62‐2: High‐precision Human Eye Recognition System Based on Kalman Prediction
SID Symposium Digest of Technical Papers · 2026-08 · 57 (S1) · 614-617
DOI: 10.1002/sdtp.70003_160 ↗Kurz gefasst
Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Jinhui Hua und 6 weiteren Autor:innen. Die Arbeit nennt 5 Literaturangaben.
Abstract (Originalsprache)
To address the issue of asynchrony in image rendering caused by non‐uniform eye movements and system latency in head‐up display (HUD) gaze interaction systems, this paper proposes an adaptive Kalman filter‐based eye tracking prediction method. The method accounts for the non‐uniform characteristics of driver eye movements by dynamically adjusting the process noise covariance matrix to accommodate rapid changes in eye motion states. Additionally, a time‐adaptive state transition matrix is introduced to handle fluctuations in frame rate, thereby compensating for system latency. Furthermore, a smoothing algorithm is incorporated to mitigate micro‐jitter in 3D display caused by fluctuations in eye coordinate data. Experimental results demonstrate that the proposed method significantly improves prediction accuracy, coordinate stability, and visual smoothness in fast eye movement scenarios, thereby enhancing the real‐time performance and visual fluency of HUD gaze interaction systems.
Zitieren
APA
Hua, J., Zhang, Y., Dai, J., Liu, X., Wu, W., Lu, F., & Lyu, B. (2026). 62‐2: High‐precision Human Eye Recognition System Based on Kalman Prediction. SID Symposium Digest of Technical Papers, 57(S1), 614-617. https://doi.org/10.1002/sdtp.70003_160
Vancouver
Hua J, Zhang Y, Dai J, Liu X, Wu W, Lu F, et al. 62‐2: High‐precision Human Eye Recognition System Based on Kalman Prediction. SID Symposium Digest of Technical Papers. 2026;57(S1):614-617. doi:10.1002/sdtp.70003_160
BibTeX
@article{Hua2026,
author = {Hua, Jinhui and Zhang, Yanjun and Dai, Jiahui and Liu, Xinyue and Wu, Wei and Lu, Feng and Lyu, Bojia},
title = {62‐2: High‐precision Human Eye Recognition System Based on Kalman Prediction},
journal = {SID Symposium Digest of Technical Papers},
year = {2026},
volume = {57},
number = {S1},
pages = {614--617},
doi = {10.1002/sdtp.70003_160}
}
EUVIMED