M
Miao Zhang
Researcher at Harbin Institute of Technology
Publications - 44
Citations - 196
Miao Zhang is an academic researcher from Harbin Institute of Technology. The author has contributed to research in topics: Hyperspectral imaging & Support vector machine. The author has an hindex of 5, co-authored 42 publications receiving 128 citations.
Papers
More filters
Proceedings ArticleDOI
Convolutional neural network based classification for hyperspectral data
TL;DR: A novel deep learning classification method for hyperspectral data based on convolutional neural network is proposed, to restructure spectral feature images and choose convolution filters with a reasonable size so that the spectral features of different land coverings in high dimensions can be extracted properly.
Journal ArticleDOI
Spatial Revising Variational Autoencoder-Based Feature Extraction Method for Hyperspectral Images
Wenbo Yu,Miao Zhang,Yi Shen +2 more
TL;DR: A novel unsupervised hyperspectral feature extraction architecture based on spatial revising variational autoencoder (AE) achieves better classification results compared with comparison methods and the proposed loss function guarantees the consistency of the probability distributions of various latent spatial features, which obtained from the same neighbor region.
Proceedings ArticleDOI
Spectral-spatial hyperspectral image classification via SVM and superpixel segmentation
TL;DR: A novel spectral-spatial classification method inspired by the support vector machine (SVM) and superpixel segmentation and found that it yields more accurate classification results compared to the state-of-the-art techniques.
Journal ArticleDOI
Learning a local manifold representation based on improved neighborhood rough set and LLE for hyperspectral dimensionality reduction
Wenbo Yu,Miao Zhang,Yi Shen +2 more
TL;DR: Experimental results performed over two real-world hyperspectral datasets indicate the proposed INRSLLE not only considers the spectral-spatial information of hyperspectrals data, but also selects more suitable neighbors on local manifolds and increases the anti-noise ability.
Journal ArticleDOI
Hypergraph Learning and Reweighted $\ell _1$ -Norm Minimization for Hyperspectral Unmixing
Peiyuan Jia,Miao Zhang,Yi Shen +2 more
TL;DR: A hypergraph is constructed to exploit the fact that spatial neighboring pixels have a high probability of sharing similar spectral information and the complicated large-scale regression problem is decomposed into subproblems to obtain the optimal solution within the framework of alternating direction method of multipliers.