Active Vision and Seeing Robots View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1996

AUTHORS

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

ABSTRACT

In this paper we argue that the study of seeing systems or robots should be performed from a systems perspective. This implies that the importance of a computational mechanism should be established in view of the tasks that the system can perform using it.Since such robots usually are aimed at functioning in real environments the figure-ground problem becomes essential. Computational approaches based on minimal information, commonly studied in the field, could hence be applied first after such problems are solved. We argue that for a seeing robot, capable of actively fixating and holding gaze on object 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 segementation 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 it, 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.We support these ideas with an implementation of a mobile visual observer, functioning in realtime in a cluttered environment. More... »

PAGES

416-427

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4471-1021-7_45

DOI

http://dx.doi.org/10.1007/978-1-4471-1021-7_45

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1030059807


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": "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": "In this paper we argue that the study of seeing systems or robots should be performed from a systems perspective. This implies that the importance of a computational mechanism should be established in view of the tasks that the system can perform using it.Since such robots usually are aimed at functioning in real environments the figure-ground problem becomes essential. Computational approaches based on minimal information, commonly studied in the field, could hence be applied first after such problems are solved. We argue that for a seeing robot, capable of actively fixating and holding gaze on object 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 segementation 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 it, 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.We support these ideas with an implementation of a mobile visual observer, functioning in realtime in a cluttered environment.", 
    "editor": [
      {
        "familyName": "Giralt", 
        "givenName": "Georges", 
        "type": "Person"
      }, 
      {
        "familyName": "Hirzinger", 
        "givenName": "Gerhard", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4471-1021-7_45", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-1-4471-1257-0", 
        "978-1-4471-1021-7"
      ], 
      "name": "Robotics Research", 
      "type": "Book"
    }, 
    "keywords": [
      "view-based recognition", 
      "such robots", 
      "active vision", 
      "real environment", 
      "cluttered environments", 
      "entire scene", 
      "robot", 
      "efficient implementation", 
      "figure-ground problem", 
      "computational mechanisms", 
      "observed objects", 
      "different features", 
      "multiple cues", 
      "predetermined set", 
      "local statistics", 
      "such problems", 
      "objects", 
      "implementation", 
      "minimal information", 
      "recent theories", 
      "computational approach", 
      "environment", 
      "target selection", 
      "realtime", 
      "segementation", 
      "systems perspective", 
      "early process", 
      "features", 
      "scene", 
      "task", 
      "visual observers", 
      "system", 
      "vision", 
      "further properties", 
      "recognition", 
      "cues", 
      "processing", 
      "information", 
      "gaze", 
      "set", 
      "view", 
      "important point", 
      "idea", 
      "problem", 
      "selection", 
      "output", 
      "observer", 
      "perspective", 
      "theory", 
      "target analysis", 
      "dimensions", 
      "motion", 
      "statistics", 
      "terms", 
      "process", 
      "point", 
      "end", 
      "field", 
      "importance", 
      "study", 
      "properties", 
      "shape", 
      "layer", 
      "approach", 
      "analysis", 
      "mechanism", 
      "paper"
    ], 
    "name": "Active Vision and Seeing Robots", 
    "pagination": "416-427", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1030059807"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4471-1021-7_45"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4471-1021-7_45", 
      "https://app.dimensions.ai/details/publication/pub.1030059807"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:13", 
    "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_213.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-1-4471-1021-7_45"
  }
]
 

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.10.1007/978-1-4471-1021-7_45'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-1021-7_45'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-1021-7_45'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-1021-7_45'


 

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

152 TRIPLES      22 PREDICATES      92 URIs      85 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4471-1021-7_45 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N345b95b66b4b44f49388cd2e0b5a5fdc
4 schema:datePublished 1996
5 schema:datePublishedReg 1996-01-01
6 schema:description In this paper we argue that the study of seeing systems or robots should be performed from a systems perspective. This implies that the importance of a computational mechanism should be established in view of the tasks that the system can perform using it.Since such robots usually are aimed at functioning in real environments the figure-ground problem becomes essential. Computational approaches based on minimal information, commonly studied in the field, could hence be applied first after such problems are solved. We argue that for a seeing robot, capable of actively fixating and holding gaze on object 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 segementation 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 it, 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.We support these ideas with an implementation of a mobile visual observer, functioning in realtime in a cluttered environment.
7 schema:editor N6293b8bf8ee94f4c9c20e4b9487ea1e5
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N889bf91804c143ab83a89d19f558f73f
11 schema:keywords active vision
12 analysis
13 approach
14 cluttered environments
15 computational approach
16 computational mechanisms
17 cues
18 different features
19 dimensions
20 early process
21 efficient implementation
22 end
23 entire scene
24 environment
25 features
26 field
27 figure-ground problem
28 further properties
29 gaze
30 idea
31 implementation
32 importance
33 important point
34 information
35 layer
36 local statistics
37 mechanism
38 minimal information
39 motion
40 multiple cues
41 objects
42 observed objects
43 observer
44 output
45 paper
46 perspective
47 point
48 predetermined set
49 problem
50 process
51 processing
52 properties
53 real environment
54 realtime
55 recent theories
56 recognition
57 robot
58 scene
59 segementation
60 selection
61 set
62 shape
63 statistics
64 study
65 such problems
66 such robots
67 system
68 systems perspective
69 target analysis
70 target selection
71 task
72 terms
73 theory
74 view
75 view-based recognition
76 vision
77 visual observers
78 schema:name Active Vision and Seeing Robots
79 schema:pagination 416-427
80 schema:productId Ne0ca4559cc764d238e247c54f2545475
81 Nf451719468184f6d9fff5acf8eb11a44
82 schema:publisher N89a947aca588477680e1946edf03d2c7
83 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030059807
84 https://doi.org/10.1007/978-1-4471-1021-7_45
85 schema:sdDatePublished 2022-11-24T21:13
86 schema:sdLicense https://scigraph.springernature.com/explorer/license/
87 schema:sdPublisher Nfaca1a5f44fb419aa640509be8099a7f
88 schema:url https://doi.org/10.1007/978-1-4471-1021-7_45
89 sgo:license sg:explorer/license/
90 sgo:sdDataset chapters
91 rdf:type schema:Chapter
92 N33c0049bdab64c77994fa3e0ee7979d8 rdf:first sg:person.015250537731.93
93 rdf:rest Ne489417f54424a129cde8d93d4192f3d
94 N345b95b66b4b44f49388cd2e0b5a5fdc rdf:first sg:person.014400652155.17
95 rdf:rest Nddc77433d13240f9b513b4d5879f9c68
96 N4a92ee829bf449beb2c7e91da8a3569a schema:familyName Hirzinger
97 schema:givenName Gerhard
98 rdf:type schema:Person
99 N5ed6311765174e4c826940a6ae976525 schema:familyName Giralt
100 schema:givenName Georges
101 rdf:type schema:Person
102 N6293b8bf8ee94f4c9c20e4b9487ea1e5 rdf:first N5ed6311765174e4c826940a6ae976525
103 rdf:rest N659aa115e4074258aa6e2a4aea65f503
104 N659aa115e4074258aa6e2a4aea65f503 rdf:first N4a92ee829bf449beb2c7e91da8a3569a
105 rdf:rest rdf:nil
106 N889bf91804c143ab83a89d19f558f73f schema:isbn 978-1-4471-1021-7
107 978-1-4471-1257-0
108 schema:name Robotics Research
109 rdf:type schema:Book
110 N89a947aca588477680e1946edf03d2c7 schema:name Springer Nature
111 rdf:type schema:Organisation
112 Nddc77433d13240f9b513b4d5879f9c68 rdf:first sg:person.011303253273.54
113 rdf:rest N33c0049bdab64c77994fa3e0ee7979d8
114 Ne0ca4559cc764d238e247c54f2545475 schema:name doi
115 schema:value 10.1007/978-1-4471-1021-7_45
116 rdf:type schema:PropertyValue
117 Ne489417f54424a129cde8d93d4192f3d rdf:first sg:person.012735745111.12
118 rdf:rest rdf:nil
119 Nf451719468184f6d9fff5acf8eb11a44 schema:name dimensions_id
120 schema:value pub.1030059807
121 rdf:type schema:PropertyValue
122 Nfaca1a5f44fb419aa640509be8099a7f schema:name Springer Nature - SN SciGraph project
123 rdf:type schema:Organization
124 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
125 schema:name Information and Computing Sciences
126 rdf:type schema:DefinedTerm
127 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
128 schema:name Artificial Intelligence and Image Processing
129 rdf:type schema:DefinedTerm
130 sg:person.011303253273.54 schema:affiliation grid-institutes:grid.5037.1
131 schema:familyName Uhlin
132 schema:givenName Tomas
133 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011303253273.54
134 rdf:type schema:Person
135 sg:person.012735745111.12 schema:affiliation grid-institutes:grid.5037.1
136 schema:familyName Maki
137 schema:givenName Atsuto
138 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012735745111.12
139 rdf:type schema:Person
140 sg:person.014400652155.17 schema:affiliation grid-institutes:grid.5037.1
141 schema:familyName Eklundh
142 schema:givenName Jan-Olof
143 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014400652155.17
144 rdf:type schema:Person
145 sg:person.015250537731.93 schema:affiliation grid-institutes:grid.5037.1
146 schema:familyName Nordlund
147 schema:givenName Peter
148 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015250537731.93
149 rdf:type schema:Person
150 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
151 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
152 rdf:type schema:Organization
 




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


...