A line based pose representation for human action recognition

Simple item page
buir.advisorDuygulu, Pınar
dc.contributor.authorBaysal, Sermetcan
dc.date.accessioned2016-01-08T18:14:24Z
dc.date.available2016-01-08T18:14:24Z
dc.date.issued2011
dc.descriptionAnkara : The Department of Computer Engineering and the Institute of Engineering and Science of Bilkent University, 2011.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 2011.en_US
dc.descriptionIncludes bibliographical references leaves 42-45.en_US
dc.description.abstractIn this thesis, we utilize a line based pose representation to recognize human actions in videos. We represent the pose in each frame by employing a collection of line-pairs, so that limb and joint movements are better described and the geometrical relationships among the lines forming the human figure is captured. We contribute to the literature by proposing a new method that matches line-pairs of two poses to compute the similarity between them. Moreover, to encapsulate the global motion information of a pose sequence, we introduce line-flow histograms, which are extracted by matching line segments in consecutive frames. Experimental results on Weizmann and KTH datasets, emphasize the power of our pose representation; and show the effectiveness of using pose ordering and line-flow histograms together in grasping the nature of an action and distinguishing one from the others. Finally, we demonstrate the applicability of our approach to multi-camera systems on the IXMAS dataset.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T18:14:24Z (GMT). No. of bitstreams: 1 0005015.pdf: 7491820 bytes, checksum: e3b671927052f7931a6838bc850a3333 (MD5)en
dc.description.statementofresponsibilityBaysal, Sermetcanen_US
dc.format.extentxi, 45 leaves, illustrationsen_US
dc.identifier.urihttp://hdl.handle.net/11693/15162
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectHuman motionen_US
dc.subjectaction recognitionen_US
dc.subjectpose similarityen_US
dc.subjectpose matchingen_US
dc.subjectline-flowen_US
dc.subject.lccQP301 .B39 2011en_US
dc.subject.lcshHuman locomotion--Computer simulation.en_US
dc.subject.lcshBody, Human--Computer simulation.en_US
dc.subject.lcshImage processing--Digital techniques.en_US
dc.subject.lcshComputer simulation.en_US
dc.subject.lcshDigital computer vision.en_US
dc.subject.lcshPattern recognition systems.en_US
dc.titleA line based pose representation for human action recognitionen_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
Thumbnail Image
Name:
0005015.pdf
Size:
7.14 MB
Format:
Adobe Portable Document Format
Download

Collections

Graduate School of Engineering and Science