An augmented crowd simulation system using automatic determination of navigable areas

Simple item page
buir.contributor.authorDoğan, Yalım
buir.contributor.authorSonlu, Sinan
buir.contributor.authorGüdükbay, Uğur
buir.contributor.orcidDoğan, Yalım|0000-0002-0814-2439
buir.contributor.orcidSonlu, Sinan|0000-0002-9743-6833
buir.contributor.orcidGüdükbay, Uğur|0000-0003-2462-6959
dc.citation.epage155en_US
dc.citation.spage141en_US
dc.citation.volumeNumber95en_US
dc.contributor.authorDoğan, Yalım
dc.contributor.authorSonlu, Sinan
dc.contributor.authorGüdükbay, Uğur
dc.date.accessioned2022-02-01T14:04:31Z
dc.date.available2022-02-01T14:04:31Z
dc.date.issued2021-04
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractCrowd simulations imitate the group dynamics of individuals in different environments. Applications in entertainment, security, and education require augmenting simulated crowds into videos of real people. In such cases, virtual agents should realistically interact with the environment and the people in the video. One component of this augmentation task is determining the navigable regions in the video. In this work, we utilize semantic segmentation and pedestrian detection to automatically locate and reconstruct the navigable regions of surveillance-like videos. We place the resulting flat mesh into our 3D crowd simulation environment to integrate virtual agents that navigate inside the video avoiding collision with real pedestrians and other virtual agents. We report the performance of our open-source system using real-life surveillance videos, based on the accuracy of the automatically determined navigable regions and camera configuration. We show that our system generates accurate navigable regions for realistic augmented crowd simulations.en_US
dc.description.provenanceSubmitted by Samet Emre (samet.emre@bilkent.edu.tr) on 2022-02-01T14:04:31Z No. of bitstreams: 1 An_augmented_crowd_simulation_system_using_automatic_determination_of_navigable_areas.pdf: 861855 bytes, checksum: d5e8551a19eb56e204c83796e0dec12c (MD5)en
dc.description.provenanceMade available in DSpace on 2022-02-01T14:04:31Z (GMT). No. of bitstreams: 1 An_augmented_crowd_simulation_system_using_automatic_determination_of_navigable_areas.pdf: 861855 bytes, checksum: d5e8551a19eb56e204c83796e0dec12c (MD5) Previous issue date: 2021-04en
dc.embargo.release2023-04-30
dc.identifier.doi10.1016/j.cag.2021.01.012en_US
dc.identifier.issn0097-8493
dc.identifier.urihttp://hdl.handle.net/11693/76956
dc.language.isoEnglishen_US
dc.publisherElsevier Ltden_US
dc.relation.isversionofhttps://doi.org/10.1016/j.cag.2021.01.012en_US
dc.source.titleComputers & Graphicsen_US
dc.subjectPedestrian detection and trackingen_US
dc.subjectData-driven simulationen_US
dc.subjectThree-dimensional reconstructionen_US
dc.subjectCrowd simulationen_US
dc.subjectAugmented realityen_US
dc.subjectDeep learningen_US
dc.titleAn augmented crowd simulation system using automatic determination of navigable areasen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
An_augmented_crowd_simulation_system_using_automatic_determination_of_navigable_areas.pdf
Size:
841.66 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Computer Engineering