.png){kind=icon}
Return
Two-Stage Hyperspectral Image Classification Using Few Labeled Samples
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2023.3244196.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hyperspectral image classification (HIC) has attracted considerable attention in the last two decades, and significant progress has been made. However, the small sample size problem of HIC is still challenging. This letter presents a two-stage HIC approach that achieves high classification accuracies with few labeled samples. For a given hyperspectral image (HSI), the spatial features are first extracted by local binary patterns (LBPs). Spatial features and spectral features for each pixel are then stacked into feature vectors. These vectors are fed into support vector machine (SVM) to finish the first classification stage. Based on the preliminary classification results, a superpixel segmentation method is introduced for selecting some superpixels which include training samples and all test pixels assigned to some class. These selected superpixels with their labels obtained by SVM are then added to training samples. According to the enlarged training sample set, random multigraph (RMG) is finally utilized to classify the remaining samples. Experimental results on three benchmark HSI datasets demonstrate that the proposed LBP and RMG-based two-stage method (LBP-RMG2) significantly outperforms several state-of-the-art algorithms with a few labeled samples.
Keywords:
Hyperspectral image classification (HIC)
local binary pattern
random multigraph (RMG)
small sample size
superpixel segmentation
Journal
IF:
16.4
Papers:
1.0W
Citations:
5.1K
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSaveShareSave
ShareSave
View more