Prediction of pedestrian-vehicle conflicts at signalized intersections based on long short-term memory neural network. 2020

Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
Department of Civil, Environmental & Construction Engineering, University of Central Florida, Orlando, FL 32816, USA. Electronic address: shirleyzhang@Knights.ucf.edu.

Pedestrian protection is an important component of road safety. Intersections are dangerous locations for pedestrians with mixed traffic. This paper aims to predict potential traffic conflicts between pedestrians and vehicles at signalized intersections. Using detection and tracking techniques in computer vision, pedestrians' and vehicles' features are extracted from video data. An LSTM (Long Short-term Memory) neural network is proposed to predict the pedestrian-vehicle conflicts 2 s ahead. The established model reaches an accuracy of 88.5 % at one signalized intersection. It is further tested at a new intersection, reaching the accuracy of 84.9 %, while the new data merely takes up 30 % of the training data set. This indicates that the proposed model is promising to be implemented at different locations. Moreover, the proposed model can also be applied to develop collision warning systems under the Connected Vehicles' environment.

UI MeSH Term Description Entries
D010363 Pattern Recognition, Automated In INFORMATION RETRIEVAL, machine-sensing or identification of visible patterns (shapes, forms, and configurations). (Harrod's Librarians' Glossary, 7th ed) Automated Pattern Recognition,Pattern Recognition System,Pattern Recognition Systems
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D000063 Accidents, Traffic Accidents on streets, roads, and highways involving drivers, passengers, pedestrians, or vehicles. Traffic accidents refer to AUTOMOBILES (passenger cars, buses, and trucks), BICYCLING, and MOTORCYCLES but not OFF-ROAD MOTOR VEHICLES; RAILROADS nor snowmobiles. Traffic Collisions,Traffic Crashes,Traffic Accidents,Accident, Traffic,Collision, Traffic,Collisions, Traffic,Crashes, Traffic,Traffic Accident,Traffic Collision
D000069636 Pedestrians Persons traveling on foot.
D000076624 Built Environment The man-made physical elements of the environment (e.g., homes, buildings, streets, open spaces, and infrastructure). The built environment influences a person's level of physical activity and may have other impacts on health in a community. Built Environments
D012449 Safety Freedom from exposure to danger and protection from the occurrence or risk of injury or loss. It suggests optimal precautions in the workplace, on the street, in the home, etc., and includes personal safety as well as the safety of property. Safeties
D016571 Neural Networks, Computer A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming. Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron

Related Publications

Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
April 2019, Chinese journal of traumatology = Zhonghua chuang shang za zhi,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
February 2014, Accident; analysis and prevention,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
September 2011, Accident; analysis and prevention,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
November 2023, Journal of hazardous materials,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
March 2020, Accident; analysis and prevention,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
January 2020, Accident; analysis and prevention,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
August 2021, Mathematical biosciences and engineering : MBE,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
April 2021, Scientific reports,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
November 2016, Accident; analysis and prevention,
Shile Zhang, and Mohamed Abdel-Aty, and Qing Cai, and Pei Li, and Jorge Ugan
August 2019, Accident; analysis and prevention,
Copied contents to your clipboard!