The viewpoint consistency constraint View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1987-03

AUTHORS

David G. Lowe

ABSTRACT

The viewpoint consistency constraint requires that the locations of all object features in an image must be consistent with projection from a single viewpoint. The application of this constraint is central to the problem of achieving robust recognition, since it allows the spatial information in an image to be compared with prior knowledge of an object's shape to the full degree of available image resolution. In addition, the constraint greatly reduces the size of the search space during model-based matching by allowing a few initial matches to provide tight constraints for the locations of other model features. Unfortunately, while simple to state, this constraint has seldom been effectively applied in model-based computer vision systems. This paper reviews the history of attempts to make use of the viewpoint consistency constraint and then describes a number of new techniques for applying it to the process of model-based recognition. A method is presented for probabilistically evaluating new potential matches to extend and refine an initial viewpoint estimate. This evaluation allows the model-based verification process to proceed without the expense of backtracking or search. It will be shown that the effective application of the viewpoint consistency constraint, in conjunction with bottom-up image description based upon principles of perceptual organization, can lead to robust three-dimensional object recognition from single gray-scale images. More... »

PAGES

57-72

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bf00128526

DOI

http://dx.doi.org/10.1007/bf00128526

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1004547452


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": "Courant Institute of Mathematical Sciences", 
          "id": "https://www.grid.ac/institutes/grid.482020.c", 
          "name": [
            "Courant Institute of Mathematical Sciences, New York University, 251 Mercer Street, 10012, New York, NY"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lowe", 
        "givenName": "David G.", 
        "id": "sg:person.011623556032.50", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011623556032.50"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/0004-3702(81)90031-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004895212"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/027836498400300301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010407489"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/027836498400300301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010407489"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(81)90028-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020015186"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/358669.358692", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033921345"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1476589.1476631", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035186929"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0096-1523.1.3.214", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035937976"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1098/rspb.1980.0020", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038702537"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(73)90003-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042376059"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(73)90003-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042376059"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4613-2551-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051061361", 
          "https://doi.org/10.1007/978-1-4613-2551-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4613-2551-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051061361", 
          "https://doi.org/10.1007/978-1-4613-2551-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0004-3702(71)90005-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053196033"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog0701_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053486805"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog0701_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053486805"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/scientificamerican1284-106", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1056645015", 
          "https://doi.org/10.1038/scientificamerican1284-106"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1068/p120203", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058162540"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1068/p120203", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058162540"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.171.3972.701", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062502296"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1987-03", 
    "datePublishedReg": "1987-03-01", 
    "description": "The viewpoint consistency constraint requires that the locations of all object features in an image must be consistent with projection from a single viewpoint. The application of this constraint is central to the problem of achieving robust recognition, since it allows the spatial information in an image to be compared with prior knowledge of an object's shape to the full degree of available image resolution. In addition, the constraint greatly reduces the size of the search space during model-based matching by allowing a few initial matches to provide tight constraints for the locations of other model features. Unfortunately, while simple to state, this constraint has seldom been effectively applied in model-based computer vision systems. This paper reviews the history of attempts to make use of the viewpoint consistency constraint and then describes a number of new techniques for applying it to the process of model-based recognition. A method is presented for probabilistically evaluating new potential matches to extend and refine an initial viewpoint estimate. This evaluation allows the model-based verification process to proceed without the expense of backtracking or search. It will be shown that the effective application of the viewpoint consistency constraint, in conjunction with bottom-up image description based upon principles of perceptual organization, can lead to robust three-dimensional object recognition from single gray-scale images.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/bf00128526", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "1"
      }
    ], 
    "name": "The viewpoint consistency constraint", 
    "pagination": "57-72", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "15ab5c77f9a409ff5b28913ca06996cb0637e4b45f7d4ef7c2eb82a332c87d3f"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bf00128526"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1004547452"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/bf00128526", 
      "https://app.dimensions.ai/details/publication/pub.1004547452"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T14:02", 
    "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/v90/0000000371_0000000371/records_130831_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007/BF00128526"
  }
]
 

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/bf00128526'

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/bf00128526'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bf00128526'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bf00128526'


 

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

105 TRIPLES      21 PREDICATES      41 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bf00128526 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N7729078cabe348cba8f4cd860934cc7b
4 schema:citation sg:pub.10.1007/978-1-4613-2551-2
5 sg:pub.10.1038/scientificamerican1284-106
6 https://doi.org/10.1016/0004-3702(71)90005-1
7 https://doi.org/10.1016/0004-3702(73)90003-9
8 https://doi.org/10.1016/0004-3702(81)90028-x
9 https://doi.org/10.1016/0004-3702(81)90031-x
10 https://doi.org/10.1037/0096-1523.1.3.214
11 https://doi.org/10.1068/p120203
12 https://doi.org/10.1098/rspb.1980.0020
13 https://doi.org/10.1126/science.171.3972.701
14 https://doi.org/10.1145/1476589.1476631
15 https://doi.org/10.1145/358669.358692
16 https://doi.org/10.1177/027836498400300301
17 https://doi.org/10.1207/s15516709cog0701_3
18 schema:datePublished 1987-03
19 schema:datePublishedReg 1987-03-01
20 schema:description The viewpoint consistency constraint requires that the locations of all object features in an image must be consistent with projection from a single viewpoint. The application of this constraint is central to the problem of achieving robust recognition, since it allows the spatial information in an image to be compared with prior knowledge of an object's shape to the full degree of available image resolution. In addition, the constraint greatly reduces the size of the search space during model-based matching by allowing a few initial matches to provide tight constraints for the locations of other model features. Unfortunately, while simple to state, this constraint has seldom been effectively applied in model-based computer vision systems. This paper reviews the history of attempts to make use of the viewpoint consistency constraint and then describes a number of new techniques for applying it to the process of model-based recognition. A method is presented for probabilistically evaluating new potential matches to extend and refine an initial viewpoint estimate. This evaluation allows the model-based verification process to proceed without the expense of backtracking or search. It will be shown that the effective application of the viewpoint consistency constraint, in conjunction with bottom-up image description based upon principles of perceptual organization, can lead to robust three-dimensional object recognition from single gray-scale images.
21 schema:genre research_article
22 schema:inLanguage en
23 schema:isAccessibleForFree false
24 schema:isPartOf N582eb24d97fb4ddbac17cb25755bfa7d
25 N6376d3767ad04d1f89ab9eba305f75e6
26 sg:journal.1032807
27 schema:name The viewpoint consistency constraint
28 schema:pagination 57-72
29 schema:productId N363343ba746746da904a702d72e72930
30 N4cba7d13ca0e4e5a85d73a7a17530031
31 Nbc44acb155b74d8ab72546c2682e8ed3
32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004547452
33 https://doi.org/10.1007/bf00128526
34 schema:sdDatePublished 2019-04-11T14:02
35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
36 schema:sdPublisher N160506a715114aac81a0ade2827331f1
37 schema:url http://link.springer.com/10.1007/BF00128526
38 sgo:license sg:explorer/license/
39 sgo:sdDataset articles
40 rdf:type schema:ScholarlyArticle
41 N160506a715114aac81a0ade2827331f1 schema:name Springer Nature - SN SciGraph project
42 rdf:type schema:Organization
43 N363343ba746746da904a702d72e72930 schema:name readcube_id
44 schema:value 15ab5c77f9a409ff5b28913ca06996cb0637e4b45f7d4ef7c2eb82a332c87d3f
45 rdf:type schema:PropertyValue
46 N4cba7d13ca0e4e5a85d73a7a17530031 schema:name doi
47 schema:value 10.1007/bf00128526
48 rdf:type schema:PropertyValue
49 N582eb24d97fb4ddbac17cb25755bfa7d schema:issueNumber 1
50 rdf:type schema:PublicationIssue
51 N6376d3767ad04d1f89ab9eba305f75e6 schema:volumeNumber 1
52 rdf:type schema:PublicationVolume
53 N7729078cabe348cba8f4cd860934cc7b rdf:first sg:person.011623556032.50
54 rdf:rest rdf:nil
55 Nbc44acb155b74d8ab72546c2682e8ed3 schema:name dimensions_id
56 schema:value pub.1004547452
57 rdf:type schema:PropertyValue
58 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
59 schema:name Information and Computing Sciences
60 rdf:type schema:DefinedTerm
61 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
62 schema:name Artificial Intelligence and Image Processing
63 rdf:type schema:DefinedTerm
64 sg:journal.1032807 schema:issn 0920-5691
65 1573-1405
66 schema:name International Journal of Computer Vision
67 rdf:type schema:Periodical
68 sg:person.011623556032.50 schema:affiliation https://www.grid.ac/institutes/grid.482020.c
69 schema:familyName Lowe
70 schema:givenName David G.
71 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011623556032.50
72 rdf:type schema:Person
73 sg:pub.10.1007/978-1-4613-2551-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051061361
74 https://doi.org/10.1007/978-1-4613-2551-2
75 rdf:type schema:CreativeWork
76 sg:pub.10.1038/scientificamerican1284-106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056645015
77 https://doi.org/10.1038/scientificamerican1284-106
78 rdf:type schema:CreativeWork
79 https://doi.org/10.1016/0004-3702(71)90005-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053196033
80 rdf:type schema:CreativeWork
81 https://doi.org/10.1016/0004-3702(73)90003-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042376059
82 rdf:type schema:CreativeWork
83 https://doi.org/10.1016/0004-3702(81)90028-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1020015186
84 rdf:type schema:CreativeWork
85 https://doi.org/10.1016/0004-3702(81)90031-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1004895212
86 rdf:type schema:CreativeWork
87 https://doi.org/10.1037/0096-1523.1.3.214 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035937976
88 rdf:type schema:CreativeWork
89 https://doi.org/10.1068/p120203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058162540
90 rdf:type schema:CreativeWork
91 https://doi.org/10.1098/rspb.1980.0020 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038702537
92 rdf:type schema:CreativeWork
93 https://doi.org/10.1126/science.171.3972.701 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062502296
94 rdf:type schema:CreativeWork
95 https://doi.org/10.1145/1476589.1476631 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035186929
96 rdf:type schema:CreativeWork
97 https://doi.org/10.1145/358669.358692 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033921345
98 rdf:type schema:CreativeWork
99 https://doi.org/10.1177/027836498400300301 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010407489
100 rdf:type schema:CreativeWork
101 https://doi.org/10.1207/s15516709cog0701_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053486805
102 rdf:type schema:CreativeWork
103 https://www.grid.ac/institutes/grid.482020.c schema:alternateName Courant Institute of Mathematical Sciences
104 schema:name Courant Institute of Mathematical Sciences, New York University, 251 Mercer Street, 10012, New York, NY
105 rdf:type schema:Organization
 




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


...