☆ 4.7 Article

Prediction of jaywalker-vehicle conflicts based on encoder-decoder framework utilizing multi-source data

ACCIDENT ANALYSIS AND PREVENTION (2024)

Related references

Note: Only part of the references are listed.

Article Ergonomics

Physics-informed multi-step real-time conflict-based vehicle safety prediction

Handong Yao et al.

Summary: This study proposes a physics-informed multi-step real-time conflict-based vehicle safety prediction model to enhance roadway safety. Phys-ics insights are combined with data-driven features extracted from deep-learning techniques to improve prediction accuracy. A time series of future vehicle safety indicators are pre-dicted to give vehicles/drivers enough time to take precautions.

ACCIDENT ANALYSIS AND PREVENTION (2023)

Add to Collection

Article Ergonomics

Traffic conflict assessment using macroscopic traffic flow variables: A novel framework for real-time applications

Ninad Gore et al.

Summary: The present study develops a comprehensive traffic conflict assessment framework using macroscopic traffic state variables. Vehicular trajectories extracted for a midblock section of a ten-lane divided Western Urban Expressway in India are used. The study finds that intermediately congested traffic flow conditions are critical for traffic safety, and the random forest (RF) model is the best-fitted model to predict time spent in conflict (TSC) based on macroscopic traffic variables. The developed machine learning model facilitates real-time traffic safety monitoring.

ACCIDENT ANALYSIS AND PREVENTION (2023)

Add to Collection

Article Ergonomics

Investigating jaywalker crossing risks from the sequential-conflict perspective: A grouped random parameters generalized ordered probit model

Ziqian Zhang et al.

Summary: Jaywalking at the mid-blocks without crossing facilities is identified as a dangerous behavior, which may result in sequential conflicts. This study investigates the risks of jaywalking from a sequential-conflict perspective, revealing the influence of previous conflict-related factors on subsequent conflicts. The results show that as the conflict sequence increases, more jaywalkers tend to behave aggressively, and slight conflicts become more common. Practical suggestions are provided to reduce jaywalking activities and prevent accidents.

ACCIDENT ANALYSIS AND PREVENTION (2023)

Add to Collection

Article Transportation Science & Technology

A context-aware pedestrian trajectory prediction framework for automated vehicles

Arash Kalatian et al.

Summary: Studying pedestrian behavior in automated urban environments is crucial, and current datasets lack pedestrian perspectives. Virtual reality data can be used as a complementary resource to measure pedestrian behavior in specific conditions. In this study, a context-aware pedestrian trajectory prediction framework is proposed, incorporating pedestrian head orientations and distance to vehicles to predict future pedestrian trajectories.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Psychology, Applied

Evaluation of motorized two-wheeler rider responses towards jaywalking pedestrians through mockup control studies for urban streets

Pradhan Kumar Akinapalli et al.

Summary: This study models the evasive-action behavior of motorized two-wheeler riders towards jaywalking pedestrians using a mockup study. The results show that 32% of riders perform hard braking in surprise scenarios, with 90% of surprise events resulting in a loss of control of the motorized two-wheeler. These observations provide a basis for improving pedestrian and motorized two-wheeler rider safety.

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Real-Time Pedestrian Conflict Prediction Model at the Signal Cycle Level Using Machine Learning Models

Shile Zhang et al.

Summary: Compared with traditional traffic studies, real-time safety analyses can be better incorporated into proactive traffic management strategies to improve traffic safety. This paper proposes a method that uses machine learning models and logistic regression to predict pedestrian conflicts, combining closed-circuit television videos and traffic data for analysis and prediction.

IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Ergonomics

Safety effects of law enforcement cameras at non-signalized crosswalks: A case study in China

Haojie Li et al.

Summary: The implementation of law enforcement cameras at non-signalized crosswalks can increase the probability of drivers yielding to pedestrians and reduce the likelihood of serious conflicts. Improving awareness of yielding rules is necessary due to a high percentage of illegitimate yielding behavior, and the use of law enforcement cameras can help increase legitimate yielding behavior. Factors such as adjacent vehicle yielding behavior and pedestrian characteristics significantly impact conflict severity and drivers' yielding behavior.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Add to Collection

Article Transportation Science & Technology

Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network

Jintao Ke et al.

Summary: With the rapid development of mobile-internet technologies, on-demand ride-sourcing services have become popular and demand prediction is crucial. Traditional zone-based prediction models face challenges due to the complex spatial and temporal dependencies among OD demands. A novel deep learning model is proposed to address this issue and outperforms existing technologies in forecasting ride-sourcing demand.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

Add to Collection

Article Engineering, Industrial

Investigation of pedestrian jaywalking behaviour at mid-block locations using artificial neural networks

Md Asif Hasan Anik et al.

Summary: This research utilizes artificial neural networks to predict jaywalker trajectories, determining the best model through testing various ANN architectures, and uncovering movement patterns and position shifting strategies of jaywalkers.

SAFETY SCIENCE (2021)

Add to Collection

Article Ergonomics

Investigating conflict behaviours and characteristics in shared space for pedestrians, conventional bicycles and e-bikes

Xinyu Liang et al.

Summary: Shared spaces are becoming more popular worldwide, with pedestrians, conventional bicycles, and e-bikes coexisting. There is a positive relationship between traffic volume and conflict number, but an inverse relationship between traffic ratios and conflict ratios. Emergency actions such as swerving, decelerating, and accelerating were most common, with swerving particularly prevalent in slight conflicts. In serious conflicts, conventional bicycles and e-bikes exhibited low-speed characteristics compared to slight conflicts. High traffic volume and complexity were identified as main factors affecting conflicts. Conflict coefficient was proposed as a measure for shared-space safety. Conflicts and crashes between e-bikes and pedestrians were identified as high-occurrence events, with pedestrians at a higher risk of injury.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Add to Collection

Article Psychology, Applied

Analysis of the occurrence and severity of vehicle-pedestrian conflicts in marked and unmarked crosswalks through naturalistic driving study

Abbas Sheykhfard et al.

Summary: The study found that drivers in unmarked crosswalk areas yield at about half the rate of drivers in marked crosswalk areas. Analysis showed that pedestrian behavior in encounter conflicts and driver behavior in potential, slight, and serious conflicts are the main factors in preventing collisions.

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR (2021)

Add to Collection

Article Ergonomics

Prediction of pedestrian-vehicle conflicts at signalized intersections based on long short-term memory neural network

Shile Zhang et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Add to Collection

Article Ergonomics

Underestimation tendencies of vehicle speed by pedestrians when crossing unmarked roadway

Zoran Papic et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Add to Collection

Article Ergonomics

Real-time crash risk prediction on arterials based on LSTM-CNN

Pei Li et al.

ACCIDENT ANALYSIS AND PREVENTION (2020)

Add to Collection

Article Transportation Science & Technology

Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system

Siyu Hao et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2019)

Add to Collection

Article Ergonomics

A novel method of vehicle-pedestrian near-crash identification with roadside LiDAR data

Jianqing Wu et al.

ACCIDENT ANALYSIS AND PREVENTION (2018)

Add to Collection

Article Psychology, Applied

Analysis of illegal pedestrian crossing behavior on a major divided arterial road

Khaled Shaaban et al.

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR (2018)

Add to Collection

Article Ergonomics

Evaluation of pedestrian safety at intersections: A theoretical framework based on pedestrian-vehicle interaction patterns

Ying Ni et al.

ACCIDENT ANALYSIS AND PREVENTION (2016)

Add to Collection

Article Transportation Science & Technology

Using the Bayesian updating approach to improve the spatial and temporal transferability of real-time crash risk prediction models

Chengcheng Xu et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2014)

Add to Collection

Article Ergonomics

Pedestrians' intention to jaywalk: Automatic or planned? A study based on a dual-process model in China

Yaoshan Xu et al.

ACCIDENT ANALYSIS AND PREVENTION (2013)

Add to Collection

Article Psychology, Applied

The safety margin and perceived safety of pedestrians at unmarked roadway

Xiangling Zhuang et al.

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR (2012)

Add to Collection

Article Ergonomics

Pedestrians' crossing behaviors and safety at unmarked roadway in China

Xiangling Zhuang et al.

ACCIDENT ANALYSIS AND PREVENTION (2011)

Add to Collection

© Peeref 2019-2024. All rights reserved.