Skip to Main Content
Image registration is widely used in 3D modeling. In this paper, an approach for multiview image registration based on augmented Kalman filter is proposed. The position and orientation of viewpoint are considered as augmented system state vector. A simplified system state and two system models are constructed. The system state is augmented and updated recursively. The position and orientation of each viewpoint is estimated. The proposed multiview image registration method can handle the uncertainty efficiently and the registration result is globally consistent. Some experimental results are provided to validate the performance of the proposed method.