Faster upper body pose recognition and estimation using compute unified device architecture

Simple item page
dc.contributor.advisorGhaziasgar, Mehrdad
dc.contributor.advisorJames Connan, James
dc.contributor.authorBrown, Dane
dc.date.accessioned2014-07-08T08:56:42Z
dc.date.accessioned2024-10-30T14:00:51Z
dc.date.available2014-07-08T08:56:42Z
dc.date.available2024-10-30T14:00:51Z
dc.date.issued2013
dc.description>Magister Scientiae - MScen_US
dc.description.abstractThe SASL project is in the process of developing a machine translation system that can translate fully-fledged phrases between SASL and English in real-time. To-date, several systems have been developed by the project focusing on facial expression, hand shape, hand motion, hand orientation and hand location recognition and estimation. Achmed developed a highly accurate upper body pose recognition and estimation system. The system is capable of recognizing and estimating the location of the arms from a twodimensional video captured from a monocular view at an accuracy of 88%. The system operates at well below real-time speeds. This research aims to investigate the use of optimizations and parallel processing techniques using the CUDA framework on Achmed’s algorithm to achieve real-time upper body pose recognition and estimation. A detailed analysis of Achmed’s algorithm identified potential improvements to the algorithm. Are- implementation of Achmed’s algorithm on the CUDA framework, coupled with these improvements culminated in an enhanced upper body pose recognition and estimation system that operates in real-time with an increased accuracy.en_US
dc.identifier.urihttps://hdl.handle.net/10566/16969
dc.language.isoenen_US
dc.publisherUniversity of Western Capeen_US
dc.rights.holderUniversity of Western Capeen_US
dc.subjectPose recognition and estimationen_US
dc.subjectGraphics processing uniten_US
dc.subjectCompute unified device architectureen_US
dc.subjectFace detectionen_US
dc.subjectSkin detectionen_US
dc.subjectBackground subtractionen_US
dc.subjectMorphological operationsen_US
dc.subjectHaar featuresen_US
dc.subjectSupport vector machineen_US
dc.subjectBlenderen_US
dc.titleFaster upper body pose recognition and estimation using compute unified device architectureen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Brown_MSC_2013.pdf
Size:
4.77 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Plain Text
Description:
Download

Collections

Magister Scientiae - MSc (Computer Science)