A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction

Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-drivin...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Bogdan Ilie Sighencea, Rareș Ion Stanciu, Cătălin Daniel Căleanu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/23f0e81008644e838af699bf1b5c8647
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:23f0e81008644e838af699bf1b5c8647
record_format dspace
spelling oai:doaj.org-article:23f0e81008644e838af699bf1b5c86472021-11-25T18:57:20ZA Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction10.3390/s212275431424-8220https://doaj.org/article/23f0e81008644e838af699bf1b5c86472021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7543https://doaj.org/toc/1424-8220Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions.Bogdan Ilie SighenceaRareș Ion StanciuCătălin Daniel CăleanuMDPI AGarticletrajectory predictionpedestrian behaviorautonomous vehiclessensor technologiesdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7543, p 7543 (2021)
institution DOAJ
collection DOAJ
language EN
topic trajectory prediction
pedestrian behavior
autonomous vehicles
sensor technologies
deep learning
Chemical technology
TP1-1185
spellingShingle trajectory prediction
pedestrian behavior
autonomous vehicles
sensor technologies
deep learning
Chemical technology
TP1-1185
Bogdan Ilie Sighencea
Rareș Ion Stanciu
Cătălin Daniel Căleanu
A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
description Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions.
format article
author Bogdan Ilie Sighencea
Rareș Ion Stanciu
Cătălin Daniel Căleanu
author_facet Bogdan Ilie Sighencea
Rareș Ion Stanciu
Cătălin Daniel Căleanu
author_sort Bogdan Ilie Sighencea
title A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
title_short A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
title_full A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
title_fullStr A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
title_full_unstemmed A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction
title_sort review of deep learning-based methods for pedestrian trajectory prediction
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/23f0e81008644e838af699bf1b5c8647
work_keys_str_mv AT bogdaniliesighencea areviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
AT raresionstanciu areviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
AT catalindanielcaleanu areviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
AT bogdaniliesighencea reviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
AT raresionstanciu reviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
AT catalindanielcaleanu reviewofdeeplearningbasedmethodsforpedestriantrajectoryprediction
_version_ 1718410451819167744