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

Zhang, Shile; Abdel-Aty, Mohamed; Yuan, Jinghui; Pei, Li

doi:10.1177/0361198120912422

Cited by 55 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chakraborty et al [12] used an artificial neural network technique to develop a pedestrian fatal crash frequency model at the intersection level. In the research [13] Zhang et al used neural network for prediction of pedestrians' red-light crossing intentions while Das et al [14] used an artificial neural network for traffic flow modelling to build a relationship between different pedestrian flow parameters. A comparison of results linear regression model between observed and estimated values for speed and flow parameters, the performance of ANN model gives better fitness to predict data as compared to the deterministic models.…”

Section: Introductionmentioning

confidence: 99%

Development of Models for Children—Pedestrian Crossing Speed at Signalized Crosswalks

et al. 2021

View full text Add to dashboard Cite

Modeling the behavior of pedestrians is an important tool in the analysis of their behavior and consequently ensuring the safety of pedestrian traffic. Children pedestrians show specific traffic behavior which is related to cognitive development, and the parameters that affect their traffic behavior are very different. The aim of this paper is to develop a model of the children-pedestrian’s speed at a signalized pedestrian crosswalk. For the same set of data collected in the city of Osijek—Croatia, two models were developed based on neural network and multiple linear regression. In both cases the models are based on 300 data of measured children speed at signalized pedestrian crosswalks on primary city roads located near a primary school. As parameters, both models include the selected traffic infrastructure features and children’s characteristics and their movements. The models are validated on data collected on the same type of pedestrian crosswalks, using the same methodology in two other urban environments—the city of Rijeka, Croatia and Enna in Italy. It was shown that the neural network model, developed for Osijek, can be applied with sufficient reliability to the other two cities, while the multiple linear regression model is applicable with relatively satisfactory reliability only in Rijeka. A comparative analysis of the statistical indicators of reliability of these two models showed that better results are achieved by the neural network model.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of Models for Children—Pedestrian Crossing Speed at Signalized Crosswalks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this sense, long short-term memory (LSTM) neural networks using images and characteristics (i.e., gender, walking direction and group behavior) has been proposed to estimate the crossing intention with great accuracy. Nonetheless, this results in a slightly high false positive rate when trying to classify the type of pedestrian movement [ 21 ]. Another approach is a crossing intention detector based on the use of cameras onboard vehicles, which can determine—in addition to the intention to cross—if a pedestrian is crossing or standing, as well as if he/she is turning or beginning to cross.…”

Section: Introductionmentioning

confidence: 99%

Walking Secure: Safe Routing Planning Algorithm and Pedestrian’s Crossing Intention Detector Based on Fuzzy Logic App

Domínguez

Sanguino

2021

Sensors

View full text Add to dashboard Cite

Improving road safety through artificial intelligence is now crucial to achieving more secure smart cities. With this objective, a mobile app based on the integration of the smartphone sensors and a fuzzy logic strategy to determine the pedestrian’s crossing intention around crosswalks is presented. The app developed also allows the calculation, tracing and guidance of safe routes thanks to an optimization algorithm that includes pedestrian areas on the paths generated over the whole city through a cloud database (i.e., zebra crossings, pedestrian streets and walkways). The experimentation carried out consisted in testing the fuzzy logic strategy with a total of 31 volunteers crossing and walking around a crosswalk. For that, the fuzzy logic approach was subjected to a total of 3120 samples generated by the volunteers. It has been proven that a smartphone can be successfully used as a crossing intention detector system with an accuracy of 98.63%, obtaining a true positive rate of 98.27% and a specificity of 99.39% according to a receiver operating characteristic analysis. Finally, a total of 30 routes were calculated by the proposed algorithm and compared with Google Maps considering the values of time, distance and safety along the routes. As a result, the routes generated by the proposed algorithm were safer than the routes obtained with Google Maps, achieving an increase in the use of safe pedestrian areas of at least 183%.

show abstract

“…Therefore, the performance is reported to 83.33% accuracy rate. Although the detection accuracy of [6], is higher than the proposed method, but one can say that each method is useful for different tasks.…”

Section: Resultsmentioning

confidence: 90%

“…The potential capability of Mask-R-CNN algorithm [5] was inspected to localize cars, buses and pedestrians on the road to improve the accuracy of a anti-collision warning system. The Long Short-Term Memory (LSTM) neural network model [6] was utilized to produce predictions about pedestrians' red-light violation behaviors. After modelling the LSTM architecture with real traffic data, which includes labelled pedestrians' unexpected crossing intentions, the accuracy of system was established with 91.6% rate in case of testing at one signalized crosswalk.…”

Section: Introductionmentioning

confidence: 99%

Real Time Pedestrian Alert System for Vehicles

Işık

Vatansever

Anagun

et al. 2020

Eskişehir Technical University Journal of Science and Technology a - Applied Sciences and Engineering

View full text Add to dashboard Cite

In this study, we have developed a pre-collision alert system for vehicles in terms of detection pedestrians in road. The system is consisting from deep learning models and transfer learning methodologies. For this purpose, pre-trained convolutional models were considered to detect pedestrian and road. Finally, the segmented road mask and pedestrian mask were utilized to reveal the intersection of these two masks. The system generates an alert if the number of pixels is higher than predefined threshold value. By considering the test results, the proposed system gives 83.33% accuracy rate when it comes to use it to avoid collision.

show abstract

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

Cited by 55 publications

References 36 publications

Development of Models for Children—Pedestrian Crossing Speed at Signalized Crosswalks

Development of Models for Children—Pedestrian Crossing Speed at Signalized Crosswalks

Walking Secure: Safe Routing Planning Algorithm and Pedestrian’s Crossing Intention Detector Based on Fuzzy Logic App

Real Time Pedestrian Alert System for Vehicles

Contact Info

Product

Resources

About