Perception-Action Based Object Detection from Local Descriptor Combination and Reinforcement Learning View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Lucas Paletta , Gerald Fritz , Christin Seifert

ABSTRACT

This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic decision procedure in a cascaded process where visual evidence is probed at informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. The local information in terms of code book vector responses and the geometric information in the shift of attention contribute to recognition states of a Markov decision process. A Q-learner performs then performs search on useful actions towards salient locations, developing a strategy of action sequences directed in state space towards the optimization of information maximization. The method is evaluated in outdoor object recognition and demonstrates efficient performance. More... »

PAGES

639-648

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11499145_65

DOI

http://dx.doi.org/10.1007/11499145_65

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1052456525


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/2008/17", 
        "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/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Paletta", 
        "givenName": "Lucas", 
        "id": "sg:person.010060055125.29", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Gerald", 
        "id": "sg:person.011015636117.31", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Seifert", 
        "givenName": "Christin", 
        "id": "sg:person.010257616672.34", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic decision procedure in a cascaded process where visual evidence is probed at informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. The local information in terms of code book vector responses and the geometric information in the shift of attention contribute to recognition states of a Markov decision process. A Q-learner performs then performs search on useful actions towards salient locations, developing a strategy of action sequences directed in state space towards the optimization of information maximization. The method is evaluated in outdoor object recognition and demonstrates efficient performance.", 
    "editor": [
      {
        "familyName": "Kalviainen", 
        "givenName": "Heikki", 
        "type": "Person"
      }, 
      {
        "familyName": "Parkkinen", 
        "givenName": "Jussi", 
        "type": "Person"
      }, 
      {
        "familyName": "Kaarna", 
        "givenName": "Arto", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11499145_65", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-26320-3", 
        "978-3-540-31566-7"
      ], 
      "name": "Image Analysis", 
      "type": "Book"
    }, 
    "keywords": [
      "object detection", 
      "outdoor object recognition", 
      "real world environment", 
      "local image descriptors", 
      "attention contributes", 
      "attention patterns", 
      "sequential attention", 
      "visual encoding", 
      "salient locations", 
      "action sequences", 
      "Markov decision process", 
      "object recognition", 
      "image descriptors", 
      "world environment", 
      "information maximization", 
      "reinforcement learning", 
      "image location", 
      "geometric information", 
      "local information", 
      "recognition state", 
      "descriptor combinations", 
      "efficient performance", 
      "decision procedure", 
      "useful actions", 
      "decision process", 
      "state space", 
      "focus of interest", 
      "encoding", 
      "saliency", 
      "learners", 
      "information", 
      "learning", 
      "visual evidence", 
      "descriptors", 
      "attention", 
      "detection", 
      "recognition", 
      "maximization", 
      "optimization", 
      "search", 
      "environment", 
      "performance", 
      "extraction", 
      "system", 
      "location", 
      "space", 
      "process", 
      "focus", 
      "evidence", 
      "work", 
      "contributes", 
      "action", 
      "strategies", 
      "method", 
      "patterns", 
      "interest", 
      "terms", 
      "response", 
      "vector response", 
      "sequence", 
      "state", 
      "shift", 
      "combination", 
      "procedure", 
      "saccadic decision procedure", 
      "informative image locations", 
      "information theoretic saliency", 
      "theoretic saliency", 
      "informative local image descriptors", 
      "code book vector responses", 
      "book vector responses", 
      "Local Descriptor Combination"
    ], 
    "name": "Perception-Action Based Object Detection from Local Descriptor Combination and Reinforcement Learning", 
    "pagination": "639-648", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1052456525"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11499145_65"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11499145_65", 
      "https://app.dimensions.ai/details/publication/pub.1052456525"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:10", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_177.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/11499145_65"
  }
]
 

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.10.1007/11499145_65'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11499145_65'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11499145_65'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11499145_65'


 

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

156 TRIPLES      23 PREDICATES      98 URIs      91 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11499145_65 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author Ne4794806f01a4413a9ece5287421727d
4 schema:datePublished 2005
5 schema:datePublishedReg 2005-01-01
6 schema:description This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic decision procedure in a cascaded process where visual evidence is probed at informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. The local information in terms of code book vector responses and the geometric information in the shift of attention contribute to recognition states of a Markov decision process. A Q-learner performs then performs search on useful actions towards salient locations, developing a strategy of action sequences directed in state space towards the optimization of information maximization. The method is evaluated in outdoor object recognition and demonstrates efficient performance.
7 schema:editor Nddbbb7ff1add4f3b8c31122a7480447d
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf Nf5c539a101fd4808aeedcbf831676e22
12 schema:keywords Local Descriptor Combination
13 Markov decision process
14 action
15 action sequences
16 attention
17 attention contributes
18 attention patterns
19 book vector responses
20 code book vector responses
21 combination
22 contributes
23 decision procedure
24 decision process
25 descriptor combinations
26 descriptors
27 detection
28 efficient performance
29 encoding
30 environment
31 evidence
32 extraction
33 focus
34 focus of interest
35 geometric information
36 image descriptors
37 image location
38 information
39 information maximization
40 information theoretic saliency
41 informative image locations
42 informative local image descriptors
43 interest
44 learners
45 learning
46 local image descriptors
47 local information
48 location
49 maximization
50 method
51 object detection
52 object recognition
53 optimization
54 outdoor object recognition
55 patterns
56 performance
57 procedure
58 process
59 real world environment
60 recognition
61 recognition state
62 reinforcement learning
63 response
64 saccadic decision procedure
65 saliency
66 salient locations
67 search
68 sequence
69 sequential attention
70 shift
71 space
72 state
73 state space
74 strategies
75 system
76 terms
77 theoretic saliency
78 useful actions
79 vector response
80 visual encoding
81 visual evidence
82 work
83 world environment
84 schema:name Perception-Action Based Object Detection from Local Descriptor Combination and Reinforcement Learning
85 schema:pagination 639-648
86 schema:productId N5d2990e5ae37420b8db5ceaae2fcbd25
87 Nbf5c4298c0204b7e8cc66eede4afe74a
88 schema:publisher Na6ae9ad52b104b949f066823f8662ffc
89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052456525
90 https://doi.org/10.1007/11499145_65
91 schema:sdDatePublished 2022-01-01T19:10
92 schema:sdLicense https://scigraph.springernature.com/explorer/license/
93 schema:sdPublisher Nf4d4b8ac89a44625825d85fdea6be2be
94 schema:url https://doi.org/10.1007/11499145_65
95 sgo:license sg:explorer/license/
96 sgo:sdDataset chapters
97 rdf:type schema:Chapter
98 N1edf998b5f2a4a33a3d9d3da1e5c1ef9 rdf:first Ne35ded5102ed4904a5a49962f8a3f0d7
99 rdf:rest Na96feb81cf6a4488a3a1b6ae738b68d1
100 N497b3614fa8f41099e0c6d0ca8d5a89a schema:familyName Kalviainen
101 schema:givenName Heikki
102 rdf:type schema:Person
103 N5d2990e5ae37420b8db5ceaae2fcbd25 schema:name doi
104 schema:value 10.1007/11499145_65
105 rdf:type schema:PropertyValue
106 N979576ac8d284db88dc19703f726313b schema:familyName Kaarna
107 schema:givenName Arto
108 rdf:type schema:Person
109 Na6ae9ad52b104b949f066823f8662ffc schema:name Springer Nature
110 rdf:type schema:Organisation
111 Na96feb81cf6a4488a3a1b6ae738b68d1 rdf:first N979576ac8d284db88dc19703f726313b
112 rdf:rest rdf:nil
113 Nb73f6fa2db3944f594d244eec5767b61 rdf:first sg:person.011015636117.31
114 rdf:rest Nf3e589900ecc43eca5e0d8244d975870
115 Nbf5c4298c0204b7e8cc66eede4afe74a schema:name dimensions_id
116 schema:value pub.1052456525
117 rdf:type schema:PropertyValue
118 Nddbbb7ff1add4f3b8c31122a7480447d rdf:first N497b3614fa8f41099e0c6d0ca8d5a89a
119 rdf:rest N1edf998b5f2a4a33a3d9d3da1e5c1ef9
120 Ne35ded5102ed4904a5a49962f8a3f0d7 schema:familyName Parkkinen
121 schema:givenName Jussi
122 rdf:type schema:Person
123 Ne4794806f01a4413a9ece5287421727d rdf:first sg:person.010060055125.29
124 rdf:rest Nb73f6fa2db3944f594d244eec5767b61
125 Nf3e589900ecc43eca5e0d8244d975870 rdf:first sg:person.010257616672.34
126 rdf:rest rdf:nil
127 Nf4d4b8ac89a44625825d85fdea6be2be schema:name Springer Nature - SN SciGraph project
128 rdf:type schema:Organization
129 Nf5c539a101fd4808aeedcbf831676e22 schema:isbn 978-3-540-26320-3
130 978-3-540-31566-7
131 schema:name Image Analysis
132 rdf:type schema:Book
133 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
134 schema:name Psychology and Cognitive Sciences
135 rdf:type schema:DefinedTerm
136 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
137 schema:name Psychology
138 rdf:type schema:DefinedTerm
139 sg:person.010060055125.29 schema:affiliation grid-institutes:grid.8684.2
140 schema:familyName Paletta
141 schema:givenName Lucas
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29
143 rdf:type schema:Person
144 sg:person.010257616672.34 schema:affiliation grid-institutes:grid.8684.2
145 schema:familyName Seifert
146 schema:givenName Christin
147 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34
148 rdf:type schema:Person
149 sg:person.011015636117.31 schema:affiliation grid-institutes:grid.8684.2
150 schema:familyName Fritz
151 schema:givenName Gerald
152 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31
153 rdf:type schema:Person
154 grid-institutes:grid.8684.2 schema:alternateName Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
155 schema:name Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
156 rdf:type schema:Organization
 




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


...