| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:INTERAKTIVNI KOLEDAR S PODPORO NARAVNEGA VMESNIKA KINECT
Authors:ID Toplak, Matej (Author)
ID Holobar, Aleš (Mentor) More about this mentor... New window
Files:.pdf UNI_Toplak_Matej_2013.pdf (2,23 MB)
MD5: D7603AE80E6D810953ABD08B9FB10673
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomski nalogi opisujemo načrtovanje in izdelavo interaktivnega koledarja, ki ga krmilimo preko naravnega vmesnika in senzorja Microsoft Kinect. Koledar omogoča brezdotično pregledovanje in vstavljanje opravil z intuitivnimi gestami in preprostimi govornimi ukazi. Pri implementaciji smo uporabili Microsoftove programske rešitve, dodatno pa smo implementirali podporo razpoznavanju govornih ukazov v slovenskem jeziku. Razpoznava gibanja in govora je v prostoru z osvetljenostjo med 100 in 500 lux, v tišini in na razdalji 1,2–2 m od senzorja zelo natančna. Z odmikom od teh nastavitev pa natančnost razpoznave pade. Do slednjih ugotovitev smo prišli s testiranjem aplikacije pri različnih pogojih delovanja.
Keywords:Kinect, govor, gibanje, razpoznava
Place of publishing:Maribor
Publisher:[M. Toplak]
Year of publishing:2013
PID:20.500.12556/DKUM-42141 New window
UDC:004.5:004.8(043.2)
COBISS.SI-ID:17345814 New window
NUK URN:URN:SI:UM:DK:PWLSDCCZ
Publication date in DKUM:13.09.2013
Views:1808
Downloads:124
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:INTERACTIVE CALENDAR SUPPORTED BY MICROSOFT KINECT SENSOR
Abstract:We describe the development and implementation of an interactive calendar that utilises the basic functionalities of Microsoft Kinect sensor. The implementation utilizes Microsoft's programming solutions and our own module for speech recognition in Slovenian language. The calendar supports touchless interaction by recognising well defined and intuitive human gestures and voice commands. The gesture and speech recognition is highly accurate in a room with illuminance between 100 and 500 lux, no noise and at the distance from 1,2 to 2 m from the sensor. The recognition accuracy decreases at longer distances and in darker and noisier environments. These observations are justified by the results of systematic measurements presented in here.
Keywords:Kinect, speech, motion, recognition


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica