SSRN: A Nonlocal Sparse Attention and Multiscale Fusion Super Resolution Network for Spacecraft ISAR Image | IEEE Journals & Magazine | IEEE Xplore

SSRN: A Nonlocal Sparse Attention and Multiscale Fusion Super Resolution Network for Spacecraft ISAR Image


Abstract:

Inverse synthetic aperture radar (ISAR) is a popular space object detection method. However, due to the complex flight conditions of spacecraft and limited observation ti...Show More

Abstract:

Inverse synthetic aperture radar (ISAR) is a popular space object detection method. However, due to the complex flight conditions of spacecraft and limited observation time, the resolution of spacecraft ISAR images is reduced. Although there are many methods of ISAR image super resolution, but none of them aim at spacecraft. To this end, in this letter, we analyze the characteristics of spacecraft ISAR images, and first propose an approach space super resolution network (SSRN), suitable for spacecraft ISAR images. Specially, our approach is designed to utilize the repetitive structures commonly observed in spacecraft ISAR images. So we introduce nonlocal sparse attention (NLSA) to capture the long-distance self-similarity in the spacecraft ISAR image. Spherical locality sensitive hashing (SLSH) is used to construct multiple attention buckets, and the query feature and features in the same and adjacent buckets are used for attention operations. To effectively extract multiscale features and contrast features from spacecraft ISAR image, we design the Residual Atrous Spatial Pyramid Pooling block (ResASPPblock), connect a number of atrous convolution layers with different dilation rates, and add the skip connection. The experiment on the real ISAR image of a certain type spacecraft proves the effectiveness of our approach, and the performance of our approach is higher than the popular ISAR super resolution method. Overall, our approach provides a promising solution for improving the resolution of spacecraft ISAR images.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)
Article Sequence Number: 4008905
Date of Publication: 09 August 2023

ISSN Information:

Funding Agency:


References

References is not available for this document.