On Combining Multiple Features for Hyperspectral Remote Sensing Image Classification

By Lefei Zhang, Liangpei Zhang, Dacheng Tao, Xin Huang. 2012

406 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology, Remote Sensing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computer Vision and Pattern Recognition

In Media Technology

In Remote Sensing

Citations in the corpus

A Survey on Multi-view Learning (2013, background): “Zhang et al. (2012) studied the hyperspectral remote sensing image classification problem in the approach of multiview learning, and introduced the patch alignment framework to linearly combine multiple features in an optimal way and a unified low-dimensional representation of these multiple…”
Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, background): “However, the high dimensionality of hyperspectral data may produce the Hughes phenomenon [1] and thus may influence the performance of supervised classification methods.”
Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification (2017, background): “[12] unified spectrum, Gabor features, and pixel-shaped features, and then learned a low-dimensional representation of the unified features via manifold learning.”
Strathprints Institutional Repository Shuhui and Ren, Jinchang (2015) Effective and Efficient Midlevel Visual Elements-oriented Land-use Classification Using Vhr Remote Sensing Images. Ieee Transactions on Geoscience and Remote Sensing, 53 (8). Pp. 4238-4249. Issn 0196-2892 Effective and Efficient M (unknown): “Most previous works [8] [9] [10] [11] [12] [13] [14] [15] [16] [17] mainly focus on classifying pixels or objects (or rather, grouping of local homogeneous pixels) into their thematic class by extracting low-level image features (e.g. texture feature [9] [10], color feature [8], spatial and…”
Feature Mining for Hyperspectral Image Classification (2013, methodology): “[72] used the concepts of the patch alignment framework and manifold learning and linearly combined multiple features to obtain a unified lowdimensional representation of these multiple features for subsequent classification.”
Deep learning classifiers for hyperspectral imaging: A review (2019, background): “To deal with these limitations, recent research has demonstrated the benefits of exploiting the spatial arrangement of HSI data (Jiménez et al., 2005; Zhang et al., 2012; Huang and Zhang, 2013), enhancing the classification performance of standard pixel-wise HSI classification procedures (Tarabalka ”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “, in the aspects of handcrafted feature description [65]–[68], discriminative feature learning [13], [69], [70], and powerful classifier designing [71], [72].”
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework (2018, methodology): “For example, [8] integrated multiple features derived from different kinds of dimensionality reduction methods to train support vector machine (SVM) classifiers.”
Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding (2015, methodology): “The input three kind of features are extracted by the following approaches [37, 38]: (1) 191-D spectral feature, by arranging a pixel’s digital number (DN) in all of the spectral bands, (2) 60-D Gabor wavelet based texture feature over the top principal component of HSI (scale=5, direction=12), and ”
Semi-Supervised Manifold Learning Based Multigraph Fusion for High-Resolution Remote Sensing Image Classification (2014, methodology): “[2] introduced the famous Laplacian Eigenmap (LE) into a Patch Alignment Framework (PAF) [3] to jointly unify the representation of multiple features and applied it into the hyperspectral remote sensing image classification task.”
Spectral–Spatial Hyperspectral Image Classification via Multiscale Adaptive Sparse Representation (2014, background): “bined to further increase the robustness of classification [23].”
Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach (2016, background): “Specifically, rich information provided by high-resolution images may increase the intraclass variation and decrease the interclass variation in both spectral and spatial domains [4] and lead to lower interpretation accuracies.”
Hyperspectral Image Denoising Employing a Spectral–Spatial Adaptive Total Variation Model (2012, methodology): “To show that the classiﬁcation improvement after image denoising is statistically signiﬁcant, we ﬁrst randomly select a few samples from the total samples as training samples, and we then use the support vector machine (SVM) classiﬁcation method [47] to do a supervised classi-ﬁcation for the image.”