Hyperspectral Image Classification With Small Training Sample Size Using Superpixel-Guided Training Sample Enlargement

Hyperspectral Image Classification With Small Training Sample Size Using Superpixel-Guided Training Sample Enlargement

Hyperspectral image (HSI) classification (HIC) has attracted much attention in the last decade. Spectral-spatial HIC methods have been the state-of-the-art methods in recent years. Small labeled training sample size (SLTSS) problem is still an important issue in HIC. This paper presents a spectral-s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2019-10, Vol.57 (10), p.7307-7316
Main Authors: Zheng, Chengyong, Wang, Ningning, Cui, Jing
Format: Article
Language:eng
Subjects:
Algorithms
Classification
Classifiers
Clustering algorithms
Distance
Distance-weighted linear regression
Enlargement
Expansion
Feature extraction
hyperspectral image (HSI) classification (HIC)
Hyperspectral imaging
Image classification
Image processing
Image segmentation
Linear regression
Methods
Pixels
Regression analysis
Regressions
Sample size
Samples
Segmentation
small samples size problem
spectral–spatial analysis
superpixel (SP) segmentation
Training
training sample enlargement
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral image (HSI) classification (HIC) has attracted much attention in the last decade. Spectral-spatial HIC methods have been the state-of-the-art methods in recent years. Small labeled training sample size (SLTSS) problem is still an important issue in HIC. This paper presents a spectral-spatial HIC method that is based on superpixel (SP) segmentation and distance-weighted linear regression classifier to tackle the SLTSS problem. First, SP segmentation is applied to the original HSI. Then, those SPs that contain training samples belonging to only one class are first searched out, and all the pixels of each of these SPs are assigned to the class of the training samples it contains. Next, with the identified labels, all these classified pixels are added to the initial training sample set for training sample set enlargement. Later, using this enlarged training sample set, the distance-weighted linear regression classifier is applied to classify each mean vector of each SP. Finally, the last classification map is obtained by assigning each SP with the same label as its mean vector. Experimental results on three HSI data sets demonstrate that the proposed approach can solve SLTSS problem very well and outperforms several state-of-the-art algorithms in classification accuracy under different training samples sizes.
ISSN:0196-2892
1558-0644