Minimal Solutions for Pose Estimation of a Multi-Camera System View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2016

AUTHORS

Gim Hee Lee , Bo Li , Marc Pollefeys , Friedrich Fraundorfer

ABSTRACT

In this paper, we propose a novel formulation to solve the pose estimation problem of a calibrated multi-camera system. The non-central rays that pass through the 3D world points and multi-camera system are elegantly represented as Plücker lines. This allows us to solve for the depth of the points along the Plücker lines with a minimal set of 3-point correspondences. We show that the minimal solution for the depth of the points along the Plücker lines is an 8 degree polynomial that gives up to 8 real solutions. The coordinates of the 3D world points in the multi-camera frame are computed from the known depths. Consequently, the pose of the multi-camera system, i.e. the rigid transformation between the world and multi-camera frames can be obtained from absolute orientation. We also derive a closed-form minimal solution for the absolute orientation. This removes the need for the computationally expensive Singular Value Decompositions (SVD) during the evaluations of the possible solutions for the depths. We identify the correct solution and do robust estimation with RANSAC. Finally, the solution is further refined by including all the inlier correspondences in a non-linear refinement step. We verify our approach by showing comparisons with other existing approaches and results from large-scale real-world datasets. More... »

PAGES

521-538

Book

TITLE

Robotics Research

ISBN

978-3-319-28870-3
978-3-319-28872-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-28872-7_30

DOI

http://dx.doi.org/10.1007/978-3-319-28872-7_30

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1023733355


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": "Swiss Federal Institute of Technology in Zurich", 
          "id": "https://www.grid.ac/institutes/grid.5801.c", 
          "name": [
            "Department of Computer Science, ETH Z\u00fcrich"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Gim Hee", 
        "id": "sg:person.013400202764.27", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013400202764.27"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Swiss Federal Institute of Technology in Zurich", 
          "id": "https://www.grid.ac/institutes/grid.5801.c", 
          "name": [
            "Department of Computer Science, ETH Z\u00fcrich"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Li", 
        "givenName": "Bo", 
        "id": "sg:person.010164741335.48", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010164741335.48"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Swiss Federal Institute of Technology in Zurich", 
          "id": "https://www.grid.ac/institutes/grid.5801.c", 
          "name": [
            "Department of Computer Science, ETH Z\u00fcrich"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pollefeys", 
        "givenName": "Marc", 
        "id": "sg:person.013372156770.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013372156770.67"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Faculty of Civil Engineering and Surveying, Technische Universit\u00e4t M\u00fcnchen"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fraundorfer", 
        "givenName": "Friedrich", 
        "id": "sg:person.016452351373.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016452351373.65"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/358669.358692", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033921345"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cviu.2007.09.014", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040969278"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.784291", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061156983"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2004.34", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061742719"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1364/josaa.4.000629", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1065165477"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2006.264", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093301542"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ismar.2004.6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093335256"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2004.1315081", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093531651"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icra.2013.6631107", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094952694"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2007.4409116", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095670097"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.22.55", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099325590"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.21.22", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099341514"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2016", 
    "datePublishedReg": "2016-01-01", 
    "description": "In this paper, we propose a novel formulation to solve the pose estimation problem of a calibrated multi-camera system. The non-central rays that pass through the 3D world points and multi-camera system are elegantly represented as Pl\u00fccker lines. This allows us to solve for the depth of the points along the Pl\u00fccker lines with a minimal set of 3-point correspondences. We show that the minimal solution for the depth of the points along the Pl\u00fccker lines is an 8 degree polynomial that gives up\u00a0to 8 real solutions. The coordinates of the 3D world points in the multi-camera frame are computed from the known depths. Consequently, the pose of the multi-camera system, i.e. the rigid transformation between the world and multi-camera frames can be obtained from absolute orientation. We also derive a closed-form minimal solution for the absolute orientation. This removes the need for the computationally expensive Singular Value Decompositions (SVD) during the evaluations of the possible solutions for the depths. We identify the correct solution and do robust estimation with RANSAC. Finally, the solution is further refined by including all the inlier correspondences in a non-linear refinement step. We verify our approach by showing comparisons with other existing approaches and results from large-scale real-world datasets.", 
    "editor": [
      {
        "familyName": "Inaba", 
        "givenName": "Masayuki", 
        "type": "Person"
      }, 
      {
        "familyName": "Corke", 
        "givenName": "Peter", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-28872-7_30", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.3786400", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.3771942", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": {
      "isbn": [
        "978-3-319-28870-3", 
        "978-3-319-28872-7"
      ], 
      "name": "Robotics Research", 
      "type": "Book"
    }, 
    "name": "Minimal Solutions for Pose Estimation of a Multi-Camera System", 
    "pagination": "521-538", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-28872-7_30"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "7112342498ac29e2c30c8b730fd9f6078f1acd82ee0d5991d8d209d506c66eae"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1023733355"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-28872-7_30", 
      "https://app.dimensions.ai/details/publication/pub.1023733355"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T21:58", 
    "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_8693_00000257.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-319-28872-7_30"
  }
]
 

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.10.1007/978-3-319-28872-7_30'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-28872-7_30'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-28872-7_30'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-28872-7_30'


 

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

133 TRIPLES      23 PREDICATES      39 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-28872-7_30 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nccddbf1e106b49d5aff4795bd0eca2d8
4 schema:citation https://doi.org/10.1016/j.cviu.2007.09.014
5 https://doi.org/10.1109/34.784291
6 https://doi.org/10.1109/cvpr.2004.1315081
7 https://doi.org/10.1109/cvpr.2006.264
8 https://doi.org/10.1109/iccv.2007.4409116
9 https://doi.org/10.1109/icra.2013.6631107
10 https://doi.org/10.1109/ismar.2004.6
11 https://doi.org/10.1109/tpami.2004.34
12 https://doi.org/10.1145/358669.358692
13 https://doi.org/10.1364/josaa.4.000629
14 https://doi.org/10.5244/c.21.22
15 https://doi.org/10.5244/c.22.55
16 schema:datePublished 2016
17 schema:datePublishedReg 2016-01-01
18 schema:description In this paper, we propose a novel formulation to solve the pose estimation problem of a calibrated multi-camera system. The non-central rays that pass through the 3D world points and multi-camera system are elegantly represented as Plücker lines. This allows us to solve for the depth of the points along the Plücker lines with a minimal set of 3-point correspondences. We show that the minimal solution for the depth of the points along the Plücker lines is an 8 degree polynomial that gives up to 8 real solutions. The coordinates of the 3D world points in the multi-camera frame are computed from the known depths. Consequently, the pose of the multi-camera system, i.e. the rigid transformation between the world and multi-camera frames can be obtained from absolute orientation. We also derive a closed-form minimal solution for the absolute orientation. This removes the need for the computationally expensive Singular Value Decompositions (SVD) during the evaluations of the possible solutions for the depths. We identify the correct solution and do robust estimation with RANSAC. Finally, the solution is further refined by including all the inlier correspondences in a non-linear refinement step. We verify our approach by showing comparisons with other existing approaches and results from large-scale real-world datasets.
19 schema:editor N8b7fd3635fe543c19ace147ab4772737
20 schema:genre chapter
21 schema:inLanguage en
22 schema:isAccessibleForFree false
23 schema:isPartOf N0b8ae138c19e422991b27ad282ec171a
24 schema:name Minimal Solutions for Pose Estimation of a Multi-Camera System
25 schema:pagination 521-538
26 schema:productId N0af7ff2328174e1daf742e4f464d58e7
27 N5a2cd66deaf841398d5fbf86208f96a9
28 Nf9950e26e82b436d80fdf5eaa5622a36
29 schema:publisher N7e52bf272bf0415d940688cca7b2a18d
30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023733355
31 https://doi.org/10.1007/978-3-319-28872-7_30
32 schema:sdDatePublished 2019-04-15T21:58
33 schema:sdLicense https://scigraph.springernature.com/explorer/license/
34 schema:sdPublisher Nb3954c14f2eb4a9aa03702c0aaaa5482
35 schema:url http://link.springer.com/10.1007/978-3-319-28872-7_30
36 sgo:license sg:explorer/license/
37 sgo:sdDataset chapters
38 rdf:type schema:Chapter
39 N083ff0d96a13411abc933019fba67b00 rdf:first sg:person.016452351373.65
40 rdf:rest rdf:nil
41 N0af7ff2328174e1daf742e4f464d58e7 schema:name dimensions_id
42 schema:value pub.1023733355
43 rdf:type schema:PropertyValue
44 N0b8ae138c19e422991b27ad282ec171a schema:isbn 978-3-319-28870-3
45 978-3-319-28872-7
46 schema:name Robotics Research
47 rdf:type schema:Book
48 N16ed67abf5224be791fb3e64a31e6ee9 schema:familyName Corke
49 schema:givenName Peter
50 rdf:type schema:Person
51 N2009523c7a9645e4aef2a1f7ff87bccf rdf:first N16ed67abf5224be791fb3e64a31e6ee9
52 rdf:rest rdf:nil
53 N2ce33fbae640459ab827c9649f125f2d schema:name Faculty of Civil Engineering and Surveying, Technische Universität München
54 rdf:type schema:Organization
55 N559b79567e034e52a082ae693b168ff8 schema:familyName Inaba
56 schema:givenName Masayuki
57 rdf:type schema:Person
58 N5a2cd66deaf841398d5fbf86208f96a9 schema:name doi
59 schema:value 10.1007/978-3-319-28872-7_30
60 rdf:type schema:PropertyValue
61 N7e52bf272bf0415d940688cca7b2a18d schema:location Cham
62 schema:name Springer International Publishing
63 rdf:type schema:Organisation
64 N7f6da657ee0348d4b9003ac1e859983d rdf:first sg:person.010164741335.48
65 rdf:rest Nf5fadc2c3b5c45e4851e724479e38890
66 N8b7fd3635fe543c19ace147ab4772737 rdf:first N559b79567e034e52a082ae693b168ff8
67 rdf:rest N2009523c7a9645e4aef2a1f7ff87bccf
68 Nb3954c14f2eb4a9aa03702c0aaaa5482 schema:name Springer Nature - SN SciGraph project
69 rdf:type schema:Organization
70 Nccddbf1e106b49d5aff4795bd0eca2d8 rdf:first sg:person.013400202764.27
71 rdf:rest N7f6da657ee0348d4b9003ac1e859983d
72 Nf5fadc2c3b5c45e4851e724479e38890 rdf:first sg:person.013372156770.67
73 rdf:rest N083ff0d96a13411abc933019fba67b00
74 Nf9950e26e82b436d80fdf5eaa5622a36 schema:name readcube_id
75 schema:value 7112342498ac29e2c30c8b730fd9f6078f1acd82ee0d5991d8d209d506c66eae
76 rdf:type schema:PropertyValue
77 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
78 schema:name Information and Computing Sciences
79 rdf:type schema:DefinedTerm
80 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
81 schema:name Artificial Intelligence and Image Processing
82 rdf:type schema:DefinedTerm
83 sg:grant.3771942 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-28872-7_30
84 rdf:type schema:MonetaryGrant
85 sg:grant.3786400 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-28872-7_30
86 rdf:type schema:MonetaryGrant
87 sg:person.010164741335.48 schema:affiliation https://www.grid.ac/institutes/grid.5801.c
88 schema:familyName Li
89 schema:givenName Bo
90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010164741335.48
91 rdf:type schema:Person
92 sg:person.013372156770.67 schema:affiliation https://www.grid.ac/institutes/grid.5801.c
93 schema:familyName Pollefeys
94 schema:givenName Marc
95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013372156770.67
96 rdf:type schema:Person
97 sg:person.013400202764.27 schema:affiliation https://www.grid.ac/institutes/grid.5801.c
98 schema:familyName Lee
99 schema:givenName Gim Hee
100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013400202764.27
101 rdf:type schema:Person
102 sg:person.016452351373.65 schema:affiliation N2ce33fbae640459ab827c9649f125f2d
103 schema:familyName Fraundorfer
104 schema:givenName Friedrich
105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016452351373.65
106 rdf:type schema:Person
107 https://doi.org/10.1016/j.cviu.2007.09.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040969278
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1109/34.784291 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061156983
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/cvpr.2004.1315081 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093531651
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1109/cvpr.2006.264 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093301542
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1109/iccv.2007.4409116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095670097
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1109/icra.2013.6631107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094952694
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1109/ismar.2004.6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093335256
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1109/tpami.2004.34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742719
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1145/358669.358692 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033921345
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1364/josaa.4.000629 schema:sameAs https://app.dimensions.ai/details/publication/pub.1065165477
126 rdf:type schema:CreativeWork
127 https://doi.org/10.5244/c.21.22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099341514
128 rdf:type schema:CreativeWork
129 https://doi.org/10.5244/c.22.55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325590
130 rdf:type schema:CreativeWork
131 https://www.grid.ac/institutes/grid.5801.c schema:alternateName Swiss Federal Institute of Technology in Zurich
132 schema:name Department of Computer Science, ETH Zürich
133 rdf:type schema:Organization
 




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


...