Intersection Stop Research Articles

Vision-Based Algorithm for Precise Traffic Sign and Lane Line Matching in Multi-Lane Scenarios

With the rapid development of intelligent transportation systems, lane detection and traffic sign recognition have become critical technologies for achieving full autonomous driving. These technologies offer crucial real-time insights into road conditions, with their precision and resilience being paramount to the safety and dependability of autonomous vehicles. This paper introduces an innovative method for detecting and recognizing multi-lane lines and intersection stop lines using computer vision technology, which is integrated with traffic signs. In the image preprocessing phase, the Sobel edge detection algorithm and weighted filtering are employed to eliminate noise and interference information in the image. For multi-lane lines and intersection stop lines, detection and recognition are implemented using a multi-directional and unilateral sliding window search, as well as polynomial fitting methods, from a bird’s-eye view. This approach enables the determination of both the lateral and longitudinal positioning on the current road, as well as the sequencing of the lane number for each lane. This paper utilizes convolutional neural networks to recognize multi-lane traffic signs. The required dataset of multi-lane traffic signs is created following specific experimental parameters, and the YOLO single-stage target detection algorithm is used for training the weights. In consideration of the impact of inadequate lighting conditions, the V channel within the HSV color space is employed to assess the intensity of light, and the SSR algorithm is utilized to process images that fail to meet the threshold criteria. In the detection and recognition stage, each lane sign on the traffic signal is identified and then matched with the corresponding lane on the ground. Finally, a visual module joint experiment is conducted to verify the effectiveness of the algorithm.

Research Progress and Prospects of Transit Priority Signal Intersection Control Considering Carbon Emissions in a Connected Vehicle Environment

Transit priority control is not only an important means for improving the operating speed and reliability of public transport systems, but it is also a key measure for promoting green and sustainable urban transportation development. A review of signal intersection transit priority control strategy in a connected vehicle environment is conducive to discovering important research results on transit priority control at home and abroad and will promote further developments in urban public transport. This study analyzed and reviewed signal intersection transit priority control at four levels: traffic control sub-area divisions, transit signal priority (TSP) strategy, speed guidance strategy, and the impacts of intersection signal control on carbon emissions. In summary, the findings were the following: (1) In traffic control sub-area divisions, the existing methods were mainly based on the similarity of traffic characteristics and used clustering or search methods to divide the intersections with high similarity into the same control sub-areas. (2) The existing studies on the TSP control strategy have mainly focused on transit priority control based on fixed phase sequences or phase combinations under the condition of exclusive bus lanes. (3) Studies on speed guidance strategy were mainly based on using constant bus speeds to predict bus arrival times at intersection stop lines, and it was common to guide only based on bus speed. (4) The carbon emissions model for vehicles within the intersection mainly considered two types of vehicles, namely, fuel vehicles and pure electric vehicles. Finally, by analyzing deficiencies in the existing studies, future development directions for transit priority control are proposed.

Traffic noise modelling at intersections in mid-sized cities: an artificial neural network approach.

Traffic noise has emerged as one major environmental concern, which is causing a severe impact on the health of urban dwellers. This issue becomes more critical near intersections in mid-sized cities due to poor planning and a lack of noise mitigation strategies. Therefore, the current study develops a precise intersection-specific traffic noise model for mid-sized cities to assess the traffic noise level and to investigate the effect of different noise-influencing variables. This study employs artificial neural network (ANN) approach and utilizes 342h of field data collected at nineteen intersections of Kanpur, India, for model development. The sensitivity analysis illustrates that traffic volume, median width, carriageway width, honking, and receiver distance from the intersection stop line have a prominent effect on the traffic noise level. The study reveals that role of noise-influencing variables varies in the proximity of intersections. For instance, a wider median reduces the noise level at intersections, while the noise level increases within a 50-m distance from intersection stop line. In summary, the present study findings offer valuable insights, providing a foundation for developing an effective managerial action plan to combat traffic noise at intersections in mid-sized cities.

Strategy and safety at stop intersections in older adults with mild cognitive impairment and visual decline

This study assessed the impact of age-related cognitive and visual declines on stop-controlled intersection stopping and scanning behaviors across varying roadway, traffic, and environmental challenges.Real-world driver data, collected from drivers’ personal vehicles using in-vehicle sensor systems, was analyzed in 68 older adults (65–90 years old) with and without mild cognitive impairment (MCI) and with a range of age-related visual declines. Driver behavior, environmental characteristics, and traffic characteristic were examined across 2,596 approaches at 173 stop-controlled intersections. A mixed-effects logistic regression modeled stopping behavior as a binary response (full stop or rolling/no-stop).Overall, drivers who scanned more on intersection approaches (OR = 0.77) or had more visual decline (OR = 2.28) were more likely to make full stops at a stop-controlled approach. Drivers with a contrast sensitivity logMAR score > 0.8 showed the greatest probability of making a full stop compared across all drivers. Drivers without MCI were ∼ 5 times more likely to come to a full stop when they scanned more (23 % versus 5 % when they scanned less) compared to drivers with MCI, who were only twice as likely to stop (14 % versus 6 % when they scanned less). Drivers were more likely to fully stop on two-lane roadways (1.5 %), during night (2.0 %), and at intersections with opposing vehicles (10.4 %).Findings illuminate how driver strategies interact with underlying impairment. While drivers with visual decline adopt strategies that may improve safety, when drivers with MCI adopt strategies it did not result in the same degree of improvement in stopping which may result in greater risk.

Queue Length Estimation Based on Probe Vehicle Data at Signalized Intersections

Queue length is one of the important indexes to evaluate the operation efficiency of signalized intersection and also the key parameter of intersection signal control optimization. Traditional queue length estimation models are mostly based on fixed detection equipment, and the models assumptions are too harsh; there are certain limitations. Based on the probe vehicle data, this paper establishes a model of queue length estimation for signalized intersection based on shockwave theory. First, based on the speed and location data of the probe vehicle, the vehicle density is calculated to estimate the intersection stop line. A real-time calculation method of vehicle arrival rate is proposed to improve the applicability of the model. Then, based on the shockwave theory, the meeting time of the queue forming wave and the queue discharging wave are calculated after the green light is on. Finally, the queue length is summed in sections, including the distance between the last queued probe vehicle and the stop line during the red light period, the length of the subsequent vehicles arriving during the residual red light time, and the newly increased queue length within the queue discharging time. This paper uses the VISSIM software to simulate the actual intersection. The simulation results show that when the penetration of probe vehicle is 50%, 25%, and 10%, their corresponding mean absolute relative error are 11.27%, 27.77%, and 39.12%, respectively. It can be seen that with the increase of penetration, the error gradually decreases. The average absolute relative error is within the acceptable range. After analyzing the existing similar methods, although the accuracy of the method proposed in this paper does not reach the highest level, it has the advantages of simple operation, less computation, and good real-time computation. Relevant research results can provide support for traffic control at signalized intersections.

Hierarchical Multi-Objective Optimization for Dedicated Bus Punctuality and Supply-Demand Balance Control.

Public transportation is a crucial component of urban transportation systems, and improving passenger sharing rates can help alleviate traffic congestion. To enhance the punctuality and supply-demand balance of dedicated buses, we propose a hierarchical multi-objective optimization model to optimize bus guidance speeds and bus operation schedules. Firstly, we present an intelligent decision-making method for bus driving speed based on the mathematical description of bus operation states and the application of the Lagrange multiplier method, which improves the overall punctuality rate of the bus line. Secondly, we propose an optimization method for bus operation schedules that respond to passenger needs by optimizing departure time intervals and station schedules for supply-demand balance. The experiments were conducted in Future Science City, Beijing, China. The results show that the bus line's punctuality rate has increased to 90.53%, while the retention rate for platform passengers and the intersection stop rate have decreased by 36.22% and 60.93%, respectively. These findings verify the effectiveness and practicality of the proposed hierarchical multi-objective optimization model.

Dynamic dilemma zone protection system for high-speed signalized intersections: A comprehensive safety -operational assessment

Dynamic dilemma zone protection (DZP) system with continuous vehicle tracking via radar sensors has been implemented at multiple locations in Alabama to promote the safety and operational efficiency of high-speed signalized intersections. The present study discusses the main features of the DZP system, and its comprehensive assessment in three important aspects: changes in (1) vehicle arrival distributions in different signal intervals (green, yellow, and red), (2) dilemma zone length and location, and (3) dilemma zone conflicts before and after the DZP system implementation. For the system assessment, an extensive amount of data collection and analysis efforts were performed with radar sensor-based vehicle attribute data and high-resolution signal controller data collected from seven intersection approaches where a DZP system has been recently implemented. The analysis results showed that vehicle arrivals on green intervals were significantly increased after the DZP system implementation, while vehicle arrivals on the yellow and red intervals were both reduced significantly despite no change in total vehicle arrivals before and after the system implementation. The chance of dilemma zone conflicts (i.e., red-light running and abrupt stops) was also significantly reduced after the DZP system implementation. Results also showed that the dilemma zone length became shorter, and its location was closer to the intersection stop bar after its implementation. Thus, the present study claims that the DZP system promotes intersection operational efficiency by effectively utilizing available green time as well as improving intersection safety by reducing the number of vehicles trapped within the dilemma zone.

Sugar and stops in drivers with insulin-dependent type 1 diabetes

BackgroundDiabetes is a major public health challenge, affecting millions of people worldwide. Abnormal physiology in diabetes, particularly hypoglycemia, can cause driver impairments that affect safe driving. While diabetes driver safety has been previously researched, few studies link real-time physiologic changes in drivers with diabetes to objective real-world driver safety, particularly at high-risk areas like intersections. To address this, we investigated the role of acute physiologic changes in drivers with type 1 diabetes mellitus (T1DM) on safe stopping at stop intersections. Methods18 T1DM drivers (21–52 years, μ = 31.2 years) and 14 controls (21–55 years, μ = 33.4 years) participated in a 4-week naturalistic driving study. At induction, each participant’s personal vehicle was instrumented with a camera and sensor system to collect driving data (e.g., GPS, video, speed). Video was processed with computer vision algorithms detecting traffic elements (e.g., traffic signals, stop signs). Stop intersections were geolocated with clustering methods, state intersection databases, and manual review. Videos showing driver stop intersection approaches were extracted and manually reviewed to classify stopping behavior (full, rolling, and no stop) and intersection traffic characteristics. ResultsMixed-effects logistic regression models determined how diabetes driver stopping safety (safe vs. unsafe stop) was affected by 1) disease and 2) at-risk, acute physiology (hypo- and hyperglycemia). Diabetes drivers who were acutely hyperglycemic (≥ 300 mg/dL) had 2.37 increased odds of unsafe stopping (95% CI: 1.26–4.47, p = 0.008) compared to those with normal physiology. Acute hypoglycemia did not associate with unsafe stopping (p = 0.537), however the lower frequency of hypoglycemia (vs. hyperglycemia) warrants a larger sample of drivers to investigate this effect. Critically, presence of diabetes alone did not associate with unsafe stopping, underscoring the need to evaluate driver physiology in licensing guidelines. ConclusionThis study links acute, abnormal physiologic fluctuations in drivers with diabetes to driver safety based on unsafe stopping at stop-controlled intersections, providing recommendations for clinicians aimed at improving patient safety, fair licensing guidelines, and targets for developing advanced driver assistance systems.

Identifying Potentially Risky Intersections for Heavy-Duty Truck Drivers Based on Individual Driving Styles

In developing countries, heavy-duty trucks play an important role in transportation for infrastructure construction. However, frequent truck accidents cause great losses. Previous studies have mainly focused on passenger drivers; to date, little has been done to assess the driving behavior of heavy truck drivers. The overall objective of this study is to classify driving styles at intersections, analyze the impacts of differing types of traffic control at intersections on driving styles, and identify potentially risky intersections. We selected 11 heavy-duty truck drivers and collected kinematic driving parameters (including driving speed and both lateral and longitudinal acceleration) from field experiments in Nanjing for our study. Our study on driving styles followed the following steps. First, we reduced data size and extracted data features on the basis of time windows in Python. Second, driving styles were classified into three driving styles: cautious, normal, and aggressive, based on the K-means clustering method, and the corresponding thresholds for each category were obtained. Kinematic driving parameters were used as driving style measurements. Third, according to classifications of driving style, the impacts of four different intersection traffic control types: two-phase signalized, multiphase signalized, stop, and yield intersections, on driving styles have been analyzed using the multinomial logit model. Moreover, based on the above analysis, potentially risky intersections were identified. The results suggest that different types of traffic control at intersections lead to variations in driving styles and have different influences on driving styles. In terms of accuracy, our method, which uses driving speed, both lateral and longitudinal acceleration, and jerk as features, performs better than traditional methods which only use speed and acceleration. The results of the study allow us to analyze the driving data of heavy-duty trucks and identify drivers who drive more aggressively during a trip. In addition, the results show that aggressive driving styles mostly occur at stop intersections and in the dilemma zones of signalized intersections. Therefore, early-warning interventions can be provided during a driver’s trip by analyzing the different types of traffic control at intersections on the route in advance. Finally, the cumulative analysis of driving styles at intersections over multiple trips can be used to identify potentially high-risk intersections. It is possible to eliminate potential risks in these areas through measures such as early warnings and by improving traffic management control methods.

Assessing the Impact of Older Driver Visual and Cognitive Impairment on Intersection Stopping Behavior (P17-3.002)

Assessing the Impact of Older Driver Visual and Cognitive Impairment on Intersection Stopping Behavior (P17-3.002)

Do stop-signs improve the safety for all road users? A before-after study of stop-controlled intersections using video-based trajectories and surrogate measures of safety

Converting minor-approach-only stop (MAS) intersections to all-way-stop (AWS) intersections is a prevailing safety countermeasure in North American urban areas. Although the general population positively perceives the installation of stop-signs in residential areas, little research has investigated the impact of AWS on road safety and road user behaviour. This paper investigated the safety effectiveness of converting MAS to AWS intersections using an observational before and after approach and surrogate measures of safety. More specifically, the safety impacts of AWS conversion were investigated using multiple indicators, including vehicle speed measures, vehicle–pedestrian, vehicle-cyclist, vehicles-vehicle interactions as well as yielding rates before and after the treatment implementation. A multi-level regression approach was adopted to determine the effect of stop signs controlling for built environments, traffic exposure, and intersection geometry factors as well as site-specific unobserved heterogeneity.A unique sample of 31 intersections were used in this before-after study. From this sample, video data were collected before and after implementing AWS. In total, 245 h of video were automatically processed and corrected using a specialized computer vision software. More than 68,000 (37,668 before and 31,305 after AWS treatment) road user trajectories were obtained from 104 approaches. The results show that the conversion of MAS to AWS intersections significantly decreased vehicle speed and increased post-encroachment time. This work also shows that implementing AWS significantly increased the yielding rates from 45.7% to 76.7% in MAS conditions and reduced the average speed of motor-vehicles. Using multi-level regression model, it is estimated that when the intersection was converted from MAS to AWS, the minimum speed in the major approaches was reduced by 60.0%.

A Scalable Deep Learning Framework for Extracting Model Inventory of Roadway Element Intersection Control Types From Panoramic Images

In the United States, the Model Inventory of Roadway Element (MIRE) provides a comprehensive list of data that are needed to support states’ data-driven safety programs. The intersection control is part of the MIRE Fundamental Data Elements (FDE) for which state Departments of Transportation are required to complete the collection by September 30, 2026. It is essential roadway data that have been used widely in traffic safety studies. This study proposes a scalable and automated deep learning framework for detecting and classifying stop and yield intersection controls using panoramic street view images. The Faster Region-based Convolutional Neural Networks (Faster R-CNN) model architecture was used to detect and classify stop and yield signs from the images. A transfer learning process was deployed using the Inception-ResNet-v2 generic feature extractor to accelerate the training and performance of the deep learning model with less data collection effort. The effectiveness and scalability of the proposed framework were tested on a sample of road intersections in the state of Michigan. The proposed deep learning model achieved a recall value of 97.7% and 98.2% for detecting and classifying stop and yield signs respectively. The evaluation of the model performance at a county level suggests that the model can be scaled to a statewide level without a substantial increase in the demand for computational resources. As demonstrated in this study, state DOTs can leverage the advancement of deep learning techniques and the availability of imagery data to expedite the process of collecting the MIRE data.

Predicting time-varying, speed-varying dilemma zones using machine learning and continuous vehicle tracking

This paper proposes an innovative framework of predicting driver behavior under varying dilemma zone conditions using artificial intelligence-based machine learning. The framework utilizes multiple machine learning techniques to process vehicle attribute data (e.g., speed, location, and time-of-arrival) collected at the onset of the yellow indication, and eventually predicts drivers’ stop-or-go decision based on the data. A linear SVM was used to extract through vehicles from all approaching vehicles detected from radar sensors. A hierarchical clustering method was utilized to classify different traffic patterns by time-of-day. Finally, driver behavior prediction models were developed using three machine learning techniques (i.e., linear SVM, polynomial SVM, and ANN) widely adopted for binary classification problems. Model validation results showed that all the prediction models perform well with high prediction accuracies. The ANN model, which showed the best performance among the three, was selected to represent dilemma zone boundaries. Results show that the dilemma zone start- and end-points would both locate further from the stop bar with higher approaching speeds. Furthermore, the dilemma zone end-point would be more sensitive to the approaching speed than the start-point is. As a result, the dilemma zone length would become longer with higher approaching speeds. Results also showed that the dilemma zone length and location would vary by time-of-day regardless of the speed of approaching vehicles. The analysis showed that the dilemma zone length would be longer and its location would be much further from the stop bar for vehicles arriving during rush hours, as compared to those arriving during non-rush or nighttime hours. This indicates that drivers’ decision location to stop or go (when they are faced with a dilemma zone situation) is distributed farther from the intersection stop bar during rush hours. The proposed method shows an effective way of predicting driver behavior on signalized intersections. It is expected for the transportation agencies to use the method to improve intersection signal operations more effectively and safely.

Neighborhood environment and muscle mass and function among rural older adults: a 3-year longitudinal study

BackgroundSarcopenia, resulting from loss of muscle mass and function, is highly prevalent in the ageing societies and is associated with risk of falls, frailty, loss of independence, and mortality. It is important to identify environmental risk factors, so that evidence-based interventions to prevent sarcopenia can be implemented at the population level. This study aimed to examine the potential effect of several objectively measured neighborhood environmental factors on longitudinal change of muscle mass and function among older adults living in rural Japanese towns where the population is ageing.MethodsThis study was based on data from the Shimane CoHRE Study conducted by the Center for Community-based Healthcare Research and Education (CoHRE) at Shimane University in 3 rural towns in the Shimane Prefecture, Japan. Subjects older than 60 years, who participated in an annual health examination in 2016 and any follow-up years until 2019, i.e., 4 possible time points in total, were included (n = 2526). The skeletal muscle mass index (SMI) and grip strength were assessed objectively for each year as a measure of muscle mass and function, respectively. Neighborhood environmental factors, i.e., hilliness, bus stop density, intersection density, residential density, and distance to a community center were measured by geographic information systems (GIS). Linear mixed models were applied to examine the potential effect of each neighborhood environmental factor on the change of SMI and grip strength over time.ResultsMales living far from community centers had a less pronounced decline in SMI compared to those living close to community centers. Females living in areas with higher residential density had a less pronounced decline in grip strength compared to those living in areas with lower residential density.ConclusionsNeighborhood environmental factors had limited effects on change of SMI and grip strength among rural older adults within the 3 years follow up. Further long-term follow up studies are necessary by also taking into account other modifiable neighborhood environmental factors.

Signal Timing Optimization Model for Intersections in Traffic Incidents

The intersection control and management can alleviate the traffic congestion caused by traffic incidents. Therefore, it becomes essential to develop a signal optimization method for intersections influenced by traffic incidents, which will be beneficial to prevent congestion spreading. In this paper, the proposed model is capable of maximizing the intersection throughput by comprehensively considering the queue length as the penalty value. The headway of leaving vehicles is assumed to follow the Cowan’s M3 headway distribution, where formulas for queue length can be derived based on gap acceptance theory. To satisfy the conditions for efficiently identifying feasible solutions in a short time, a heuristic algorithm (simulated annealing algorithm) is employed to solve the model. The numerical results can validate that the proposed method can solve the problem more efficiently and alleviate the intersection congestion caused by the incidents more desirably. When the incident occurs away from the intersection stop line, the impacts on intersection throughput will be gradually weakened. The proposed method is capable of improving the signalized intersection throughput while preventing the congestion from spreading to the upstream intersection.

ドライブレコーダで計測した一時停止交差点での緊急制動頻度・左右確認行動と高齢ドライバの認知身体特性・運転意識の関係

ドライブレコーダで計測した一時停止交差点での緊急制動頻度・左右確認行動と高齢ドライバの認知身体特性・運転意識の関係

Determination and Utilization of Dilemma Zone Length and Location for Safety Assessment of Rural High-Speed Signalized Intersections

The objective of the present study is to see how the dilemma zone length and location are related to intersection safety at rural high-speed signalized intersections. For that, dilemma zones at 30 rural signalized intersection approaches where similar traffic operations and land-use conditions are present were identified, and traffic conflicts associated with the dilemma zones were investigated. Drivers’ stop or go behaviors as well as vehicle dynamics (e.g., vehicle speeds and locations) during the yellow and red clearance intervals were collected and analyzed to determine the dilemma zone length and location of each site. Red-light running violations and vehicles’ abrupt stops were also collected to investigate the relationship between such conflicts and dilemma zone length and location. As a result, two dilemma zone conflict models were developed. The analysis results show that the conflict models are accurate enough to predict the safety level of high-speed signalized intersections using the two dilemma zone variables. Results show that the chance of intersection angle conflicts increases if the dilemma zone is located farther from the intersection stop bar. Results also show that there would be a high chance of rear-end conflicts if the dilemma zone length is longer. The models were validated with additional datasets, and acceptable root means square error and mean absolute percentage error values were obtained as a result.

Threshold Determination for Sharing Bus Rapid Transit–Exclusive Lanes with Conventional Buses

Sharing bus rapid transit (BRT) exclusive lanes with conventional buses is being considered to solve the problem of low utilization rate of BRT-exclusive lanes. However, the quantitative conditions and threshold that determine when to share need to be study. This paper took the common section of BRT and conventional bus lines as its research object. Practical investigation was conducted to analyze shared characteristics from multiple perspectives and explore influencing factors and mechanisms for sharing implementation. Based on the survey results, analytical models were established to quantify the influencing factors from three perspectives of road section, intersection, and bus stop. We selected departure volume of conventional buses as a threshold index and then summarized the constraints and the calculation process of sharing threshold. Finally, numerical examples of different scenarios were used to verify the feasibility and effectiveness of the method. The operation efficiency of the road section on exclusive lanes was the constraint on the lower limit of the shared threshold, while the upper limit was constrained by queuing probability or bus operation time under different intersections and stop spacing, which can provide reference for the shared setting of exclusive bus lanes.

Predicting STOP-Sign Compliance at All-Way Stop Intersections in Close Proximity to Signalized Intersections

Predicting STOP-Sign Compliance at All-Way Stop Intersections in Close Proximity to Signalized Intersections

Investigating secondary pedestrian-vehicle interactions at non-signalized intersections using vision-based trajectory data

Vision-based trajectory data provides great details for investigating microscopic behavior and road safety at the level of interactions. Most studies investigating pedestrian-vehicle interactions at non-signalized intersections have focused on interactions at the crosswalk on the same approach where the vehicle is coming from, which are referred to as primary interactions in this study. However, secondary interactions, defined as interactions between vehicles exiting the intersection and crossing pedestrians, have not been adequately studied. Second interactions can pose more dangers to pedestrians due to the driver’s unclear knowledge of right-of-way, acceleration attempts to recover the speed, and the complex situation the driver faces in the intersection. This paper aims at studying the safety issue of secondary pedestrian-vehicle interactions at non-signalized intersections. For that purpose, a methodology is proposed based on surrogate measures of safety and behavioral measures derived from vision-based trajectories. This methodology is implemented through a case study involving ten all-way stop intersections from Montreal, Canada. Road user trajectory data are automatically extracted from the videos. Different measures are used in the study: from the interaction analysis that determines vehicle-pedestrian interactions based on a Distance-Velocity (DV) model, average crossing speeds and vehicle approaching behaviors in terms of speed and acceleration. Computer tools are developed to extract these measures from the trajectory data. Based on these measures, a comparative analysis is carried out between primary and secondary interactions. Results show that secondary interactions are more dangerous than primary interactions. Among the three secondary interaction types, secondary through interactions are the most dangerous.