Road Condition Evaluation Research Articles

Research on road crack segmentation based on deep convolution and transformer with multi-branch feature fusion

Abstract Efficient and precise identification of road pavement cracks contributes to better evaluation of road conditions. In practical road maintenance and safety assessment, traditional manual crack detection methods are time-consuming, physically demanding, and highly subjective. In addition, crack recognition based on image processing techniques lacks robustness. In this paper, a multi-branch feature fusion road crack segmentation network model (DTPC) based on deep convolution and transformer modules is proposed. The model is used for pixel-level segmentation of road crack images, which is a good solution to the existing needs and helps to repair dangerous cracks promptly in the follow-up work to prevent serious disasters due to crack breakage. Firstly, combine deep convolution with transformer modules to achieve precise local extraction and global contextual feature extraction. Secondly, a dual-channel attention mechanism is em-ployed to help the model better address information loss and positional offset issues. Finally, three-branch outputs are fused to obtain prediction maps that intuitively determine recognition results. The proposed model is tested for accuracy using a dedicated road pavement crack dataset. Results show that compared to mainstream models such as SegFormer, HRNet, PSPNet, and FCN, the DTPC model achieves the highest MIoU score (86.72%) and F1 score (92.49%).

A multimodal deep learning approach for gravel road condition evaluation through image and audio integration

This study investigates the combination of audio and image data to classify road conditions, particularly focusing on loose gravel scenarios. The dataset underwent binary categorisation, comprising audio segments capturing gravel sounds and corresponding images. Early feature fusion, utilising a pre-trained Very Deep Convolutional Networks 19 (VGG19) and Principal component analysis (PCA), improved the accuracy of the Random Forest classifier, surpassing other models in accuracy, precision, recall, and F1-score. Late fusion, involving decision-level processing with logical disjunction and conjunction gates (AND and OR) in combination with individual classifiers for images and audio based on Densely Connected Convolutional Networks 121 (DenseNet121), demonstrated notable performance, especially with the OR gate, achieving 97 % accuracy. The late fusion method enhances adaptability by compensating for limitations in one modality with information from the other. Adapting maintenance based on identified road conditions minimises unnecessary environmental impact. This method can help to identify loose gravel on gravel roads, substantially improving road safety and implementing a precise maintenance strategy through a data-driven approach.

An economic approach to road condition assessment using road user feedback: A new model and its application

ABSTRACT Assessing roadway assets condition is the prerequisite of an efficient road management system. It requires participation from the top management, equipment, trained human resources, and dedicated funding. Newfoundland and Labrador have 13,500 lane kilometers of roads, of which almost 7,700 kilometers belong to the local jurisdictions. Local agencies typically consult the Transportation Association of Canada's pavement management guidelines for managing the road networks. But, municipality roads require more specified guidelines considering issues like lack of human resources, equipment, inadequate funding, environmental factors, and public expectations. To better maintain these roads, evaluation of road conditions is the first step. However, a proper evaluation system needs considerable funding, a trained workforce, and necessary equipment. Hence, the idea of using road users’ feedback is introduced in this paper. Citizens from 108 municipalities of the province participated in a feedback survey where they were asked questions about roadway assets condition. The survey resulted in a significant amount of data. First, an exploratory analysis of the road users’ feedback data was conducted. Then, a simple distress-based pavement performance model was developed. This model can be adopted by the local agencies as a simple decision-making tool. To make the model practical, a smartphone application called MUNPave is also introduced in this paper.

Local Intensity Order Transformation for Robust Curvilinear Object Segmentation.

Segmentation of curvilinear structures is important in many applications, such as retinal blood vessel segmentation for early detection of vessel diseases and pavement crack segmentation for road condition evaluation and maintenance. Currently, deep learning-based methods have achieved impressive performance on these tasks. Yet, most of them mainly focus on finding powerful deep architectures but ignore capturing the inherent curvilinear structure feature (e.g., the curvilinear structure is darker than the context) for a more robust representation. In consequence, the performance usually drops a lot on cross-datasets, which poses great challenges in practice. In this paper, we aim to improve the generalizability by introducing a novel local intensity order transformation (LIOT). Specifically, we transfer a gray-scale image into a contrast-invariant four-channel image based on the intensity order between each pixel and its nearby pixels along with the four (horizontal and vertical) directions. This results in a representation that preserves the inherent characteristic of the curvilinear structure while being robust to contrast changes. Cross-dataset evaluation on three retinal blood vessel segmentation datasets demonstrates that LIOT improves the generalizability of some state-of-the-art methods. Additionally, the cross-dataset evaluation between retinal blood vessel segmentation and pavement crack segmentation shows that LIOT is able to preserve the inherent characteristic of curvilinear structure with large appearance gaps. An implementation of the proposed method is available at https://github.com/TY-Shi/LIOT.

Classification of the Acoustics of Loose Gravel.

Road condition evaluation is a critical part of gravel road maintenance. One of the assessed parameters is the amount of loose gravel, as this determines the driving quality and safety. Loose gravel can cause tires to slip and the driver to lose control. An expert assesses the road conditions subjectively by looking at images and notes. This method is labor-intensive and subject to error in judgment; therefore, its reliability is questionable. Road management agencies look for automated and objective measurement systems. In this study, acoustic data on gravel hitting the bottom of a car was used. The connection between the acoustics and the condition of loose gravel on gravel roads was assessed. Traditional supervised learning algorithms and convolution neural network (CNN) were applied, and their performances are compared for the classification of loose gravel acoustics. The advantage of using a pre-trained CNN is that it selects relevant features for training. In addition, pre-trained networks offer the advantage of not requiring days of training or colossal training data. In supervised learning, the accuracy of the ensemble bagged tree algorithm for gravel and non-gravel sound classification was found to be 97.5%, whereas, in the case of deep learning, pre-trained network GoogLeNet accuracy was 97.91% for classifying spectrogram images of the gravel sounds.

Live Road Condition Assessment with Internal Vehicle Sensors

Modern cars are equipped with many sensors that measure information about the vehicle and its surroundings. These measurements are therefore related to the ride-surface conditions over which the vehicle is passing. The paper commences by outlining a four-component vision for performing road condition evaluation based on in-vehicle sensor readings and subsequent feeding of pavement management systems (PMSs) with live condition information. This is expected to enrich the functionalities of PMSs, and ultimately lead to improved maintenance and repair decisions. Next the LiRA (Live Road Assessment) project—an ongoing proof-of-concept attempt to realize the vision components—is presented. The project elements and software architecture are described in detail, listing any assumptions, compromises, and challenges. LiRA involves a fleet of 400 electric cars operating in Copenhagen, both within the city streets and nearby highways. Sensor data collection is performed with a customized Internet of Things (IoT) device installed in the cars. Data processing and structuring involve new software tools for quality control, spatio-temporal interpolation, and map matching. A hybrid approach, combining machine learning models with physical (mechanics-based) models, is currently being applied to convert data into relevant information for PMSs. Based on the experience thus far with LiRA, the vision actualization is deemed achievable, workable, and up-scalable.

Calibration of smartphone sensors to evaluate the ride quality of paved and unpaved roads

ABSTRACT Transportation agencies report that millions of crashes are caused by poor road conditions every year, which makes the localisation of roadway anomalies extremely important. Common methods of road condition evaluation require special types of equipment that are usually expensive and time-consuming. Therefore, the use of smartphones has become a potential alternative. However, differences in the sensitivity of their inertial sensors and their sample rate can result in measurement inconsistencies. This study validated those inconsistencies by using three different types of smartphones to collect data from the traversal of both a paved and an unpaved road. Three calibration methods were used including the reference-mean, reference-maximum, and reference-road-type methods. Statistical testing under identical conditions of device mounting using the same vehicle revealed that the roughness indices derived from each device and road type are normally distributed with unequal means. Consequently, applying a calibration coefficient to equalise the means of the distributions of roughness indices produced from any device using the reference mean method resulted in consistent measurements for both road types.

Evaluation of road condition based on BA-BP algorithm

BP (Back Propagation) neural network has been widely applied for classification tasks including road condition evaluation, however, BP model has the problem of lower accuracy and slow convergence rate. A novel road condition evaluation method based on BA-BP (Bat-Back Propagation) algorithm is proposed for the unstructured small road condition evaluation, which filled the vacancy of specific small road scenes. Firstly, five kinds of road condition features including roughness, curvature, obstacle width to height ratio, obstacle effective area ratio, obstacle coefficient are defined and extracted. Then obstacles from region of interest (ROI) in front of the vehicle are analyzed. Finally, Bat algorithm is used to optimize the searching of initial network weights and thresholds, which obtained a higher accuracy of 95.15% and efficient training process. Comparison experiments showed that the proposed approach improved the accuracy with 5.31%, 3.32%, 3.17% than the BP, GA-BP and FA-BP model, respectively. As for the processing time of collected road data, BA-BP network consumed less time of 2 s and 3.9 s compared with GA-BP and FA-BP. Proposed method also outperformed than most of the state-of-the-art approaches with higher accuracy and simpler hardware environments, which proved its potential of being popularized in large scale real-time systems.

Lane Marking Detection and Reconstruction with Line-Scan Imaging Data.

Lane marking detection and localization are crucial for autonomous driving and lane-based pavement surveys. Numerous studies have been done to detect and locate lane markings with the purpose of advanced driver assistance systems, in which image data are usually captured by vision-based cameras. However, a limited number of studies have been done to identify lane markings using high-resolution laser images for road condition evaluation. In this study, the laser images are acquired with a digital highway data vehicle (DHDV). Subsequently, a novel methodology is presented for the automated lane marking identification and reconstruction, and is implemented in four phases: (1) binarization of the laser images with a new threshold method (multi-box segmentation based threshold method); (2) determination of candidate lane markings with closing operations and a marching square algorithm; (3) identification of true lane marking by eliminating false positives (FPs) using a linear support vector machine method; and (4) reconstruction of the damaged and dash lane marking segments to form a continuous lane marking based on the geometry features such as adjacent lane marking location and lane width. Finally, a case study is given to validate effects of the novel methodology. The findings indicate the new strategy is robust in image binarization and lane marking localization. This study would be beneficial in road lane-based pavement condition evaluation such as lane-based rutting measurement and crack classification.

Automatic Pixel-Level Pavement Crack Detection Using Information of Multi-Scale Neighborhoods

Robust automatic pavement crack detection is critical to automated road condition evaluation. However, research on crack detection is still limited and pixel-level automatic crack detection remains a challenging problem, due to heterogeneous pixel intensity, complex crack topology, poor illumination condition, and noisy texture background. In this paper, we propose a novel approach for automatically detecting pavement cracks at pixel level, leveraging on multi-scale neighborhood information, and pixel intensity. Using pixel intensity information, a probabilistic generative model (PGM) based method is developed to calculate the probability of a crack for each pixel. This produces a probability map consisting of the probability of each pixel being part of the crack. We demonstrate that the neighborhoods of each pixel contain critical information for crack detection, and propose a support vector machine (SVM) based method to calculate the probability maps using information of multi-scale neighborhoods. We develop a fusion algorithm to merge the multiple probability maps, obtained from both PGM and SVM approaches, into a fused map, which can detect cracks with accuracy higher than any of the original probability maps. We also propose a weighted dilation operation that relies on the fused probability map to enhance the recognition of borderline pixels and improve the crack continuity without increasing the crack width improperly. Experimental results demonstrate that our algorithm achieves better performance in terms of precision, recall, f1-score, and receiver operating characteristic, in comparison with the state-of-the-art pavement crack detection algorithms.

Research on application of the rural road performance assessment method in Jiangsu Province

Although China’s rural road construction has achieved rapid development and the road network scale has been formed basically, the maintenance and management level of rural road is still relatively low. At present, there is no assessment system applicable to China’s rural road. Combining the actual situations of Jiangsu province, this study proposes a scientific rural road condition evaluation method which has proved the feasibility and applicability through field test. Due to its features such as simplicity, quickness and easy to use, this method is significant and meaningful for maintenance and management of rural road.

Ground-Penetrating Radar for Inspection of In-Road Structures and Data Interpretation by Numerical Modeling

In recent decades, road inspections have increasingly relied on the use of nondestructive instrumentation for the evaluation of road conditions. This work aims to test a ground-penetrating radar system to provide insight into nonvisible subsurface engineering with respect to an underpass arch-shaped structure. One important structural parameter that affects the stability of the arch structure and must be monitored is the quantity and thickness of the backfill used to fill the structure until the road is level. Frequencies of 500 and 200 MHz were used to detect the different layers over an arch structure. However, the heterogeneity of the backfill over the arch hampered interpretation of the field data. Finite-difference time-domain modeling was used to understand the response of the radar wave and to assist in interpretation. More realistic models were created based on the accurate geometry provided by a mobile light detection and ranging (LiDAR) device. The methodology is not excessively time-consuming, with all of the procedures taking a total of approximately 7 h. With this system, the layers built and their thicknesses can be defined with a maximum error of 5%. Appropriate nondestructive testing of the subsurface structure is useful in facilitating structural analysis and the prediction of critical failures.

A Study on Evaluation of Road Conditions for Promotion of Bicycle Usage

A Study on Evaluation of Road Conditions for Promotion of Bicycle Usage