Deep supervised learning for hyperspectral data classification through convolutional neural networks

By Konstantinos Makantasis, K. Karantzalos, Anastasios D. Doulamis, N. Doulamis. IEEE International Geoscience and Remote Sensing Symposium, 2015

926 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/8027c90cad2c41275c96ed058e4c90c7426ace0b

How researchers see this paper

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

In Analytical Chemistry

In Atmospheric Science

In Media Technology

Citations in the corpus

Deep learning for remote sensing image classification: A survey (2018, methodology): “Thus, Makantasis, Karantzalos, Doulamis, and Doulamis (2015) employed randomized principal components analysis to condense the spectral dimension of entire HSI to 10 or 30 dimensions (principal components, PCs) first.”
Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review (2019, background): “Other examples of spatial–spectral approaches were found in [148,153], in which CNN pixel classiﬁcation methods that hierarchically construct high level features were presented.”
Deep Recurrent Neural Networks for Hyperspectral Image Classification (2017, methodology): “[31] presented a deep learningbased classification method that hierarchically constructs highlevel features automatically.”
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers (2018, background): “Large-scale deep neural networks or DNNs have made breakthroughs in many fields, such as image recognition [16,17,12], speech recognition [13,4], game playing [24], and driver-less cars [23].”
Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network (2017, methodology): “In CNN based hyperspectral applications, Makantasis et al. integrated spatial-spectral information into CNN using a randomized principal component analysis (RPCA) [53].”
Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, neutral): “The 2D CNN for classification of hyperspectral data proposed in [48].”
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network (2017, neutral): “Randomized PCA (R-PCA) was also introduced along the spectral dimension to compress the entire HSI in [34], with the first 10 or 30 PCs being retained.”
Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery (2018, methodology): “Using this approach, the multispectral image was decomposed into patches, which have both spectral and spatial information for a given pixel, and a class label is assigned to the center of each patch [40].”
Fusion of Deep Convolutional Neural Networks for Land Cover Classification of High-Resolution Imagery (2017, methodology): “DCNN has been used to classify a wide variety of remotely sensed imagery, including synthetic aperture radar [1], hyperspectral [2], and high-resolution electro-optical imagery [3]–[5].”
Stacked Autoencoders Driven by Semi-Supervised Learning for Building Extraction from near Infrared Remote Sensing Imagery (2021, result): “This is also shown in one of our earliest works [10,11].”
Deep Learning Advances in Computer Vision with 3D Data (2017, methodology): “Makantasis et al. [2015] also proposed a DL-based classiﬁcation method, which extracts a feature representation from spectral and spatial data based on a CNN.”