DSpace Repository

Markerless Tracking for Augmented Reality System on Android Tablets

Show simple item record

dc.contributor.advisor Dailey, Matthew (Chairman) en_US
dc.contributor.author Sirisilp, Kongsilp en_US
dc.contributor.other Preda, Marius (External) en_US
dc.contributor.other Guha, Sumanta (Member) en_US
dc.contributor.other Crespi, Noel (Member) en_US
dc.date.accessioned 2015-01-12T10:41:43Z
dc.date.available 2015-01-12T10:41:43Z
dc.date.issued 2012-05 en_US
dc.identifier.other AIT Thesis no.CS-12-01 en_US
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/407
dc.description.abstract As smart phone and tablets are becoming part of our everyday life, they are becoming powerful tools enabling new kinds of applications. Augmented reality based systems are among these new kinds of applications. However, due to complicated algorithms requiring very expensive computing time, the performance of the final application is far from perfect. While the most successful work so far uses special markers to track objects in the real world, this thesis focuses on natural feature tracking to recognize real objects in the real world. I prove the concept of a real time application on a mobile device through optimization of the algorithm. I implemented an application on an Android tablet that recognizes a certain number of predefined images in real time. Through optimization of the Speeded-Up Robust Feature (SURF) algorithm by fitting certain parameters and taking advantage of software and hardware resources, the algorithm can achieve real time performance. To my knowledge, this is a first successful attempt to bring markerless real time augmented reality to a commodity mobile device. en_US
dc.language.iso eng en_US
dc.subject.lcsh Others en_US
dc.title Markerless Tracking for Augmented Reality System on Android Tablets en_US
dc.type Thesis en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account