本文提出了一種基於可見光影像的視線追蹤系統，採用單一高速相機，取代傳統依賴紅外光源或專用傳感器的方案，從而顯著提升了使用者體驗。然而，這種設置在補償頭部移動方面面臨更大的挑戰。為解決此問題，我們設計了一種新型視線追蹤系統，結合了精確的頭部姿態估計方法。該方法通過識別臉部特徵點並解決 2D 到 3D 的對應問題，獲取特徵點的 3D 坐標，進而估算頭部運動。該系統能夠實時更新眼球模型並準確計算虹膜區域的初始位置。實驗結果表明，當使用者進行輕微頭部移動或旋轉時，該系統能有效提高視線追蹤的精度與準確性。

This paper proposes a visible-light-based gaze tracking system that utilizes a single high-speed camera, replacing traditional systems that rely on infrared light sources or dedicated sensors, thereby significantly enhancing user experience. However, this configuration poses greater challenges in compensating for head movements. To address this issue, we designed a novel gaze tracking system that integrates an accurate head pose estimation method. The method identifies facial feature points and resolves the 2D-to-3D correspondence problem to obtain the 3D coordinates of these points, which are then used to estimate head motion. The system is capable of real-time updates to the eye model and precise calculation of the initial position of the iris region. Experimental results demonstrate that the system effectively improves gaze tracking accuracy and precision when users perform slight head movements or rotations.

X. Wang, J. Zhang, H. Zhang, S. Zhao, and H. Liu, “Vision-based gaze estimation: A review,” IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 2, pp. 316–332, 2021.
E. Arcoverde, R. Duarte, R. Barreto, J. Magalhaes, C. Bastos, T. Ing Ren, and G. Cavalcanti, “Enhanced real-time head pose estimation system for mobile device,” Integrated Computer Aided Engineering, vol. 21, pp. 281–293, 04 2014.
N. Ruiz, E. Chong, and J. M. Rehg, “Fine-grained head pose estimation without keypoints,” in Proceedings of the IEEE conference on computer vision and pattern
recognition workshops, 2018, pp. 2074–2083.
V. Blanz and T. Vetter, “A morphable model for the synthesis of 3d faces,” in Seminal Graphics Papers: Pushing the Boundaries, Volume 2, 2023, pp. 157–164.
A. K. Chaudhary, R. Kothari, M. Acharya, S. Dangi, N. Nair, R. Bailey, C. Kanan, G. Diaz, and J. B. Pelz, “Ritnet: Real-time semantic segmentation of the eye for gaze tracking,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, 2019, pp. 3698–3702.
Z. Wang, J. Chai, and S. Xia, “Realtime and accurate 3d eye gaze capture with dcnn-based iris and pupil segmentation,” IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 1, pp. 190–203, 2021.
S.-J. Baek, K.-A. Choi, C. Ma, Y.-H. Kim, and S.-J. Ko, “Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems,” IEEE Transactions on Consumer Electronics, vol. 59, no. 2, pp. 415–421, 2013.
W.-C. Kao, K.-J. Huang, and Y.-C. Chiu, “Eyeball model construction with head movement compensation for gaze tracking systems,” in 2020 IEEE International Conference on Consumer Electronics (ICCE), 2020, pp. 1–2.
W.-C. Kao, J.-Y. Li, S.-C. Lin, and Y.-C. Chiu, “High precision canthus alignment for visible-spectrum gaze tracking system,” in 2019 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW), 2019, pp. 1–2.
R. Valle, J. M. Buenaposada, and L. Baumela, “Multi-task head pose estimation in-the-wild,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 8, pp. 2874–2881, 2020.
Y. Feng, H. Feng, M. J. Black, and T. Bolkart, “Learning an animatable detailed 3D face model from in-the-wild images,” ACM Transactions on Graphics, (Proc. SIGGRAPH), vol. 40, no. 8, 2021. [Online]. Available: https://doi.org/10.1145/3450626.3459936
O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 2015, pp. 234–241.
G. Huang, Z. Liu, and K. Q. Weinberger, “Densely connected convolutional networks,” CoRR, vol. abs/1608.06993, 2016. [Online]. Available: http://arxiv.org/abs/1608.06993
S. J. Garbin, Y. Shen, I. Schuetz, R. Cavin, G. Hughes, and S. S. Talathi, “Openeds:Open eye dataset,” arXiv preprint arXiv:1905.03702, 2019.
F. N. Iandola, M. W. Moskewicz, K. Ashraf, S. Han, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size,” CoRR, vol. abs/1602.07360, 2016. [Online]. Available: http://arxiv.org/abs/1602.07360
K. Fornalczyk and A. Wojciechowski, “Robust face model based approach to headpose estimation,” in 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), 2017, pp. 1291–1295.
H. Proenca, S. Filipe, R. Santos, J. Oliveira, and L. A. Alexandre, “The ubiris.v2: A database of visible wavelength iris images captured on-the-move and at-a-distance,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 8, pp.1529–1535, 2010.
M. Arsalan, R. A. Naqvi, D. S. Kim, P. H. Nguyen, M. Owais, and K. R. Park, “Irisdensenet: Robust iris segmentation using densely connected fully convolutional networks in the images by visible light and near-infrared light camera sensors,” Sensors, vol. 18, no. 5, 2018. [Online]. Available: https://www.mdpi.com/1424-8220/18/5/1501