Hyperspectral image classification method based on immune evolutionary strategy

Abstract

The invention relates to a hyperspectral image classification method based on an immune evolutionary strategy and develops a corresponding simulation prototype system. The system comprises the following four functional modules: a human-machine interface module, a hyperspectral optimal band selection module, a hyperspectral terrain classification module and a classification result output module. The method comprises the following steps: 1. obtaining the initial data and related initialization operations; 2. initializing populations; 3. initially selecting the populations; 4. cloning the populations; 5. mutating the populations in a mixed manner; 6. selecting the memory populations; 7. supplementing the population antibodies; 8. carrying out iterative computations and repeating the steps from 3 to 7 until achieving the maximum evolutionary generation; 9. using the optimal antibody to carry out terrain classification on the hyperspectral data; and 10. outputting the terrain classification results of the hyperspectral images. The method can adaptively select the optimal band combination needed by different terrain classifications under different scenes, has better time complexity and good robustness and is high in classification precision and wide in applicable scope.

Description

technical field [0001] The invention relates to a hyperspectral image classification method based on an immune evolution strategy, especially used in a hyperspectral data processing system, and belongs to the field of hyperspectral data processing. Background technique [0002] One of the greatest achievements of remote sensing technology in the 1980s was the rise of hyperspectral remote sensing technology, which has been widely used in civilian and military fields due to the advantages of both imaging and spectral detection. With the improvement of the spectral resolution of hyperspectral images, substances that cannot be detected in conventional remote sensing can be detected in hyperspectral remote sensing, which provides a prerequisite for detailed classification of ground objects in the later stage. Although hyperspectral can provide a wealth of ground information, its large number of bands makes the amount of data huge, resulting in information redundancy and increasin...

AI Technical Summary

Problems solved by technology

[0006] In the hyperspectral data processing system, due to the computational complexity requirements, the classification algorithm should have a relatively small amount of calculation, and the algorithm that meets this requirement often has poor classification accuracy.

Due to the requirement of classification accuracy, the classification algorithm must have good robustness to different classification scenarios, and the algorithm that meets this requirement often has high computational complexity

Images