DeepORCA: Realistic crowd simulation for varying scenes
Abstract Crowd simulation is a challenging problem, aiming to generate realistic pedestrians motions in virtual environment. Nowadays, ORCA is a widely used simulation algorithm in practice because of its stable and efficient performance. However, this algorithm cannot regenerate continuity and dive...
Published in: | Computer Animation and Virtual Worlds |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2022
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cav.2067 |
id |
crwiley:10.1002/cav.2067 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/cav.2067 2024-06-02T08:12:45+00:00 DeepORCA: Realistic crowd simulation for varying scenes Li, Yaqiang Mao, Tianlu Meng, Ruoyu Yan, Qinyuan Wang, Zhaoqi 2022 http://dx.doi.org/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cav.2067 en eng Wiley http://onlinelibrary.wiley.com/termsAndConditions#vor Computer Animation and Virtual Worlds volume 33, issue 3-4 ISSN 1546-4261 1546-427X journal-article 2022 crwiley https://doi.org/10.1002/cav.2067 2024-05-03T11:17:45Z Abstract Crowd simulation is a challenging problem, aiming to generate realistic pedestrians motions in virtual environment. Nowadays, ORCA is a widely used simulation algorithm in practice because of its stable and efficient performance. However, this algorithm cannot regenerate continuity and diversity of pedestrian motions in real data, leading to defects in motion fidelity. Otherwise, trajectory prediction methods based on deep learning have progressed in real pedestrians movement patterns mining. However, they are rarely applied in simulation due to the lack of ability to avoid collision and adapt to manufactured scenarios. Our work proposes a simulation method DeepORCA that integrates ORCA with a CVAE‐based velocity probability generator, which can model motion continuity, variable intentions, and scene semantics. Moreover, DeepORCA converts the velocity optimization into quadratic programming, which accelerates the calculation while maintaining the collision‐avoidance ability of ORCA. In the experiments of real and artificial scenes, our method produces more realistic crowd simulation results than ORCA quantitatively and qualitatively, while keeps the computational efficiency at the same order of magnitude. Article in Journal/Newspaper Orca Wiley Online Library Computer Animation and Virtual Worlds 33 3-4 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Abstract Crowd simulation is a challenging problem, aiming to generate realistic pedestrians motions in virtual environment. Nowadays, ORCA is a widely used simulation algorithm in practice because of its stable and efficient performance. However, this algorithm cannot regenerate continuity and diversity of pedestrian motions in real data, leading to defects in motion fidelity. Otherwise, trajectory prediction methods based on deep learning have progressed in real pedestrians movement patterns mining. However, they are rarely applied in simulation due to the lack of ability to avoid collision and adapt to manufactured scenarios. Our work proposes a simulation method DeepORCA that integrates ORCA with a CVAE‐based velocity probability generator, which can model motion continuity, variable intentions, and scene semantics. Moreover, DeepORCA converts the velocity optimization into quadratic programming, which accelerates the calculation while maintaining the collision‐avoidance ability of ORCA. In the experiments of real and artificial scenes, our method produces more realistic crowd simulation results than ORCA quantitatively and qualitatively, while keeps the computational efficiency at the same order of magnitude. |
format |
Article in Journal/Newspaper |
author |
Li, Yaqiang Mao, Tianlu Meng, Ruoyu Yan, Qinyuan Wang, Zhaoqi |
spellingShingle |
Li, Yaqiang Mao, Tianlu Meng, Ruoyu Yan, Qinyuan Wang, Zhaoqi DeepORCA: Realistic crowd simulation for varying scenes |
author_facet |
Li, Yaqiang Mao, Tianlu Meng, Ruoyu Yan, Qinyuan Wang, Zhaoqi |
author_sort |
Li, Yaqiang |
title |
DeepORCA: Realistic crowd simulation for varying scenes |
title_short |
DeepORCA: Realistic crowd simulation for varying scenes |
title_full |
DeepORCA: Realistic crowd simulation for varying scenes |
title_fullStr |
DeepORCA: Realistic crowd simulation for varying scenes |
title_full_unstemmed |
DeepORCA: Realistic crowd simulation for varying scenes |
title_sort |
deeporca: realistic crowd simulation for varying scenes |
publisher |
Wiley |
publishDate |
2022 |
url |
http://dx.doi.org/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/pdf/10.1002/cav.2067 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/cav.2067 |
genre |
Orca |
genre_facet |
Orca |
op_source |
Computer Animation and Virtual Worlds volume 33, issue 3-4 ISSN 1546-4261 1546-427X |
op_rights |
http://onlinelibrary.wiley.com/termsAndConditions#vor |
op_doi |
https://doi.org/10.1002/cav.2067 |
container_title |
Computer Animation and Virtual Worlds |
container_volume |
33 |
container_issue |
3-4 |
_version_ |
1800759289553354752 |