Automatic determination of navigable areas, pedestrian detection, and augmentation of virtual agents in real crowd videos

buir.advisorGüdükbay, Uğur
dc.contributor.authorDoğan, Yalım
dc.date.accessioned2019-01-02T08:29:28Z
dc.date.available2019-01-02T08:29:28Z
dc.date.copyright2018-12
dc.date.issued2018-12
dc.date.submitted2018-12-31
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (M.S.): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2018.en_US
dc.descriptionIncludes bibliographical references (leaves 76-86).en_US
dc.description.abstractCrowd simulations imitate the behavior of crowds and individual agents in the crowd with personality and appearance, which determines the overall model of a multi-agent system. In such studies, the models are often compared with real-life scenarios for assessment. Yet apart from side-by-side comparison and trajectory analysis, there are no practical, out-of-the-box tools to test how a given arbitrary model simulate the scenario that takes place in the real world. We propose a framework for augmenting virtual agents in real-life crowd videos. The framework locates the navigable areas on the ground plane using the automaticallyextracted detection data of the pedestrians in the crowd video. Then it places the three-dimensional (3D) models of real pedestrians in the 3D model of the scene. An interactive user interface is provided for users to add and control virtual agents, which are simulated together with detected real pedestrians using collision avoidance algorithms.en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2019-01-02T08:29:28Z No. of bitstreams: 1 10225253.pdf: 52330423 bytes, checksum: d38b8ccd10a1b5f3ab66969a25e4a9bb (MD5)en
dc.description.provenanceMade available in DSpace on 2019-01-02T08:29:28Z (GMT). No. of bitstreams: 1 10225253.pdf: 52330423 bytes, checksum: d38b8ccd10a1b5f3ab66969a25e4a9bb (MD5) Previous issue date: 2018-12en
dc.description.statementofresponsibilityby Yalım Doğan.en_US
dc.embargo.release2019-06-30
dc.format.extentxii, 90 leaves : illustrations (some color), charts (some color) , 30 cm.en_US
dc.identifier.itemidB159508
dc.identifier.urihttp://hdl.handle.net/11693/48225
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectImage Processingen_US
dc.subjectPedestrian Detection And Trackingen_US
dc.subjectComputer Visionen_US
dc.subjectThree-Dimensional Reconstructionen_US
dc.subjectComputer Graphicsen_US
dc.subjectCrowd Simulationen_US
dc.subjectAugmented Realityen_US
dc.titleAutomatic determination of navigable areas, pedestrian detection, and augmentation of virtual agents in real crowd videosen_US
dc.title.alternativeGerçek kalabalık videolarında gezilebilir alanların belirlenmesi, yayaların tespiti ve sanal bireyler eklenmesien_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
10225253.pdf
Size:
49.91 MB
Format:
Adobe Portable Document Format
Description:
Full printable version

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: