关于时空插值的卡尔曼滤波器解。

On Kalman filter solution of space-time interpolation.

出版信息

IEEE Trans Image Process. 2001;10(4):663-6. doi: 10.1109/83.913601.

Abstract

The approximate Kalman filtering algorithm presented previously (see ibid., vol.3, p.773-88, Nov. 1994) for image sequence processing can introduce unacceptable negative eigenvalues in the information matrix and can have degraded performance in some applications. The improved algorithm presented in this note guarantees a positive definite information matrix, leading to more stable filter performance.

摘要

前文提出的图像序列处理近似卡尔曼滤波算法（见该期第 3 卷第 773-88 页，1994 年 11 月）可能会在信息矩阵中引入不可接受的负特征值，并在某些应用中导致性能下降。本文提出的改进算法保证了信息矩阵的正定，从而使滤波器性能更加稳定。