SAR image fine registration method based on deep learning

Abstract

The invention discloses an SAR (Synthetic Aperture Radar) image precise registration method based on deep learning, and mainly solves the problems that local distortion cannot be corrected and time isconsumed in a traditional method. According to the implementation scheme, the method comprises the steps of 1) obtaining a training data set; 2) constructing a neural network for SAR image fine registration; 3) constructing a loss function of a neural network model for SAR image fine registration; 4) training a neural network for SAR image fine registration by using the training data set to obtain a trained network model; and 5) inputting the SAR image to be registered and the SAR image as a reference into the trained network model to obtain a registered SAR image. The SAR image registrationmethod can correct the overall deformation and local distortion between the SAR images, improves the registration performance, accelerates the registration speed, and can be used for SAR image fusionand change detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a SAR image fine registration method, which can be used for SAR image fusion and change detection. Background technique [0002] Synthetic Aperture Radar (SAR) is an active microwave imaging system, which has the ability to observe the ground and sea surface all-weather under different climate and light conditions, and has played an important role in many applications such as geological resource exploration, ocean monitoring and urban planning. . With the continuous development of SAR imaging technology, SAR imaging system has obtained a large amount of valuable earth observation data. In SAR image processing, it is often necessary to analyze and process two or more SAR images, such as SAR image fusion and SAR image change detection, and SAR image registration technology is the premise of these image processing tasks. [0003] Currently, SAR image registration methods ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that in the process of establishing the scale space and obtaining the feature descriptor, the amount of calculation is large and the time consumption is serious.

However, in addition to the overall deformation between the actual two SAR images, there are also local distortions due to the difference in observation angle. The existence of these local distortions is not conducive to the subsequent SAR image processing, but the traditional registration of two SAR images cannot Correcting these local distortions affects the registration performance and the improvement of the registration speed

Images