.png){kind=icon}
Return
A Learning-Based Optimization Algorithm: Image Registration Optimizer Network
.png){kind=icon}
OA
AI
DOI：10.1109/LGRS.2021.3062334.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Remote sensing image registration is valuable for image-based navigation system despite posing many challenges. As the search space of image registration is usually nonconvex, the optimization algorithm, which aims to find the optimal parameters in search space, is a challenging step. Conventional optimization algorithms can hardly reconcile the contradiction of rapid convergence and global optimization. In this letter, a novel learning-based optimization algorithm named image registration optimizer network (IRON) is proposed, which can predict the global optimum straightforwardly. The IRON is trained by a 3-D tensor (9 x 9 x 9) which consists of similar metric values. Each value of the 3-D tensor corresponds to the initial parameters' 9 x 9 x 9 neighbors in the search space. The 3-D tensor's label is a vector which points to the global optimal parameters from the initial parameters. Because of the special design, our IRON could predict the global optimum directly. The experimental results demonstrate that the proposed algorithm performs better than other classical optimization algorithms as it shows higher accuracy, lower root-of-mean-square error (RMSE), and more convergence efficiency. The code is publicly available at https://www.github.com/jaxwangkd04/IRON.
Keywords:
Measurement
Iron
Image registration
Tensors
Prediction algorithms
Deep learning
Training
Deep learning
image registration
learning-based optimization
optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
16.4
Papers:
1.0W
Citations:
5.1K