Abstract
Dynamic distortion is one of the most critical factors affecting the experience of automotive augmented reality head-up displays (AR-HUDs). A wide range of views and the extensive display area result in extraordinarily complex distortions. Existing methods based on the neural network first obtain distorted images and then get the predistorted data for training mostly. This paper proposes a distortion prediction framework based on the neural network. It directly trains the network with the distorted data, realizing dynamic adaptation for AR-HUD distortion correction and avoiding errors in coordinate interpolation. Additionally, we predict the distortion offsets instead of the distortion coordinates and present a field of view (FOV)-weighted loss function based on the spatial-variance characteristic to further improve the prediction accuracy of distortion. Experiments show that our methods improve the prediction accuracy of AR-HUD dynamic distortion without increasing the network complexity or data processing overhead.
© 2023 Optica Publishing Group
Full Article | PDF ArticleMore Like This
An Li, Yisi Wu, Xinxing Xia, Yuejin Huang, Chaoqi Feng, and Zhenrong Zheng
Appl. Opt. 54(9) 2441-2449 (2015)
Yuichi Hiroi, Kiyosato Someya, and Yuta Itoh
Opt. Express 30(22) 40628-40644 (2022)
Rundong Fan, Shili Wei, Huiru Ji, Zhuang Qian, Hao Tan, Yan Mo, and Donglin Ma
Opt. Express 31(6) 10758-10774 (2023)