Detecting, localizing and grouping repeated scene elements from an image View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1996

AUTHORS

Thomas Leung , Jitendra Malik

ABSTRACT

This paper presents an algorithm for detecting, localizing and grouping instances of repeated scene elements. The grouping is represented by a graph where nodes correspond to individual elements and arcs join spatially neighboring elements. Associated with each arc is an affine map that best transforms the image patch at one location to the other. The approach we propose consists of 4 steps: (1) detecting “interesting” elements in the image; (2) matching elements with their neighbors and estimating the affine transform between them; (3) growing the element to form a more distinctive unit; and (4) grouping the elements. The idea is analogous to tracking in dynamic imagery. In our context, we “track” an element to spatially neighboring locations in one image, while in temporal tracking, one would perform the search in neighboring image frames. More... »

PAGES

546-555

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bfb0015565

DOI

http://dx.doi.org/10.1007/bfb0015565

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1037014904


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 Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Leung", 
        "givenName": "Thomas", 
        "id": "sg:person.016034550437.98", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016034550437.98"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Malik", 
        "givenName": "Jitendra", 
        "id": "sg:person.01364521761.84", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01364521761.84"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1996", 
    "datePublishedReg": "1996-01-01", 
    "description": "This paper presents an algorithm for detecting, localizing and grouping instances of repeated scene elements. The grouping is represented by a graph where nodes correspond to individual elements and arcs join spatially neighboring elements. Associated with each arc is an affine map that best transforms the image patch at one location to the other. The approach we propose consists of 4 steps: (1) detecting \u201cinteresting\u201d elements in the image; (2) matching elements with their neighbors and estimating the affine transform between them; (3) growing the element to form a more distinctive unit; and (4) grouping the elements. The idea is analogous to tracking in dynamic imagery. In our context, we \u201ctrack\u201d an element to spatially neighboring locations in one image, while in temporal tracking, one would perform the search in neighboring image frames.", 
    "editor": [
      {
        "familyName": "Buxton", 
        "givenName": "Bernard", 
        "type": "Person"
      }, 
      {
        "familyName": "Cipolla", 
        "givenName": "Roberto", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/bfb0015565", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-61122-6", 
        "978-3-540-49949-7"
      ], 
      "name": "Computer Vision \u2014 ECCV '96", 
      "type": "Book"
    }, 
    "keywords": [
      "scene elements", 
      "image frames", 
      "image patches", 
      "affine transform", 
      "temporal tracking", 
      "dynamic imagery", 
      "images", 
      "algorithm", 
      "localizing", 
      "graph", 
      "tracking", 
      "nodes", 
      "neighbors", 
      "individual elements", 
      "instances", 
      "search", 
      "imagery", 
      "frame", 
      "maps", 
      "location", 
      "transform", 
      "idea", 
      "elements", 
      "context", 
      "affine maps", 
      "step", 
      "grouping", 
      "consist", 
      "patches", 
      "units", 
      "arc", 
      "distinctive units", 
      "paper", 
      "approach"
    ], 
    "name": "Detecting, localizing and grouping repeated scene elements from an image", 
    "pagination": "546-555", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1037014904"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bfb0015565"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/bfb0015565", 
      "https://app.dimensions.ai/details/publication/pub.1037014904"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:14", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/chapter/chapter_241.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/bfb0015565"
  }
]
 

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/bfb0015565'

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/bfb0015565'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bfb0015565'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bfb0015565'


 

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

105 TRIPLES      22 PREDICATES      59 URIs      52 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bfb0015565 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nc399df199fe1480e8ee0c45b93cccbd0
4 schema:datePublished 1996
5 schema:datePublishedReg 1996-01-01
6 schema:description This paper presents an algorithm for detecting, localizing and grouping instances of repeated scene elements. The grouping is represented by a graph where nodes correspond to individual elements and arcs join spatially neighboring elements. Associated with each arc is an affine map that best transforms the image patch at one location to the other. The approach we propose consists of 4 steps: (1) detecting “interesting” elements in the image; (2) matching elements with their neighbors and estimating the affine transform between them; (3) growing the element to form a more distinctive unit; and (4) grouping the elements. The idea is analogous to tracking in dynamic imagery. In our context, we “track” an element to spatially neighboring locations in one image, while in temporal tracking, one would perform the search in neighboring image frames.
7 schema:editor N401cf8d6b9ef4b3ba3994e93d00ab437
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N25ec32534bf4457895323fffb6d4420f
11 schema:keywords affine maps
12 affine transform
13 algorithm
14 approach
15 arc
16 consist
17 context
18 distinctive units
19 dynamic imagery
20 elements
21 frame
22 graph
23 grouping
24 idea
25 image frames
26 image patches
27 imagery
28 images
29 individual elements
30 instances
31 localizing
32 location
33 maps
34 neighbors
35 nodes
36 paper
37 patches
38 scene elements
39 search
40 step
41 temporal tracking
42 tracking
43 transform
44 units
45 schema:name Detecting, localizing and grouping repeated scene elements from an image
46 schema:pagination 546-555
47 schema:productId N47adf604628e4a6bbc00c0429a0a345c
48 N57eba9b12d8847d2ab37221e2931ea30
49 schema:publisher N1db715aced4c482892aa5b85f25ca6f3
50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037014904
51 https://doi.org/10.1007/bfb0015565
52 schema:sdDatePublished 2022-11-24T21:14
53 schema:sdLicense https://scigraph.springernature.com/explorer/license/
54 schema:sdPublisher N038b637fd3b244508f271b08c564fe7b
55 schema:url https://doi.org/10.1007/bfb0015565
56 sgo:license sg:explorer/license/
57 sgo:sdDataset chapters
58 rdf:type schema:Chapter
59 N038b637fd3b244508f271b08c564fe7b schema:name Springer Nature - SN SciGraph project
60 rdf:type schema:Organization
61 N03cb8fbcaaf647dba73d39ca79c54844 rdf:first sg:person.01364521761.84
62 rdf:rest rdf:nil
63 N1db715aced4c482892aa5b85f25ca6f3 schema:name Springer Nature
64 rdf:type schema:Organisation
65 N25ec32534bf4457895323fffb6d4420f schema:isbn 978-3-540-49949-7
66 978-3-540-61122-6
67 schema:name Computer Vision — ECCV '96
68 rdf:type schema:Book
69 N2bb9d7fe91124d4a8c3e5dfa09973261 schema:familyName Cipolla
70 schema:givenName Roberto
71 rdf:type schema:Person
72 N401cf8d6b9ef4b3ba3994e93d00ab437 rdf:first N614f6661281b4dbe8b38a8e752da611f
73 rdf:rest Nab6307243afd46cb9a8b205ecd8d6ed9
74 N47adf604628e4a6bbc00c0429a0a345c schema:name dimensions_id
75 schema:value pub.1037014904
76 rdf:type schema:PropertyValue
77 N57eba9b12d8847d2ab37221e2931ea30 schema:name doi
78 schema:value 10.1007/bfb0015565
79 rdf:type schema:PropertyValue
80 N614f6661281b4dbe8b38a8e752da611f schema:familyName Buxton
81 schema:givenName Bernard
82 rdf:type schema:Person
83 Nab6307243afd46cb9a8b205ecd8d6ed9 rdf:first N2bb9d7fe91124d4a8c3e5dfa09973261
84 rdf:rest rdf:nil
85 Nc399df199fe1480e8ee0c45b93cccbd0 rdf:first sg:person.016034550437.98
86 rdf:rest N03cb8fbcaaf647dba73d39ca79c54844
87 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
88 schema:name Information and Computing Sciences
89 rdf:type schema:DefinedTerm
90 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
91 schema:name Artificial Intelligence and Image Processing
92 rdf:type schema:DefinedTerm
93 sg:person.01364521761.84 schema:affiliation grid-institutes:grid.47840.3f
94 schema:familyName Malik
95 schema:givenName Jitendra
96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01364521761.84
97 rdf:type schema:Person
98 sg:person.016034550437.98 schema:affiliation grid-institutes:grid.47840.3f
99 schema:familyName Leung
100 schema:givenName Thomas
101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016034550437.98
102 rdf:type schema:Person
103 grid-institutes:grid.47840.3f schema:alternateName Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA
104 schema:name Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, 94720, Berkeley, CA
105 rdf:type schema:Organization
 




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


...