End-to-end neural network InSAR phase unwrapping method based on mixed attention

By constructing a hybrid attention RFAUNet model, the problem of InSAR phase unwrapping in low coherence and noisy environments is solved, high-precision and noise-resistant phase unwrapping effects are achieved, and the accuracy and robustness of unwrapping are improved.

CN120689715APending Publication Date: 2025-09-23GUILIN UNIV OF ELECTRONIC TECH
0 Cites 3 Cited by

Patent Information

Application Number
CN202510632572.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-16
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Existing InSAR phase unwrapping methods do not perform well in low-coherence areas or when there is a lot of noise, and it is difficult to perform correct phase unwrapping in dense fringe areas.

Method used

A hybrid attention-based end-to-end neural network RFAUNet model is constructed, which includes an encoder and a decoder, combined with convolutional layers, CBAM modules, ASPP modules and RFB layers. The network parameters are updated through the training dataset, and the root mean square error function is used for optimization to achieve high-precision and noise-resistant phase unwrapping.

Benefits of technology

Under the influence of low coherence and noise, the RFAUNet model shows good unwrapping ability and robustness, and the obtained unwrapped phase is smooth and clear, which is better than traditional methods.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of remote sensing image processing, in particular to an end-to-end neural network InSAR (Interferometric Synthetic Aperture Radar) phase unwrapping method based on mixed attention, which takes U-Net as a basic framework, extracts key features and improves resolution through down-sampling and up-sampling operations, thereby effectively recovering detail information. Specifically, a convolutional block attention module (CBAM) and two receptive field modules, namely cavity spatial pyramid pooling (ASPP) and a receptive field module (RFB) are combined to construct an RFAUNet network model, and then simulation data sets generated by two methods of digital elevation inversion and random matrix generation are used for training a neural network until a good unwrapping effect is obtained. And finally, carrying out a phase unwrapping experiment on simulation data and real data to verify the effectiveness and robustness of the RFAUNet network model.
Need to check novelty before this filing date? Find Prior Art