A CNN-Based High-Accuracy Registration for Remote Sensing Images
In this paper, a convolutional neural network-based registration framework is proposed for remote sensing to improve the registration accuracy between two remote-sensed images acquired from different times and viewpoints. The proposed framework consists of four stages. In the first stage, key-points...
Main Authors: | Wooju Lee, Donggyu Sim, Seoung-Jun Oh |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/8/1482 |
Similar Items
-
Multi-Temporal Remote Sensing Image Registration Using Deep Convolutional Features
by: Zhuoqian Yang, et al.
Published: (2018-01-01) -
A Two-Stage Deep Learning Registration Method for Remote Sensing Images Based on Sub-Image Matching
by: Yuan Chen, et al.
Published: (2021-08-01) -
Satellite-Borne Optical Remote Sensing Image Registration Based on Point Features
by: Xinan Hou, et al.
Published: (2021-04-01) -
An Instance Segmentation-Based Framework for a Large-Sized High-Resolution Remote Sensing Image Registration
by: Junyan Lu, et al.
Published: (2021-04-01) -
Robust Local Structure Visualization for Remote Sensing Image Registration
by: Jiaxuan Chen, et al.
Published: (2021-01-01)