Hyperspectral image recognition method and device based on spatial spectrum group covariance characteristics

Abstract

The invention discloses a hyperspectral image recognition method and device based on spatial spectrum group covariance features and a computer readable storage medium. The method comprises the following steps: acquiring a hyperspectral image to be identified, mapping the hyperspectral image to be identified to a Riemann space, and calculating the Riemann distance between data points in the Riemann space; and on the basis of a Riemann cutting space and a local linear measurement criterion, performing adaptive neighborhood calculation on each data point; projecting the data points in the Riemann space to a Riemann local tangent space according to the self-adaptive neighborhood information of each data point; obtaining the low-dimensional image features of the to-be-recognized hyperspectral image by performing eigenvalue decomposition on the reconstruction weight matrix obtained in the linear reconstruction process, and recognizing the surface features of the hyperspectral image based on the low-dimensional image features, so that the surface feature recognition accuracy of the hyperspectral image is effectively improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a hyperspectral image recognition method, device and computer-readable storage medium based on spatial spectral group covariance features. Background technique [0002] Hyperspectral images are usually collected and obtained by means of imaging spectrometers. Hyperspectral images contain information of dozens or even hundreds of bands, and each band corresponds to a two-dimensional response image. The two-dimensional images of each band are stacked in sequence. A three-dimensional cube structure will appear. Each pixel in the hyperspectral image corresponds to a nearly continuous spectral characteristic curve to fully reveal the characteristics of the ground object. [0003] After the hyperspectral image is obtained from the spectral imager, the features contained in it will be identified. Related technologies usually use the nearest neighbor method such as th...

AI Technical Summary

Problems solved by technology

[0004] However, since this method uses a fixed neighborhood for all data points, it cannot adapt to changes in the curvature of the Riemannian manifold and the dense distribution of data points.

The choice of the number of neighborhoods will greatly affect the quality of the final extracted features, which in turn will affect the recognition accuracy of ground objects in hyperspectral images.

Images