Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Real-time Evaluation Framework for Pedestrian's Potential Risk at Non-Signalized Intersections Based on Predicted Post-Encroachment Time

Tengfeng Lin, Zhixiong Jin, Seongjin Choi, Hwasoo Yeo

TL;DR

This work presents a real-time framework for assessing pedestrian risk at non-signalized intersections using a novel surrogate safety measure, Predicted Post-Encroachment Time (P-PET). It integrates CCTV-based trajectory extraction, arrival-time prediction with GRU/LSTM/Transformer models, and a P-PET–driven risk evaluation that distinguishes pedestrians as kids, adults, and cyclists. The approach demonstrates improved predictive accuracy and risk identification over traditional methods, with real-field validation at a non-signalized intersection and a detailed analysis of real-time feasibility on GPU hardware. The results support proactive pedestrian protection and offer planners data-driven insights for safer intersection design, while also outlining limitations and directions for edge-device deployment and broader pedestrian groups.

Abstract

Addressing pedestrian safety at intersections is one of the paramount concerns in the field of transportation research, driven by the urgency of reducing traffic-related injuries and fatalities. With advances in computer vision technologies and predictive models, the pursuit of developing real-time proactive protection systems is increasingly recognized as vital to improving pedestrian safety at intersections. The core of these protection systems lies in the prediction-based evaluation of pedestrian's potential risks, which plays a significant role in preventing the occurrence of accidents. The major challenges in the current prediction-based potential risk evaluation research can be summarized into three aspects: the inadequate progress in creating a real-time framework for the evaluation of pedestrian's potential risks, the absence of accurate and explainable safety indicators that can represent the potential risk, and the lack of tailor-made evaluation criteria specifically for each category of pedestrians. To address these research challenges, in this study, a framework with computer vision technologies and predictive models is developed to evaluate the potential risk of pedestrians in real time. Integral to this framework is a novel surrogate safety measure, the Predicted Post-Encroachment Time (P-PET), derived from deep learning models capable to predict the arrival time of pedestrians and vehicles at intersections. To further improve the effectiveness and reliability of pedestrian risk evaluation, we classify pedestrians into distinct categories and apply specific evaluation criteria for each group. The results demonstrate the framework's ability to effectively identify potential risks through the use of P-PET, indicating its feasibility for real-time applications and its improved performance in risk evaluation across different categories of pedestrians.

A Real-time Evaluation Framework for Pedestrian's Potential Risk at Non-Signalized Intersections Based on Predicted Post-Encroachment Time

TL;DR

This work presents a real-time framework for assessing pedestrian risk at non-signalized intersections using a novel surrogate safety measure, Predicted Post-Encroachment Time (P-PET). It integrates CCTV-based trajectory extraction, arrival-time prediction with GRU/LSTM/Transformer models, and a P-PET–driven risk evaluation that distinguishes pedestrians as kids, adults, and cyclists. The approach demonstrates improved predictive accuracy and risk identification over traditional methods, with real-field validation at a non-signalized intersection and a detailed analysis of real-time feasibility on GPU hardware. The results support proactive pedestrian protection and offer planners data-driven insights for safer intersection design, while also outlining limitations and directions for edge-device deployment and broader pedestrian groups.

Abstract

Addressing pedestrian safety at intersections is one of the paramount concerns in the field of transportation research, driven by the urgency of reducing traffic-related injuries and fatalities. With advances in computer vision technologies and predictive models, the pursuit of developing real-time proactive protection systems is increasingly recognized as vital to improving pedestrian safety at intersections. The core of these protection systems lies in the prediction-based evaluation of pedestrian's potential risks, which plays a significant role in preventing the occurrence of accidents. The major challenges in the current prediction-based potential risk evaluation research can be summarized into three aspects: the inadequate progress in creating a real-time framework for the evaluation of pedestrian's potential risks, the absence of accurate and explainable safety indicators that can represent the potential risk, and the lack of tailor-made evaluation criteria specifically for each category of pedestrians. To address these research challenges, in this study, a framework with computer vision technologies and predictive models is developed to evaluate the potential risk of pedestrians in real time. Integral to this framework is a novel surrogate safety measure, the Predicted Post-Encroachment Time (P-PET), derived from deep learning models capable to predict the arrival time of pedestrians and vehicles at intersections. To further improve the effectiveness and reliability of pedestrian risk evaluation, we classify pedestrians into distinct categories and apply specific evaluation criteria for each group. The results demonstrate the framework's ability to effectively identify potential risks through the use of P-PET, indicating its feasibility for real-time applications and its improved performance in risk evaluation across different categories of pedestrians.
Paper Structure (45 sections, 5 equations, 11 figures, 10 tables, 1 algorithm)

This paper contains 45 sections, 5 equations, 11 figures, 10 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Review of Current Research
  4. Traditional Pedestrian Safety Analysis
  5. Vision techniques in pedestrian trajectory extraction
  6. Post-interaction-based pedestrian risk evaluation study
  7. Predicted-based potential risk evaluation study
  8. Research limitation Summarizing
  9. Research contribution
  10. Paper structure
  11. Methodology
  12. Framework
  13. Video Dataset Preprocessing
  14. Site Introduction
  15. Video Processing with Computer Vision
  16. ...and 30 more sections

Figures (11)

  • Figure 1: Framework for Potential Risk Evaluation
  • Figure 2: Two views of the Target Intersection in Sejong City. (a) Bird's Eye View. (b) CCTV Camera View.
  • Figure 3: Segmentation Target Points for Pedestrians and Vehicles in Different Directions.
  • Figure 4: Calibration figures that demonstrate calibration points, world coordinates, and trajectory examples in both pixel and world coordinates.
  • Figure 5: Illustration of Area Division Rules Applied to the Site
  • ...and 6 more figures