Spatiotemporal kernel density clustering for wide area near Real-Time pothole detection

Gu Y., Zhang H., Han L.D., Khattak A.

Non-recurrent traffic congestion arising from traffic incidents is unpredictable but should be addressed efficiently to mitigate its adverse impacts on safety and travel time reliability. Numerous studies have been conducted about incident clearance time, while the recovery time, due to the limitations of data collection, is often inadvertently neglected in assessing incident-induced duration (i.e., the time from incident occurrence to the normal flow of traffic). Overlooking the recovery time is likely to underestimate the total incident-induced impact. Furthermore, the spatiotemporal heterogeneity of observed factors is not adequately captured in incident duration models. To address these gaps, this study specifically investigated traffic crashes as they reflect safety issues and are the primary cause of non-recurrent congestion. The emerging crowdsourced traffic reports were harnessed to estimate crash recovery time, which can complement the blind zone of fixed detectors. A geographically and temporally weighted proportional hazard (GWTPH) model was developed to untangle factors associated with the interval-censored crash duration. The results show that the GWTPH model outperforms the global model in goodness-of-fit. Many factors present a spatiotemporally heterogeneous effect. For example, the global model merely revealed that deploying dynamic message signs (DMS) shortened the crash time to normal. Notably, the GWTPH model highlights an average reduction of 32.8% with a standard deviation of 31% in time to normal. The study's findings and application of new spatiotemporal techniques are valuable for practitioners to localize strategies for incident management. For instance, deploying DMS can be very helpful in corridors when incidents happen, especially during peak hours.

Liu Y., Hoseinzadeh N., Gu Y., Han L.D., Brakewood C., Zhang Z.

Researchers are increasingly aware of the importance of crowdsourced data and consider them as possible complementary data sources to existing traffic monitoring systems. In this study, we investigated the coverage, timeliness, and location accuracy of Waze user reports over the years (2018–2021) by comparing their reports with official abnormal event records. The results indicate that the coverage of Waze reports is not constant over time and space. The matching rate of Waze crashes to official records was affected by traffic volumes. It dropped at the start of the COVID-19 pandemic (March 2020) and recovered gradually in 2021, coinciding with the decline and recovery of traffic during the COVID-19 period. Other factors affecting the matching rate include incident duration and location. In addition, Waze reports were timely. On average, 55% of the crashes were reported sooner by Waze users than by the official records. Location accuracy was evaluated as well, and the average absolute distance difference was 0.40 mi for crashes and 0.29 mi for stopped vehicles. Nearly all (90%) of the distance differences between Waze reports and Tennessee Department of Transportation (TDOT) records were between −0.85 and 0.80 mi for crashes and −0.67 to 0.62 mi for stopped vehicles. No obvious change in the spatiotemporal accuracy over time could be observed. Moreover, those Waze reports that could not be matched to TDOT records were analyzed, and the number of crashes covered by those reports was estimated. The results suggest that Waze reports have potential value in identifying missed/unreported crash records and complementing the existing incident database.

Zhang K., Wang Z.

Environmental factors and truck traffic loads have significant impacts on asphalt pavement performance. This study implements geospatial hot spot, correlation, and decision tree analyses to investigate the impacts of environmental factors and truck traffic loads on asphalt pavement performance. A pavement database with 1725 asphalt pavement sections from the Long-Term Pavement Performance (LTPP) program was built and analyzed using geospatial hot spot analysis to characterize the spatial patterns of environmental factors, truck traffic loads, and asphalt pavement distresses in different climatic regions across the United States and Canada. The statistical correlation analysis was conducted to identify significant correlations among hot spots of environmental factors, truck traffic loads, and asphalt pavement distresses. The decision tree model, which is a supervised machine learning method, was used to assess pavement performance in an area that is associated with higher risks of distress based on contributing environmental and traffic conditions. The hot spot analysis showed that the pavement sections located in the dry no-freeze region had higher percentages of hot spots of truck traffic loads and associated load-induced distresses, such as fatigue cracking, longitudinal wheel path cracking, and rutting. In the dry no-freeze region, higher percentages of pavement sections were also classified as hot spots of transverse cracking. The pavement sections in the wet freeze region are more likely to experience longitudinal non-wheel path cracking and surface roughness. The decision tree models were built to identify the likeliness of hot spots of asphalt pavement distresses using environmental factors and truck traffic loads. These decision tree models provide enhanced decision-making information in pavement design and maintenance.

Gamage Y.T., Thotawaththa T.A., Wijayasiri A.

Zhang A.A., Wang K.C., Liu Y., Zhan Y., Yang G., Wang G., Yang E., Zhang H., Dong Z., He A., Xu J., Shang J.

Karimzadeh A., Shoghli O., Sabeti S., Tabkhi H.

Transportation agencies constantly strive to tackle the challenge of limited budgets and continuously deteriorating highway infrastructure. They look for optimal solutions to make intelligent maintenance and repair investments. Condition prediction of highway assets and, in turn, prediction of their maintenance needs are key elements of effective maintenance optimization and prioritization. This paper proposes a novel risk-based framework that expands the potential of available data by considering the probabilistic susceptibility of assets in the prediction process. It combines a risk score generator with machine learning to forecast the hotspots of multiple defects while considering the interrelations between defects. With this, we developed a scalable algorithm, Multi-asset Defect Hotspot Predictor (MDHP), and then demonstrated its performance in a real-world case. In the case study, MDHP predicted the hotspots of three defects on paved ditches, considering the interrelation between paved ditches and five nearby assets. The results demonstrate an acceptable accuracy in predicting hotspots while highlighting the interrelation between adjacent assets and their contribution to future defects. Overall, this study offers a scalable approach with contribution in data-driven multi-asset maintenance planning with potential benefits to a broader range of linear infrastructures such as sewers, water networks, and railroads.

Praharaj S., Zahura F.T., Chen T.D., Shen Y., Zeng L., Goodall J.L.

Climate change and sea-level rise are increasingly leading to higher and prolonged high tides, which, in combination with the growing intensity of rainfall and storm surges, and insufficient drainage infrastructure, result in frequent recurrent flooding in coastal cities. There is a pressing need to understand the occurrence of roadway flooding incidents in order to enact appropriate mitigation measures. Agency data for roadway flooding events are scarce and resource-intensive to collect. Crowdsourced data can provide a low-cost alternative for mapping roadway flood incidents in real time; however, the reliability is questionable. This research demonstrates a framework for asserting trustworthiness on crowdsourced flood incident data in a case study of Norfolk, Virginia. Publicly available (but spatially limited) flood incident data from the city in combination with different environmental and topographical factors are used to create a logistic regression model to predict the probability of roadway flooding at any location on the roadway network. The prediction accuracy of the model was found to be 90.5%. When applying this model to crowdsourced Waze flood incident data, 71.7% of the reports were predicted to be trustworthy. This study demonstrates the potential for using Waze incident report data for roadway flooding detection, providing a framework for cities to identify trustworthy reports in real time to enable rapid situation assessment and mitigation to reduce incident impact.

Staniek M.

The purpose of the paper is to analyse the effectiveness of a solution known as road condition tool (RCT) based on data crowdsourcing from smartphones users in the transport system. The tool developed by the author of the paper, enabling identification and assessment of road pavement defects by analysing the dynamics of vehicle motion in the road network. Transport system users equipped with a smartphone with the RCT mobile application on board record data of linear accelerations, speed, and vehicle location, and then, without any intervention, send them to the RCT server database in an aggregated form. The aggregated data are processed in the combined time and location criterion, and the road pavement condition assessment index is estimated for fixed 10 m long measuring sections. The measuring sections correspond to the sections of roads defined in the pavement management systems (PMS) used by municipal road infrastructure administration bodies. Both the research in question and the results obtained by the method proposed for purposes of the road pavement condition assessment were compared with a set of reference data of the road infrastructure administration body which conducted surveys using highly specialised measuring equipment. The results of this comparison, performed using binary classifiers, confirm the potential RCT solution proposed by the author. This solution makes it possible to global monitor the road infrastructure condition on a continuous basis via numerous users of the transport system, which guarantees that such an assessment is kept up to date.

Liu Y., Zhang Z., Han L.D., Brakewood C.

Traffic queues, especially queues caused by non-recurrent events such as incidents, are unexpected to high-speed drivers approaching the end of queue (EOQ) and become safety concerns. Though the topic has been extensively studied, the identification of EOQ has been limited by the spatial-temporal resolution of traditional data sources. This study explores the potential of location-based crowdsourced data, specifically Waze user reports. It presents a dynamic clustering algorithm that can group the location-based reports in real time and identify the spatial-temporal extent of congestion as well as the EOQ. The algorithm is a spatial-temporal extension of the density-based spatial clustering of applications with noise (DBSCAN) algorithm for real-time streaming data with an adaptive threshold selection procedure. The proposed method was tested with 34 traffic congestion cases in the Knoxville,Tennessee area of the United States. It is demonstrated that the algorithm can effectively detect spatial-temporal extent of congestion based on Waze report clusters and identify EOQ in real-time. The Waze report-based detection are compared to the detection based on roadside sensor data. The results are promising: The EOQ identification time of Waze is similar to the EOQ detection time of traffic sensor data, with only 1.1 min difference on average. In addition, Waze generates 1.9 EOQ detection points every mile, compared to 1.8 detection points generated by traffic sensor data, suggesting the two data sources are comparable in respect of reporting frequency. The results indicate that Waze is a valuable complementary source for EOQ detection where no traffic sensors are installed.

Zhang Z., Liu Y., Han L.D., Freeze P.B.

Secondary crashes are crashes that occur as a result of the nonrecurrent congestion originating from primary crashes, and always have a greater impact on safety and traffic than a single crash. A better understanding of secondary crashes would benefit traffic incident management, and this requires accurate identification of secondary crashes. This study explores using crowdsourced Waze user reports to identify secondary crashes. A network-based clustering algorithm is proposed to extract the primary crash cluster, including all user reports originating from the primary crash, and any crash that occurred within the cluster would be a secondary crash. This method works as a filter to select accurate primary–secondary relationships, thus precisely identifying secondary crashes. A case study is performed with crashes occurring from June to December 2019 on a 30-mi stretch of I-40 in Knoxville, TN. A static threshold method (crash duration and 10 mi) was used to preselect the potential primary–secondary crash pairs, and 75 out of 708 crashes were identified as potential secondary crashes. Based on the preselected primary–secondary crash pairs, 17 secondary crashes were obtained with the proposed method and the results were compared with one of the commonly used methods, the speed contour plot method. Though the proposed method captured fewer secondary crashes, it did identify several secondary crashes that could not be observed with the speed contour plot method. The results showed the applicability of the method and the potential of crowdsourced Waze user reports in secondary crash identification.

Patra S., Middya A.I., Roy S.

Proper maintenance of roads is an extremely complex task and also an important issue all over the world. One of the most critical road monitoring and maintenance activities is the detection of road anomalies such as potholes. Identification of potholes is necessary to avoid road accidents, prevent damage of vehicles, enhance travelling comforts, etc. Although maintenance of roads is considered to be a serious issue by the authorities over the years, lack of proper detection and mapping of road potholes makes the issue more severe. To overcome this problem, an end-to-end system called PotSpot is built for real-time detection, monitoring, and spatial mapping of potholes across the city A Convolutional Neural Network (CNN) model is proposed and evaluated on real-world dataset for pothole detection. Additionally, real-time pothole-marked maps are generated with the help of Google Maps API (Application Programming Interface). To provide an end-to-end service through this system, both the pothole detection and pothole mapping are integrated through an android application. The proposed model is also compared with six baselines namely Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and three pre-trained CNN models InceptionV3, VGG19 and VGG16 in terms of performance metrics to verify its effectiveness. The proposed model achieves better accuracy (≈ 97.6 %) as compared to the above-mentioned baseline methods. It is also observed that the Area Under the Curve (AUC) value for the proposed pothole detection model (AUC= 0.97) is higher than the baseline methods.

Zhang Z., Han L.D., Liu Y.

Hoseinzadeh N., Gu Y., Han L.D., Brakewood C., Freeze P.B.

In traffic operations, the aim of transportation agencies and researchers is typically to reduce congestion and improve safety. To attain these goals, agencies need continuous and accurate information about the traffic situation. Level-of-Service (LOS) is a beneficial index of traffic operations used to monitor freeways. The Highway Capacity Manual (HCM) provides analytical methods to assess LOS based on traffic density and highway characteristics. Generally, obtaining reliable density data on every road in large networks using traditional fixed location sensors and cameras is expensive and otherwise unrealistic. Traditional intelligent transportation system facilities are typically limited to major urban areas in different states. Crowdsourced data are an emerging, low-cost solution that can potentially improve safety and operations. This study incorporates crowdsourced data provided by Waze to propose an algorithm for LOS assessment on an hourly basis. The proposed algorithm exploits various features from big data (crowdsourced Waze user alerts and speed/travel time variation) to perform LOS classification using machine learning models. Three categories of model inputs are introduced: Basic statistical measures of speed; travel time reliability measures; and the number of hourly Waze alerts. Data collected from fixed location sensors were used to calculate ground truth LOS. The results reveal that using Waze crowdsourced alerts can improve the LOS estimation accuracy by about 10% (accuracy = 0.93, Kappa = 0.83). The proposed method was also tested and confirmed by using data from after coronavirus disease 2019 (COVID-19) with severe traffic breakdown due to a stay-at-home policy. The proposed method is extendible for freeways in other locations. The results of this research provide transportation agencies with a LOS method based on crowdsourced data on different freeway segments, regardless of the availability of traditional fixed location sensors.

Li X., Dadashova B., Yu S., Zhang Z.

Identification of traffic crash hot spots is of great importance for improving roadway safety and maintaining the transportation system’s sustainability. Traditionally, police crash reports (PCR) have been used as the primary source of crash data in safety studies. However, using PCR as the sole source of information has several drawbacks. For example, some crashes, which do not cause extensive property damage, are mostly underreported. Underreporting of crashes can significantly influence the effectiveness of data-driven safety analysis and prevent safety analysts from reaching statistically meaningful results. Crowdsourced traffic incident data such as Waze have great potential to complement traditional safety analysis by providing user-captured crash and traffic incident data. However, using these data sources also has some challenges. One of the major problems is data redundancy because many people may report the same event. In this paper, the authors explore the potential of using crowdsourced Waze incident reports (WIRs) to identify high-risk road segments. The researchers first propose a new methodology to eliminate redundant WIRs. Then, the researchers use WIRs and PCRs from an I-35 corridor in North Texas to conduct the safety analysis. Results demonstrated that WIRs and PCRs are spatially correlated; however, their temporal distributions are significantly different. WIRs have broader coverage, with 60.24 percent of road segments in the study site receiving more WIRs than PCRs. Moreover, by combining WIRs with PCRs, more high-risk road segments can be identified (14 miles) than the results generated from PCRs (8 miles).

Wu C., Wang Z., Hu S., Lepine J., Na X., Ainalis D., Stettler M.

Road surface monitoring and maintenance are essential for driving comfort, transport safety and preserving infrastructure integrity. Traditional road condition monitoring is regularly conducted by specially designed instrumented vehicles, which requires time and money and is only able to cover a limited proportion of the road network. In light of the ubiquitous use of smartphones, this paper proposes an automatic pothole detection system utilizing the built-in vibration sensors and global positioning system receivers in smartphones. We collected road condition data in a city using dedicated vehicles and smartphones with a purpose-built mobile application designed for this study. A series of processing methods were applied to the collected data, and features from different frequency domains were extracted, along with various machine-learning classifiers. The results indicated that features from the time and frequency domains outperformed other features for identifying potholes. Among the classifiers tested, the Random Forest method exhibited the best classification performance for potholes, with a precision of 88.5% and recall of 75%. Finally, we validated the proposed method using datasets generated from different road types and examined its universality and robustness.

Qiao Y., Wang J., Zhang X., Huang J., Liang H., Zhang R.

Abstract Potholes present a significant safety risk on non-motorized vehicle lanes, especially under low-visibility conditions. Effective pothole detection on non-motorized vehicle lanes is crucial to improve public transportation safety. This study proposes an integrated algorithm that harnesses smartphone sensors to enhance pothole detection accuracy. The algorithm begins with data processing, incorporating techniques such as the quaternion algorithm, synthetic minority over-sampling technique, and wavelet-domain denoising. This preprocessing addresses challenges such as significant smartphone placement uncertainty, limited pothole data, and intense noise signals, all of which severely affect the prediction accuracy of machine learning models. The processed data is subsequently used to train machine learning models for pothole detection, including artificial neural networks (ANNs), bootstrap forest, and Naïve Bayes. The accuracy and precision of the models are evaluated and compared. The results show that the accuracy of pothole detection with the integrated algorithm improved to 92%–97%, surpassing the 70%–90% accuracy reported in previous studies. Using the ANN prediction model, the integrated algorithm achieved the highest overall accuracy of 97.02%, with an F-measure of 95.15%. Additionally, the Naïve Bayes model effectively addresses the class imbalance in pothole detection, achieving the highest precision (97.93%). These results confirm the effectiveness and improved accuracy of the proposed integrated pothole detection algorithm.

Upadhyay M.R., Ushasukhanya S., Ravi Teja V.R., Malleswari T.N., Mahendra K.V.

Gu Y., Liu D., Kim H., Han L.D.

Kindo A.A., Kalmogo L., Malo S.

Kim J., Jeon W., Kim S.

Identifying road segments with a high crash incidence is essential for improving road safety. Conventional methods for detecting these segments rely on historical data from various sensors, which may inadequately capture rapidly changing road conditions and emerging hazards. To address these limitations, this study proposes leveraging crowdsourced data alongside historical traffic accident records to identify areas prone to crashes. By integrating real-time public observations and user feedback, the research hypothesizes that traffic accidents are more likely to occur in areas with frequent user-reported feedback. To evaluate this hypothesis, spatial autocorrelation and clustering analyses are conducted on both crowdsourced data and accident records. After defining hotspot areas based on user feedback and fatal accident records, a density analysis is performed on such hotspots. The results indicate that integrating crowdsourced data can complement traditional methods, providing a more dynamic and adaptive framework for identifying and mitigating road-related risks. Furthermore, this study demonstrates that crowdsourced data can serve as a strategic and sustainable resource for enhancing road safety and informing more effective road management practices.

Paramarthalingam A., Sivaraman J., Theerthagiri P., Vijayakumar B., Baskaran V.

Visually impaired individuals encounter numerous impediments when traveling, such as navigating unfamiliar routes, accessing information, and transportation, which can limit their mobility and restrict their access to opportunities. However, assistive technologies and infrastructure solutions such as tactile paving, audio cues, voice announcements, and smartphone applications have been developed to mitigate these challenges. Visually impaired individuals also face difficulties when encountering potholes while traveling. Potholes can pose a significant safety hazard, as they can cause individuals to trip and fall, potentially leading to injury. For visually impaired individuals, identifying and avoiding potholes can be particularly challenging. The solutions ensure that all individuals can travel safely and independently, regardless of their visual abilities. An innovative approach that leverages the You Only Look Once (YOLO) algorithm to detect potholes and provide auditory or haptic feedback to visually impaired individuals has been proposed in this paper. The dataset of pothole images was trained and integrated into an application for detecting potholes in real-time image data using a camera. The app provides feedback to the user, allowing them to navigate potholes and increasing their mobility and safety. This approach highlights the potential of YOLO for pothole detection and provides a valuable tool for visually impaired individuals. According to the testing, the model achieved 82.7% image accuracy and 30 Frames Per Second (FPS) accuracy in live video. The model is trained to detect potholes close to the user, but it may be hard to detect potholes far away from the user. The current model is only trained to detect potholes, but visually impaired people face other challenges. The proposed technology is a portable option for visually impaired people.

Gu Y., Khojastehpour M., Jia X., Han L.D.

Monitoring pavement conditions is critical to pavement management and maintenance. Traditionally, pavement distress is mainly identified via accelerometers, videos, and laser scanning. However, the geographical coverage and temporal frequency are constrained by the limited amount of equipment and labor, which sometimes may delay road maintenance. By contrast, crowdsourced data, in a manner of crowdsensing, can provide real-time and valuable roadway information for extensive coverage. This study exploited crowdsourced Waze pothole and weather reports for pavement condition evaluation. Two surrogate measures are proposed, namely, the Pothole Report Density (PRD) and the Weather Report Density (WRD). They are compared with the Pavement Quality Index (PQI), which is calculated using laser truck data from the Tennessee Department of Transportation (TDOT). A geographically weighted random forest (GWRF) model was developed to capture the complicated relationships between the proposed measures and PQI. The results show that the PRD is highly correlated with the PQI, and the correlation also varies across the routes. It is also found to be the second most important factor (i.e., followed by pavement age) affecting the PQI values. Although Waze weather reports contribute to PQI values, their impact is significantly smaller compared to that of pothole reports. This paper demonstrates that surrogate pavement condition measures aggregated by crowdsourced data could be integrated into the state decision-making process by establishing nuanced relationships between the surrogated performance measures and the state pavement condition indices. The endeavor of this study also has the potential to enhance the granularity of pavement condition evaluation.