Hyperspectral data classification method based on space-spectrum combination information

Abstract

The invention discloses a hyperspectral data classification method based on space-spectrum combination information, and the method provided by the invention employs a convolution neural network and asuperpixel dividing method, and solves a utilization problem of the space information of a current hyperspectral image. The method comprises the steps: 1, building a convolution neural network model,carrying out the feature extraction, and obtaining an extracted feature vector; 2, carrying out the superpixel dividing of the hyperspectral image through an M-SLIC algorithm, and obtaining a label image after superpixel dividing; 3, carrying out the clustering of a hyperspectral feature image, generating a new feature vector through combining a BoVM model, and completing the classification process. The method achieves the extraction of high-dimensional nonlinear features through the convolution neural network, multiple convolution layers and a downloading layer, reduces the impact on the spectrum information from the photographing condition difference through adding spatial information, achieves the clustering of the feature spectrum image, replaces the feature spectrum obtained through primary feature extraction via the convolution neural network by the secondary features obtained through the BoVM model, further reduces the classification errors, and is higher in theoretical and engineering practice significance.

Description

technical field [0001] The invention relates to a classification method in the field of pattern recognition, in particular to a classification method based on a convolutional neural network that adds space-spectrum joint information. Background technique [0002] Hyperspectral remote sensing technology can obtain continuous images that combine spatial information and spectral information. As a kind of earth observation data, hyperspectral images are playing an increasingly important role in environmental monitoring, crop growth monitoring and fine detection of vegetation. However, hyperspectral images have a large number of bands and serious correlation, and the redundancy of data affects the accuracy of classification, so the feature extraction step before classification is very important. Hyperspectral images are greatly affected by external disturbances, such as slight shaking of the camera and different atmospheric scattering conditions, which will lead to differences i...

AI Technical Summary

Problems solved by technology

However, although the spatial information of hyperspectral images is fully utilized in superpixel segmentation, it is very rough to directly classify all sample points in superpixels into the same category.

Images