Show simple item record

3D hand reconstruction from RGB-D/RGB video frames in real-time

dc.contributor.authorToda Mas, Aleix
dc.contributor.otherUniversitat Politècnica de Catalunya
dc.date.accessioned2019-05-16T21:05:31Z
dc.date.available2019-05-16T21:05:31Z
dc.date.issued2019-04-30
dc.identifier.urihttp://hdl.handle.net/2117/133121
dc.description.abstractWe present a pipeline able to extract 3D real-world measurements from RGB-D images with high accuracy in real-time. A new method bottom-up multi-person for hand-body pose detection evolved from OpenPifPaf has been presented. Two novel training strategies using multiple datasets are presented.
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya
dc.subjectÀrees temàtiques de la UPC::Informàtica
dc.subject.lcshMachine learning
dc.subject.lcshComputer vision
dc.subject.lcshArtificial intelligence
dc.subject.lcshVideo recording
dc.subject.otherhand pose
dc.subject.otherbody pose
dc.subject.otheropenpifpaf
dc.subject.otheropenpose
dc.subject.other3d reconstruction
dc.subject.otherdepth images
dc.subject.otherRGB-D
dc.subject.othercontext understanding
dc.subject.otherpoint cloud
dc.subject.otherbackground subtraction
dc.subject.otherring size
dc.subject.otherfinger width measurement
dc.subject.other3d measurement
dc.subject.otherreal-time
dc.subject.otherpoint cloud library
dc.subject.otherbottom-up hand pose
dc.subject.othermulti-person hand pose
dc.subject.othermulti-person pose
dc.title3D hand reconstruction from RGB-D/RGB video frames in real-time
dc.typeMaster thesis
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacVisió per ordinador
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacVídeo
dc.identifier.slug137377
dc.rights.accessOpen Access
dc.date.updated2019-05-08T13:06:08Z
dc.audience.educationlevelMàster
dc.audience.mediatorFacultat d'Informàtica de Barcelona
dc.audience.degreeMÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017)
dc.contributor.covenanteeÉcole polytechnique fédérale de Lausanne


Files in this item

Thumbnail
Name:
137377.pdf
Size:
13,09Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record