2-B hareket kestirimi ile baş dönüş hareketinin siniflandirilmasi

Translated title of the contribution: Head motion classification with 2D motion estimation

Inci M. Baytas, Bilge Gunsel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work aims to classify the changes in head pose of a user sitting in front of a screen by using the estimated head rotation. Considered classes include ∓15, ∓30, ve ∓ 45 degree pan, tilt and combinations of these poses. SIFT flow algorithm is used for motion estimation. Two dimensional feature vectors are extracted by calculating the magnitude and the angle of the flow vectors. Classification has been performed by Support Vector Machine and Naive Bayesian classifiers. Test results reported on Pointing'04 database demonstrate that SIFT flow vectors enable us classifying head rotation with high accuracy, when the desired resolution is not in the order of degrees.

Translated title of the contributionHead motion classification with 2D motion estimation
Original languageTurkish
Title of host publication2014 22nd Signal Processing and Communications Applications Conference, SIU 2014 - Proceedings
PublisherIEEE Computer Society
Pages325-328
Number of pages4
ISBN (Print)9781479948741
DOIs
Publication statusPublished - 2014
Event2014 22nd Signal Processing and Communications Applications Conference, SIU 2014 - Trabzon, Turkey
Duration: 23 Apr 201425 Apr 2014

Publication series

Name2014 22nd Signal Processing and Communications Applications Conference, SIU 2014 - Proceedings

Conference

Conference2014 22nd Signal Processing and Communications Applications Conference, SIU 2014
Country/TerritoryTurkey
CityTrabzon
Period23/04/1425/04/14

Fingerprint

Dive into the research topics of 'Head motion classification with 2D motion estimation'. Together they form a unique fingerprint.

Cite this