Cargando…
EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction
To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to di...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8548167/ https://www.ncbi.nlm.nih.gov/pubmed/34712320 http://dx.doi.org/10.1155/2021/9985401 |
_version_ | 1784590516710539264 |
---|---|
author | Kong, Wei Liu, Yun Li, Hui Wang, Chuanxu |
author_facet | Kong, Wei Liu, Yun Li, Hui Wang, Chuanxu |
author_sort | Kong, Wei |
collection | PubMed |
description | To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to distance, ignoring the influence of far pedestrians; the range of network input (receptive field) is small. In this paper, an extended graph attention network (EGAT) is proposed to increase receptive field, which focuses not only on local pedestrians, but also on those who are far away, to further strengthen pedestrian interaction. In the temporal domain, TSG-LSTM (TS-LSTM and TG-LSTM) and P-LSTM are proposed based on LSTM to enhance information transmission by residual connection. Compared with state-of-the-art methods, the model EGAT achieves excellent performance on both ETH and UCY public datasets and generates more reliable trajectories. |
format | Online Article Text |
id | pubmed-8548167 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-85481672021-10-27 EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction Kong, Wei Liu, Yun Li, Hui Wang, Chuanxu Comput Intell Neurosci Research Article To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to distance, ignoring the influence of far pedestrians; the range of network input (receptive field) is small. In this paper, an extended graph attention network (EGAT) is proposed to increase receptive field, which focuses not only on local pedestrians, but also on those who are far away, to further strengthen pedestrian interaction. In the temporal domain, TSG-LSTM (TS-LSTM and TG-LSTM) and P-LSTM are proposed based on LSTM to enhance information transmission by residual connection. Compared with state-of-the-art methods, the model EGAT achieves excellent performance on both ETH and UCY public datasets and generates more reliable trajectories. Hindawi 2021-10-19 /pmc/articles/PMC8548167/ /pubmed/34712320 http://dx.doi.org/10.1155/2021/9985401 Text en Copyright © 2021 Wei Kong et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Kong, Wei Liu, Yun Li, Hui Wang, Chuanxu EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title | EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title_full | EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title_fullStr | EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title_full_unstemmed | EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title_short | EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction |
title_sort | egat: extended graph attention network for pedestrian trajectory prediction |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8548167/ https://www.ncbi.nlm.nih.gov/pubmed/34712320 http://dx.doi.org/10.1155/2021/9985401 |
work_keys_str_mv | AT kongwei egatextendedgraphattentionnetworkforpedestriantrajectoryprediction AT liuyun egatextendedgraphattentionnetworkforpedestriantrajectoryprediction AT lihui egatextendedgraphattentionnetworkforpedestriantrajectoryprediction AT wangchuanxu egatextendedgraphattentionnetworkforpedestriantrajectoryprediction |