Change search
ReferencesLink to record
Permanent link

Direct link
Vision Gesture Control.
KTH, School of Computer Science and Communication (CSC).
2012 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In the last few years, televisions have started being connected to the Internet. These ``smart-TVs'' allow the user to access the Internet and use applications, in a similar way as with a modern smartphone. However, the input methods that are available for televisions are often just a regular remote control.

This project was an attempt to change that. It proposed a gesture control system which uses hand gestures to control the TV application. This was accomplished by using a smartphone and its camera to capture video of the user, which was evaluated in real time to detect hand gestures. When a gesture was detected a command was sent to the TV application which acted on it.

This project's focus was mainly on the technical aspects of gesture recognition, and created a method with a recognition rate of about 99% from a set of six gestures.

Abstract [sv]

Under de senaste åren har TV-apparater börjat bli anslutna till Internet. Dessa "smart-TV" låter användaren komma åt Internet och att använda applikationer, ungefär som på moderna smarta mobiltelefoner. Fortfarande är ofta en vanlig fjärrkontroll det enda sättet att interagera med applikationerna.

Det här projektet var ett försök att ändra det. Det föreslog ett geststyrningssystem som använder handgester för att styra TV-applikationen. Detta uppnåddes genom att använda en mobiltelefon och dens kamera för att filma användaren. Filmen analyserades i realtid för at upptäcka gester. När en gest upptäcktes skickades ett meddelande till TV-applikationen som agerade utefter meddelandet.

Det här projektet fokuserade främst på de tekniska aspekterna av hur gestigenkänningen skulle gå till, och skapade en metod som uppnådde en igenkänningsgrad av 99% för sex definierade gester.

Place, publisher, year, edition, pages
Trita-CSC-E, ISSN 1653-5715 ; 2012:042
National Category
Computer Science
URN: urn:nbn:se:kth:diva-130922OAI: diva2:654368
Educational program
Master of Science in Engineering - Computer Science and Technology
Available from: 2013-10-07 Created: 2013-10-07

Open Access in DiVA

No full text

Other links
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 267 hits
ReferencesLink to record
Permanent link

Direct link