Hyper-spectral classification method based on low-order mutual information and spectral context band selection

Abstract

The invention discloses a hyper-spectral classification method based on low-order mutual information and spectral context band selection, and mainly aims to solve the problem that the computational complexity is high and the classification performance is poor for hyper-spectral image classification in the prior art. The implementation scheme comprises the following steps: first, automatically removing noise bands based on context priori information between neighborhoods of spectral bands of hyper-spectral images; second, selecting a band subset with low redundancy and high information content from a band set obtained after removal of the noise bands by a sequence forward search method according to self information of a maximum single band and regularization mutual information between a minimum band and other bands; and finally, performing object classification by using the selected bands. By adopting the method of the invention, a high-accuracy high-efficiency result of hyper-spectral image classification can be obtained. The method can be used for object distinguishing and identifying in soil survey, urban environment monitoring, disaster evaluation and other fields.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral image classification method, which is used for the distinction and identification of ground objects in fields such as soil investigation, urban environment monitoring, and disaster assessment. Background technique [0002] Hyperspectral resolution remote sensing is the frontier of current remote sensing technology. It is capable of acquiring many very narrow and spectrally continuous image data in the visible, near-infrared, mid-infrared, and thermal infrared bands of the electromagnetic spectrum. Hyperspectral remote sensing images effectively combine the spectral information that reflects the attributes of ground objects and the image information that reveals the spatial relationship of ground objects, and have the characteristics of "map-spectrum integration". It can detect substances that cannot be detected in broadband rem...

AI Technical Summary

Problems solved by technology

These clustering-based methods select the most representative band by calculating the similarity of paired bands in each cluster, and ignore the correlation between multiple bands in each cluster. Therefore, the most informative band cannot be selected

[0008] In summary, the existing sorting-based methods and clustering-based methods all have poor band selection performance, resulting in poor classification accuracy and high time complexity.

Images