A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images
Open Access
- 22 October 2019
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 11 (20) , 2454
Abstract
Filter banks transferred from a pre-trained deep convolutional network exhibit significant performance in heightening the inter-class separability for hyperspectral image feature extraction, but weakening the intra-class consistency simultaneously. In this paper, we propose a new superpixel-based relational auto-encoder for cohesive spectral–spatial feature learning. Firstly, multiscale local spatial information and global semantic features of hyperspectral images are extracted by filter banks transferred from the pre-trained VGG-16. Meanwhile, we utilize superpixel segmentation to construct the low-dimensional manifold embedded in the spectral domain. Then, representational consistency constraint among each superpixel is added in the objective function of sparse auto-encoder, which iteratively assist and supervisedly learn hidden representation of deep spatial feature with greater cohesiveness. Superpixel-based local consistency constraint in this work not only reduces the computational complexity, but builds the neighborhood relationships adaptively. The final feature extraction is accomplished by collaborative encoder of spectral–spatial feature and weighting fusion of multiscale features. A large number of experimental results demonstrate that our proposed method achieves expected results in discriminant feature extraction and has certain advantages over some existing methods, especially on extremely limited sample conditions.Keywords
Funding Information
- National Natural Science Foundation of China (61901198, 61871306)
- Doctoral Scientific Research Foundation of Jiangxi University of Science and Technology (jxxjbs19006)
This publication has 34 references indexed in Scilit:
- Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral ImagesJournal of Sensors, 2015
- Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing ImageryRemote Sensing, 2015
- Learning Hierarchical Spectral–Spatial Features for Hyperspectral Image ClassificationIEEE Transactions on Cybernetics, 2015
- Spectral–spatial classification of hyperspectral images using deep convolutional neural networksRemote Sensing Letters, 2015
- Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief NetworkIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Deep Convolutional Neural Networks for Hyperspectral Image ClassificationJournal of Sensors, 2015
- Intrinsic Image Decomposition for Feature Extraction of Hyperspectral ImagesIEEE Transactions on Geoscience and Remote Sensing, 2014
- Deep Learning-Based Classification of Hyperspectral DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Feature Extraction of Hyperspectral Images With Image Fusion and Recursive FilteringIEEE Transactions on Geoscience and Remote Sensing, 2013
- On the power of small-depth threshold circuitscomputational complexity, 1991