A study on geometrical model for human eye-gaze estimation system = 인간 시선 추정 시스템의 기하학적 모델에 대한 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 403
  • Download : 0
The dissertation proposed a method of capturing screen reflection information for the purpose of eye gaze movement. Also, an efficient method of geometrical based gaze tracking was developed. Eye gaze tracking system has been employed in both cognitive science experiments and human machine interface. Gaze estimation methods are divided into two approaches: the model-based approach and image-based approach. The model-based method utilized the user`s eye parameter and geometrical relationship among the user`s eye, the monitor screen and the camera. Once the user`s dependent parameters are estimated, the method is less sensitive to the head movements. On the other hand, the image-based method does not utilize these parameters and find a polynomial mapping function between the camera image position and corresponding monitor screen position from the calibration data. Most image-based eye gaze system used special infrared (IR) illuminator and choose IR-sensitive CCD camera to estimate eye gaze. The IR based systems has the limitation of inaccurate gaze detection in ambient natural light and the number of IR illuminator and their particular location has also effect on gaze detection. In this dissertation, First, present image-based detection technique based on computer screen illumination as light emitting sources and choose high speed camera for image acquisition. The high speed camera has higher frame rate than the screen refresh rate. In order to capture the periodic refresh rate patterns we operate the camera frame rate greater than twice of the screen refresh rate. The screen illumination produced a mark on the corneal surface of the subject`s eye as screen-glint. The screen reflection information has two fold advantages. First, we can utilize the screen reflection as screen-glint, which is very useful to determine where eye is gazing. Secondly, the screen glint information utilize to localized eye in face image. The direction of the user`s eye gaze can be deter...
Advisors
Lee, Soo-Youngresearcher이수영
Description
한국과학기술원 : 바이오및뇌공학과,
Publisher
한국과학기술원
Issue Date
2013
Identifier
561910/325007  / 020044522
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 바이오및뇌공학과, 2013.8, [ viii, 82 p. ]

Keywords

Human-computer interface; 각막 추정 방법; 모델 기반 시선 추정; 시선 추적; 인간-컴퓨터 상호작용; cornea estimation method; eye-tracking; model-based eye-gaze estimation

URI
http://hdl.handle.net/10203/196338
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=561910&flag=dissertation
Appears in Collection
BiS-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0