Inverse Composition for Multi-kernel Tracking View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2006

AUTHORS

Rémi Megret , Mounia Mikram , Yannick Berthoumieu

ABSTRACT

Existing multi-kernel tracking methods are based on a forwards additive motion model formulation. However this approach suffers from the need to estimate an update matrix for each iteration. This paper presents a general framework that extends the existing approach and that allows to introduce a new inverse compositional formulation which shifts the computation of the update matrix to a one time initialisation step. The proposed approach thus reduces the computational complexity of each iteration, compared to the existing forwards approach. The approaches are compared both in terms of algorithmic complexity and quality of the estimation. More... »

PAGES

480-491

References to SciGraph publications

  • 2004-02. Lucas-Kanade 20 Years On: A Unifying Framework in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2002. Color-Based Probabilistic Tracking in COMPUTER VISION — ECCV 2002
  • Book

    TITLE

    Computer Vision, Graphics and Image Processing

    ISBN

    978-3-540-68301-8
    978-3-540-68302-5

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/11949619_43

    DOI

    http://dx.doi.org/10.1007/11949619_43

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1024847760


    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/2008/0802", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Computation Theory and Mathematics", 
            "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": "University of Bordeaux", 
              "id": "https://www.grid.ac/institutes/grid.412041.2", 
              "name": [
                "UMR 5131, Laboratoire d\u2019Automatique, Productique et Signal, Universit\u00e9 Bordeaux 1/ENSEIRB, Talence, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Megret", 
            "givenName": "R\u00e9mi", 
            "id": "sg:person.015455063145.04", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015455063145.04"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Bordeaux", 
              "id": "https://www.grid.ac/institutes/grid.412041.2", 
              "name": [
                "UMR 5131, Laboratoire d\u2019Automatique, Productique et Signal, Universit\u00e9 Bordeaux 1/ENSEIRB, Talence, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mikram", 
            "givenName": "Mounia", 
            "id": "sg:person.010425301173.29", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010425301173.29"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Bordeaux", 
              "id": "https://www.grid.ac/institutes/grid.412041.2", 
              "name": [
                "UMR 5131, Laboratoire d\u2019Automatique, Productique et Signal, Universit\u00e9 Bordeaux 1/ENSEIRB, Talence, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Berthoumieu", 
            "givenName": "Yannick", 
            "id": "sg:person.010636166221.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010636166221.26"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/3-540-47969-4_44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013439571", 
              "https://doi.org/10.1007/3-540-47969-4_44"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000011205.11775.fd", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039145888", 
              "https://doi.org/10.1023/b:visi.0000011205.11775.fd"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2002.1017625", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742398"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2003.1195991", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742511"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2004.1262335", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742668"
            ], 
            "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.2004.1315112", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093348562"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.242", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093794478"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2001.990652", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094583216"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.162", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095244632"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.65", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095432958"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2003.1211432", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095573206"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2006", 
        "datePublishedReg": "2006-01-01", 
        "description": "Existing multi-kernel tracking methods are based on a forwards additive motion model formulation. However this approach suffers from the need to estimate an update matrix for each iteration. This paper presents a general framework that extends the existing approach and that allows to introduce a new inverse compositional formulation which shifts the computation of the update matrix to a one time initialisation step. The proposed approach thus reduces the computational complexity of each iteration, compared to the existing forwards approach. The approaches are compared both in terms of algorithmic complexity and quality of the estimation.", 
        "editor": [
          {
            "familyName": "Kalra", 
            "givenName": "Prem K.", 
            "type": "Person"
          }, 
          {
            "familyName": "Peleg", 
            "givenName": "Shmuel", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/11949619_43", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-540-68301-8", 
            "978-3-540-68302-5"
          ], 
          "name": "Computer Vision, Graphics and Image Processing", 
          "type": "Book"
        }, 
        "name": "Inverse Composition for Multi-kernel Tracking", 
        "pagination": "480-491", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/11949619_43"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "76603e4d0386cf2980cb8fb93792f0e467f9947c2466fbaa11958d5989373094"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1024847760"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/11949619_43", 
          "https://app.dimensions.ai/details/publication/pub.1024847760"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T11:08", 
        "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/v90/0000000001_0000000264/records_8659_00000559.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/11949619_43"
      }
    ]
     

    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.10.1007/11949619_43'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11949619_43'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11949619_43'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11949619_43'


     

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

    122 TRIPLES      23 PREDICATES      39 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/11949619_43 schema:about anzsrc-for:08
    2 anzsrc-for:0802
    3 schema:author N0d684a1760c54c2cbabb0fa6236e2eaf
    4 schema:citation sg:pub.10.1007/3-540-47969-4_44
    5 sg:pub.10.1023/b:visi.0000011205.11775.fd
    6 https://doi.org/10.1109/cvpr.2001.990652
    7 https://doi.org/10.1109/cvpr.2003.1211432
    8 https://doi.org/10.1109/cvpr.2004.1315112
    9 https://doi.org/10.1109/cvpr.2005.242
    10 https://doi.org/10.1109/cvpr.2005.65
    11 https://doi.org/10.1109/cvpr.2006.162
    12 https://doi.org/10.1109/tpami.2002.1017625
    13 https://doi.org/10.1109/tpami.2003.1195991
    14 https://doi.org/10.1109/tpami.2004.1262335
    15 https://doi.org/10.1109/tpami.2004.2
    16 schema:datePublished 2006
    17 schema:datePublishedReg 2006-01-01
    18 schema:description Existing multi-kernel tracking methods are based on a forwards additive motion model formulation. However this approach suffers from the need to estimate an update matrix for each iteration. This paper presents a general framework that extends the existing approach and that allows to introduce a new inverse compositional formulation which shifts the computation of the update matrix to a one time initialisation step. The proposed approach thus reduces the computational complexity of each iteration, compared to the existing forwards approach. The approaches are compared both in terms of algorithmic complexity and quality of the estimation.
    19 schema:editor N642a358284be48b3babf9292ee15cac0
    20 schema:genre chapter
    21 schema:inLanguage en
    22 schema:isAccessibleForFree true
    23 schema:isPartOf Nfcdc0dab872e4f039a268516d2433b2c
    24 schema:name Inverse Composition for Multi-kernel Tracking
    25 schema:pagination 480-491
    26 schema:productId N17f457f57d7446068174396c0d063e7a
    27 N53295dd6ff4d4e79912493b6a93898f8
    28 Ne00d123ddcbf451a93a4fbb1f7fcca11
    29 schema:publisher Nf86e2eee73ee4a7abd19e76ee3d9eb48
    30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024847760
    31 https://doi.org/10.1007/11949619_43
    32 schema:sdDatePublished 2019-04-15T11:08
    33 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    34 schema:sdPublisher Nabd4e4dbaa5443b4a5bfcb4f71c94dcd
    35 schema:url http://link.springer.com/10.1007/11949619_43
    36 sgo:license sg:explorer/license/
    37 sgo:sdDataset chapters
    38 rdf:type schema:Chapter
    39 N08f3ba965fd54443bb21046ee92a225d rdf:first sg:person.010425301173.29
    40 rdf:rest Na784faa494eb4bed8c3a7beb2c3c04b3
    41 N0d684a1760c54c2cbabb0fa6236e2eaf rdf:first sg:person.015455063145.04
    42 rdf:rest N08f3ba965fd54443bb21046ee92a225d
    43 N17f457f57d7446068174396c0d063e7a schema:name dimensions_id
    44 schema:value pub.1024847760
    45 rdf:type schema:PropertyValue
    46 N53295dd6ff4d4e79912493b6a93898f8 schema:name doi
    47 schema:value 10.1007/11949619_43
    48 rdf:type schema:PropertyValue
    49 N642a358284be48b3babf9292ee15cac0 rdf:first N9d2ac792f9694e7997eb5e4523f44efa
    50 rdf:rest Nb29deb1367bb48a98d57aa018b3120d4
    51 N9d2ac792f9694e7997eb5e4523f44efa schema:familyName Kalra
    52 schema:givenName Prem K.
    53 rdf:type schema:Person
    54 Na3a6d2ba9abd4f8a9169e32a5404e5fb schema:familyName Peleg
    55 schema:givenName Shmuel
    56 rdf:type schema:Person
    57 Na784faa494eb4bed8c3a7beb2c3c04b3 rdf:first sg:person.010636166221.26
    58 rdf:rest rdf:nil
    59 Nabd4e4dbaa5443b4a5bfcb4f71c94dcd schema:name Springer Nature - SN SciGraph project
    60 rdf:type schema:Organization
    61 Nb29deb1367bb48a98d57aa018b3120d4 rdf:first Na3a6d2ba9abd4f8a9169e32a5404e5fb
    62 rdf:rest rdf:nil
    63 Ne00d123ddcbf451a93a4fbb1f7fcca11 schema:name readcube_id
    64 schema:value 76603e4d0386cf2980cb8fb93792f0e467f9947c2466fbaa11958d5989373094
    65 rdf:type schema:PropertyValue
    66 Nf86e2eee73ee4a7abd19e76ee3d9eb48 schema:location Berlin, Heidelberg
    67 schema:name Springer Berlin Heidelberg
    68 rdf:type schema:Organisation
    69 Nfcdc0dab872e4f039a268516d2433b2c schema:isbn 978-3-540-68301-8
    70 978-3-540-68302-5
    71 schema:name Computer Vision, Graphics and Image Processing
    72 rdf:type schema:Book
    73 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    74 schema:name Information and Computing Sciences
    75 rdf:type schema:DefinedTerm
    76 anzsrc-for:0802 schema:inDefinedTermSet anzsrc-for:
    77 schema:name Computation Theory and Mathematics
    78 rdf:type schema:DefinedTerm
    79 sg:person.010425301173.29 schema:affiliation https://www.grid.ac/institutes/grid.412041.2
    80 schema:familyName Mikram
    81 schema:givenName Mounia
    82 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010425301173.29
    83 rdf:type schema:Person
    84 sg:person.010636166221.26 schema:affiliation https://www.grid.ac/institutes/grid.412041.2
    85 schema:familyName Berthoumieu
    86 schema:givenName Yannick
    87 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010636166221.26
    88 rdf:type schema:Person
    89 sg:person.015455063145.04 schema:affiliation https://www.grid.ac/institutes/grid.412041.2
    90 schema:familyName Megret
    91 schema:givenName Rémi
    92 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015455063145.04
    93 rdf:type schema:Person
    94 sg:pub.10.1007/3-540-47969-4_44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013439571
    95 https://doi.org/10.1007/3-540-47969-4_44
    96 rdf:type schema:CreativeWork
    97 sg:pub.10.1023/b:visi.0000011205.11775.fd schema:sameAs https://app.dimensions.ai/details/publication/pub.1039145888
    98 https://doi.org/10.1023/b:visi.0000011205.11775.fd
    99 rdf:type schema:CreativeWork
    100 https://doi.org/10.1109/cvpr.2001.990652 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094583216
    101 rdf:type schema:CreativeWork
    102 https://doi.org/10.1109/cvpr.2003.1211432 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095573206
    103 rdf:type schema:CreativeWork
    104 https://doi.org/10.1109/cvpr.2004.1315112 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093348562
    105 rdf:type schema:CreativeWork
    106 https://doi.org/10.1109/cvpr.2005.242 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093794478
    107 rdf:type schema:CreativeWork
    108 https://doi.org/10.1109/cvpr.2005.65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095432958
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1109/cvpr.2006.162 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095244632
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1109/tpami.2002.1017625 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742398
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1109/tpami.2003.1195991 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742511
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1109/tpami.2004.1262335 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742668
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1109/tpami.2004.2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742707
    119 rdf:type schema:CreativeWork
    120 https://www.grid.ac/institutes/grid.412041.2 schema:alternateName University of Bordeaux
    121 schema:name UMR 5131, Laboratoire d’Automatique, Productique et Signal, Université Bordeaux 1/ENSEIRB, Talence, France
    122 rdf:type schema:Organization
     




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


    ...