Natural user interface as a supplement of the holographic Raman tweezers

0434981 - ÚPT 2015 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Tomori, Z. - Kaňka, Jan - Kesa, P. - Jákl, Petr - Šerý, Mojmír - Bernatová, Silvie - Antalík, M. - Zemánek, Pavel
Natural user interface as a supplement of the holographic Raman tweezers.
Optical Trapping and Optical Micromanipulation XI (Proceedings of SPIE 9164). Bellingham: SPIE, 2014, 91642P:1-7. ISBN 9781628411911. ISSN 0277-786X.
[Optical Trapping and Optical Micromanipulation /11./. San Diego (US), 17.08.2014-21.08.2014]
Grant CEP: GA MŠMT(CZ) LO1212
Institucionální podpora: RVO:68081731
Klíčová slova: Holography * Interfaces * Cameras * Eye * Particles * Sensors * Speech recognition * Gesture recognition * Tablets * Software
Kód oboru RIV: BH - Optika, masery a lasery

Holographic Raman tweezers (HRT) manipulates with microobjects by controlling the positions of multiple optical traps via the mouse or joystick. Several attempts have appeared recently to exploit touch tablets, 2D cameras or Kinect game console instead. We proposed a multimodal “Natural User Interface” (NUI) approach integrating hands tracking, gestures recognition, eye tracking and speech recognition. For this purpose we exploited “Leap Motion” and “MyGaze” low-cost sensors and a simple speech recognition program “Tazti”. We developed own NUI software which processes signals from the sensors and sends the control commands to HRT which subsequently controls the positions of trapping beams, micropositioning stage and the acquisition system of Raman spectra. System allows various modes of operation proper for specific tasks. Virtual tools (called “pin” and “tweezers”) serving for the manipulation with particles are displayed on the transparent “overlay” window above the live camera image. Eye tracker identifies the position of the observed particle and uses it for the autofocus. Laser trap manipulation navigated by the dominant hand can be combined with the gestures recognition of the secondary hand. Speech commands recognition is useful if both hands are busy. Proposed methods make manual control of HRT more efficient and they are also a good platform for its future semi-automated and fully automated work.
Trvalý link: http://hdl.handle.net/11104/0238911