Dimensionality Reduction and Classification in Hyperspectral Images Using Deep Learning

2021 ◽  
pp. 113-140
Author(s):  
Satyajit Swain ◽  
Anasua Banerjee ◽  
Mainak Bandyopadhyay ◽  
Suresh Chandra Satapathy
Keyword(s):  
Deep Learning ◽  
Dimensionality Reduction ◽  
Hyperspectral Images

scholarly journals Improved Prototypical Network Model for Forest Species Classification in Complex Stand

2020 ◽  
Vol 12 (22) ◽  
pp. 3839
Author(s):  
Xiaomin Tian ◽  
Long Chen ◽  
Xiaoli Zhang ◽  
Erxue Chen
Keyword(s):  
Deep Learning ◽  
Dimensionality Reduction ◽  
Image Classification ◽  
Small Sample ◽  
Hyperspectral Images ◽  
Test Accuracy ◽  
Forest Species ◽  
Species Classification ◽  
Sample Classification ◽  
Sample Window

Deep learning has become an effective method for hyperspectral image classification. However, the high band correlation and data volume associated with airborne hyperspectral images, and the insufficiency of training samples, present challenges to the application of deep learning in airborne image classification. Prototypical networks are practical deep learning networks that have demonstrated effectiveness in handling small-sample classification. In this study, an improved prototypical network is proposed (by adding L2 regularization to the convolutional layer and dropout to the maximum pooling layer) to address the problem of overfitting in small-sample classification. The proposed network has an optimal sample window for classification, and the window size is related to the area and distribution of the study area. After performing dimensionality reduction using principal component analysis, the time required for training using hyperspectral images shortened significantly, and the test accuracy increased drastically. Furthermore, when the size of the sample window was 27 × 27 after dimensionality reduction, the overall accuracy of forest species classification was 98.53%, and the Kappa coefficient was 0.9838. Therefore, by using an improved prototypical network with a sample window of an appropriate size, the network yielded desirable classification results, thereby demonstrating its suitability for the fine classification and mapping of tree species.

Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis

2018 ◽  
Vol 46 (8) ◽  
pp. 1297-1306 ◽  
Author(s):  
Taskin Kavzoglu ◽  
Hasan Tonbul ◽  
Merve Yildiz Erdemir ◽  
Ismail Colkesen
Keyword(s):  
Image Analysis ◽  
Dimensionality Reduction ◽  
Hyperspectral Images ◽  
Object Based Image Analysis ◽  
Object Based

scholarly journals Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

2018 ◽  
Vol 10 (11) ◽  
pp. 1827 ◽  
Author(s):  
Ahram Song ◽  
Jaewan Choi ◽  
Youkyung Han ◽  
Yongil Kim
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Spatial Information ◽  
Short Term Memory ◽  
Hyperspectral Images ◽  
Convolutional Network ◽  
Ground Truth Data ◽  
Fully Convolutional Network ◽  
Training Samples ◽  
Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

Tongue tumor detection in hyperspectral images using deep learning semantic segmentation

2020 ◽  
pp. 1-1 ◽  
Author(s):  
Stojan Trajanovski ◽  
Caifeng Shan ◽  
Pim J.C. Weijtmans ◽  
Susan G. Brouwer de Koning ◽  
Theo J. M. Ruers
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
Tumor Detection ◽  
Hyperspectral Images ◽  
Tongue Tumor

Deep Learning-Based Enhancement of Hyperspectral Images Using Simulated Ground Truth

2018 ◽  
Author(s):  
Artem Nikonorov ◽  
Maksim Petrov ◽  
Sergey Bibikov ◽  
Viktoria Kutikova ◽  
Pavel Yakimov ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ground Truth ◽  
Hyperspectral Images
Sign in / Sign up

Export Citation Format

Share Document