Deep Learning Architectures for Skateboarder–Pedestrian Surrogate Safety Measures

Skateboarding as a method of transportation has become prevalent, which has increased the occurrence and likelihood of pedestrian–skateboarder collisions and near-collision scenarios in shared-use roadway areas. Collisions between pedestrians and skateboarders can result in significant injury. New approaches are needed to evaluate shared-use areas prone to hazardous pedestrian–skateboarder interactions, and perform real-time, in situ (e.g., on-device) predictions of pedestrian–skateboarder collisions as road conditions vary due to changes in land usage and construction. A mechanism called the Surrogate Safety Measures for skateboarder–pedestrian interaction can be computed to evaluate high-risk conditions on roads and sidewalks using deep learning object detection models. In this paper, we present the first ever skateboarder–pedestrian safety study leveraging deep learning architectures. We view and analyze state of the art deep learning architectures, namely the Faster R-CNN and two variants of the Single Shot Multi-box Detector (SSD) model to select the correct model that best suits two different tasks: automated calculation of Post Encroachment Time (PET) and finding hazardous conflict zones in real-time. We also contribute a new annotated data set that contains skateboarder–pedestrian interactions that has been collected for this study. Both our selected models can detect and classify pedestrians and skateboarders correctly and efficiently. However, due to differences in their architectures and based on the advantages and disadvantages of each model, both models were individually used to perform two different set of tasks. Due to improved accuracy, the Faster R-CNN model was used to automate the calculation of post encroachment time, whereas to determine hazardous regions in real-time, due to its extremely fast inference rate, the Single Shot Multibox MobileNet V1 model was used. An outcome of this work is a model that can be deployed on low-cost, small-footprint mobile and IoT devices at traffic intersections with existing cameras to perform on-device inferencing for in situ Surrogate Safety Measurement (SSM), such as Time-To-Collision (TTC) and Post Encroachment Time (PET). SSM values that exceed a hazard threshold can be published to an Message Queuing Telemetry Transport (MQTT) broker, where messages are received by an intersection traffic signal controller for real-time signal adjustment, thus contributing to state-of-the-art vehicle and pedestrian safety at hazard-prone intersections.

Surrogate Safety Measures Prediction at Multiple Timescales in V2P Conflicts Based on Gated Recurrent Unit

Improving pedestrian safety at urban intersections requires intelligent systems that should not only understand the actual vehicle–pedestrian (V2P) interaction state but also proactively anticipate the event’s future severity pattern. This paper presents a Gated Recurrent Unit-based system that aims to predict, up to 3 s ahead in time, the severity level of V2P encounters, depending on the current scene representation drawn from on-board radars’ data. A car-driving simulator experiment has been designed to collect sequential mobility features on a cohort of 65 licensed university students who faced different V2P conflicts on a planned urban route. To accurately describe the pedestrian safety condition during the encounter process, a combination of surrogate safety indicators, namely TAdv (Time Advantage) and T2 (Nearness of the Encroachment), are considered for modeling. Due to the nature of these indicators, multiple recurrent neural networks are trained to separately predict T2 continuous values and TAdv categories. Afterwards, their predictions are exploited to label serious conflict interactions. As a comparison, an additional Gated Recurrent Unit (GRU) neural network is developed to directly predict the severity level of inner-city encounters. The latter neural model reaches the best performance on the test set, scoring a recall value of 0.899. Based on selected threshold values, the presented models can be used to label pedestrians near accident events and to enhance existing intelligent driving systems.

Investigation of surrogate measures for safety assessment of two-way stop controlled intersections.

Crash prediction models used to estimate safety at intersections, road, and highway segments are traditionally developed using various traffic volume measures. There are issues with this approach and surrogate safety measures such as conflicts and delays can overcome them. This study investigates the relationships between crash frequencies and traffic volume, intersection delay, and conflicts to explore the viability of these models for estimating safety at two-way stop controlled intersections. The database used includes 78 three leg and 55 four leg intersections within the Greater Toronto Area. Crash prediction models were developed and evaluated based on goodness-of-fit measures and CURE plots. Two conflict estimation techniques are compared in order to determine which is best suited for two-way stop controlled intersection simulations. This study also investigates the use of the models for estimating the safety impact of implementing a left turn lane on a major approach of a three leg intersection.

Investigation of surrogate measures for safety assessment of two-way stop controlled intersections.

Crash prediction models used to estimate safety at intersections, road, and highway segments are traditionally developed using various traffic volume measures. There are issues with this approach and surrogate safety measures such as conflicts and delays can overcome them. This study investigates the relationships between crash frequencies and traffic volume, intersection delay, and conflicts to explore the viability of these models for estimating safety at two-way stop controlled intersections. The database used includes 78 three leg and 55 four leg intersections within the Greater Toronto Area. Crash prediction models were developed and evaluated based on goodness-of-fit measures and CURE plots. Two conflict estimation techniques are compared in order to determine which is best suited for two-way stop controlled intersection simulations. This study also investigates the use of the models for estimating the safety impact of implementing a left turn lane on a major approach of a three leg intersection.

Crash- and Simulation-Based Safety Performance Evaluation of Freeway Rest Area

The main objective of this study was to evaluate the safety effects caused by altering the lengths of deceleration and acceleration lanes at rest areas on expressways in Korea. Although general conclusions can be found through crash-based safety analysis, to examine more specific optimal conditions considering various traffic conditions, this study proposes a novel framework to explore and evaluate crash-based and simulation-based safety performances. For this purpose, the safety performance function (SPF) and crash modification factor (CMF) were developed to reflect real-world safety impacts. To consider nonlinear trends of the parameters, nonlinearizing link functions were introduced into the analysis. Two types of simulation analyses were conducted to (1) find the combination of surrogate safety measures (SSMs) that best fit with the crash-based safety performance results and (2) determine the optimal lengths of deceleration lane and acceleration lanes for different traffic conditions. The results showed that the best length of deceleration lane of a rest area is between 240 and 260 m, depending on the traffic conditions. The results also indicated that the optimal length of acceleration lane of a rest area is between 385 and 400 m, depending on the traffic parameters. The findings of this study could be used to determine the safety solutions with a micro-traffic simulator.