Predicting real-time traffic conflicts using deep learning

Formosa, Nicolette; Quddus, Mohammed; Ison, Stephen; Abdel-Aty, Mohamed; Yuan, Jinghui

doi:10.1016/j.aap.2019.105429

Cited by 124 publications

(56 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And the absolute value of the difference was the PET value. The PET threshold was set to be 6 s according to the literature to determine if there was a dangerous condition for the pedestrian (33,34). pedestrians waited for the pedestrian signal then crossed.…”

Section: Evaluation Of the Pedestrian Safety At The Study Sitementioning

confidence: 99%

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

Zhang

Abdel-Aty

Yuan

et al. 2020

Transportation Research Record

Self Cite

View full text Add to dashboard Cite

Traffic violations of pedestrians at intersections are major causes of road crashes involving pedestrians, especially red-light crossing behaviors. To predict the pedestrians’ red-light crossing intentions, video data from real traffic scenes are collected. Using detection and tracking techniques in computer vision, some pedestrians’ characteristics, including location information, are generated. A long short-term memory neural network is established and trained to predict pedestrians’ red-light crossing intentions. The experimental results show that the model has an accuracy rate of 91.6% based on internal testing at one signalized crosswalk. This model can be further implemented in the vehicle-to-infrastructure communication environment and prevent crashes because of the pedestrians’ red-light crossing behaviors.

show abstract

Section: Evaluation Of the Pedestrian Safety At The Study Sitementioning

confidence: 99%

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

Zhang

Abdel-Aty

Yuan

et al. 2020

Transportation Research Record

Self Cite

View full text Add to dashboard Cite

show abstract

“…CNN is highly adept in areas like identification of objects and traffic signs, besides being able to generate vision on self-driving cars. In CV, application and usage of CNN can be seen in the literature [18], [19], [21], [55], where most CNN models are used for accident analysis and prevention, that are applied in some research to efficiently map crash risk, traffic conflicts and perception models for network traffic control. A software-defined network (SDN) model, SeDaTive [21] implements CNN model to provide data input to the model, where the CNN model studies the hidden patterns in data nodes, to plan the most optimal route for the model.…”

Section: ) Convolutional Neural Network (Cnn)mentioning

confidence: 99%

“…Conventional Neural Network and Naïve Bayes: For safety aspect, CNN and Naïve Bayes are considered as two main selected techniques in this paper, based on [17]- [19]. NB, are used in [17]as they are reliable, and fast for collision prediction through the sending of alerts and notifications.…”

Section: ) Safety: Data Analysis In Physical Layer Usingmentioning

confidence: 99%

“…In the CV environment, for real-time and minimum data collection, NB is a technique that suits well as it has a fast computation time and produces the right decision quickly. CNN is also selected, as it can analyze collision risks at intersections [18], as well as to detect vehicles and lane through image processing obtained from a single front-facing camera [19]. It is believed that the combinations of NB and CNN can provide an optimum alert or notification system for collision prediction in a CV environment.…”

Section: ) Safety: Data Analysis In Physical Layer Usingmentioning

confidence: 99%

See 1 more Smart Citation

Conceptual Model for Connected Vehicles Safety and Security using Big Data Analytics

Razali¹,

Shamsaimon²,

Wook³

et al. 2020

IJACSA

View full text Add to dashboard Cite

The capability of Connected Vehicles (CVs) connecting to a nearby vehicle, surrounding infrastructure and cyberspace presents a high risk in the aspect of safety and security of the CV and others. Data volume generated from the sensors and infrastructure in CVs environment are enormous. Thus, CVs implementations require a real-time big data processing and analytics to detect any anomaly in the CVs's environment which are physical layer, network layer and application layer. CVs are exposed to various vulnerabilities associated with exploitations or malfunctions of the components in each layer that could result in various safety and security event such as congestion and collision. The safety and security risks added an extra layer of required protection for the CVs implementation that need to be studied and refined. To address this gap, this research aims to determine the basic components of safety and security for CVs implementation and propose a conceptual model for safety and security in CVs by applying the machine learning and deep learning techniques. The proposed model is highly correlated to safety and security and could be applied in congestion and collision prediction.

show abstract

“…Furthermore, there is growing interest in using traffic safety analysis techniques. Recently, Formosa et al [72] have presented a centralized digital architecture and employed a Deep Learning methodology to predict traffic conflicts. Traffic conflicts have been identified by a Regional-Convolution Neural Network (R-CNN) model which has detected lane markings and tracks vehicles from images captured by a single front-facing camera of an instrumented vehicle.…”

Section: Introductionmentioning

confidence: 99%

Development of a Binary Classification Model to Assess Safety in Transportation Systems Using GMDH-Type Neural Network Algorithm

Guido

Haghshenas

et al. 2020

Sustainability

View full text Add to dashboard Cite

Evaluating road safety is an enduring research topic in Infrastructure and Transportation Engineering. The prediction of crash risk is very important for avoiding other crashes and safeguarding road users. According to this task, awareness of the number of vehicles involved in an accident contributes greatly to safety analysis, hence, it is necessary to predict it. In this study, the main aim is to develop a binary model for predicting the number of vehicles involved in an accident using Neural Networks and the Group Method of Data Handling (GMDH). For this purpose, 775 accident cases were accurately recorded and evaluated from the urban and rural areas of Cosenza in southern Italy and some notable parameters were considered as input data including Daylight, Weekday, Type of accident, Location, Speed limit and Average speed; and the number of vehicles involved in an accident was considered as output. In this study, 581 cases were selected randomly from the dataset to train and the rest were used to test the developed binary model. A confusion matrix and a Receiver Operating Characteristic curve were used to investigate the performance of the proposed model. According to the obtained results, the accuracy values of the prediction model were 83.5% and 85.7% for testing and training, respectively. Finally, it can be concluded that the developed binary model can be applied as a reliable tool for predicting the number of vehicles involved in an accident.

show abstract

Predicting real-time traffic conflicts using deep learning

Cited by 124 publications

References 38 publications

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

Conceptual Model for Connected Vehicles Safety and Security using Big Data Analytics

Development of a Binary Classification Model to Assess Safety in Transportation Systems Using GMDH-Type Neural Network Algorithm

Contact Info

Product

Resources

About