Developing an active observer View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1996

AUTHORS

Jan-Olof Eklundh , Tomas Uhlin , Peter Nordlund , Atsuto Maki

ABSTRACT

Seeing robots are usually aimed at functioning in real environments. Hence the figure-ground problem is essential. We argue that for a seeing robot, capable of actively fixating and holding gaze on objects in three dimensions, this problem is manageable, in particular if multiple cues can be used. An important point here is that a seeing robot should be able to utilize what the environment offers, rather than relying on a predetermined set of features.Furthermore, if there are early processes for figure-ground segmentation the local statistics of an observed (yet unknown) objects should be simpler than that of the entire scene. That suggest that processing to derive further properties, of e.g the shape or motion of that object, or even recognizing, could be based on other features than those used to segment out the object. Such a view fits well with recent theories about view-based recognition. It also allows efficient implementations in terms of a visual-front-end, since both the target selection and the target analysis can be based on the output from such a layer, even though different features are used. More... »

PAGES

181-190

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-60793-5_73

DOI

http://dx.doi.org/10.1007/3-540-60793-5_73

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1024506796


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/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive 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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Eklundh", 
        "givenName": "Jan-Olof", 
        "id": "sg:person.014400652155.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014400652155.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Uhlin", 
        "givenName": "Tomas", 
        "id": "sg:person.011303253273.54", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011303253273.54"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Nordlund", 
        "givenName": "Peter", 
        "id": "sg:person.015250537731.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015250537731.93"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maki", 
        "givenName": "Atsuto", 
        "id": "sg:person.012735745111.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012735745111.12"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1996", 
    "datePublishedReg": "1996-01-01", 
    "description": "Seeing robots are usually aimed at functioning in real environments. Hence the figure-ground problem is essential. We argue that for a seeing robot, capable of actively fixating and holding gaze on objects in three dimensions, this problem is manageable, in particular if multiple cues can be used. An important point here is that a seeing robot should be able to utilize what the environment offers, rather than relying on a predetermined set of features.Furthermore, if there are early processes for figure-ground segmentation the local statistics of an observed (yet unknown) objects should be simpler than that of the entire scene. That suggest that processing to derive further properties, of e.g the shape or motion of that object, or even recognizing, could be based on other features than those used to segment out the object. Such a view fits well with recent theories about view-based recognition. It also allows efficient implementations in terms of a visual-front-end, since both the target selection and the target analysis can be based on the output from such a layer, even though different features are used.", 
    "editor": [
      {
        "familyName": "Li", 
        "givenName": "Stan Z.", 
        "type": "Person"
      }, 
      {
        "familyName": "Mital", 
        "givenName": "Dinesh P.", 
        "type": "Person"
      }, 
      {
        "familyName": "Teoh", 
        "givenName": "Eam Khwang", 
        "type": "Person"
      }, 
      {
        "familyName": "Wang", 
        "givenName": "Han", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-60793-5_73", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-60793-9", 
        "978-3-540-49448-5"
      ], 
      "name": "Recent Developments in Computer Vision", 
      "type": "Book"
    }, 
    "keywords": [
      "figure-ground problem", 
      "figure-ground segmentation", 
      "view-based recognition", 
      "multiple cues", 
      "recent theories", 
      "active observer", 
      "target selection", 
      "early process", 
      "entire scene", 
      "objects", 
      "cues", 
      "real environment", 
      "robot", 
      "gaze", 
      "observed objects", 
      "different features", 
      "processing", 
      "predetermined set", 
      "recognition", 
      "scene", 
      "observer", 
      "theory", 
      "environment", 
      "dimensions", 
      "important point", 
      "features", 
      "view", 
      "problem", 
      "segmentation", 
      "process", 
      "terms", 
      "set", 
      "local statistics", 
      "selection", 
      "analysis", 
      "statistics", 
      "end", 
      "point", 
      "further properties", 
      "motion", 
      "shape", 
      "efficient implementation", 
      "implementation", 
      "output", 
      "target analysis", 
      "properties", 
      "layer"
    ], 
    "name": "Developing an active observer", 
    "pagination": "181-190", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1024506796"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-60793-5_73"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-60793-5_73", 
      "https://app.dimensions.ai/details/publication/pub.1024506796"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:48", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_202.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-60793-5_73"
  }
]
 

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.10.1007/3-540-60793-5_73'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-60793-5_73'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-60793-5_73'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-60793-5_73'


 

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

150 TRIPLES      22 PREDICATES      74 URIs      65 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-60793-5_73 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:17
4 anzsrc-for:1701
5 schema:author N3088e7282f804e96868e62ca2f9aed11
6 schema:datePublished 1996
7 schema:datePublishedReg 1996-01-01
8 schema:description Seeing robots are usually aimed at functioning in real environments. Hence the figure-ground problem is essential. We argue that for a seeing robot, capable of actively fixating and holding gaze on objects in three dimensions, this problem is manageable, in particular if multiple cues can be used. An important point here is that a seeing robot should be able to utilize what the environment offers, rather than relying on a predetermined set of features.Furthermore, if there are early processes for figure-ground segmentation the local statistics of an observed (yet unknown) objects should be simpler than that of the entire scene. That suggest that processing to derive further properties, of e.g the shape or motion of that object, or even recognizing, could be based on other features than those used to segment out the object. Such a view fits well with recent theories about view-based recognition. It also allows efficient implementations in terms of a visual-front-end, since both the target selection and the target analysis can be based on the output from such a layer, even though different features are used.
9 schema:editor N04ef335e0af749b485a095a32ab5e21e
10 schema:genre chapter
11 schema:isAccessibleForFree false
12 schema:isPartOf N49cc488fc40048b7b939ccc69979185e
13 schema:keywords active observer
14 analysis
15 cues
16 different features
17 dimensions
18 early process
19 efficient implementation
20 end
21 entire scene
22 environment
23 features
24 figure-ground problem
25 figure-ground segmentation
26 further properties
27 gaze
28 implementation
29 important point
30 layer
31 local statistics
32 motion
33 multiple cues
34 objects
35 observed objects
36 observer
37 output
38 point
39 predetermined set
40 problem
41 process
42 processing
43 properties
44 real environment
45 recent theories
46 recognition
47 robot
48 scene
49 segmentation
50 selection
51 set
52 shape
53 statistics
54 target analysis
55 target selection
56 terms
57 theory
58 view
59 view-based recognition
60 schema:name Developing an active observer
61 schema:pagination 181-190
62 schema:productId N5c78e429b241459298689dc0e9781174
63 N7315aa72d76d4fb68ecce8829fba441e
64 schema:publisher N7dfdd474deb9414ead7aea965bd9adf9
65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024506796
66 https://doi.org/10.1007/3-540-60793-5_73
67 schema:sdDatePublished 2022-12-01T06:48
68 schema:sdLicense https://scigraph.springernature.com/explorer/license/
69 schema:sdPublisher Nc746c40ba1da48fda52a394ffa1d1e0f
70 schema:url https://doi.org/10.1007/3-540-60793-5_73
71 sgo:license sg:explorer/license/
72 sgo:sdDataset chapters
73 rdf:type schema:Chapter
74 N04ef335e0af749b485a095a32ab5e21e rdf:first Nce4371df045f4042847dd415f21498bb
75 rdf:rest N72df537f632840448c76f72eda7a2975
76 N3088e7282f804e96868e62ca2f9aed11 rdf:first sg:person.014400652155.17
77 rdf:rest N3a298972bed946c59008ae29b2e59795
78 N3a298972bed946c59008ae29b2e59795 rdf:first sg:person.011303253273.54
79 rdf:rest Nf03d7bc52bb54e1ba76d5bcafa6acf0d
80 N4659def39df44c65a4aca77a685ce0ef schema:familyName Teoh
81 schema:givenName Eam Khwang
82 rdf:type schema:Person
83 N49cc488fc40048b7b939ccc69979185e schema:isbn 978-3-540-49448-5
84 978-3-540-60793-9
85 schema:name Recent Developments in Computer Vision
86 rdf:type schema:Book
87 N4a2f331b3c46405f835fe4c33373cd16 rdf:first sg:person.012735745111.12
88 rdf:rest rdf:nil
89 N5c78e429b241459298689dc0e9781174 schema:name doi
90 schema:value 10.1007/3-540-60793-5_73
91 rdf:type schema:PropertyValue
92 N72df537f632840448c76f72eda7a2975 rdf:first N72ef021de43e453a9a411352e9bc1acc
93 rdf:rest Nfc07817c699348f3ab658509b63f9b9f
94 N72ef021de43e453a9a411352e9bc1acc schema:familyName Mital
95 schema:givenName Dinesh P.
96 rdf:type schema:Person
97 N7315aa72d76d4fb68ecce8829fba441e schema:name dimensions_id
98 schema:value pub.1024506796
99 rdf:type schema:PropertyValue
100 N7dfdd474deb9414ead7aea965bd9adf9 schema:name Springer Nature
101 rdf:type schema:Organisation
102 Nbcd72ec9f6b6400c835e04dec97c6fb8 schema:familyName Wang
103 schema:givenName Han
104 rdf:type schema:Person
105 Nc746c40ba1da48fda52a394ffa1d1e0f schema:name Springer Nature - SN SciGraph project
106 rdf:type schema:Organization
107 Nce4371df045f4042847dd415f21498bb schema:familyName Li
108 schema:givenName Stan Z.
109 rdf:type schema:Person
110 Ned2fcd20863b4d01bd9b94ec1f0949d1 rdf:first Nbcd72ec9f6b6400c835e04dec97c6fb8
111 rdf:rest rdf:nil
112 Nf03d7bc52bb54e1ba76d5bcafa6acf0d rdf:first sg:person.015250537731.93
113 rdf:rest N4a2f331b3c46405f835fe4c33373cd16
114 Nfc07817c699348f3ab658509b63f9b9f rdf:first N4659def39df44c65a4aca77a685ce0ef
115 rdf:rest Ned2fcd20863b4d01bd9b94ec1f0949d1
116 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
117 schema:name Information and Computing Sciences
118 rdf:type schema:DefinedTerm
119 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
120 schema:name Artificial Intelligence and Image Processing
121 rdf:type schema:DefinedTerm
122 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
123 schema:name Psychology and Cognitive Sciences
124 rdf:type schema:DefinedTerm
125 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
126 schema:name Psychology
127 rdf:type schema:DefinedTerm
128 sg:person.011303253273.54 schema:affiliation grid-institutes:grid.5037.1
129 schema:familyName Uhlin
130 schema:givenName Tomas
131 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011303253273.54
132 rdf:type schema:Person
133 sg:person.012735745111.12 schema:affiliation grid-institutes:grid.5037.1
134 schema:familyName Maki
135 schema:givenName Atsuto
136 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012735745111.12
137 rdf:type schema:Person
138 sg:person.014400652155.17 schema:affiliation grid-institutes:grid.5037.1
139 schema:familyName Eklundh
140 schema:givenName Jan-Olof
141 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014400652155.17
142 rdf:type schema:Person
143 sg:person.015250537731.93 schema:affiliation grid-institutes:grid.5037.1
144 schema:familyName Nordlund
145 schema:givenName Peter
146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015250537731.93
147 rdf:type schema:Person
148 grid-institutes:grid.5037.1 schema:alternateName Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden
149 schema:name Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), S-100 44, Stockholm, Sweden
150 rdf:type schema:Organization
 




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


...