A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction
Pedestrian modeling remains a formidable challenge in transportation science due to the complicated nature of pedestrian behavior and the irregular movement patterns. To this extent, accurate and reliable positioning technologies and techniques play a significant role in the pedestrian simulation st...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9762760/ |
| _version_ | 1811306517242052608 |
|---|---|
| author | Vasileia Papathanasopoulou Ioanna Spyropoulou Harris Perakis Vassilis Gikas Eleni Andrikopoulou |
| author_facet | Vasileia Papathanasopoulou Ioanna Spyropoulou Harris Perakis Vassilis Gikas Eleni Andrikopoulou |
| author_sort | Vasileia Papathanasopoulou |
| collection | DOAJ |
| description | Pedestrian modeling remains a formidable challenge in transportation science due to the complicated nature of pedestrian behavior and the irregular movement patterns. To this extent, accurate and reliable positioning technologies and techniques play a significant role in the pedestrian simulation studies. The objective of this research is to predict pedestrian movement in various perspectives utilizing historical trajectory data. The study features considered in this research are pedestrian class, speed and position. The ensemble of these features provides a thorough description of pedestrian movement prediction, whilst contributes to the context of pedestrian modeling and Intelligent Transportation Systems. More specifically, pedestrian movement is grouped into different classes considering gender, walking pace and distraction by employing random forest algorithms. Then, position and speed prediction is computed employing suitable data-driven methods, in particular, the locally weighted regression (LOESS method), taking into account the individual pedestrian’s profile. An LSTM-based (Long Short-Term Memory) model is also applied for comparison. The methodology is applied on pedestrian trajectory data that were collected in a controlled experiment undertaken at the Campus of the National Technical University of Athens (NTUA), Greece. Prediction of pedestrian’s movement is achieved, yielding satisfactory results. |
| first_indexed | 2024-04-13T08:45:55Z |
| format | Article |
| id | doaj.art-be9fd63d27cc4d029b0a85be1877ac5c |
| institution | Directory Open Access Journal |
| issn | 2687-7813 |
| language | English |
| last_indexed | 2024-04-13T08:45:55Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj.art-be9fd63d27cc4d029b0a85be1877ac5c2022-12-22T02:53:40ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132022-01-01332833910.1109/OJITS.2022.31697009762760A Data-Driven Model for Pedestrian Behavior Classification and Trajectory PredictionVasileia Papathanasopoulou0https://orcid.org/0000-0001-5153-8466Ioanna Spyropoulou1https://orcid.org/0000-0001-7801-3395Harris Perakis2https://orcid.org/0000-0003-4574-1091Vassilis Gikas3Eleni Andrikopoulou4School of Rural, Surveying and Geoinformatics Engineering (SRSE), National Technical University of Athens, Zografou, GreeceSchool of Rural, Surveying and Geoinformatics Engineering (SRSE), National Technical University of Athens, Zografou, GreeceSchool of Rural, Surveying and Geoinformatics Engineering (SRSE), National Technical University of Athens, Zografou, GreeceSchool of Rural, Surveying and Geoinformatics Engineering (SRSE), National Technical University of Athens, Zografou, GreeceSchool of Rural, Surveying and Geoinformatics Engineering (SRSE), National Technical University of Athens, Zografou, GreecePedestrian modeling remains a formidable challenge in transportation science due to the complicated nature of pedestrian behavior and the irregular movement patterns. To this extent, accurate and reliable positioning technologies and techniques play a significant role in the pedestrian simulation studies. The objective of this research is to predict pedestrian movement in various perspectives utilizing historical trajectory data. The study features considered in this research are pedestrian class, speed and position. The ensemble of these features provides a thorough description of pedestrian movement prediction, whilst contributes to the context of pedestrian modeling and Intelligent Transportation Systems. More specifically, pedestrian movement is grouped into different classes considering gender, walking pace and distraction by employing random forest algorithms. Then, position and speed prediction is computed employing suitable data-driven methods, in particular, the locally weighted regression (LOESS method), taking into account the individual pedestrian’s profile. An LSTM-based (Long Short-Term Memory) model is also applied for comparison. The methodology is applied on pedestrian trajectory data that were collected in a controlled experiment undertaken at the Campus of the National Technical University of Athens (NTUA), Greece. Prediction of pedestrian’s movement is achieved, yielding satisfactory results.https://ieeexplore.ieee.org/document/9762760/Behavior classificationdistractionpedestrian speed predictionpedestrian trajectory predictionrandom forestsGNSS |
| spellingShingle | Vasileia Papathanasopoulou Ioanna Spyropoulou Harris Perakis Vassilis Gikas Eleni Andrikopoulou A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction IEEE Open Journal of Intelligent Transportation Systems Behavior classification distraction pedestrian speed prediction pedestrian trajectory prediction random forests GNSS |
| title | A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction |
| title_full | A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction |
| title_fullStr | A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction |
| title_full_unstemmed | A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction |
| title_short | A Data-Driven Model for Pedestrian Behavior Classification and Trajectory Prediction |
| title_sort | data driven model for pedestrian behavior classification and trajectory prediction |
| topic | Behavior classification distraction pedestrian speed prediction pedestrian trajectory prediction random forests GNSS |
| url | https://ieeexplore.ieee.org/document/9762760/ |
| work_keys_str_mv | AT vasileiapapathanasopoulou adatadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT ioannaspyropoulou adatadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT harrisperakis adatadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT vassilisgikas adatadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT eleniandrikopoulou adatadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT vasileiapapathanasopoulou datadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT ioannaspyropoulou datadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT harrisperakis datadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT vassilisgikas datadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction AT eleniandrikopoulou datadrivenmodelforpedestrianbehaviorclassificationandtrajectoryprediction |