- 學位論文
新型自由頭部運動之長距離眼動追蹤演算法
Novel Algorithms for Long Distance Free Head Motion Gaze Estimation System
若您是本文的作者，可授權文章由華藝線上圖書館中協助推廣。
摘要
眼動追蹤技術在未來的人機互動以及虛擬實境等領域裡都有很大的應用潛力。雖然眼對追蹤有長久的研究歷史，時至今日，仍有許多限制。大部分眼動追蹤針對大約70 cm 左右的操作距離，並且可能不允許頭部自由運動。對比於靜態坐姿的追蹤，動態頭部的長距離追蹤則需要更多改善。本研究旨在開發一定程度頭部運動下的長距離眼動追蹤系統。本研究提出四種方法且針對其中三種進行實驗。從實驗結果得知，本研究確實有效減少內插式眼動追蹤法的頭部運動誤差，其中平均誤差均小於1°，符合精準型的凝視點偵測，且測試頭部有效運動範圍為60×16×40以上，操作距離可達2米，整體表現相對於其他研究還算相當不錯。
並列摘要
Gaze estimation is a potential technique in future Human Computer Interaction (HCI) and virtual reality. Although the long history of gaze estimation research, there are still many limits in algorithms nowadays. Oftentimes, many approaches are only valid to use in a distance around 70 cm and might not allow free head motion. This is not desirable when it comes to dynamic and long range head motion gaze estimation instead of stationary sitting gaze estimation.This work aims at developing long range gaze estimation system which allows certain degree of head motion. And four proposed methods with experiment for three methods are also provided. From the experiment, it could be shown that this work indeed effectively reduce the head motion error in interpolation based gaze estimation, and the average error are all below 1° which could be regarded as high accuracy gaze estimation. And the tested effective head motion range could be larger than 60×16×40 and the operation distance is 2 m. The overall performance of this work is fairly well compared with other researches.
參考文獻
REFERENCES
[1] S. P. Liversedge and J. M. Findlay, “Saccadic eye movements and cognition,” Trends in Cognitive Science, vol. 4, no. 1, pp. 6–14, 2000.
[2] R. J. K. Jacob, “The use of eye movements in human computer interaction techniques: What you look at is what you get,” ACM Trans. Inf. Syst., vol. 9, no. 3, pp. 152–169, 1991.
[3] G. Underwood, Cognitive Processes in Eye Guidance. Oxford Univ. Press, 2005.
[4] S. P. Liversedge and J. M. Findlay, “Saccadic eye movements and cognition,” Trends in Cognitive Science, vol. 4, no. 1, pp. 6–14, 2000.
延伸閱讀
- Liao, Y. C. (2006). 可以自由移動頭部之視線追蹤演算法 [master's thesis, National Central University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0031-0207200917340265
- Lu, I. C., Hsu, H. T., Soo, L. Y., Lu, D. V., Chen, T. I., Wang, J. J., & Chu, K. S. (2007). 以超音波檢查評估施行肌間溝臂神經叢阻斷術之最佳頭部轉動姿勢. Acta Anaesthesiologica Taiwanica, 45(2), 73-78. https://www.airitilibrary.com/Article/Detail?DocID=02541319-200706-45-2-73-78-a
- 侯俊成（2006）。頭部姿勢辨識應用於游標與機器人之控制〔碩士論文，國立中央大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0031-0207200917335801
- 陸念聞（2010）。應用類神經網路定位為基礎的主動視覺於人形機器人罰踢之研究〔碩士論文，淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2010.00136
- Jin, Y., & Ruan, Q. Q. (2009). Orthogonal Locality Sensitive Discriminant Analysis for Face Recognition. Journal of Information Science and Engineering, 25(2), 419-433. https://doi.org/10.6688/JISE.2009.25.2.6