High-speed Intersection Research Articles

Exploring nighttime pedestrian crash patterns at intersection and segments: Findings from the machine learning algorithm

Introduction: Pedestrian safety at nighttime is an ongoing critical traffic safety concern. Although poor visibility is primarily associated with nighttime pedestrian crashes, other contributing factors such as humans, vehicles, roadways, and environmental factors interact with each other to cause a crash. Additionally, the pattern of nighttime pedestrian crashes differs significantly according to the intersection and segment location, which requires further exploration. Data: This study applied Association Rules Mining (ARM), a rule-based machine learning method, to reveal the association of nighttime pedestrian crash risk factors according to the intersection and segment locations using 2,505 nighttime pedestrian fatal and injury crashes in Louisiana (2015–2019). Results and conclusions: Based on the generated rules, the results show that nighttime pedestrian crashes at the intersection are associated with right-turn vehicle movement, older drivers (>64 years) at the high-speed intersection, senior pedestrians (>64 years) in rainy weather conditions, violation by pedestrian age group ‘<15 years’, and alcohol-intoxicated pedestrian violation in business/industrial areas. Additionally, ‘careless operation’ at the intersection is associated with alcohol-involved drivers. Most of the nighttime pedestrian crashes at segments are associated with roadways with no physical separation and the absence of streetlights. Driver alcohol involvement and their physical condition (inattentive/distracted) are also associated with pedestrian crashes associated at the segment location at night. Other segment pedestrian crashes are linked to the interstate in dark conditions, open country locations, and high-speed roadways. Additionally, the crash site investigation identified several critical pedestrian safety concerns including the lack of crosswalk facilities, high driveway density, and pedestrian behavioral patterns (e.g., crossing at roadway segments close to the intersection location). Practical Applications: The findings of this study can be used for selecting the appropriate countermeasures based on a case-by-case basis. The exposure patterns can be used in educational campaigns to strategically reduce nighttime pedestrian crashes.

Investigating pedestrian crash patterns at high-speed intersection and road segments: Findings from the unsupervised learning algorithm

Pedestrian crashes at high-speed locations are a persistent road safety concern. Driving at high speeds means that the driver has less time to react and make evasive maneuvers to avoid a pedestrian crash. On top of this, other crash-contributing factors such as humans (pedestrians or drivers), vehicles, roadways, and surrounding environmental factors actively interact together to cause a crash at high-speed locations. The pattern of pedestrian crashes also differs significantly according to the high-speed intersection and segment locations which require further investigation. This study applied association rules mining (ARM), an unsupervised learning algorithm, to reveal the hidden association of pedestrian crash risk factors according to the high-speed intersection and segments separately. The study used Louisiana pedestrian fatal and injury crash data (2010 to 2019). Any crash location with a posted speed limit of 45 mph or above is classified as a high-speed location. Based on the generated association rules, the results show that pedestrian crashes at a high-speed intersection are associated with the intersection geometry (3-leg) and control (1 stop, no traffic control device), driver characteristics (careless operation, failure to yield, inattentive-distracted, older, and younger driver), pedestrian-related factors (violations, alcohol/drug involvement), settings (open country, residential, business, industrial), dark lighting conditions and so on. Most pedestrian crashes at high-speed segments are associated with roadways with no physical separation, dark-no-streetlight conditions, open country locations, interstates and so on. The findings of the study may help to select appropriate countermeasures to reduce pedestrian crashes at high-speed locations.

Self-Supervised multi-image Super-Resolution Network for Space Image Restoration

Space-based space surveillance (SBSS) has the advantage of being flexible and highly interpretable, allowing it to play a strategic role in monitoring space targets. During actual missions, however, bursts of push-frame imaging methods, dynamic noise during observation, large motions and other factors can result in visible degradation, and it isn’t easy to have the corresponding high-resolution (HR) images for the low-resolution (LR) images acquired at the high-speed intersection, which seriously limits the existing multi-image super-resolution (MISR) methods for space-based applications. To overcome these problems, this paper proposes a self-supervised video super-resolution deep learning method that can be trained end-to-end in space-based observations without LR/HR image pairs. We generate extra training pairs using different sizes of sampling factors for LR videos and train the video hyper-resolution network from coarse to fine using a pyramid format. Extensive experiments on the public satellite dataset BUAA-SID-share1.0 show that our approach outperforms traditional video hyper-resolution methods.

On Concentration Detection of FAE Cloud at High-speed Intersection between FAE Cloud and Sub-fuze

On Concentration Detection of FAE Cloud at High-speed Intersection between FAE Cloud and Sub-fuze

Influence of following vehicle’s tailway and classification on subject driver’s response to the circular yellow indication

Traffic crashes at signalized intersections are frequently linked to driver behavior at the onset of the circular yellow (CY) indication. To better understand behavioral factors that influence a driver’s decision to stop or go at an intersection, this study analyzed the behavior of the driver of a subject vehicle at the onset of the CY indication. Driver performance data from 53 participants were collected in the Oregon State University Driving Simulator, simulating scenarios of driving through high-speed intersections under various conditions. Data included interactions where the driver stopped at the stop line (n = 644) or proceeded through the intersection (n = 628) in response to a CY indication. Data were analyzed as panel data while considering 12 indicator variables related to the driver’s stop/go decision. These indicator variables included time to stop line (TTSL), tailway time, following vehicle type, vehicle speed at the onset of the CY indication, and demographics (age, gender, driving experience, level of education, personal vehicle type, number of times driving per week, number of miles driving last year, participation in previous simulation studies. A random-parameter binary logit model was used to determine contributing factors for driver decision making at the onset of CY indication while accounting for unobserved heterogeneity. Four indicator variables were significantly related to the driver’s stop/go decision, but three factors varied across observations. Findings showed that a driver’s stop/go decision in response to a CY indication was associated with the time to the stop line (TTSL), tailway time to the following vehicle, subject vehicle speed at the onset of the CY indication, and driver’s age (20–36 years), but was not significantly associated with classification of the following vehicle. Also, the findings indicated that a shorter tailway increased a subject driver’s red-light running frequency. These findings provide insights into variables that affect driver decisions in a vehicle-following situation at the onset of the CY indication. This information can help make better decisions in smart traffic control systems such as to extend/decrease the green interval slightly to avoid decisions that are more difficult.

Impact of Intersection Control on Battery Electric Vehicle Energy Consumption

Battery electric vehicle (BEV) sales have significantly increased in recent years. They have different energy consumption patterns compared to the fuel consumption patterns of internal combustion engine vehicles (ICEVs). This study quantified the impact of intersection control approaches—roundabout, traffic signal, and two-way stop controls—on BEVs’ energy consumption. The paper systematically investigates BEVs’ energy consumption patterns compared to the fuel consumption of ICEVs. The results indicate that BEVs’ energy consumption patterns are significantly different than ICEVs’ patterns. For example, for BEVs approaching a high-speed intersection, the roundabout was found to be the most energy-efficient intersection control, while the two-way stop sign was the least efficient. In contrast, for ICEVs, the two-way stop sign was the most fuel-efficient control, while the roundabout was the least efficient. Findings also indicate that the energy saving of traffic signal coordination was less significant for BEVs compared to the fuel consumption of ICEVs since more regenerative energy is produced when partial or poorly coordinated signal plans are implemented. The study confirms that BEV regenerative energy is a major factor in energy efficiency, and that BEVs recover different amounts of energy in different urban driving environments. The study suggests that new transportation facilities and control strategies should be designed to enhance BEVs’ energy efficiency, particularly in zero emission zones.

A Comparative Study on Drivers’ Stop/Go Behavior at Signalized Intersections Based on Decision Tree Classification Model

The stop/go decisions at signalized intersections are closely related to driving speed during signal change intervals. The speed during stop/go decision-making has a significant influence on the dilemma area, resulting in changes of stop/go decisions and high complexity of the decision-making process. Considering that traffic delays and vehicle exhaust pollution are mainly caused by queuing at intersections, the stop-line passing speed during the signal change interval will affect both vehicle operation safety and the atmospheric environment. This paper presents a comparative study on drivers’ stop/go behaviors when facing a transition signal period consisting of 3 s green flashing light (FG) and 3 s yellow light (Y) at rural high-speed intersections and urban intersections. For this study, 1,459 high-quality vehicle trajectories of five intersections in Shanghai during the transition signal period were collected. Of these five intersections, three are high-speed intersections with a speed limit of 80 km/h, and the other two are urban intersections with a speed limit of 50 km/h. Trajectory data of these vehicle samples were statistically analyzed to investigate the general characteristics of potential influencing factors, including the instantaneous speed and the distance to the intersection at the start of FG, the vehicle type, and so on. Decision Tree Classification (DTC) models are developed to reveal the relationship between the drivers’ stop/go decisions and these possible influencing factors. The results indicate that the instantaneous speed of FG onset, the distance to the intersection at the start of FG, and the vehicle type are the most important predictors for both types of intersections. Besides, a DTC model can offer a simple way of modeling drivers’ stopping decision behavior and produce good results for urban intersections.

Real-Time Prediction of Vehicle Trajectories for Proactively Identifying Risky Driving Behaviors at High-Speed Intersections

At high-speed intersections in many Chinese cities, a traffic-light warning sequence at the end of the green phase—three seconds of flashing green followed by three seconds of yellow—is commonly implemented. Such a long phase transition time leads to heterogeneous decision-making by approaching drivers as to whether to pass the signal or stop. Therefore, risky driving behaviors such as red-light running, abrupt stop, and aggressive pass are more likely to occur at these intersections. Proactive identification of risky behaviors can facilitate mitigation of the dilemma zone and development of on-board safety altering strategies. In this study, a real-time vehicle trajectory prediction method is proposed to help identify risky behaviors during the signal phase transition. Two cases are considered and treated differently in the proposed method: a single vehicle case and a following vehicle case. The adaptive Kalman filter (KF) model and the K-nearest neighbor model are integrated to predict vehicle trajectories. The adaptive KF model and intelligent driver model are fused to predict the following vehicles’ trajectories. The proposed models are calibrated and validated using 1,281 vehicle trajectories collected at three high-speed intersections in Shanghai. Results indicate that the root mean square error between the predicted trajectories and the actual trajectories is 5.02 m for single vehicles and 2.33 m for following vehicles. The proposed method is further applied to predict risky behaviors, including red-light running, abrupt stop, aggressive pass, speeding pass, and aggressive following. The overall prediction accuracy is 95.1% for the single vehicle case and 96.2% for the following vehicle case.

Investigating drivers’ decision zones at high-speed intersections in China based on the acceleration-deceleration diagram

The objective of this paper is to empirically investigate drivers’ decision zones at the onset of flashing green and yellow indication at rural high-speed intersections in China. 1122 high-resolution trajectories of the first-to-stop and the last-to-go vehicles during the phase transition time period were collected at four intersection approaches in Shanghai. Speed-Distance (S-D) diagram and Acceleration-Deceleration (A-D) diagram were then used to analyze the distribution of drivers’ decision zones in response to the onset of flashing green and yellow respectively. The former is a conventional approach based on a fundamental assumption that no drivers would accelerate to cross or make an abrupt stop. The latter is a more flexible method based on the required acceleration rate to cross and the required deceleration rate to stop which can be extracted from vehicle trajectory data. Results support that the installation of flashing green helps to reduce the dilemma zone according to the A-D diagram. There are limits when using S-D diagram to analyse the driving situations based on G.H.M model.

Assessing the Impact of Speed-Limit Reduction near Signalized High-Speed Intersections Equipped with Advance-Warning Flashers

AbstractAn advance-warning flasher alerts drivers of the imminent onset of a yellow light at a signalized intersection, and it is widely used to reduce crash frequency and severity. Recently, a mor...

Empirical Analysis and Modeling of Stop-Line Crossing Time and Speed at Signalized Intersections.

In China, a flashing green (FG) indication of 3 s followed by a yellow (Y) indication of 3 s is commonly applied to end the green phase at signalized intersections. Stop-line crossing behavior of drivers during such a phase transition period significantly influences safety performance of signalized intersections. The objective of this study is thus to empirically analyze and model drivers’ stop-line crossing time and speed in response to the specific phase transition period of FG and Y. High-resolution trajectories for 1465 vehicles were collected at three rural high-speed intersections with a speed limit of 80 km/h and two urban intersections with a speed limit of 50 km/h in Shanghai. With the vehicle trajectory data, statistical analyses were performed to look into the general characteristics of stop-line crossing time and speed at the two types of intersections. A multinomial logit model and a multiple linear regression model were then developed to predict the stop-line crossing patterns and speeds respectively. It was found that the percentage of stop-line crossings during the Y interval is remarkably higher and the stop-line crossing time is approximately 0.7 s longer at the urban intersections, as compared with the rural intersections. In addition, approaching speed and distance to the stop-line at the onset of FG as well as area type significantly affect the percentages of stop-line crossings during the FG and Y intervals. Vehicle type and stop-line crossing pattern were found to significantly influence the stop-line crossing speed, in addition to the above factors. The red-light-running seems to occur more frequently at the large intersections with a long cycle length.

Exploring stop-go decision zones at rural high-speed intersections with flashing green signal and insufficient yellow time in China

The objective of this study is to empirically analyze and model the stop-go decision behavior of drivers at rural high-speed intersections in China, where a flashing green signal of 3s followed by a yellow signal of 3s is commonly applied to end a green phase. 1, 186 high-resolution vehicle trajectories were collected at four typical high-speed intersection approaches in Shanghai and used for the identification of actual stop-go decision zones and the modeling of stop-go decision behavior. Results indicate that the presence of flashing green significantly changed the theoretical decision zones based on the conventional Dilemma Zone theory. The actual stop-go decision zones at the study intersections were thus formulated and identified based on the empirical data. Binary Logistic model and Fuzzy Logic model were then developed to further explore the impacts of flashing green on the stop-go behavior of drivers. It was found that the Fuzzy Logic model could produce comparably good estimation results as compared to the traditional Binary Logistic models. The findings of this study could contribute the development of effective dilemma zone protection strategies, the improvement of stop-go decision model embedded in the microscopic traffic simulation software and the proper design of signal change and clearance intervals at high-speed intersections in China.

Modeling Risky Driver Behavior Under the Influence of Flashing Green Signal with Vehicle Trajectory Data

In China, a 3-s flashing green (FG) indication followed by a 3-s yellow (Y) indication is commonly applied to end the green phase at signalized intersections regardless of speed limits. Past research has indicated that the FG may bring more uncertainty and dynamics to drivers’ stop–go decisions at the end of the green phase, particularly at high-speed intersections. Hence, the objective of this study was to propose a probabilistic model for interpreting drivers’ dynamic decision-making processes in response to the combination of FG and Y at rural high-speed intersections, which could help quantitatively analyze the safety effects of FG. The inputs of the proposed model included mainly the acceleration and deceleration rate and the perception-and-reaction time. The outputs were the frequencies of risky behavior, including abrupt stop and aggressive pass on the basis of the cycle. The trajectories of 1,186 vehicles, collected at three rural high-speed intersections in Shanghai, China, with a speed limit of 80 km/h were used for the uncertainty analysis of input variables and model validation. On the basis of the proposed model, three typical scenarios of phase transition periods—3-s FG + 3-s Y, 0-s FG + 5-s Y, and 0-s FG + 3-s Y—were valuated. Results showed that the proposed model was capable of producing an average error of less than 10%. In addition, the scenario of 0-s FG + 5-s Y performed best in reducing risky behavior. It is recommended that a 5-s Y be implemented for high-speed intersections when most of the traffic consists of passenger cars.

Operational Effects of Transverse Rumble Strips on Approaches to High-Speed Intersections

The objective of this study was to determine whether the application of transverse rumble strips was an effective warning device for drivers approaching high-speed intersections. Performance was evaluated for attention-getting characteristics, driver speed choice, and braking behavior. Five intersection approaches on US-280 in Alabama were selected and monitored during both daytime and nighttime conditions. Acoustic and tactile signatures were measured by a specially equipped passenger car under different speed ranges. To examine effectiveness on speed changes, vehicle mean speeds were recorded by radar measurements along the approach to the intersections: 400 ft (122 m) upstream of the transverse rumble strips, right before the transverse rumble strips, and right after the transverse rumble strips. Video cameras were also in place to survey the brake lights of vehicles driving over the transverse rumble strips to quantify driver behavior. An analysis of variance F-test and Tukey’s honest significance test revealed that the strips created a recognizable amount of interior noise and vibration when an automobile crossed over the transverse rumble strips. The installation of transverse rumble strips generally produced statistically significant ( p ≤ .05) reductions in approach speeds. During daytime and at night, drivers drove at lower speeds through the intersections compared with the initial upstream speed. The transverse rumble strips also exerted certain effects on driver braking behavior.

Modeling Drivers' Dynamic Decision-Making Behavior During the Phase Transition Period: An Analytical Approach Based on Hidden Markov Model Theory

A flashing green indication of 3 s followed by a yellow indication of 3s is commonly applied to end a green phase at signalized intersections in many Chinese cities. This paper proposes an analytical approach based on the hidden Markov model theory to interpret the dynamic decision-making process of drivers during the phase transition period at high-speed signalized intersections. In the proposed model, the hidden states are the unobservable time-dependent decisions of drivers concerning whether to stop or pass, and the observable states are the instantaneous vehicle speeds and acceleration/deceleration rates that are obtained from the high-resolution vehicle trajectory data. The data were collected by videotaping four typical high-speed intersection approaches with a speed limit of 80 km/h in Shanghai. Eventually, 698 vehicle trajectories including 179 trucks and 519 passenger cars were extracted from the videos and used for model estimation and validation. It was found that the proposed model could predict stop–pass decisions with very high accuracy and revealed that approximately 50% of drivers used a two-step decision-making process. In addition, a large percentage of decision changes occurred 0–1.2 s after the onset of yellow, which is based on a driver's perceived environment. The important implications of the proposed model and the findings are also discussed in this paper.

The History of Traffic Safety: Describing 100 Years

We need ways to express the history of traffic safety. The death of 100 million people (and counting) through a completely manmade system must be explained from different angles. The historical perspective is necessary to help the traffic safety community avoid repeating and continuing this human catastrophe. Of course it was never the intention that a transport system would have such consequences. Sadly, it became accepted that the loss of human life was a routine part of this complex enterprise. Of course this assumption is false. History can help to explain the tragedy in a scientific form, without blaming or demonizing those involved in the process who tried different cures they no doubt believed in. Many of us who work in policymaking to improve traffic safety have recognized that newcomers, like newly elected transport ministers and their teams, have good intentions but an amateur’s knowledge of how to improve traffic safety. Education and information, which are often useless, are usually the first tools that are applied, sometimes followed by enforcement. Historical reflections on traffic safety might help inspire effective solutions from the beginning. Peter Norton’s “four paradigms” are a meaningful attempt to describe the approaches to auto safety over the last 100 years. At first it might seem strange that it is possible to present such a long process with just four headings, but his analysis is sharp and insightful. There is little doubt that there was a dramatic shift from seeing the automobile as a potentially dangerous machine to viewing it as one controllable by sensible and responsible individuals. For many this probably marks the beginning of the catastrophe. Imagine what might have happened if the car industry and infrastructure providers at that moment had taken on the responsibility for automobile safety. History would have looked very different. Nicholas Oddy’s article on signage is the perfect first example of the amateur’s attempt at prevention, an impulse still strong today. It demonstrates Norton’s first and second paradigms, offering a good example of how responsibility moved from the provider to the user. Massimo Moraglio takes us even further into the period of handing over responsibility to the individual user, resulting in the widely held idea that bicycles and cars in themselves can be considered safe. In Donald Weber’s wonderful article about the formation of crash statistics, it becomes even clearer that from the 1920s to 1940s, there was a question of dividing the blame, assigning it first to motorists and later to other road users like pedestrians. Weber writes: “The Touring Club’s approach was intended to allow motorists to avoid, or at least to share, the blame for the numerous traffic accidents.” As we learned later, in both aviation and road traffic safety the “blame game” is one of the major obstacles to effective prevention. It biases information, hides higher-degree prevention initiatives, and draws attention away from the fact that these problems are partly a result of how we as a society organize traffic safety to limit the responsibility for those designing and operating the road transport system. Most importantly, it discourages the development of other solutions such as new road or vehicle design. Steve Bernardin’s “Taking the Problem to the People” is a great example of what happens when a paradigm gets tied up with politics and elaborated through lobbying and professional marketing methods. While we still do not have to question their intentions, it is clear that the car industry lobby was getting more nervous about the continuously increasing number of deaths and the counterforces that sooner or later would gain momentum. And as we all know, they did! Jameson Wetmore insightfully describes what was really a paradigm shift from “blaming the victim” to “designing the driver out of the problem,” a very quick change of view that turned everything upside down. The problem was not the automotive industry, however. The problem was that the providers of the road infrastructure never understood that the advocates of crashworthiness meant a crashworthy system, not simply crash-worthy cars and restraints. Unfortunately the highway agencies and the urban designers continued to build high-speed intersections with traffic signals instead of roundabouts, and... Language: en

Stochastic effects of traffic randomness on the determination of signal change and clearance intervals at signalised intersections

Conventional methods of intergreen time design are based on deterministic traffic flow theory and are difficult to fully reflect traffic randomness especially driver's decision differences. This study is to develop a probabilistic model to extensively investigate the effects of traffic flow randomness and driver's decision errors on the determination of intergreen times. An analytical framework was proposed based on a safety reliability model earlier developed by the authors and validated based on field data at a typical high-speed intersection in Shanghai. Then, comprehensive sensitivity analysis was performed to look into the fluctuation of safety reliability towards critical variables as well as their variations and correlations. Two logistic regression models were developed to quantify the effects of each random component on the probabilities of risky behaviour and clearance failure, that is, safety reliability indicators for intergreen intervals. To facilitate easy applications of the proposed approach, a set of scenario analysis were done to calculate the required intergreen intervals under different traffic conditions and safety reliability levels. Application tables were finally provided for signal design, which are able to recommend more sophisticated intergreen times and thus aid the practitioners to select proper intergreen times according to local conditions without complicated calculation.

A Comparitive Analysis of Stop/Go Driving Behavior during the Amber Light at City Signalized Intersecdtions

This paper investigates the relationship between the driver’s stop/go behavior when encountering signal change from green to amber and traffic parameters of each car arriving at the intersection during the amber light. The data was collected from two intersections (one is high speed the other is low speed) both located in Beijing with video camera for a period of two weeks. 462 samples are extracted from the video using the software Adobe Premiere Pro CS4. Each sample include the stop/go decision, vehicle’s yellow onset speeds, vehicle’s yellow onset distance from the intersection, position (leading/following) in the traffic flow, vehicle’s speed, amber light time when vehicle travel through the stopline. The line regression technology and decision tree model are respectively used to analyse the difference of influence of traffic parameters to stop/go driving behavior between the high speed and low speed intersections. And it is clearly observed that the dilemma zone at low speed intersection is a little wider than that at high speed intersection althouth the averge arriving speed is lower. And the decision tree model result shows that parameter location play the most important role in sotp/go decisions, and parameter speed only works when the car falls into dilemma zone.

Impacts of Flashing Green on Dilemma Zone Behavior at High-Speed Intersections: Empirical Study in China

AbstractThis study investigated the impacts of flashing green on dilemma zone (DZ) behavior at the high-speed intersections with insufficient yellow interval. 360 high-resolution vehicle trajectories, used in the study, were obtained from an extensive survey at a typical rural high-speed intersection in Shanghai. Results indicate that with the presence of a flashing green signal, the measured behavioral parameters related to DZ determination at the onset of yellow tend to be remarkably smaller. The vast majority of drivers reacted to the onset of flashing green, instead of yellow onset. Flashing green significantly reduced the area of Type I DZ at the onset of yellow, while enlarged the areas of option zone and Type II DZ. Time to stop line at the onset of flashing green positively affected the stopping probability. Flashing green induced conservative stops by 30%, while encouraged aggressive passes slightly.

Yellow light dilemma zone researches: a review

The yellow light dilemma zone is widely known as an area on the high-speed intersection approach, where vehicles neither safely stop before the stop line nor proceed through the intersection during amber interval. Within such an area, a vehicle might be involved in a right-angle crash or rear-end collision. This issue has been extensively discussed over five decades in traffic engineering field, covering from theory to practice. However, few comprehensive review literatures on the amber signal dilemma zone problems can be found. The objective of this paper is to summarize the evolution of yellow light dilemma zone researches. Basic definition and boundary of dilemma zone followed by driver behavior and dilemma zone hazard measurement are depicted. At last, the future directions of yellow light dilemma zone research are discussed.