Region Covariance: A Fast Descriptor for Detection and Classification View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2006

AUTHORS

Oncel Tuzel , Fatih Porikli , Peter Meer

ABSTRACT

We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix. More... »

PAGES

589-600

References to SciGraph publications

  • 2001-06. Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1998-01. EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2003. A Metric for Covariance Matrices in GEODESY-THE CHALLENGE OF THE 3RD MILLENNIUM
  • Book

    TITLE

    Computer Vision – ECCV 2006

    ISBN

    978-3-540-33834-5
    978-3-540-33835-2

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/11744047_45

    DOI

    http://dx.doi.org/10.1007/11744047_45

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1007677236


    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/2008/0801", 
            "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/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Mitsubishi Electric (United States)", 
              "id": "https://www.grid.ac/institutes/grid.466925.a", 
              "name": [
                "Computer Science Department, USA", 
                "Mitsubishi Electric Research Laboratories, 02139, Cambridge, MA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tuzel", 
            "givenName": "Oncel", 
            "id": "sg:person.01362254313.69", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01362254313.69"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Mitsubishi Electric (United States)", 
              "id": "https://www.grid.ac/institutes/grid.466925.a", 
              "name": [
                "Mitsubishi Electric Research Laboratories, 02139, Cambridge, MA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Porikli", 
            "givenName": "Fatih", 
            "id": "sg:person.0636650213.92", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0636650213.92"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Rutgers University", 
              "id": "https://www.grid.ac/institutes/grid.430387.b", 
              "name": [
                "Computer Science Department, USA", 
                "Electrical and Computer Engineering Department, Rutgers University, 08854, Piscataway, NJ, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Meer", 
            "givenName": "Peter", 
            "id": "sg:person.01302754400.24", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01302754400.24"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1007939232436", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044450893", 
              "https://doi.org/10.1023/a:1007939232436"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1011126920638", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046312359", 
              "https://doi.org/10.1023/a:1011126920638"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-662-05296-9_31", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052329830", 
              "https://doi.org/10.1007/978-3-662-05296-9_31"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmc.1977.4309663", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052358347"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052687286", 
              "https://doi.org/10.1023/b:visi.0000029664.99615.94"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.254061", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061155931"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2004.2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742707"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.1991.139758", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086328381"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2001.990517", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093187020"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2003.1238382", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093204290"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.287", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093459358"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2001.990922", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095591703"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2000.854761", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095616234"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.188", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095717805"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2006", 
        "datePublishedReg": "2006-01-01", 
        "description": "We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.", 
        "editor": [
          {
            "familyName": "Leonardis", 
            "givenName": "Ale\u0161", 
            "type": "Person"
          }, 
          {
            "familyName": "Bischof", 
            "givenName": "Horst", 
            "type": "Person"
          }, 
          {
            "familyName": "Pinz", 
            "givenName": "Axel", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/11744047_45", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-540-33834-5", 
            "978-3-540-33835-2"
          ], 
          "name": "Computer Vision \u2013 ECCV 2006", 
          "type": "Book"
        }, 
        "name": "Region Covariance: A Fast Descriptor for Detection and Classification", 
        "pagination": "589-600", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1007677236"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/11744047_45"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "2491c35e13d72c5057dbe3b661b192b08f913c39519b16b7c19d086973010ae6"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/11744047_45", 
          "https://app.dimensions.ai/details/publication/pub.1007677236"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T07:31", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000356_0000000356/records_57889_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F11744047_45"
      }
    ]
     

    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.10.1007/11744047_45'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11744047_45'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11744047_45'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11744047_45'


     

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

    140 TRIPLES      23 PREDICATES      41 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/11744047_45 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd95c8374ed37483d81600f4425fb4ec1
    4 schema:citation sg:pub.10.1007/978-3-662-05296-9_31
    5 sg:pub.10.1023/a:1007939232436
    6 sg:pub.10.1023/a:1011126920638
    7 sg:pub.10.1023/b:visi.0000029664.99615.94
    8 https://doi.org/10.1109/34.254061
    9 https://doi.org/10.1109/cvpr.1991.139758
    10 https://doi.org/10.1109/cvpr.2000.854761
    11 https://doi.org/10.1109/cvpr.2001.990517
    12 https://doi.org/10.1109/cvpr.2001.990922
    13 https://doi.org/10.1109/cvpr.2005.188
    14 https://doi.org/10.1109/cvpr.2005.287
    15 https://doi.org/10.1109/iccv.2003.1238382
    16 https://doi.org/10.1109/tpami.2004.2
    17 https://doi.org/10.1109/tsmc.1977.4309663
    18 schema:datePublished 2006
    19 schema:datePublishedReg 2006-01-01
    20 schema:description We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.
    21 schema:editor Nf3fa1b7429174a1f81450fc7a4e72e7d
    22 schema:genre chapter
    23 schema:inLanguage en
    24 schema:isAccessibleForFree true
    25 schema:isPartOf N31eae6f1f26d430c92b0df72b09d4ad4
    26 schema:name Region Covariance: A Fast Descriptor for Detection and Classification
    27 schema:pagination 589-600
    28 schema:productId N44d52f4171c543098a6dc2dbb0759eac
    29 N61f1ad9bc59d40268de26b06f182122f
    30 Nf63c8ee687f849cea9c10bea2bfa3625
    31 schema:publisher N9257107028ad46edb397a2137272b24c
    32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007677236
    33 https://doi.org/10.1007/11744047_45
    34 schema:sdDatePublished 2019-04-16T07:31
    35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    36 schema:sdPublisher N87f09229b1404e1bbd08ded000de1ac1
    37 schema:url https://link.springer.com/10.1007%2F11744047_45
    38 sgo:license sg:explorer/license/
    39 sgo:sdDataset chapters
    40 rdf:type schema:Chapter
    41 N0da5d0a19da1406ea62ff7e9f9ef9a91 rdf:first N6cb73f738cc141bfb8aaa98582f70bcf
    42 rdf:rest rdf:nil
    43 N23ad539fe25d447ea8c6ac813b6b6587 rdf:first sg:person.01302754400.24
    44 rdf:rest rdf:nil
    45 N31eae6f1f26d430c92b0df72b09d4ad4 schema:isbn 978-3-540-33834-5
    46 978-3-540-33835-2
    47 schema:name Computer Vision – ECCV 2006
    48 rdf:type schema:Book
    49 N43e7a49bf0ee4888a6a929115db9f4b7 schema:familyName Leonardis
    50 schema:givenName Aleš
    51 rdf:type schema:Person
    52 N44d52f4171c543098a6dc2dbb0759eac schema:name doi
    53 schema:value 10.1007/11744047_45
    54 rdf:type schema:PropertyValue
    55 N61f1ad9bc59d40268de26b06f182122f schema:name dimensions_id
    56 schema:value pub.1007677236
    57 rdf:type schema:PropertyValue
    58 N6cb73f738cc141bfb8aaa98582f70bcf schema:familyName Pinz
    59 schema:givenName Axel
    60 rdf:type schema:Person
    61 N87f09229b1404e1bbd08ded000de1ac1 schema:name Springer Nature - SN SciGraph project
    62 rdf:type schema:Organization
    63 N9257107028ad46edb397a2137272b24c schema:location Berlin, Heidelberg
    64 schema:name Springer Berlin Heidelberg
    65 rdf:type schema:Organisation
    66 N9b3a55e852f549789a075761ce908741 schema:familyName Bischof
    67 schema:givenName Horst
    68 rdf:type schema:Person
    69 Na25c666a74334237adf2403b2d78df9c rdf:first sg:person.0636650213.92
    70 rdf:rest N23ad539fe25d447ea8c6ac813b6b6587
    71 Nb0b91d5d0612474fb07301b8bb48a25e rdf:first N9b3a55e852f549789a075761ce908741
    72 rdf:rest N0da5d0a19da1406ea62ff7e9f9ef9a91
    73 Nd95c8374ed37483d81600f4425fb4ec1 rdf:first sg:person.01362254313.69
    74 rdf:rest Na25c666a74334237adf2403b2d78df9c
    75 Nf3fa1b7429174a1f81450fc7a4e72e7d rdf:first N43e7a49bf0ee4888a6a929115db9f4b7
    76 rdf:rest Nb0b91d5d0612474fb07301b8bb48a25e
    77 Nf63c8ee687f849cea9c10bea2bfa3625 schema:name readcube_id
    78 schema:value 2491c35e13d72c5057dbe3b661b192b08f913c39519b16b7c19d086973010ae6
    79 rdf:type schema:PropertyValue
    80 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    81 schema:name Information and Computing Sciences
    82 rdf:type schema:DefinedTerm
    83 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    84 schema:name Artificial Intelligence and Image Processing
    85 rdf:type schema:DefinedTerm
    86 sg:person.01302754400.24 schema:affiliation https://www.grid.ac/institutes/grid.430387.b
    87 schema:familyName Meer
    88 schema:givenName Peter
    89 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01302754400.24
    90 rdf:type schema:Person
    91 sg:person.01362254313.69 schema:affiliation https://www.grid.ac/institutes/grid.466925.a
    92 schema:familyName Tuzel
    93 schema:givenName Oncel
    94 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01362254313.69
    95 rdf:type schema:Person
    96 sg:person.0636650213.92 schema:affiliation https://www.grid.ac/institutes/grid.466925.a
    97 schema:familyName Porikli
    98 schema:givenName Fatih
    99 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0636650213.92
    100 rdf:type schema:Person
    101 sg:pub.10.1007/978-3-662-05296-9_31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052329830
    102 https://doi.org/10.1007/978-3-662-05296-9_31
    103 rdf:type schema:CreativeWork
    104 sg:pub.10.1023/a:1007939232436 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044450893
    105 https://doi.org/10.1023/a:1007939232436
    106 rdf:type schema:CreativeWork
    107 sg:pub.10.1023/a:1011126920638 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046312359
    108 https://doi.org/10.1023/a:1011126920638
    109 rdf:type schema:CreativeWork
    110 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    111 https://doi.org/10.1023/b:visi.0000029664.99615.94
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.1109/34.254061 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155931
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1109/cvpr.1991.139758 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086328381
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1109/cvpr.2000.854761 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095616234
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1109/cvpr.2001.990517 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093187020
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1109/cvpr.2001.990922 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095591703
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1109/cvpr.2005.188 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095717805
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1109/cvpr.2005.287 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093459358
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/iccv.2003.1238382 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093204290
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/tpami.2004.2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742707
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/tsmc.1977.4309663 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052358347
    132 rdf:type schema:CreativeWork
    133 https://www.grid.ac/institutes/grid.430387.b schema:alternateName Rutgers University
    134 schema:name Computer Science Department, USA
    135 Electrical and Computer Engineering Department, Rutgers University, 08854, Piscataway, NJ, USA
    136 rdf:type schema:Organization
    137 https://www.grid.ac/institutes/grid.466925.a schema:alternateName Mitsubishi Electric (United States)
    138 schema:name Computer Science Department, USA
    139 Mitsubishi Electric Research Laboratories, 02139, Cambridge, MA, USA
    140 rdf:type schema:Organization
     




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


    ...