HYPERSPECTRAL IMAGE CLASSIFICATION USING LOCAL SPECTRAL ANGLE-BASED MANIFOLD LEARNING

2014 ◽  
Vol 28 (06) ◽  
pp. 1450016 ◽  
Author(s):  
FULIN LUO ◽  
JIAMIN LIU ◽  
HONG HUANG ◽  
YUMEI LIU
Keyword(s):  
Large Scale ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Remote Sensing Data ◽  
Image Data ◽  
Locally Linear Embedding ◽  
Data Sets ◽  
K Nearest Neighbors ◽  
Actual Geometry ◽  
Spectral Angle

Locally linear embedding (LLE) depends on the Euclidean distance (ED) to select the k-nearest neighbors. However, the ED may not reflect the actual geometry structure of data, which may lead to the selection of ineffective neighbors. The aim of our work is to make full use of the local spectral angle (LSA) to find proper neighbors for dimensionality reduction (DR) and classification of hyperspectral remote sensing data. At first, we propose an improved LLE method, called local spectral angle LLE (LSA-LLE), for DR. It uses the ED of data to obtain large-scale neighbors, then utilizes the spectral angle to get the exact neighbors in the large-scale neighbors. Furthermore, a local spectral angle-based nearest neighbor classifier (LSANN) has been proposed for classification. Experiments on two hyperspectral image data sets demonstrate the effectiveness of the presented methods.

scholarly journals CLASSIFIER FUSION OF POLSAR, HYPERSPECTRAL AND PAN REMOTE SENSING DATA FOR IMPROVING LAND USE CLASSIFICATION

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 913-916
Author(s):  
R. Saadi ◽  
M. Hasanlou ◽  
A. Safari
Keyword(s):  
Hyperspectral Image ◽  
Remote Sensing Data ◽  
Image Data ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Majority Voting ◽  
Classifier Fusion ◽  
Data Sets ◽  
Simple Majority ◽  
Land Use Classification

Abstract. The combined use of PolSAR and hyperspectral data can improve the classification accuracy. This paper proposes a new classification approach for combining use of PolSAR and hyperspectral image data sets. At the first step, polarization signature is generated from coherency matrix of PolSAR image data. In the second step, in order to improve spatial resolution, the Hyperion image was pan-sharped with the ALI Pan image. In the third step, the Random Forest (RF) classifier is used for classifying PolSAR and hyperspectral data sets in five different classes including: Water (Wa), urban area (Ur), vegetation (Vg), road (Ro), and soil (So). Then, in order to fuse the output of RF for incorporated two data sets, simple majority voting (MV) and weighted majority voting (WMV) methods are used. Three UAVSAR, Hyperion and ALI images that acquired on April 2015 was chosen for this study. The results showed the ability of the polarimetric data for classifying urban and vegetation, and hyperspectral images for water, soil and road classes. Also, the combination of two data sets by using of WMV method causes the improvements of the classification performance.

An Incremental Isomap Method for Hyperspectral Dimensionality Reduction and Classification

2021 ◽  
Vol 87 (6) ◽  
pp. 445-455
Author(s):  
Yi Ma ◽  
Zezhong Zheng ◽  
Yutang Ma ◽  
Mingcang Zhu ◽  
Ran Huang ◽  
...  
Keyword(s):  
Manifold Learning ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Training Data ◽  
Support Vector ◽  
Data Sets ◽  
K Nearest Neighbor ◽  
Data Set ◽  
Data Points

Many manifold learning algorithms conduct an eigen vector analysis on a data-similarity matrix with a size of N×N, where N is the number of data points. Thus, the memory complexity of the analysis is no less than O(N2). We pres- ent in this article an incremental manifold learning approach to handle large hyperspectral data sets for land use identification. In our method, the number of dimensions for the high-dimensional hyperspectral-image data set is obtained with the training data set. A local curvature varia- tion algorithm is utilized to sample a subset of data points as landmarks. Then a manifold skeleton is identified based on the landmarks. Our method is validated on three AVIRIS hyperspectral data sets, outperforming the comparison algorithms with a k–nearest-neighbor classifier and achieving the second best performance with support vector machine.

Parallel kNN Queries for Big Data Based on Voronoi Diagram Using MapReduce

2015 ◽  
pp. 392-414
Author(s):  
Wei Yan
Keyword(s):  
Big Data ◽  
Voronoi Diagram ◽  
Spatial Databases ◽  
Nearest Neighbor ◽  
Programming Model ◽  
Dimensional Space ◽  
Data Sets ◽  
Two Dimensional ◽  
K Nearest Neighbor ◽  
K Nearest Neighbors

In cloud computing environments parallel kNN queries for big data is an important issue. The k nearest neighbor queries (kNN queries), designed to find k nearest neighbors from a dataset S for every object in another dataset R, is a primitive operator widely adopted by many applications including knowledge discovery, data mining, and spatial databases. This chapter proposes a parallel method of kNN queries for big data using MapReduce programming model. Firstly, this chapter proposes an approximate algorithm that is based on mapping multi-dimensional data sets into two-dimensional data sets, and transforming kNN queries into a sequence of two-dimensional point searches. Then, in two-dimensional space this chapter proposes a partitioning method using Voronoi diagram, which incorporates the Voronoi diagram into R-tree. Furthermore, this chapter proposes an efficient algorithm for processing kNN queries based on R-tree using MapReduce programming model. Finally, this chapter presents the results of extensive experimental evaluations which indicate efficiency of the proposed approach.

scholarly journals An Efficient Clustering Method for Hyperspectral Optimal Band Selection via Shared Nearest Neighbor

2019 ◽  
Vol 11 (3) ◽  
pp. 350 ◽  
Author(s):  
Qiang Li ◽  
Qi Wang ◽  
Xuelong Li
Keyword(s):  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Local Density ◽  
Computational Time ◽  
Band Selection ◽  
Data Sets ◽  
Selection Methods ◽  
Clustering Method ◽  
Slope Change ◽  
Shared Nearest Neighbor

A hyperspectral image (HSI) has many bands, which leads to high correlation between adjacent bands, so it is necessary to find representative subsets before further analysis. To address this issue, band selection is considered as an effective approach that removes redundant bands for HSI. Recently, many band selection methods have been proposed, but the majority of them have extremely poor accuracy in a small number of bands and require multiple iterations, which does not meet the purpose of band selection. Therefore, we propose an efficient clustering method based on shared nearest neighbor (SNNC) for hyperspectral optimal band selection, claiming the following contributions: (1) the local density of each band is obtained by shared nearest neighbor, which can more accurately reflect the local distribution characteristics; (2) in order to acquire a band subset containing a large amount of information, the information entropy is taken as one of the weight factors; (3) a method for automatically selecting the optimal band subset is designed by the slope change. The experimental results reveal that compared with other methods, the proposed method has competitive computational time and the selected bands achieve higher overall classification accuracy on different data sets, especially when the number of bands is small.

Identification of Outliers in Hyperspectral Raman Image Data by Nearest Neighbor Comparison

2002 ◽  
Vol 56 (11) ◽  
pp. 1458-1461 ◽  
Author(s):  
Caleb J. Behrend ◽  
Catherine P. Tarnowski ◽  
Michael D. Morris
Keyword(s):  
Nearest Neighbor ◽  
Polynomial Interpolation ◽  
Image Data ◽  
Data Sets ◽  
Outlier Identification ◽  
Contaminated Data ◽  
Central Pixel ◽  
Data Points ◽  
Highly Correlated ◽  
Raman Image

A new algorithm for removal of cosmic spikes from hyperspectral Raman image data sets is presented. Spectra in a 3 × 3 pixel neighborhood are used to identify outlier-contaminated data points in the central pixel of that neighborhood. A preliminary despiking of the neighboring spectra is performed by median filtering. Correlations between the central pixel spectrum and its despiked neighbors are calculated, and the most highly correlated spectrum is used to identify outliers. Spike-contaminated data are replaced using results of polynomial interpolation. Because the neighborhood contains spectra obtained in three different frames, even large multi-pixel spikes are identified. Spatial, spectral, and temporal variation in signal is used to accurately identify outliers without the acquisition of any spectra other than those needed to generate the image itself. Sharp boundaries between regions of high chemical contrast do not interfere with outlier identification.

scholarly journals Hyperspectral Image Classification Based on Improved Rotation Forest Algorithm

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3601 ◽  
Author(s):  
Fei Lv ◽  
Min Han
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Image Data ◽  
Classification Method ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Rotation Forest ◽  
Public Data ◽  
Learning Machine ◽  
Q Statistic

Hyperspectral image classification is a hot issue in the field of remote sensing. It is possible to achieve high accuracy and strong generalization through a good classification method that is used to process image data. In this paper, an efficient hyperspectral image classification method based on improved Rotation Forest (ROF) is proposed. It is named ROF-KELM. Firstly, Non-negative matrix factorization( NMF) is used to do feature segmentation in order to get more effective data. Secondly, kernel extreme learning machine (KELM) is chosen as base classifier to improve the classification efficiency. The proposed method inherits the advantages of KELM and has an analytic solution to directly implement the multiclass classification. Then, Q-statistic is used to select base classifiers. Finally, the results are obtained by using the voting method. Three simulation examples, classification of AVIRIS image, ROSIS image and the UCI public data sets respectively, are conducted to demonstrate the effectiveness of the proposed method.

High-Dimensional Image Data Sets Retrieval: Improving Accuracy Using a Weighted Relevance Feedback

2015 ◽  
Vol 09 (02) ◽  
pp. 239-259
Author(s):  
Abir Gallas ◽  
Walid Barhoumi ◽  
Ezzeddine Zagrouba
Keyword(s):  
Relevance Feedback ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Image Data ◽  
High Dimensional ◽  
General Context ◽  
Query Image ◽  
Data Set ◽  
Dimensional Image ◽  
Minimum Number

The user's interaction with the retrieval engines, while seeking a particular image (or set of images) in large-scale databases, defines better his request. This interaction is essentially provided by a relevance feedback step. In fact, the semantic gap is increasing in a remarkable way due to the application of approximate nearest neighbor (ANN) algorithms aiming at resolving the curse of dimensionality. Therefore, an additional step of relevance feedback is necessary in order to get closer to the user's expectations in the next few retrieval iterations. In this context, this paper details a classification of the different relevance feedback techniques related to region-based image retrieval applications. Moreover, a technique of relevance feedback based on re-weighting regions of the query-image by selecting a set of negative examples is elaborated. Furthermore, the general context to carry out this technique which is the large-scale heterogeneous image collections indexing and retrieval is presented. In fact, the main contribution of the proposed work is affording efficient results with the minimum number of relevance feedback iterations for high dimensional image databases. Experiments and assessments are carried out within an RBIR system for "Wang" data set in order to prove the effectiveness of the proposed approaches.

scholarly journals DESIGN AND IMPLEMENTATION OF A FOVEAL PROJECTION DISPLAY

2008 ◽  
Vol 08 (02) ◽  
pp. 243-263 ◽  
Author(s):  
BENJAMIN A. AHLBORN ◽  
OLIVER KREYLOS ◽  
SOHAIL SHAFII ◽  
BERND HAMANN ◽  
OLIVER G. STAADT
Keyword(s):  
High Resolution ◽  
Large Scale ◽  
Image Data ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Resolution Image ◽  
High Resolution Image ◽  
Projection Display ◽  
Display Resolution

We introduce a system that adds a foveal inset to large-scale projection displays. The effective resolution of the foveal inset projection is higher than the original display resolution, allowing the user to see more details and finer features in large data sets. The foveal inset is generated by projecting a high-resolution image onto a mirror mounted on a panCtilt unit that is controlled by the user with a laser pointer. Our implementation is based on Chromium and supports many OpenGL applications without modifications.We present experimental results using high-resolution image data from medical imaging and aerial photography.

Sign in / Sign up

Export Citation Format

Share Document