Dense Semi-rigid Scene Flow Estimation from RGBD Images View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2014

AUTHORS

Julian Quiroga , Thomas Brox , Frédéric Devernay , James Crowley

ABSTRACT

Scene flow is defined as the motion field in 3D space, and can be computed from a single view when using an RGBD sensor. We propose a new scene flow approach that exploits the local and piecewise rigidity of real world scenes. By modeling the motion as a field of twists, our method encourages piecewise smooth solutions of rigid body motions. We give a general formulation to solve for local and global rigid motions by jointly using intensity and depth data. In order to deal efficiently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evaluation demonstrates that the proposed method achieves the best results in the most commonly used scene flow benchmark. Through additional experiments we indicate the general applicability of our approach in a variety of different scenarios. More... »

PAGES

567-582

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_37

DOI

http://dx.doi.org/10.1007/978-3-319-10584-0_37

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1009233262


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": "Departamento de Electr\u00f3nica, Pontificia Universidad Javeriana, Colombia", 
          "id": "http://www.grid.ac/institutes/grid.41312.35", 
          "name": [
            "PRIMA team, INRIA, Grenoble, France", 
            "Departamento de Electr\u00f3nica, Pontificia Universidad Javeriana, Colombia"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Quiroga", 
        "givenName": "Julian", 
        "id": "sg:person.01151464171.03", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01151464171.03"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science, University of Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Department of Computer Science, University of Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "PRIMA team, INRIA, Grenoble, France", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "PRIMA team, INRIA, Grenoble, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Devernay", 
        "givenName": "Fr\u00e9d\u00e9ric", 
        "id": "sg:person.013346715753.73", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013346715753.73"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "PRIMA team, INRIA, Grenoble, France", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "PRIMA team, INRIA, Grenoble, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Crowley", 
        "givenName": "James", 
        "id": "sg:person.014722332567.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014722332567.51"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2014", 
    "datePublishedReg": "2014-01-01", 
    "description": "Scene flow is defined as the motion field in 3D space, and can be computed from a single view when using an RGBD sensor. We propose a new scene flow approach that exploits the local and piecewise rigidity of real world scenes. By modeling the motion as a field of twists, our method encourages piecewise smooth solutions of rigid body motions. We give a general formulation to solve for local and global rigid motions by jointly using intensity and depth data. In order to deal efficiently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evaluation demonstrates that the proposed method achieves the best results in the most commonly used scene flow benchmark. Through additional experiments we indicate the general applicability of our approach in a variety of different scenarios.", 
    "editor": [
      {
        "familyName": "Fleet", 
        "givenName": "David", 
        "type": "Person"
      }, 
      {
        "familyName": "Pajdla", 
        "givenName": "Tomas", 
        "type": "Person"
      }, 
      {
        "familyName": "Schiele", 
        "givenName": "Bernt", 
        "type": "Person"
      }, 
      {
        "familyName": "Tuytelaars", 
        "givenName": "Tinne", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-10584-0_37", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-10583-3", 
        "978-3-319-10584-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2014", 
      "type": "Book"
    }, 
    "keywords": [
      "scene flow estimation", 
      "real-world scenes", 
      "RGBD sensor", 
      "global rigid motion", 
      "RGBD images", 
      "scene flow", 
      "single view", 
      "world scenes", 
      "depth data", 
      "motion field", 
      "flow estimation", 
      "flow benchmarks", 
      "different scenarios", 
      "rigid motion", 
      "better results", 
      "body motion", 
      "flow approach", 
      "scene", 
      "camera", 
      "rigid components", 
      "benchmarks", 
      "images", 
      "solver", 
      "scenarios", 
      "general applicability", 
      "sensors", 
      "rigid body motion", 
      "method", 
      "motion", 
      "general formulation", 
      "space", 
      "applicability", 
      "estimation", 
      "field", 
      "solution", 
      "data", 
      "order", 
      "experiments", 
      "view", 
      "evaluation", 
      "variety", 
      "components", 
      "results", 
      "Additional experiments", 
      "formulation", 
      "flow", 
      "smooth solutions", 
      "intensity", 
      "approach", 
      "twist", 
      "rigidity"
    ], 
    "name": "Dense Semi-rigid Scene Flow Estimation from RGBD Images", 
    "pagination": "567-582", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1009233262"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-10584-0_37"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-10584-0_37", 
      "https://app.dimensions.ai/details/publication/pub.1009233262"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-09-02T16:18", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/chapter/chapter_461.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-10584-0_37"
  }
]
 

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.10.1007/978-3-319-10584-0_37'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_37'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_37'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-10584-0_37'


 

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

153 TRIPLES      22 PREDICATES      76 URIs      69 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-10584-0_37 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nf41a8e309d7f42b8874e0f526a0a7792
4 schema:datePublished 2014
5 schema:datePublishedReg 2014-01-01
6 schema:description Scene flow is defined as the motion field in 3D space, and can be computed from a single view when using an RGBD sensor. We propose a new scene flow approach that exploits the local and piecewise rigidity of real world scenes. By modeling the motion as a field of twists, our method encourages piecewise smooth solutions of rigid body motions. We give a general formulation to solve for local and global rigid motions by jointly using intensity and depth data. In order to deal efficiently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evaluation demonstrates that the proposed method achieves the best results in the most commonly used scene flow benchmark. Through additional experiments we indicate the general applicability of our approach in a variety of different scenarios.
7 schema:editor N172db59d48a54cc08ca72047f8439e0f
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf Nb4c86a7d705241ce9a9fa98b1e9c2627
11 schema:keywords Additional experiments
12 RGBD images
13 RGBD sensor
14 applicability
15 approach
16 benchmarks
17 better results
18 body motion
19 camera
20 components
21 data
22 depth data
23 different scenarios
24 estimation
25 evaluation
26 experiments
27 field
28 flow
29 flow approach
30 flow benchmarks
31 flow estimation
32 formulation
33 general applicability
34 general formulation
35 global rigid motion
36 images
37 intensity
38 method
39 motion
40 motion field
41 order
42 real-world scenes
43 results
44 rigid body motion
45 rigid components
46 rigid motion
47 rigidity
48 scenarios
49 scene
50 scene flow
51 scene flow estimation
52 sensors
53 single view
54 smooth solutions
55 solution
56 solver
57 space
58 twist
59 variety
60 view
61 world scenes
62 schema:name Dense Semi-rigid Scene Flow Estimation from RGBD Images
63 schema:pagination 567-582
64 schema:productId N17662d821cf54cad8591434d7649107e
65 N3caec66d4fbd4246bff1efc53b920c48
66 schema:publisher Ne9f9a911d2d142698163b33efda28a5b
67 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009233262
68 https://doi.org/10.1007/978-3-319-10584-0_37
69 schema:sdDatePublished 2022-09-02T16:18
70 schema:sdLicense https://scigraph.springernature.com/explorer/license/
71 schema:sdPublisher Nd6c2305ab5694011ac21b82c1cf8e8b8
72 schema:url https://doi.org/10.1007/978-3-319-10584-0_37
73 sgo:license sg:explorer/license/
74 sgo:sdDataset chapters
75 rdf:type schema:Chapter
76 N0b9b6be5b9c64b9c8cbf2d425a4946e6 schema:familyName Fleet
77 schema:givenName David
78 rdf:type schema:Person
79 N1190e6c124aa454baf1312871ccd29c1 rdf:first N3baea3fb256a45f68f7300e96602b3ff
80 rdf:rest Nbdcbdd37eac54c0ebda43065ab117477
81 N172db59d48a54cc08ca72047f8439e0f rdf:first N0b9b6be5b9c64b9c8cbf2d425a4946e6
82 rdf:rest N1190e6c124aa454baf1312871ccd29c1
83 N17662d821cf54cad8591434d7649107e schema:name doi
84 schema:value 10.1007/978-3-319-10584-0_37
85 rdf:type schema:PropertyValue
86 N1f32edf1d3294ea6b3e20de55ff0ae6a rdf:first sg:person.012443225372.65
87 rdf:rest Nd34815d9259442b4a2ab31c8aa633a6f
88 N20f702a52cef40799e546f2d75d1caf1 rdf:first Nf614d56dc4f14efb9a0c8ffab5ae35af
89 rdf:rest rdf:nil
90 N3baea3fb256a45f68f7300e96602b3ff schema:familyName Pajdla
91 schema:givenName Tomas
92 rdf:type schema:Person
93 N3caec66d4fbd4246bff1efc53b920c48 schema:name dimensions_id
94 schema:value pub.1009233262
95 rdf:type schema:PropertyValue
96 N85f7e333235a47928ac7896eed98b6b9 rdf:first sg:person.014722332567.51
97 rdf:rest rdf:nil
98 Nb4c86a7d705241ce9a9fa98b1e9c2627 schema:isbn 978-3-319-10583-3
99 978-3-319-10584-0
100 schema:name Computer Vision – ECCV 2014
101 rdf:type schema:Book
102 Nbdcbdd37eac54c0ebda43065ab117477 rdf:first Ne1eeea680e9843c982cc55966c9ad4d2
103 rdf:rest N20f702a52cef40799e546f2d75d1caf1
104 Nd34815d9259442b4a2ab31c8aa633a6f rdf:first sg:person.013346715753.73
105 rdf:rest N85f7e333235a47928ac7896eed98b6b9
106 Nd6c2305ab5694011ac21b82c1cf8e8b8 schema:name Springer Nature - SN SciGraph project
107 rdf:type schema:Organization
108 Ne1eeea680e9843c982cc55966c9ad4d2 schema:familyName Schiele
109 schema:givenName Bernt
110 rdf:type schema:Person
111 Ne9f9a911d2d142698163b33efda28a5b schema:name Springer Nature
112 rdf:type schema:Organisation
113 Nf41a8e309d7f42b8874e0f526a0a7792 rdf:first sg:person.01151464171.03
114 rdf:rest N1f32edf1d3294ea6b3e20de55ff0ae6a
115 Nf614d56dc4f14efb9a0c8ffab5ae35af schema:familyName Tuytelaars
116 schema:givenName Tinne
117 rdf:type schema:Person
118 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
119 schema:name Information and Computing Sciences
120 rdf:type schema:DefinedTerm
121 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
122 schema:name Artificial Intelligence and Image Processing
123 rdf:type schema:DefinedTerm
124 sg:person.01151464171.03 schema:affiliation grid-institutes:grid.41312.35
125 schema:familyName Quiroga
126 schema:givenName Julian
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01151464171.03
128 rdf:type schema:Person
129 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
130 schema:familyName Brox
131 schema:givenName Thomas
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
133 rdf:type schema:Person
134 sg:person.013346715753.73 schema:affiliation grid-institutes:None
135 schema:familyName Devernay
136 schema:givenName Frédéric
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013346715753.73
138 rdf:type schema:Person
139 sg:person.014722332567.51 schema:affiliation grid-institutes:None
140 schema:familyName Crowley
141 schema:givenName James
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014722332567.51
143 rdf:type schema:Person
144 grid-institutes:None schema:alternateName PRIMA team, INRIA, Grenoble, France
145 schema:name PRIMA team, INRIA, Grenoble, France
146 rdf:type schema:Organization
147 grid-institutes:grid.41312.35 schema:alternateName Departamento de Electrónica, Pontificia Universidad Javeriana, Colombia
148 schema:name Departamento de Electrónica, Pontificia Universidad Javeriana, Colombia
149 PRIMA team, INRIA, Grenoble, France
150 rdf:type schema:Organization
151 grid-institutes:grid.5963.9 schema:alternateName Department of Computer Science, University of Freiburg, Germany
152 schema:name Department of Computer Science, University of Freiburg, Germany
153 rdf:type schema:Organization
 




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


...