered that local governments of the same size have similar tendencies in terms of road coverage. Moreover, we found that installing road inspection systems on only a few public vehicles can cover the entire road inspection area. We anticipate that these results will assist local governments in making informed decisions during the system introduction process and provide an indicator of the accuracy required for road inspection systems to future researchers.

An Intelligent Classification Model for Surface Defects on Cement Concrete Bridges

This paper mainly improves the visual geometry group network-16 (VGG-16), which is a classic convolutional neural network (CNN), to classify the surface defects on cement concrete bridges in an accurate manner. Specifically, the number of fully connected layers was reduced by one, and the Softmax classifier was replaced with a Softmax classification layer with seven defect tags. The weight parameters of convolutional and pooling layers were shared in the pre-trained model, and the rectified linear unit (ReLU) function was taken as the activation function. The original images were collected by a road inspection vehicle driving across bridges on national and provincial highways in Jiangxi Province, China. The images on surface defects of cement concrete bridges were selected, and divided into a training set and a test set, and preprocessed through morphology-based weight adaptive denoising. To verify its performance, the improved VGG-16 was compared with traditional shallow neural networks (NNs) like the backpropagation neural network (BPNN), support vector machine (SVM), and deep CNNs like AlexNet, GoogLeNet, and ResNet on the same sample dataset of surface defects on cement concrete bridges. Judging by mean detection accuracy and top-5 accuracy, our model outperformed all the contrastive methods, and accurately differentiated between images with seven classes of defects such as normal, cracks, fracturing, plate fracturing, corner rupturing, edge/corner exfoliation, skeleton exposure, and repairs. The results indicate that our model can effectively extract the multi-layer features from surface defect images, which highlights the edges and textures. The research findings shed important new light on the detection of surface defects and classification of defect images.