Paper Info
Title
Non-calibrated and real-time human view estimation using a mobile corneal imaging camera
Abstract
We present a mobile human view estimation system using a corneal imaging technique. Compared to the current eye gaze tracking (EGT) systems, our system does not require per-session calibrations and a frontal view (scene) camera, making it suitable for wearable glass systems because it is easier to use and more socially acceptable due to the lack of a frontal scene camera. Our glasses system consists of a glass frame and a micro eye camera that captures the eye (corneal) reflections of a user. 3D corneal pose tracking is performed for the captured images by using a particle filter-based real-time tracking method leveraged by a 3D eye model and weak perspective projection. We then compute the gaze reflection point (GRP) where the light from the point of gaze (PoG) is reflected, enabling us to identify where a user is looking in a scene image reflected on the corneal surface. We conducted experiments using a standard computer display setup and several real-world scenes, and found that the proposed method performs with considerable accuracy under non-calibrated setups. This demonstrates its potential for various purposes such as the user interface of a glasses systems and the analysis of human perceptions in actual scenes for marketing, environmental design, and quality-of-life applications.
Year
DOI
Venue
2015
10.1109/ICMEW.2015.7169846
Multimedia & Expo Workshops
Keywords
Field
DocType
estimation theory,eye,gaze tracking,image capture,medical image processing,particle filtering (numerical methods),real-time systems,user interfaces,3D corneal pose tracking,3D eye model,EGT system,GRP,corneal imaging technique,corneal reflection,corneal surface,eye gaze tracking system,eye reflection,frontal scene camera,gaze reflection point,glass frame,human perception,image capture,micro eye camera,mobile corneal imaging camera,mobile human view estimation system,noncalibrated human view estimation,particle filter-based real-time tracking method,perspective projection,point of gaze,real-time human view estimation,real-world scene,standard computer display setup,user interface,wearable glass system,corneal imaging,eye gaze tracking,glasses systems,wearable systems
Point of gaze,Computer vision,Computer graphics (images),Gaze,Wearable computer,Computer science,Particle filter,Perspective (graphical),Eye tracking,Artificial intelligence,User interface,Calibration
Conference
ISSN
Citations 
PageRank 
2330-7927
6
0.47
References 
Authors
5
3
Name
Order
Citations
PageRank
Atsushi Nakazawa1153.59
Christian Nitschke217612.87
Toyoaki Nishida31097196.19