An Integrated Multistage Framework for Automatic Road Extraction from High Resolution Satellite Imagery View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2011-03-12

AUTHORS

T. T. Mirnalinee, Sukhendu Das, Koshy Varghese

ABSTRACT

Automated procedures to rapidly identify road networks from high-resolution satellite imagery are necessary for modern applications in GIS. In this paper, we propose an approach for automatic road extraction by integrating a set of appropriate modules in a unified framework, to solve this complex problem. The two main properties of roads used are: (1) spectral contrast with respect to background and (2) locally linear path. Support Vector Machine is used to discriminate between road and non-road segments. We propose a Dominant singular Measure (DSM) for the task of detecting linear (locally) road boundaries. This pair of information of road segments, obtained using Probabilistic SVM (PSVM) and DSM, is integrated using a modified Constraint Satisfaction Neural Network. Results of this integration are not satisfactory due to occlusion of roads, variation of road material, and curvilinear pattern. Suitable post-processing modules (segment linking and region part segmentation) have been designed to address these issues. The proposed non-model based approach is verified with extensive experimentations and performance compared with two state-of-the-art techniques and a GIS based tool, using multi-spectral satellite images. The proposed methodology is robust and shows superior performance (completeness and correctness are used as measures) in automating the process of road network extraction. More... »

PAGES

1-25

References to SciGraph publications

  • 2003. Support Vector Machines for Road Extraction from Remotely Sensed Images in COMPUTER ANALYSIS OF IMAGES AND PATTERNS
  • 2000-07. Automatic extraction of roads from aerial images based on scale space and snakes in MACHINE VISION AND APPLICATIONS
  • 2007-05-05. Feature extraction for man-made objects segmentation in aerial images in MACHINE VISION AND APPLICATIONS
  • 2007-11-15. Aerial tracking of elongated objects in rural environments in MACHINE VISION AND APPLICATIONS
  • 1988-01. Snakes: Active contour models in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1995-09. Support-vector networks in MACHINE LEARNING
  • 1995. Signal Processing for Computer Vision in NONE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s12524-011-0063-9

    DOI

    http://dx.doi.org/10.1007/s12524-011-0063-9

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1016196601


    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/2008/09", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Engineering", 
            "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"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0909", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Geomatic Engineering", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India", 
              "id": "http://www.grid.ac/institutes/grid.417969.4", 
              "name": [
                "Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mirnalinee", 
            "givenName": "T. T.", 
            "id": "sg:person.010646432733.55", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010646432733.55"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India", 
              "id": "http://www.grid.ac/institutes/grid.417969.4", 
              "name": [
                "Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Das", 
            "givenName": "Sukhendu", 
            "id": "sg:person.013072277453.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013072277453.26"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Dept. of Civil Engg, Indian Institute of Technology, Madras, 600 036, Chennai, India", 
              "id": "http://www.grid.ac/institutes/grid.417969.4", 
              "name": [
                "Dept. of Civil Engg, Indian Institute of Technology, Madras, 600 036, Chennai, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Varghese", 
            "givenName": "Koshy", 
            "id": "sg:person.013722032627.76", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013722032627.76"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s00138-007-0080-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050500540", 
              "https://doi.org/10.1007/s00138-007-0080-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00133570", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1016330466", 
              "https://doi.org/10.1007/bf00133570"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00138-007-0102-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008618651", 
              "https://doi.org/10.1007/s00138-007-0102-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00994018", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025150743", 
              "https://doi.org/10.1007/bf00994018"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-45179-2_36", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011474692", 
              "https://doi.org/10.1007/978-3-540-45179-2_36"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s001380050121", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013663749", 
              "https://doi.org/10.1007/s001380050121"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4757-2377-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010741589", 
              "https://doi.org/10.1007/978-1-4757-2377-9"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2011-03-12", 
        "datePublishedReg": "2011-03-12", 
        "description": "Automated procedures to rapidly identify road networks from high-resolution satellite imagery are necessary for modern applications in GIS. In this paper, we propose an approach for automatic road extraction by integrating a set of appropriate modules in a unified framework, to solve this complex problem. The two main properties of roads used are: (1) spectral contrast with respect to background and (2) locally linear path. Support Vector Machine is used to discriminate between road and non-road segments. We propose a Dominant singular Measure (DSM) for the task of detecting linear (locally) road boundaries. This pair of information of road segments, obtained using Probabilistic SVM (PSVM) and DSM, is integrated using a modified Constraint Satisfaction Neural Network. Results of this integration are not satisfactory due to occlusion of roads, variation of road material, and curvilinear pattern. Suitable post-processing modules (segment linking and region part segmentation) have been designed to address these issues. The proposed non-model based approach is verified with extensive experimentations and performance compared with two state-of-the-art techniques and a GIS based tool, using multi-spectral satellite images. The proposed methodology is robust and shows superior performance (completeness and correctness are used as measures) in automating the process of road network extraction.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s12524-011-0063-9", 
        "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": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "39"
          }
        ], 
        "keywords": [
          "automatic road extraction", 
          "road extraction", 
          "probabilistic SVM", 
          "constraint satisfaction neural network", 
          "multi-spectral satellite images", 
          "road network extraction", 
          "post-processing modules", 
          "non-road segments", 
          "high resolution satellite imagery", 
          "high-resolution satellite imagery", 
          "neural network", 
          "satellite imagery", 
          "network extraction", 
          "road boundaries", 
          "extensive experimentation", 
          "vector machine", 
          "resolution satellite imagery", 
          "art techniques", 
          "modern applications", 
          "unified framework", 
          "road materials", 
          "road network", 
          "road segments", 
          "appropriate modules", 
          "complex problems", 
          "multistage framework", 
          "superior performance", 
          "satellite images", 
          "network", 
          "module", 
          "framework", 
          "SVM", 
          "GIS", 
          "extraction", 
          "linear path", 
          "imagery", 
          "machine", 
          "performance", 
          "road", 
          "task", 
          "images", 
          "main properties", 
          "spectral contrast", 
          "experimentation", 
          "information", 
          "set", 
          "integration", 
          "tool", 
          "applications", 
          "materials", 
          "path", 
          "methodology", 
          "properties", 
          "boundaries", 
          "issues", 
          "technique", 
          "singular measures", 
          "process", 
          "approach", 
          "segments", 
          "occlusion", 
          "results", 
          "variation", 
          "problem", 
          "respect", 
          "curvilinear pattern", 
          "state", 
          "pairs", 
          "procedure", 
          "background", 
          "measures", 
          "patterns", 
          "contrast", 
          "paper", 
          "DSM", 
          "linear (locally) road boundaries", 
          "pair of information", 
          "Satisfaction Neural Network", 
          "occlusion of roads", 
          "Suitable post-processing modules", 
          "Integrated Multistage Framework"
        ], 
        "name": "An Integrated Multistage Framework for Automatic Road Extraction from High Resolution Satellite Imagery", 
        "pagination": "1-25", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1016196601"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s12524-011-0063-9"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s12524-011-0063-9", 
          "https://app.dimensions.ai/details/publication/pub.1016196601"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2021-11-01T18:17", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/article/article_542.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s12524-011-0063-9"
      }
    ]
     

    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/s12524-011-0063-9'

    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/s12524-011-0063-9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12524-011-0063-9'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12524-011-0063-9'


     

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

    191 TRIPLES      22 PREDICATES      115 URIs      98 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s12524-011-0063-9 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 anzsrc-for:09
    4 anzsrc-for:0909
    5 schema:author N2f27e33a74f948f785df6c4a10ee6f14
    6 schema:citation sg:pub.10.1007/978-1-4757-2377-9
    7 sg:pub.10.1007/978-3-540-45179-2_36
    8 sg:pub.10.1007/bf00133570
    9 sg:pub.10.1007/bf00994018
    10 sg:pub.10.1007/s00138-007-0080-4
    11 sg:pub.10.1007/s00138-007-0102-2
    12 sg:pub.10.1007/s001380050121
    13 schema:datePublished 2011-03-12
    14 schema:datePublishedReg 2011-03-12
    15 schema:description Automated procedures to rapidly identify road networks from high-resolution satellite imagery are necessary for modern applications in GIS. In this paper, we propose an approach for automatic road extraction by integrating a set of appropriate modules in a unified framework, to solve this complex problem. The two main properties of roads used are: (1) spectral contrast with respect to background and (2) locally linear path. Support Vector Machine is used to discriminate between road and non-road segments. We propose a Dominant singular Measure (DSM) for the task of detecting linear (locally) road boundaries. This pair of information of road segments, obtained using Probabilistic SVM (PSVM) and DSM, is integrated using a modified Constraint Satisfaction Neural Network. Results of this integration are not satisfactory due to occlusion of roads, variation of road material, and curvilinear pattern. Suitable post-processing modules (segment linking and region part segmentation) have been designed to address these issues. The proposed non-model based approach is verified with extensive experimentations and performance compared with two state-of-the-art techniques and a GIS based tool, using multi-spectral satellite images. The proposed methodology is robust and shows superior performance (completeness and correctness are used as measures) in automating the process of road network extraction.
    16 schema:genre article
    17 schema:inLanguage en
    18 schema:isAccessibleForFree false
    19 schema:isPartOf N3bdf7e8a19f44a8ebc5576fc56aeed26
    20 N3cd4864f313f48b8b5c148e9902f13bf
    21 sg:journal.1136874
    22 schema:keywords DSM
    23 GIS
    24 Integrated Multistage Framework
    25 SVM
    26 Satisfaction Neural Network
    27 Suitable post-processing modules
    28 applications
    29 approach
    30 appropriate modules
    31 art techniques
    32 automatic road extraction
    33 background
    34 boundaries
    35 complex problems
    36 constraint satisfaction neural network
    37 contrast
    38 curvilinear pattern
    39 experimentation
    40 extensive experimentation
    41 extraction
    42 framework
    43 high resolution satellite imagery
    44 high-resolution satellite imagery
    45 imagery
    46 images
    47 information
    48 integration
    49 issues
    50 linear (locally) road boundaries
    51 linear path
    52 machine
    53 main properties
    54 materials
    55 measures
    56 methodology
    57 modern applications
    58 module
    59 multi-spectral satellite images
    60 multistage framework
    61 network
    62 network extraction
    63 neural network
    64 non-road segments
    65 occlusion
    66 occlusion of roads
    67 pair of information
    68 pairs
    69 paper
    70 path
    71 patterns
    72 performance
    73 post-processing modules
    74 probabilistic SVM
    75 problem
    76 procedure
    77 process
    78 properties
    79 resolution satellite imagery
    80 respect
    81 results
    82 road
    83 road boundaries
    84 road extraction
    85 road materials
    86 road network
    87 road network extraction
    88 road segments
    89 satellite imagery
    90 satellite images
    91 segments
    92 set
    93 singular measures
    94 spectral contrast
    95 state
    96 superior performance
    97 task
    98 technique
    99 tool
    100 unified framework
    101 variation
    102 vector machine
    103 schema:name An Integrated Multistage Framework for Automatic Road Extraction from High Resolution Satellite Imagery
    104 schema:pagination 1-25
    105 schema:productId N5ad55e2039b24d75b8fcae57a06e7ad9
    106 N6b37347f2bc44e5f974bdf729d6be471
    107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016196601
    108 https://doi.org/10.1007/s12524-011-0063-9
    109 schema:sdDatePublished 2021-11-01T18:17
    110 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    111 schema:sdPublisher Nee84ee63290e4a67976f1ae95a1bc5ac
    112 schema:url https://doi.org/10.1007/s12524-011-0063-9
    113 sgo:license sg:explorer/license/
    114 sgo:sdDataset articles
    115 rdf:type schema:ScholarlyArticle
    116 N2f27e33a74f948f785df6c4a10ee6f14 rdf:first sg:person.010646432733.55
    117 rdf:rest Nb475118cc6f14a5eaedeae15ba2c1d8a
    118 N3bdf7e8a19f44a8ebc5576fc56aeed26 schema:issueNumber 1
    119 rdf:type schema:PublicationIssue
    120 N3cd4864f313f48b8b5c148e9902f13bf schema:volumeNumber 39
    121 rdf:type schema:PublicationVolume
    122 N5ad55e2039b24d75b8fcae57a06e7ad9 schema:name dimensions_id
    123 schema:value pub.1016196601
    124 rdf:type schema:PropertyValue
    125 N6b37347f2bc44e5f974bdf729d6be471 schema:name doi
    126 schema:value 10.1007/s12524-011-0063-9
    127 rdf:type schema:PropertyValue
    128 Nb14e7c86d4244c228023aa9de067ff28 rdf:first sg:person.013722032627.76
    129 rdf:rest rdf:nil
    130 Nb475118cc6f14a5eaedeae15ba2c1d8a rdf:first sg:person.013072277453.26
    131 rdf:rest Nb14e7c86d4244c228023aa9de067ff28
    132 Nee84ee63290e4a67976f1ae95a1bc5ac schema:name Springer Nature - SN SciGraph project
    133 rdf:type schema:Organization
    134 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    135 schema:name Information and Computing Sciences
    136 rdf:type schema:DefinedTerm
    137 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    138 schema:name Artificial Intelligence and Image Processing
    139 rdf:type schema:DefinedTerm
    140 anzsrc-for:09 schema:inDefinedTermSet anzsrc-for:
    141 schema:name Engineering
    142 rdf:type schema:DefinedTerm
    143 anzsrc-for:0909 schema:inDefinedTermSet anzsrc-for:
    144 schema:name Geomatic Engineering
    145 rdf:type schema:DefinedTerm
    146 sg:journal.1136874 schema:issn 0255-660X
    147 0974-3006
    148 schema:name Journal of the Indian Society of Remote Sensing
    149 schema:publisher Springer Nature
    150 rdf:type schema:Periodical
    151 sg:person.010646432733.55 schema:affiliation grid-institutes:grid.417969.4
    152 schema:familyName Mirnalinee
    153 schema:givenName T. T.
    154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010646432733.55
    155 rdf:type schema:Person
    156 sg:person.013072277453.26 schema:affiliation grid-institutes:grid.417969.4
    157 schema:familyName Das
    158 schema:givenName Sukhendu
    159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013072277453.26
    160 rdf:type schema:Person
    161 sg:person.013722032627.76 schema:affiliation grid-institutes:grid.417969.4
    162 schema:familyName Varghese
    163 schema:givenName Koshy
    164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013722032627.76
    165 rdf:type schema:Person
    166 sg:pub.10.1007/978-1-4757-2377-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010741589
    167 https://doi.org/10.1007/978-1-4757-2377-9
    168 rdf:type schema:CreativeWork
    169 sg:pub.10.1007/978-3-540-45179-2_36 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011474692
    170 https://doi.org/10.1007/978-3-540-45179-2_36
    171 rdf:type schema:CreativeWork
    172 sg:pub.10.1007/bf00133570 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016330466
    173 https://doi.org/10.1007/bf00133570
    174 rdf:type schema:CreativeWork
    175 sg:pub.10.1007/bf00994018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025150743
    176 https://doi.org/10.1007/bf00994018
    177 rdf:type schema:CreativeWork
    178 sg:pub.10.1007/s00138-007-0080-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050500540
    179 https://doi.org/10.1007/s00138-007-0080-4
    180 rdf:type schema:CreativeWork
    181 sg:pub.10.1007/s00138-007-0102-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008618651
    182 https://doi.org/10.1007/s00138-007-0102-2
    183 rdf:type schema:CreativeWork
    184 sg:pub.10.1007/s001380050121 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013663749
    185 https://doi.org/10.1007/s001380050121
    186 rdf:type schema:CreativeWork
    187 grid-institutes:grid.417969.4 schema:alternateName Dept. of Civil Engg, Indian Institute of Technology, Madras, 600 036, Chennai, India
    188 Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India
    189 schema:name Dept. of Civil Engg, Indian Institute of Technology, Madras, 600 036, Chennai, India
    190 Visualization and Perception Lab, Dept. of CSE, Indian Institute of Technology, Madras, 600 036, Chennai, India
    191 rdf:type schema:Organization
     




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


    ...