A hyperspectral image classification method based on deep learning of neighborhood information

Abstract

The present invention disclosed a high -spectrum data classification method based on neighborhood information deep learning, including the following steps: for high -spectrum image data, randomly divide training sets and test sets;The class belonging to the first L of the main component of all samples in the N × N neighboring domain is scored as a spatial information of each one; the spectrum information and space information of each one of the training set are put into the convolutional neural network for model training; The spectrum information and space information of the test set are put into the model together to predict the classification results.The present invention uses the training set of each pixel to be distributed as spatial information with the main component of the main component of the samples in the neighboring domain in the picture, and uses the two -dimensional convolutional neural network to further space for this neighboring image image.Character extraction, combined with spectral dimension information, can significantly improve the category accuracy, and has good application prospects in the field of high spectral data classification.

Description

technical field [0001] The invention relates to the technical field of hyperspectral image processing, in particular to a hyperspectral data classification method based on deep learning of neighborhood information. Background technique [0002] Hyperspectral remote sensing data can simultaneously acquire spectral information and spatial information to form a three-dimensional data block, which has broad application prospects in many fields such as surface target detection, agricultural and forestry breeding guidance, and mineral development and detection. Traditional hyperspectral image classification generally uses spectral dimension information to classify pixels. Commonly used methods include: support vector machine (SVM), K-nearest neighbor algorithm (K-NN), neural network (ANN), decision tree (DT ) and Random Forest (RF) etc. [0003] The previous classification methods were mainly aimed at the classification of spectral information. However, this type of classificati...

AI Technical Summary

Problems solved by technology

However, these methods mostly involve complex hyperspectral image segmentation strategies, spectral filtering, and classification voting strategies. The classification results are greatly affected by parameter settings and the algorithm design is complex. Therefore, how to effectively use hyperspectral spatial neighborhood information needs further research. research and improvement

Images