A hyperspectral image compression reconstruction method and system guided by spectral gradient

The hyperspectral image compression and reconstruction method guided by spectral gradient utilizes the spectral gradient Transformer module and the super-prior entropy coding module to solve the problems of low compression efficiency and severe spectral distortion in the existing technology, and achieves high-fidelity reconstruction with high efficiency and low bit rate, supporting urban intelligent driving and remote sensing monitoring.

CN122156331APending Publication Date: 2026-06-05SHANGHAI UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGHAI UNIV
Filing Date
2026-04-20
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing hyperspectral image compression technologies suffer from low compression efficiency and severe spectral distortion in urban autonomous driving scenarios, failing to meet the requirements of low bit rate and high fidelity, resulting in a decline in the performance of reconstructed data in autonomous driving semantic segmentation tasks.

Method used

A hyperspectral image compression and reconstruction method guided by spectral gradient is proposed. By constructing an end-to-end spectral gradient guiding network, the local spatial features and spectral gradient information of the hyperspectral image are jointly extracted using the spectral gradient Transformer module. Combined with the super-prior entropy coding module, efficient compression and high-fidelity reconstruction are achieved.

Benefits of technology

It achieves efficient compression and high-fidelity reconstruction, accurately preserves the geometric structure of spectral curves, improves the reconstruction quality of hyperspectral images in autonomous driving scenarios, and supports the engineering implementation of urban intelligent driving and remote sensing monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122156331A_ABST
    Figure CN122156331A_ABST
Patent Text Reader

Abstract

The application provides a hyperspectral image compression reconstruction method and system guided by a spectral gradient, the method comprising collecting a hyperspectral image and performing preprocessing on the hyperspectral image to construct a hyperspectral image dataset; constructing an end-to-end spectral gradient guided network, the spectral gradient guided network comprising an encoder and a decoder; the spectral gradient Transformer module is arranged in the encoder and the decoder; the hyperspectral image dataset is used to perform end-to-end training on the spectral gradient guided network; the hyperspectral image to be compressed is input into the trained spectral gradient guided network, the encoder is used to encode the hyperspectral image to be compressed to obtain compressed encoding data; the decoder is used to decode the compressed encoding data to obtain a reconstructed hyperspectral image. The application can realize efficient compression and high-fidelity reconstruction of urban scene hyperspectral images, and provides reliable technical support for engineering landing of hyperspectral imaging technology in the field of urban intelligent driving.
Need to check novelty before this filing date? Find Prior Art