Hyperspectral Image Classification Via Spectral-Spatial Random Patches Network
Open Access
- 27 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 4753-4764
Abstract
Hyperspectral imageclassification is one of the most important steps in HSI analysis and challenging task for hyperspectral data processing, hyperspectral image contains rich spatial and spectral information. The abundance of spectral and spatial information is helpful to improve the classification accuracy. In this article, we propose a spectral-spatial random patches network (SSRPNet), which directly regards the random patches taken from the image as the convolution kernels without any training. The spectral-spatial feature extracted by SSRPNet stacked into a high dimensional vector, which combined with shallow, deep, spectral, spatial feature. Then, the high dimensional vector is fed into graph-based learning methods for classification, which can achieve excellent classification performance by randomly selecting a subset of features from a small sample point to create a graph. Experimental results on three datasets show that the proposed method can achieve satisfactory classification results compared with closely related methods.Keywords
Funding Information
- National Natural Science Foundation of China (61877021)
- Multi-Year Research (MYRG2018-00111-FST)
This publication has 43 references indexed in Scilit:
- Graph-based semi-supervised learning for spectral-spatial hyperspectral image classificationPattern Recognition Letters, 2016
- Hierarchical feature learning with dropout k-means for hyperspectral image classificationNeurocomputing, 2016
- Sample-screening MKL method via boosting strategy for hyperspectral image classificationNeurocomputing, 2016
- Semisupervised Pair-Wise Band Selection for Hyperspectral ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Spectral–spatial classification of hyperspectral images using deep convolutional neural networksRemote Sensing Letters, 2015
- Deep Learning-Based Classification of Hyperspectral DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Deep Learning Face Representation from Predicting 10,000 Classes2014
- Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural NetworksIEEE Geoscience and Remote Sensing Letters, 2014
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Extensions of Lipschitz mappings into a Hilbert space1984