Abstract
At present a lot of gaze estimation methods can get accurate result under ideal conditions, but some practical issues are still the biggest challenges affect the accuracy such as head motion and eye blinking. Improving the accuracy of gaze estimation and the tolerance of head motion are common tasks in the field of gaze estimation. Therefore, this paper aims to propose an accurate gaze estimation method without fixed head pose. The core problem is how to build the mapping relationship between image features and gaze position, and how to resist the head motion through the training samples. To this end, at first, a new input feature, which can well reflect the change of eye image features with different gaze positions, is proposed and it is based on appearance feature and distance feature. So the number of training samples in the process of calibration is significantly reduced. Then ℓ 1-optimization is used to select an optimal set, which represents the mapping relationship between input feature and gaze position. At last, a linear equation is fitted to correct the initial estimation bias which is brought by head motion. In this paper, the experimental results demonstrate that our system achieves accurate result with one camera and a small number of calibration points. The accuracy of final gaze estimation is improved by 22 % through compensation equation. In addition, our system is robustness to eye blink and distance change.
Similar content being viewed by others
References
Alnajar F, Gevers T, Valenti R, et al. (2013) Calibration-free gaze estimation using human gaze patterns. Computer Vision (ICCV), 2013 IEEE International Conference, IEEE, Washington, p 137–144
Beymer D, Flickner M (2003) Eye gaze tracking using an active stereo head. Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference, vol 2, p 451
Cheung Y, Peng Q (2015) Eye gaze tracking with a web camera in a desktop environment. IEEE Trans Hum-Mach Syst 45(4):419–430
Coutinho FL, Morimoto CH (2012) Improving head movement tolerance of cross-ratio based eye trackers. Int J Comput Vis pp. 1–23
Donoho DL (2006) For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Commun Pure Appl Math 59(6):797–829
Donoho DL, Elad M (2003) Optimally sparse representation from overcomplete dictionaries via l1 norm minimization. Proc Natl Acad Sci U S A 100(5):2197–2002
Donoho DL, Tsaig Y (2008) Fast solution of l1-norm minimization problems when the solution may be sparse. Information Theory IEEE Transactions 54(11):4789–4812
Drori I, Donoho DL (2006) Solution of l1 minimization problems by LARS/homotopy methods. Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference, vol 3, pp III–III
Grauman K, Betke M, Gips J et al (2001) Communication via eye blinks—detection and duration analysis in real time. CVPR, 2011, 1:I-1010–I-1017
Guestrin ED, Eizenman M (2008) Remote point-of-gaze estimation requiring a single-point calibration for applications with infants. Etra Proceedings of the Symposium on Eye Tracking Research & Applications, pp 267–274
Hansen D, Ji Q (2010) In the eye of the beholder: a survey of models for eyes and gaze. IEEE Trans Pattern Anal Mach Intell 32(3):478–500
Hansen DW, Pece AEC (2005) Eye tracking in the wild. Comput Vis Image Underst 98(1):155–181
Jafari R, Ziou D (2015) Eye-gaze estimation under various head positions and iris states. Expert Syst Appl 42(1):510–518
Lee WO, Lee EC, Park KR (2010) Blink detection robust to various facial poses. J Neurosci Methods 193(2):356–372
Lu F, Sugano Y, Okabe T, et al. (2011) Inferring human gaze from appearance via adaptive linear regression. IEEE International Conference on Computer Vision, vol 23, pp 153–160
Lu F, Sugano Y, Okabe T et al (2014) Adaptive linear regression for appearance-based gaze estimation. IEEE Trans Pattern Anal Mach Intell 36(10):2033–2046
Lu F, Okabe T, Sugano Y et al (2014) Learning gaze biases with head motion for head pose-free gaze estimation. Image Vis Comput 32(3):169–179
Markuš N, Frljak M, Pandžić IS et al (2014) Eye pupil localization with an ensemble of randomized trees. Pattern Recogn 47(2):578–587
Martinez F, Carbone A, Pissaloux E (2012) Gaze estimation using local features and non-linear regression. Proceedings/ICIP ... International Conference on Image Processing, pp 1961–1964
Morimoto CH, Mimica MRM (2005) Eye gaze tracking techniques for interactive applications. Comput Vis Image Underst 98(1):4–24
Nagamatsu, Iwamoto, Sugano et al (2012) Gaze estimation method involving corneal reflection-based modeling of the eye as a general surface of revolution about the optical axis of the eye. IEICE Trans Inf Syst E95.D(6):1656–1667
Sesma-Sanchez L, Villanueva et al (2012) Gaze estimation interpolation methods based on binocular data. IEEE Trans Bio-Med Eng 59(8):2235–2243
Sugano Y, Matsushita Y, Sato Y (2012) Appearance-based gaze estimation using visual saliency. IEEE Trans Pattern Anal Mach Intell 35(2):329–341
Sun L, Liu Z, Sun MT (2015) Real Time gaze estimation with a consumer depth camera. Inf Sci 320:346–360
Tan K, Kriegman, N Ahuja (2002) Appearance-based eye gaze estimation. In Applications of Computer Vision (WACV 2002). Proceedings. Sixth IEEE Workshop, pp 191–195
Timm F, Barth E (2011) Accurate Eye Centre Localisation by Means of Gradients. In VISAPP, pp 125–130
Valenti R, Gevers T (2012) Accurate eye center location through invariant isocentric patterns. IEEE Trans Pattern Anal Mach Intell 34(9):1785–1798
Valenti R, Sebe N, Gevers T (2012) Combining head pose and eye location information for gaze estimation. IEEE Trans Image Process 21(2):802–815
Villanueva A, Cabeza R (2007) Models for gaze tracking systems. J Image Video Process 2007(3):1–16
Villanueva A, Cabeza R (2008) A novel gaze estimation system with one calibration point. IEEE Trans Syst Man Cybern B Cybern 38(4):1123–1138
Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154
Wright J, Ganesh A, Zhou Z, et al. (2008) Demo: robust face recognition via sparse representation. In 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition. doi:10.1109/AFGR.2008.4813404
Xu LQ, Machin D, Sheppard P (1998) A novel approach to real-time non-intrusive gaze finding. In BMVC, pp 1–10
Zhang X, Sugano Y, Fritz M et al. (2015) Appearance-based gaze estimation in the wild. In: Proceeding of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, pp 4511–4520
Zhu Z, Ji Q (2007) Novel eye gaze tracking techniques under natural head movement. IEEE Trans Biomed Eng 54(12):2246–2260
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Guo, Z., Zhou, Q. & Liu, Z. Appearance-based gaze estimation under slight head motion. Multimed Tools Appl 76, 2203–2222 (2017). https://doi.org/10.1007/s11042-015-3182-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-3182-4