An image compression for embedded eye-tracking applications

Human-machine interaction is becoming a sufficient part of coming future. Being a bright example of HMI, embedded eye-tracking systems allow user to interact with objects by using human's eye-movements. Due to wearable form-factor, developed eye-tracking system has to conform to low-power consumption, low-heat generation and low EM radiation as well as support wireless data transmission and be space efficient. Image capturing, finding of region of interest (ROI), compression of ROI and wireless transmission of compressed data are very beginning steps of the whole algorithm of finding coordinates of pupil. Therefore, area of concentration is to make them as performant as possible from theoretical point of view to further implementation. Combination of hardware powered ROI-finder coupled with well-tuned and optimized image compression system is aimed to speed-up wireless delivery of ROI-images to processing unit. Details of design of such system are presented and discussed.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Maria Trocan,et al.  Design of an embedded image acquisition system , 2015, 2015 IEEE International Conference on Electronics, Circuits, and Systems (ICECS).

[3]  Alejandro F. Frangi,et al.  Haar-like features with optimally weighted rectangles for rapid object detection , 2010, Pattern Recognition.

[4]  Martin J. Johnson,et al.  Real-time Computation of Haar-like features at generic angles for detection algorithms , 2006 .

[5]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[6]  Christopher H. Messom,et al.  Stream processing for fast and efficient rotated Haar-like features using rotated integral images , 2009, Int. J. Intell. Syst. Technol. Appl..