Abstract
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 are extracted from two input images—a reference and a sensed image. Then, a patch is constructed at each key-point. The second stage consists of three processes for patch matching—candidate patch pair list generation, one-to-one matched label selection, and geometric distortion compensation. One-to-one matched patch pairs between two images are found, and the exact matching is found by compensating for geometric distortions in the matched patch pairs. A global geometric affine parameter set is computed using the random sample consensus algorithm (RANSAC) algorithm in the third stage. Finally, a registered image is generated after warping the input sensed image using the affine parameter set. The proposed high-accuracy registration framework is evaluated using the KOMPSAT-3 dataset by comparing the conventional frameworks based on machine learning and deep-learning-based frameworks. The proposed framework obtains the least root mean square error value of 34.922 based on all control points and achieves a 68.4% increase in the matching accuracy compared with the conventional registration framework.
Highlights
Image registration is the process of geometric synchronization between a reference image and a current image from the same area
We proposed a convolutional neural network (CNN)-based registration framework remote sensing the registration accuracy by 165.786, but the RMS
The deep belief network (DBN)-based reduced the φ value quired from the different timespoints and viewpoints
Summary
Image registration is the process of geometric synchronization between a reference image and a current image from the same area. Zagoruyko and his colleagues proposed an image matching method by training the joint features of patches from two input images and evaluating the features extracted from two similar CNNs or two different CNNs [22] Wang and his colleagues proposed a deep learning framework for remote sensing image registration [19]. Unlike conventional feature-based frameworks, their proposal directly trained an end-to-end mapping function by taking the image patch pairs as inputs using DBN and matching the labels as output. They attempted to reduce the computation cost in the training step.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
