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


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2018-07-19

AUTHORS

Taskin Kavzoglu, Hasan Tonbul, Merve Yildiz Erdemir, Ismail Colkesen

ABSTRACT

Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries–Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier. More... »

PAGES

1297-1306

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s12524-018-0803-1

DOI

http://dx.doi.org/10.1007/s12524-018-0803-1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1105700644


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey", 
          "id": "http://www.grid.ac/institutes/grid.448834.7", 
          "name": [
            "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kavzoglu", 
        "givenName": "Taskin", 
        "id": "sg:person.010500456471.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010500456471.94"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey", 
          "id": "http://www.grid.ac/institutes/grid.448834.7", 
          "name": [
            "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tonbul", 
        "givenName": "Hasan", 
        "id": "sg:person.012400670463.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012400670463.26"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey", 
          "id": "http://www.grid.ac/institutes/grid.448834.7", 
          "name": [
            "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yildiz Erdemir", 
        "givenName": "Merve", 
        "id": "sg:person.013313242306.04", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013313242306.04"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey", 
          "id": "http://www.grid.ac/institutes/grid.448834.7", 
          "name": [
            "Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Colkesen", 
        "givenName": "Ismail", 
        "id": "sg:person.013251461425.95", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013251461425.95"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/a:1010933404324", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024739340", 
          "https://doi.org/10.1023/a:1010933404324"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-77058-9_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024329151", 
          "https://doi.org/10.1007/978-3-540-77058-9_1"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-07-19", 
    "datePublishedReg": "2018-07-19", 
    "description": "Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries\u2013Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s12524-018-0803-1", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1136874", 
        "issn": [
          "0255-660X", 
          "0974-3006"
        ], 
        "name": "Journal of the Indian Society of Remote Sensing", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "8", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "46"
      }
    ], 
    "keywords": [
      "object-based image analysis", 
      "pixel-based approach", 
      "conventional accuracy metrics", 
      "traditional pixel-based approach", 
      "image analysis", 
      "high dimensional data", 
      "object-based approach", 
      "performances of pixel", 
      "AVIRIS hyperspectral sensor", 
      "hyperspectral data sets", 
      "random forest classifier", 
      "object-based classification", 
      "image objects", 
      "dimensionality curse", 
      "semantic information", 
      "dimensional data", 
      "feature selection", 
      "Jeffries\u2013Matusita distance", 
      "NN classifier", 
      "dimensionality reduction", 
      "forest classifier", 
      "accuracy metrics", 
      "hyperspectral images", 
      "classifier", 
      "parametric classifiers", 
      "RF classifier", 
      "JM distance", 
      "nearest neighbours", 
      "PCA technique", 
      "recent sensors", 
      "data sets", 
      "images", 
      "hyperspectral sensors", 
      "principal component analysis", 
      "sample data", 
      "objects", 
      "accurate results", 
      "ground sample data", 
      "comprehensive image analysis", 
      "ground reference data", 
      "vast increase", 
      "classification", 
      "sensors", 
      "pixels", 
      "component analysis", 
      "spectral bands", 
      "metrics", 
      "curse", 
      "reference data", 
      "information", 
      "set", 
      "data", 
      "performance", 
      "great importance", 
      "high spatial resolution", 
      "features", 
      "principal components", 
      "spatial resolution", 
      "technique", 
      "distance", 
      "selection", 
      "accessibility", 
      "availability", 
      "neighbours", 
      "analysis", 
      "assumption", 
      "components", 
      "resolution", 
      "results", 
      "delineation", 
      "normal distribution", 
      "consideration", 
      "dimensions", 
      "importance", 
      "cases", 
      "landscape features", 
      "distribution", 
      "reduction", 
      "study", 
      "band", 
      "increase", 
      "effect", 
      "approach", 
      "Statistical parametric classifiers", 
      "limited ground sample data", 
      "Indian Pines hyperspectral data set", 
      "Pines hyperspectral data set", 
      "limited ground reference data"
    ], 
    "name": "Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis", 
    "pagination": "1297-1306", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1105700644"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s12524-018-0803-1"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s12524-018-0803-1", 
      "https://app.dimensions.ai/details/publication/pub.1105700644"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2021-12-01T19:43", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/article/article_773.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s12524-018-0803-1"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s12524-018-0803-1'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s12524-018-0803-1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12524-018-0803-1'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12524-018-0803-1'


 

This table displays all metadata directly associated to this object as RDF triples.

175 TRIPLES      22 PREDICATES      115 URIs      105 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s12524-018-0803-1 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N2232b0d97c7c4d41b9089aebdc0921b6
4 schema:citation sg:pub.10.1007/978-3-540-77058-9_1
5 sg:pub.10.1023/a:1010933404324
6 schema:datePublished 2018-07-19
7 schema:datePublishedReg 2018-07-19
8 schema:description Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries–Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier.
9 schema:genre article
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf N154d258b3d3b4308ba5b2eb91e1fca9a
13 N47a1d6dfd9f64c65aebf19d3c9906e92
14 sg:journal.1136874
15 schema:keywords AVIRIS hyperspectral sensor
16 Indian Pines hyperspectral data set
17 JM distance
18 Jeffries–Matusita distance
19 NN classifier
20 PCA technique
21 Pines hyperspectral data set
22 RF classifier
23 Statistical parametric classifiers
24 accessibility
25 accuracy metrics
26 accurate results
27 analysis
28 approach
29 assumption
30 availability
31 band
32 cases
33 classification
34 classifier
35 component analysis
36 components
37 comprehensive image analysis
38 consideration
39 conventional accuracy metrics
40 curse
41 data
42 data sets
43 delineation
44 dimensional data
45 dimensionality curse
46 dimensionality reduction
47 dimensions
48 distance
49 distribution
50 effect
51 feature selection
52 features
53 forest classifier
54 great importance
55 ground reference data
56 ground sample data
57 high dimensional data
58 high spatial resolution
59 hyperspectral data sets
60 hyperspectral images
61 hyperspectral sensors
62 image analysis
63 image objects
64 images
65 importance
66 increase
67 information
68 landscape features
69 limited ground reference data
70 limited ground sample data
71 metrics
72 nearest neighbours
73 neighbours
74 normal distribution
75 object-based approach
76 object-based classification
77 object-based image analysis
78 objects
79 parametric classifiers
80 performance
81 performances of pixel
82 pixel-based approach
83 pixels
84 principal component analysis
85 principal components
86 random forest classifier
87 recent sensors
88 reduction
89 reference data
90 resolution
91 results
92 sample data
93 selection
94 semantic information
95 sensors
96 set
97 spatial resolution
98 spectral bands
99 study
100 technique
101 traditional pixel-based approach
102 vast increase
103 schema:name Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis
104 schema:pagination 1297-1306
105 schema:productId N39b01069acd44afba7a6b7ef90509ea4
106 Ne74df863e4fe4d10ab8669a7ab3f00c5
107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105700644
108 https://doi.org/10.1007/s12524-018-0803-1
109 schema:sdDatePublished 2021-12-01T19:43
110 schema:sdLicense https://scigraph.springernature.com/explorer/license/
111 schema:sdPublisher Nf57eace52cc44f9aba6b1c1c784ca53b
112 schema:url https://doi.org/10.1007/s12524-018-0803-1
113 sgo:license sg:explorer/license/
114 sgo:sdDataset articles
115 rdf:type schema:ScholarlyArticle
116 N154d258b3d3b4308ba5b2eb91e1fca9a schema:issueNumber 8
117 rdf:type schema:PublicationIssue
118 N2232b0d97c7c4d41b9089aebdc0921b6 rdf:first sg:person.010500456471.94
119 rdf:rest N6be06fcf03ea4a30af30880f87c6c807
120 N39b01069acd44afba7a6b7ef90509ea4 schema:name doi
121 schema:value 10.1007/s12524-018-0803-1
122 rdf:type schema:PropertyValue
123 N3eb6a780b9cc47f3949bfbaead98a18a rdf:first sg:person.013251461425.95
124 rdf:rest rdf:nil
125 N45939f469dfc4261807e7b40960bf40f rdf:first sg:person.013313242306.04
126 rdf:rest N3eb6a780b9cc47f3949bfbaead98a18a
127 N47a1d6dfd9f64c65aebf19d3c9906e92 schema:volumeNumber 46
128 rdf:type schema:PublicationVolume
129 N6be06fcf03ea4a30af30880f87c6c807 rdf:first sg:person.012400670463.26
130 rdf:rest N45939f469dfc4261807e7b40960bf40f
131 Ne74df863e4fe4d10ab8669a7ab3f00c5 schema:name dimensions_id
132 schema:value pub.1105700644
133 rdf:type schema:PropertyValue
134 Nf57eace52cc44f9aba6b1c1c784ca53b schema:name Springer Nature - SN SciGraph project
135 rdf:type schema:Organization
136 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
137 schema:name Information and Computing Sciences
138 rdf:type schema:DefinedTerm
139 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
140 schema:name Artificial Intelligence and Image Processing
141 rdf:type schema:DefinedTerm
142 sg:journal.1136874 schema:issn 0255-660X
143 0974-3006
144 schema:name Journal of the Indian Society of Remote Sensing
145 schema:publisher Springer Nature
146 rdf:type schema:Periodical
147 sg:person.010500456471.94 schema:affiliation grid-institutes:grid.448834.7
148 schema:familyName Kavzoglu
149 schema:givenName Taskin
150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010500456471.94
151 rdf:type schema:Person
152 sg:person.012400670463.26 schema:affiliation grid-institutes:grid.448834.7
153 schema:familyName Tonbul
154 schema:givenName Hasan
155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012400670463.26
156 rdf:type schema:Person
157 sg:person.013251461425.95 schema:affiliation grid-institutes:grid.448834.7
158 schema:familyName Colkesen
159 schema:givenName Ismail
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013251461425.95
161 rdf:type schema:Person
162 sg:person.013313242306.04 schema:affiliation grid-institutes:grid.448834.7
163 schema:familyName Yildiz Erdemir
164 schema:givenName Merve
165 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013313242306.04
166 rdf:type schema:Person
167 sg:pub.10.1007/978-3-540-77058-9_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024329151
168 https://doi.org/10.1007/978-3-540-77058-9_1
169 rdf:type schema:CreativeWork
170 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
171 https://doi.org/10.1023/a:1010933404324
172 rdf:type schema:CreativeWork
173 grid-institutes:grid.448834.7 schema:alternateName Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
174 schema:name Department of Geomatics Engineering, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
175 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...