scholarly journals Efficient Unsupervised Classification of Hyperspectral Images Using Voronoi Diagrams and Strong Patterns

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5684
Author(s):  
Laura Bianca Bilius ◽  
Ştefan Gheorghe Pentiuc
Keyword(s):  
Heuristic Method ◽  
Voronoi Diagrams ◽  
Ground Truth ◽  
Unsupervised Classification ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Spectral Signature ◽  
Area Of Interest ◽  
Parafac Decomposition

Hyperspectral images (HSIs) are a powerful tool to classify the elements from an area of interest by their spectral signature. In this paper, we propose an efficient method to classify hyperspectral data using Voronoi diagrams and strong patterns in the absence of ground truth. HSI processing consumes a great deal of computing resources because HSIs are represented by large amounts of data. We propose a heuristic method that starts by applying Parafac decomposition for reduction and to construct the abundances matrix. Furthermore, the representative nodes from the abundances map are searched for. A multi-partition of these nodes is found, and based on this, strong patterns are obtained. Then, based on the hierarchical clustering of strong patterns, an optimum partition is found. After strong patterns are labeled, we construct the Voronoi diagram to extend the classification to the entire HSI.

scholarly journals Sparse Subspace Clustering in Hyperspectral Images using Incomplete Pixels

TecnoLógicas ◽  
2019 ◽  
Vol 22 (46) ◽  
pp. 1-14 ◽  
Author(s):  
Jorge Luis Bacca ◽  
Henry Arguello
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Subspace Clustering ◽  
Unsupervised Classification ◽  
Hyperspectral Images ◽  
Image Clustering ◽  
Spectral Signature ◽  
Spectral Image ◽  
Sparse Subspace Clustering

Spectral image clustering is an unsupervised classification method which identifies distributions of pixels using spectral information without requiring a previous training stage. The sparse subspace clustering-based methods (SSC) assume that hyperspectral images lie in the union of multiple low-dimensional subspaces.  Using this, SSC groups spectral signatures in different subspaces, expressing each spectral signature as a sparse linear combination of all pixels, ensuring that the non-zero elements belong to the same class. Although these methods have shown good accuracy for unsupervised classification of hyperspectral images, the computational complexity becomes intractable as the number of pixels increases, i.e. when the spatial dimension of the image is large. For this reason, this paper proposes to reduce the number of pixels to be classified in the hyperspectral image, and later, the clustering results for the missing pixels are obtained by exploiting the spatial information. Specifically, this work proposes two methodologies to remove the pixels, the first one is based on spatial blue noise distribution which reduces the probability to remove cluster of neighboring pixels, and the second is a sub-sampling procedure that eliminates every two contiguous pixels, preserving the spatial structure of the scene. The performance of the proposed spectral image clustering framework is evaluated in three datasets showing that a similar accuracy is obtained when up to 50% of the pixels are removed, in addition, it is up to 7.9 times faster compared to the classification of the data sets without incomplete pixels.

scholarly journals Unsupervised Clustering for Hyperspectral Images

Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 277 ◽  
Author(s):  
Laura Bilius ◽  
Stefan Pentiuc
Keyword(s):  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Spectral Bands ◽  
Long Time ◽  
Parafac Decomposition ◽  
Classification Time

Hyperspectral images are becoming a valuable tool much used in agriculture, mineralogy, and so on. The challenge is to successfully classify the materials founded in the field relevant for different applications. Due to a large amount of data corresponding to a big number of spectral bands, the classification programs require a long time to analyze and classify the data. The purpose is to find a better method for reducing the classification time. We exploit various algorithms on real hyperspectral data sets to find out which algorithm is more effective. This paper presents a comparison of unsupervised hyperspectral image classification such as K-means, Hierarchical clustering, and Parafac decomposition, which allows the performance of the model reduction and feature extraction. The results showed that the method useful for big data is the classification of data after Parafac Decomposition.

scholarly journals Overview of Hyperspectral Image Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Wenjing Lv ◽  
Xiaofei Wang
Keyword(s):  
Supervised Classification ◽  
Hyperspectral Image ◽  
Unsupervised Classification ◽  
Hyperspectral Images ◽  
Hyperspectral Image Classification ◽  
Remote Sensing Technology ◽  
Sensing Technology ◽  
Good Classification ◽  
Semisupervised Classification

With the development of remote sensing technology, the application of hyperspectral images is becoming more and more widespread. The accurate classification of ground features through hyperspectral images is an important research content and has attracted widespread attention. Many methods have achieved good classification results in the classification of hyperspectral images. This paper reviews the classification methods of hyperspectral images from three aspects: supervised classification, semisupervised classification, and unsupervised classification.

scholarly journals HYPERSPECTRAL HYPERION IMAGERY ANALYSIS AND ITS APPLICATION USING SPECTRAL ANALYSIS

2015 ◽  
Vol XL-3/W2 ◽  
pp. 169-175 ◽  
Author(s):  
W. Pervez ◽  
S. A. Khan ◽  
Valiuddin
Keyword(s):  
Machine Learning ◽  
Vegetation Index ◽  
Hyperspectral Image ◽  
Atmospheric Correction ◽  
Hyperspectral Data ◽  
Supervised Machine Learning ◽  
Spectral Signature ◽  
Processing Application ◽  
Significant Difference

Rapid advancement in remote sensing open new avenues to explore the hyperspectral Hyperion imagery pre-processing techniques, analysis and application for land use mapping. The hyperspectral data consists of 242 bands out of which 196 calibrated/useful bands are available for hyperspectral applications. Atmospheric correction applied to the hyperspectral calibrated bands make the data more useful for its further processing/ application. Principal component (PC) analysis applied to the hyperspectral calibrated bands reduced the dimensionality of the data and it is found that 99% of the data is held in first 10 PCs. Feature extraction is one of the important application by using vegetation delineation and normalized difference vegetation index. The machine learning classifiers uses the technique to identify the pixels having significant difference in the spectral signature which is very useful for classification of an image. Supervised machine learning classifier technique has been used for classification of hyperspectral image which resulted in overall efficiency of 86.6703 and Kappa co-efficient of 0.7998.

scholarly journals Characterization and Mapping of Fuel Types for the Mediterranean Ecosystems of Pollino National Park in Southern Italy by Using Hyperspectral MIVIS Data

2006 ◽  
Vol 10 (13) ◽  
pp. 1-11 ◽  
Author(s):  
Rosa Lasaponara ◽  
Antonio Lanorte ◽  
Stefano Pignatti
Keyword(s):  
Remote Sensing ◽  
National Park ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Mediterranean Ecosystems ◽  
Remotely Sensed ◽  
Hyperspectral Data ◽  
Test Area ◽  
Sensing Data

Abstract The characterization and mapping of fuel types is one of the most important factors that should be taken into consideration for wildland fire prevention and prefire planning. This research aims to investigate the usefulness of hyperspectral data to recognize and map fuel types in order to ascertain how well remote sensing data can provide an exhaustive classification of fuel properties. For this purpose airborne hyperspectral Multispectral Infrared and Visible Imaging Spectrometer (MIVIS) data acquired in November 1998 have been analyzed for a test area of 60 km2 selected inside Pollino National Park in the south of Italy. Fieldwork fuel-type recognitions, performed at the same time as remote sensing data acquisition, were used as a ground-truth dataset to assess the results obtained for the considered test area. The method comprised the following three steps: 1) adaptation of Prometheus fuel types for obtaining a standardization system useful for remotely sensed classification of fuel types and properties in the considered Mediterranean ecosystems; 2) model construction for the spectral characterization and mapping of fuel types based on a maximum likelihood (ML) classification algorithm; and 3) accuracy assessment for the performance evaluation based on the comparison of MIVIS-based results with ground truth. Results from our analysis showed that the use of remotely sensed data at high spatial and spectral resolution provided a valuable characterization and mapping of fuel types being that the achieved classification accuracy was higher than 90%.

scholarly journals Hybrid Depth-Separable Residual Networks for Hyperspectral Image Classification

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-17
Author(s):  
Cuijie Zhao ◽  
Hongdong Zhao ◽  
Guozhen Wang ◽  
Hong Chen
Keyword(s):  
Hyperspectral Image ◽  
Computational Cost ◽  
Ground Truth ◽  
Hyperspectral Data ◽  
Deep Convolutional Neural Networks ◽  
Convolutional Network ◽  
Benchmark Datasets ◽  
Deep Convolutional Network ◽  
3D Cnn

At present, the classification of the hyperspectral image (HSI) based on the deep convolutional network has made great progress. Due to the high dimensionality of spectral features, limited samples of ground truth, and high nonlinearity of hyperspectral data, effective classification of HSI based on deep convolutional neural networks is still difficult. This paper proposes a novel deep convolutional network structure, namely, a hybrid depth-separable residual network, for HSI classification, called HDSRN. The HDSRN model organically combines 3D CNN, 2D CNN, multiresidual network ROR, and depth-separable convolutions to extract deeper abstract features. On the one hand, due to the addition of multiresidual structures and skip connections, this model can alleviate the problem of over fitting, help the backpropagation of gradients, and extract features more fully. On the other hand, the depth-separable convolutions are used to learn the spatial feature, which reduces the computational cost and alleviates the decline in accuracy. Extensive experiments on the popular HSI benchmark datasets show that the performance of the proposed network is better than that of the existing prevalent methods.

Sign in / Sign up

Export Citation Format

Share Document