scholarly journals Mapping of reindeer ranges in the Kautokeino area, Northern Norway, by use of Landsat 5/TM data

Rangifer ◽  
1987 ◽  
Vol 7 (2) ◽  
pp. 2 ◽  
Author(s):  
H. Tømmervik ◽  
I. Lauknes
Keyword(s):  
Satellite Data ◽  
Supervised Classification ◽  
Median Filter ◽  
Ground Truth ◽  
Unsupervised Classification ◽  
Northern Norway ◽  
Quantitative Basis ◽  
Landsat 5 Tm ◽  
In The Beginning

<p>The aim of this study was to test the utility of Landsat 5/TM data to detect and map reindeer ranges (winter ranges). The area which has been investigated is the &Aacute;vzze area in Kautokeino, Northern Norway, on the means of Landsat 5 TM-data. A &laquo;hybrid&raquo; non-supervised/supervised classification routine was elaborated and applied in this project. The initial stage was an analysis of several bandcombinations, and the 5/4/3 combination gave the preferable combination as input to the cluster algorithm (unsupervised classification). The image was divided in 4 sections of size 512 samples and 512 lines. One of this sections (the section which cover the ground truth map) was selected for the non-supervised classification. In the beginning 17 classes were merged, and a median filter was applied for the resultant image, which comprises 12 classes. The statistics from the final result from the non-supervised classification were then used together with the TM bandcombination 5/4/3 for the whole image, as input to the minimum distance classification algorithm. This algorithm was applied to every section in turn. A mosaic of the 4 sections was then made and a median filter was then registred to a digitalized map (UTM-pro-jection). The final result was a colored thematic map over the whole area. The classification of the scene was successful with an overall classification of 90-1 (X)% for lichen-heaths (9dx/9c/9a/9av Dry shrub, fresh shrub) and birch-forests (6d/6dv/6dx shrubtype with lichen). The condition of the lichen-heaths could be detected on a sufficient level on the basis of the satellite data, but further analysis will be done here. The accuracy of the digital classification was assessed on a quantitative basis. Visual classification and interpretation of the satellite imagery showed that areas of conflict (roads, agriculture) could be detected. In chapter 6. &laquo;Resultater og diskusjon&raquo; some other results from other studies/investigations carried out in Scandinavia concerning remote sensing in mapping of vegetation are refered and discussed. Based on this study, we will conclude that use of satellite data is capable to serve as first stage classification in a multistage land use and reindeer range inventory and monitoring system.</p><p>&nbsp;Kartlegging av reinbeiter ved hjelp av Landsat 5/TM data i Kautokeino, Nord-Norge.</p><p>Abstract in Norwegian / Sammendrag: M&aring;let med foreliggende unders&oslash;kelse var &aring; unders&oslash;ke muligheten av bruk av satellittdata i kartlegging av vinterbeiter for rein i &Aacute;vzze-omr&aring;det i Kautokeino p&aring; bakgrunn av Landsat 5 TM -data. En &laquo;hybrid&raquo; klassifikasjonsrutine ble fulgt i prosjektet. F&oslash;rst ble en ikke styrt klassifikasjonsrutine (&laquo;duster algoritme&raquo;) p&aring; en 1/4 del av bildet/scenen hvor man hadde markdata (flybildetolkning av vegetasjon) utf&oslash;rt. Ved analyse av ulike kanalkombinasjoner kom man fram til at kanalkombinasjonen TM 5/4/3 hadde st&oslash;rst overenstemmelse med markdata. Det klassifiserte resultatet (12 klasser) ble brukt som &laquo;inndata&raquo; i en styrt klassifikasjonsrutine (&laquo;minimum dinstance&raquo; algoritme) for hele bildet/scenen. Resultatet av denne klassifikasjonen ble filtrert for enkeltpiksler (&laquo;median-filter&raquo;) og til slutt ble det klassifiserte bildet geometrisk transformert til UTM - kartprojeksjon. Resultatet ble dermed et tematisk kart. Klassifikasjon (ikke styrt/styrt) p&aring; scenen viste god overensstemmelse med det tolkede flybildet fra omr&aring;det, og klassifikasjon med hensyn til lavheier og fattige bj&oslash;rkeskoger med lav, viste fra 90-100% samsvar i forhold til det tolkede flybildet. Tilstanden av lavbeitene kunne detekteres ut fra satellittdataene, men her trenges det mer bildeanalyse og feltunders&oslash;kelser. Visuell analyse viste at inngrep i beiteomr&aring;dene som veier og landbruk og andre inngrep kunne tolkes ut. I kapittel 5. Resultater og diskusjon blir andre studier med henhold til satel-littkartlegging referert og diskutert. De foreliggende resultater viser at man kan bruke satellittdata som f&oslash;rste trinns kartlegging av reinbeiter, samt til overv&aring;king av reinbeitene over tid.</p>

Detection of Yellow Hawkweed (Hieracium pratense) with High Resolution Multispectral Digital Imagery

1995 ◽  
Vol 9 (3) ◽  
pp. 477-483 ◽  
Author(s):  
Hubert W. Carson ◽  
Lawrence W. Lass ◽  
Robert H. Callihan
Keyword(s):  
Supervised Classification ◽  
Digital Images ◽  
Ground Cover ◽  
Unsupervised Classification ◽  
Digital Imagery ◽  
Charge Coupled Device ◽  
Spectral Filters ◽  
A Charge ◽  
Northern Idaho

Yellow hawkweed infests permanent upland pastures and forest meadows in northern Idaho. Conventional surveys to determine infestations of this weed are not practical. A charge coupled device with spectral filters mounted in an airplane was used to obtain digital images (1 m resolution) of flowering yellow hawkweed. Supervised classification of the digital images predicted more area infested by yellow hawkweed than did unsupervised classification. Where yellow hawkweed was the dominant ground cover species, infestations were detectable with high accuracy from digital images. Moderate yellow hawkweed infestation detection was unreliable, and areas having less than 20% yellow hawkweed cover were not detected.

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 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 Mapeamento do Uso e Ocupação do Solo no Município de Belém de São Francisco-PE nos Anos de 1985 e 2010 (Mapping of Use and Occupancy of Soil in Town of Belém de São Francisco-PE in Years of 1985 and 2010)

2015 ◽  
Vol 7 (5) ◽  
pp. 859 ◽  
Author(s):  
Janaina Maria Oliveira de Assis ◽  
Ludmilla Oliveira Calado ◽  
Werônica Meira Souza ◽  
Maria do Carmo Sobral
Keyword(s):  
Remote Sensing ◽  
San Francisco ◽  
Supervised Classification ◽  
Bare Soil ◽  
Geographic Information ◽  
Gis And Remote Sensing ◽  
Landsat 5 Tm ◽  
Spatio Temporal ◽  
The City

R E S U M O Este artigo tem como objetivo mapear o uso e ocupação do solo no município de Belém de São Francisco, localizado na mesorregião do São Francisco, Pernambuco, na porção semiárida do nordeste brasileiro. Foram utilizadas ferramentas de Sistemas de Informações Geográficas (SIGs) e técnicas de sensoriamento remoto. Foi realizada uma classificação não-supervisionada do uso e ocupação do solo, onde foi feita a identificação de quatro temas: corpos d’água, vegetação densa, vegetação rasteira e solo exposto/área urbana, nos diferentes anos de 1985 e 2010. As imagens utilizadas foram do sensor Landsat 5 TM, coletadas no acervo de imagens do INPE. Os mapas foram elaborados no software ArcGIS 10.1, utilizando o sistema de coordenadas Sirgas2000, no fuso 24S. Os resultados mostraram diferentes fases de uso e ocupação do solo, apresentando diferentes causas de sua variação espaço-temporal, incluindo mudanças nos recursos hídricos, na vegetação e consequentemente na ocupação urbana do município.    A B S T R A C T This article aims to map the use and occupation of land in the city of Bethlehem in San Francisco , located in the middle region of the San Francisco PE in semiarid northeastern part of Brazil . Geographic Information Systems ( GIS ) and remote sensing tools were used . Water bodies , dense vegetation , low vegetation and bare soil / urban area in different years 1985 and 2010 : methodology as a non - supervised classification of the use and occupation of land , where the identification of four themes was done was done. The images used were from Landsat 5 TM , collected in the collection of images from INPE . The maps were drawn with ArcGIS 10.1 software , using SIRGAS2000 coordinate system , the spindle 24S . The results showed different phases of use and occupation of land , with different causes of their spatio-temporal variation , including changes in water resources , vegetation and consequently the urban occupation of the city .Keywords: Use and land cover, remote sensing, geographic information system.  

scholarly journals MAPEAMENTO DO USO E OCUPAÇÃO DO SOLO NO MUNICÍPIO DE BELÉM DE SÃO FRANCISCO – PE NOS ANOS DE 1985 E 2010 (MAPPING THE USE AND OCCUPANCY IN TOWN OF BELÉM FROM SAN FRANCISCO - PE IN YEARS FROM 1985 AND 2010)

2015 ◽  
Vol 7 (5) ◽  
pp. 949
Author(s):  
Janaina Maria Oliveira de Assis
Keyword(s):  
Remote Sensing ◽  
San Francisco ◽  
Supervised Classification ◽  
Bare Soil ◽  
Geographic Information ◽  
Gis And Remote Sensing ◽  
Landsat 5 Tm ◽  
Spatio Temporal ◽  
The City

Este artigo tem como objetivo mapear o uso e ocupação do solo no município de Belém de São Francisco, localizado na mesorregião do São Francisco, Pernambuco, na porção semiárida do nordeste brasileiro. Foram utilizadas ferramentas de Sistemas de Informações Geográficas (SIGs) e técnicas de sensoriamento remoto. Foi realizada uma classificação não-supervisionada do uso e ocupação do solo, onde foi feita a identificação de quatro temas: corpos d’água, vegetação densa, vegetação rasteira e solo exposto/área urbana, nos diferentes anos de 1985 e 2010. As imagens utilizadas foram do sensor Landsat 5 TM, coletadas no acervo de imagens do INPE. Os mapas foram elaborados no software ArcGIS 10.1, utilizando o sistema de coordenadas Sirgas2000, no fuso 24S. Os resultados mostraram diferentes fases de uso e ocupação do solo, apresentando diferentes causas de sua variação espaço-temporal, incluindo mudanças nos recursos hídricos, na vegetação e consequentemente na ocupação urbana do município.    A B S T R A C T This article aims to map the use and occupation of land in the city of Bethlehem in San Francisco , located in the middle region of the San Francisco PE in semiarid northeastern part of Brazil . Geographic Information Systems ( GIS ) and remote sensing tools were used . Water bodies , dense vegetation , low vegetation and bare soil / urban area in different years 1985 and 2010 : methodology as a non - supervised classification of the use and occupation of land , where the identification of four themes was done was done. The images used were from Landsat 5 TM , collected in the collection of images from INPE . The maps were drawn with ArcGIS 10.1 software , using SIRGAS2000 coordinate system , the spindle 24S . The results showed different phases of use and occupation of land , with different causes of their spatio-temporal variation , including changes in water resources , vegetation and consequently the urban occupation of the city .Keywords: Use and land cover, remote sensing, geographic information system.   

scholarly journals Semi-supervised time series classification method for quantum computing

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Sheir Yarkoni ◽  
Andrii Kleshchonok ◽  
Yury Dzerin ◽  
Florian Neukart ◽  
Marc Hilbert
Keyword(s):  
Time Series ◽  
Quantum Computing ◽  
Supervised Classification ◽  
Unsupervised Classification ◽  
Set Cover ◽  
Time Series Classification ◽  
Reconstruction Problem ◽  
Training Set ◽  
Set Cover Problem

AbstractIn this paper we develop methods to solve two problems related to time series (TS) analysis using quantum computing: reconstruction and classification. We formulate the task of reconstructing a given TS from a training set of data as an unconstrained binary optimization (QUBO) problem, which can be solved by both quantum annealers and gate-model quantum processors. We accomplish this by discretizing the TS and converting the reconstruction to a set cover problem, allowing us to perform a one-versus-all method of reconstruction. Using the solution to the reconstruction problem, we show how to extend this method to perform semi-supervised classification of TS data. We present results indicating our method is competitive with current semi- and unsupervised classification techniques, but using less data than classical techniques.

Classification

2014 ◽  
Author(s):  
Andrew J. Connolly ◽  
Jacob T. VanderPlas ◽  
Alexander Gray ◽  
Andrew J. Connolly ◽  
Jacob T. VanderPlas ◽  
...  
Keyword(s):  
Supervised Classification ◽  
Nearest Neighbor ◽  
Probability Distributions ◽  
Joint Probability ◽  
Unsupervised Classification ◽  
Data Sets ◽  
K Nearest Neighbor ◽  
Visual Appearance ◽  
Joint Probability Distributions

Chapter 6 described techniques for estimating joint probability distributions from multivariate data sets and for identifying the inherent clustering within the properties of sources. This approach can be viewed as the unsupervised classification of data. If, however, we have labels for some of these data points (e.g., an object is tall, short, red, or blue) we can utilize this information to develop a relationship between the label and the properties of a source. We refer to this as supervised classification, which is the focus of this chapter. The motivation for supervised classification comes from the long history of classification in astronomy. Possibly the most well known of these classification schemes is that defined by Edwin Hubble for the morphological classification of galaxies based on their visual appearance. This chapter discusses generative classification, k-nearest-neighbor classifier, discriminative classification, support vector machines, decision trees, and evaluating classifiers.

Clustering Analysis and Algorithms

2011 ◽  
pp. 389-396
Author(s):  
Xiangji Huang
Keyword(s):  
Cluster Analysis ◽  
Data Analysis ◽  
Clustering Analysis ◽  
Supervised Classification ◽  
Unsupervised Classification ◽  
Automatic Classification ◽  
Multidimensional Space ◽  
The Difference

Clustering is the process of grouping a collection of objects (usually represented as points in a multidimensional space) into classes of similar objects. Cluster analysis is a very important tool in data analysis. It is a set of methodologies for automatic classification of a collection of patterns into clusters based on similarity. Intuitively, patterns within the same cluster are more similar to each other than patterns belonging to a different cluster. It is important to understand the difference between clustering (unsupervised classification) and supervised classification.

Clustering Analysis and Algorithms

2011 ◽  
pp. 159-164 ◽  
Author(s):  
Xiangji Huang
Keyword(s):  
Cluster Analysis ◽  
Data Analysis ◽  
Clustering Analysis ◽  
Supervised Classification ◽  
Unsupervised Classification ◽  
Automatic Classification ◽  
Multidimensional Space ◽  
The Difference

Clustering is the process of grouping a collection of objects (usually represented as points in a multidimensional space) into classes of similar objects. Cluster analysis is a very important tool in data analysis. It is a set of methodologies for automatic classification of a collection of patterns into clusters based on similarity. Intuitively, patterns within the same cluster are more similar to each other than patterns belonging to a different cluster. It is important to understand the difference between clustering (unsupervised classification) and supervised classification.

An in-depth analysis of logarithmic data transformation and per-class normalization in machine learning: Application to unsupervised classification of a turbidite system in the Canterbury Basin, New Zealand and supervised classification of salt in the Eugene Island mini-basin, Gulf of Mexico

2021 ◽  
pp. 1-109
Author(s):  
Thang N. Ha ◽  
David Lubo-Robles ◽  
Kurt J. Marfurt ◽  
Bradley C. Wallet
Keyword(s):  
Machine Learning ◽  
New Zealand ◽  
Gulf Of Mexico ◽  
Supervised Classification ◽  
Data Transformation ◽  
Unsupervised Classification ◽  
Data Normalization ◽  
Z Score ◽  
Depth Analysis

In a machine learning workflow, data normalization is a crucial step that compensates for the large variation in data ranges and averages associated with different types of input measured with different units. However, most machine learning implementations do not provide data normalization beyond the z-score algorithm which subtracts the mean from the distribution and then scales the result by dividing by the standard deviation. Although z-score converts data with Gaussian behavior to have the same shape and size, many of our seismic attribute volumes exhibit log-normal, or even more complicated distributions. Because many machine learning applications are based on Gaussian statistics, we wish to evaluate the impact of more sophisticated data normalization techniques on the resulting classification. To do so, we provide an in-depth analysis of data normalization in machine-learning classifications by formulating and applying a logarithmic data transformation scheme to the unsupervised classifications (including PCA, ICA, SOM, and GTM) of a turbidite channel system in the Canterbury Basin, New Zealand, as well as implementing a per-class normalization scheme to the supervised probabilistic neural network (PNN) classification of salt in the Eugene Island mini-basin, Gulf of Mexico. Compared to the simple z-score normalization, a single logarithmic transformation applied to each input attribute significantly increases the spread of the resulting clusters (and corresponding color contrast), thereby enhancing subtle details in projection and unsupervised classification. However, this same uniform transformation produces less-confident results in supervised classification using probabilistic neural networks. We find that more accurate supervised classifications can be found by applying class-dependent normalization for each input attribute.

Sign in / Sign up

Export Citation Format

Share Document