Pose sentences : a new representation for understanding human actions

buir.advisorDuygulu, Pınar
dc.contributor.authorHatun, Kardelen
dc.date.accessioned2016-01-08T18:07:42Z
dc.date.available2016-01-08T18:07:42Z
dc.date.issued2008
dc.descriptionAnkara : The Department of Computer Engineering and the Institute of Engineering and Science of Bilkent University, 2008.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 2008.en_US
dc.descriptionIncludes bibliographical references leaves 55-58.en_US
dc.description.abstractIn this thesis we address the problem of human action recognition from video sequences. Our main contribution to the literature is the compact use of poses while representing videos and most importantly considering actions as pose-sentences and exploit string matching approaches for classification. We focus on single actions, where the actor performs one simple action through the video sequence. We represent actions as documents consisting of words, where a word refers to a pose in a frame. We think pose information is a powerful source for describing actions. In search of a robust pose descriptor, we make use of four well-known techniques to extract pose information, Histogram of Oriented Gradients, k-Adjacent Segments, Shape Context and Optical Flow Histograms. To represent actions, first we generate a codebook which will act as a dictionary for our action dataset. Action sequences are then represented using a sequence of pose-words, as posesentences. The similarity between two actions are obtained using string matching techniques. We also apply a bag-of-poses approach for comparison purposes and show the superiority of pose-sentences. We test the efficiency of our method with two widely used benchmark datasets, Weizmann and KTH. We show that pose is indeed very descriptive while representing actions, and without having to examine complex dynamic characteristics of actions, one can apply simple techniques with equally successful results.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T18:07:42Z (GMT). No. of bitstreams: 1 0003639.pdf: 3316251 bytes, checksum: c2631e601dd45888b286443c83f8247e (MD5)en
dc.description.statementofresponsibilityHatun, Kardelenen_US
dc.format.extentxi, 58 leaves, illustrations, graphsen_US
dc.identifier.itemidBILKUTUPB109730
dc.identifier.urihttp://hdl.handle.net/11693/14772
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectHuman motionen_US
dc.subjectAction recognitionen_US
dc.subjectString matchingen_US
dc.subjectBag-of-wordsen_US
dc.subject.lccTA1650 .H38 2008en_US
dc.subject.lcshOptical pattern recognition.en_US
dc.subject.lcshComputer vision.en_US
dc.subject.lcshImage processing--Digital techniques.en_US
dc.subject.lcshBody, Human--Computer simulation.en_US
dc.titlePose sentences : a new representation for understanding human actionsen_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:
0003639.pdf
Size:
3.16 MB
Format:
Adobe Portable Document Format