A Hyperspectral Data Classification Method Based on Space-Spectral Joint Information

Abstract

A hyperspectral data classification method based on spatial-spectral joint information. The invention proposes a convolutional neural network and a superpixel division method to solve the problem of utilizing spatial information in current hyperspectral images. The steps of the present invention are: 1. Establish a convolutional neural network model and perform feature extraction to obtain extracted feature vectors. 2. Use the M-SLIC algorithm to divide the hyperspectral image into superpixels, and obtain the label map after superpixel division. 3. Cluster the hyperspectral feature images and combine the BoVW model to generate new feature vectors to complete the classification process. The present invention utilizes a convolutional neural network to extract high-dimensional nonlinear features through multi-layer convolutional layers and down-sampling layers, and reduces the influence of shooting condition differences on spectral information by adding spatial information, and then performs clustering through characteristic spectral graphs, and The feature spectrum extracted by the convolutional neural network is replaced by the secondary feature obtained by using the BoVW model to further reduce the classification error, which has strong theoretical and engineering practical significance.

Description

(1) 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. (2) Background technology [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 diff...

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