Building Detection from Mobile Imagery Using Informative SIFT Descriptors View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Gerald Fritz , Christin Seifert , Manish Kumar , Lucas Paletta

ABSTRACT

We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computational complexity for situated interpretation of urban imagery, we propose to apply the ’Informative Descriptor Approach’ on SIFT features (i-SIFT descriptors). We learn an attentive matching of i-SIFT keypoints, resulting in a significant improvement of state-of-the-art SIFT descriptor based keypoint matching. In the off-line learning stage, firstly, standard SIFT responses are evaluated using an information theoretic quality criterion with respect to object semantics, rejecting features with insufficient conditional entropy measure, producing both sparse and discriminative object representations. Secondly, we learn a decision tree from the training data set that maps SIFT descriptors to entropy values. The key advantages of informative SIFT (i-SIFT) to standard SIFT encoding are argued from observations on performance complexity, and demonstrated in a typical outdoor mobile vision experiment on the MPG-20 reference database. More... »

PAGES

629-638

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11499145_64

DOI

http://dx.doi.org/10.1007/11499145_64

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1004976769


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": "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"
      }, 
      {
        "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": "Kumar", 
        "givenName": "Manish", 
        "id": "sg:person.016177133725.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016177133725.13"
        ], 
        "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": "Paletta", 
        "givenName": "Lucas", 
        "id": "sg:person.010060055125.29", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computational complexity for situated interpretation of urban imagery, we propose to apply the \u2019Informative Descriptor Approach\u2019 on SIFT features (i-SIFT descriptors). We learn an attentive matching of i-SIFT keypoints, resulting in a significant improvement of state-of-the-art SIFT descriptor based keypoint matching. In the off-line learning stage, firstly, standard SIFT responses are evaluated using an information theoretic quality criterion with respect to object semantics, rejecting features with insufficient conditional entropy measure, producing both sparse and discriminative object representations. Secondly, we learn a decision tree from the training data set that maps SIFT descriptors to entropy values. The key advantages of informative SIFT (i-SIFT) to standard SIFT encoding are argued from observations on performance complexity, and demonstrated in a typical outdoor mobile vision experiment on the MPG-20 reference database.", 
    "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_64", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-26320-3", 
        "978-3-540-31566-7"
      ], 
      "name": "Image Analysis", 
      "type": "Book"
    }, 
    "keywords": [
      "SIFT descriptors", 
      "object detection", 
      "off-line learning stage", 
      "robust object detection", 
      "mobile phone imagery", 
      "conditional entropy measure", 
      "mobile imagery", 
      "computational complexity", 
      "SIFT features", 
      "SIFT keypoints", 
      "keypoint matching", 
      "training data", 
      "learning stage", 
      "performance complexity", 
      "shelf devices", 
      "decision tree", 
      "vision experiments", 
      "object representations", 
      "situated interpretation", 
      "descriptors", 
      "key advantage", 
      "entropy measure", 
      "matching", 
      "complexity", 
      "reference database", 
      "urban imagery", 
      "descriptor approach", 
      "keypoints", 
      "imagery", 
      "semantics", 
      "SIFT", 
      "detection", 
      "quality criteria", 
      "encoding", 
      "features", 
      "database", 
      "representation", 
      "significant improvement", 
      "advantages", 
      "devices", 
      "goal", 
      "trees", 
      "experiments", 
      "data", 
      "improvement", 
      "state", 
      "criteria", 
      "respect", 
      "measures", 
      "interpretation", 
      "stage", 
      "values", 
      "reduction", 
      "observations", 
      "response", 
      "approach", 
      "reliable outdoor object detection", 
      "outdoor object detection", 
      "phone imagery", 
      "Informative Descriptor Approach", 
      "attentive matching", 
      "art SIFT descriptor", 
      "standard SIFT responses", 
      "SIFT responses", 
      "information theoretic quality criterion", 
      "theoretic quality criterion", 
      "insufficient conditional entropy measure", 
      "informative SIFT", 
      "standard SIFT encoding", 
      "SIFT encoding", 
      "typical outdoor mobile vision experiment", 
      "outdoor mobile vision experiment", 
      "mobile vision experiment", 
      "Informative SIFT Descriptors"
    ], 
    "name": "Building Detection from Mobile Imagery Using Informative SIFT Descriptors", 
    "pagination": "629-638", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1004976769"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11499145_64"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11499145_64", 
      "https://app.dimensions.ai/details/publication/pub.1004976769"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:24", 
    "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_413.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/11499145_64"
  }
]
 

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_64'

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_64'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11499145_64'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11499145_64'


 

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

165 TRIPLES      23 PREDICATES      100 URIs      93 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11499145_64 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N28259f36a9ed4e699abaebc91a1e0aa6
4 schema:datePublished 2005
5 schema:datePublishedReg 2005-01-01
6 schema:description We propose reliable outdoor object detection on mobile phone imagery from off-the-shelf devices. With the goal to provide both robust object detection and reduction of computational complexity for situated interpretation of urban imagery, we propose to apply the ’Informative Descriptor Approach’ on SIFT features (i-SIFT descriptors). We learn an attentive matching of i-SIFT keypoints, resulting in a significant improvement of state-of-the-art SIFT descriptor based keypoint matching. In the off-line learning stage, firstly, standard SIFT responses are evaluated using an information theoretic quality criterion with respect to object semantics, rejecting features with insufficient conditional entropy measure, producing both sparse and discriminative object representations. Secondly, we learn a decision tree from the training data set that maps SIFT descriptors to entropy values. The key advantages of informative SIFT (i-SIFT) to standard SIFT encoding are argued from observations on performance complexity, and demonstrated in a typical outdoor mobile vision experiment on the MPG-20 reference database.
7 schema:editor N09c6e5dd81d849698fb6fe291fe4b093
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N035ca96c270e4ad089d5eb160cacfc2f
12 schema:keywords Informative Descriptor Approach
13 Informative SIFT Descriptors
14 SIFT
15 SIFT descriptors
16 SIFT encoding
17 SIFT features
18 SIFT keypoints
19 SIFT responses
20 advantages
21 approach
22 art SIFT descriptor
23 attentive matching
24 complexity
25 computational complexity
26 conditional entropy measure
27 criteria
28 data
29 database
30 decision tree
31 descriptor approach
32 descriptors
33 detection
34 devices
35 encoding
36 entropy measure
37 experiments
38 features
39 goal
40 imagery
41 improvement
42 information theoretic quality criterion
43 informative SIFT
44 insufficient conditional entropy measure
45 interpretation
46 key advantage
47 keypoint matching
48 keypoints
49 learning stage
50 matching
51 measures
52 mobile imagery
53 mobile phone imagery
54 mobile vision experiment
55 object detection
56 object representations
57 observations
58 off-line learning stage
59 outdoor mobile vision experiment
60 outdoor object detection
61 performance complexity
62 phone imagery
63 quality criteria
64 reduction
65 reference database
66 reliable outdoor object detection
67 representation
68 respect
69 response
70 robust object detection
71 semantics
72 shelf devices
73 significant improvement
74 situated interpretation
75 stage
76 standard SIFT encoding
77 standard SIFT responses
78 state
79 theoretic quality criterion
80 training data
81 trees
82 typical outdoor mobile vision experiment
83 urban imagery
84 values
85 vision experiments
86 schema:name Building Detection from Mobile Imagery Using Informative SIFT Descriptors
87 schema:pagination 629-638
88 schema:productId N262b55d14e0d4560a3b449ba3538ff55
89 N7a10a608aeba487f86cd4f96c190887a
90 schema:publisher Na2849bef7ab04ca5baa239db3a412500
91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004976769
92 https://doi.org/10.1007/11499145_64
93 schema:sdDatePublished 2022-01-01T19:24
94 schema:sdLicense https://scigraph.springernature.com/explorer/license/
95 schema:sdPublisher N3efabea44e914b36a89e86473f369c6c
96 schema:url https://doi.org/10.1007/11499145_64
97 sgo:license sg:explorer/license/
98 sgo:sdDataset chapters
99 rdf:type schema:Chapter
100 N035ca96c270e4ad089d5eb160cacfc2f schema:isbn 978-3-540-26320-3
101 978-3-540-31566-7
102 schema:name Image Analysis
103 rdf:type schema:Book
104 N09c6e5dd81d849698fb6fe291fe4b093 rdf:first Nc91eb81c4d634e089cc513cfd6e87cc2
105 rdf:rest N5553e95db7ed4709bb96debfb1abca07
106 N1c78986595f24a1a80bce75167ff9a0f rdf:first sg:person.010257616672.34
107 rdf:rest Nebcbe1f8338b4b5582e85654230fa982
108 N262b55d14e0d4560a3b449ba3538ff55 schema:name doi
109 schema:value 10.1007/11499145_64
110 rdf:type schema:PropertyValue
111 N28259f36a9ed4e699abaebc91a1e0aa6 rdf:first sg:person.011015636117.31
112 rdf:rest N1c78986595f24a1a80bce75167ff9a0f
113 N3efabea44e914b36a89e86473f369c6c schema:name Springer Nature - SN SciGraph project
114 rdf:type schema:Organization
115 N5553e95db7ed4709bb96debfb1abca07 rdf:first Nbe330decb5b24fa5b8f09e0d144b5d5a
116 rdf:rest Nfadfd9571fa649f685e8d574fea3c32a
117 N67eb4a07102e489699a2f89519020e52 schema:familyName Kaarna
118 schema:givenName Arto
119 rdf:type schema:Person
120 N7a10a608aeba487f86cd4f96c190887a schema:name dimensions_id
121 schema:value pub.1004976769
122 rdf:type schema:PropertyValue
123 Na2849bef7ab04ca5baa239db3a412500 schema:name Springer Nature
124 rdf:type schema:Organisation
125 Nbe330decb5b24fa5b8f09e0d144b5d5a schema:familyName Parkkinen
126 schema:givenName Jussi
127 rdf:type schema:Person
128 Nc91eb81c4d634e089cc513cfd6e87cc2 schema:familyName Kalviainen
129 schema:givenName Heikki
130 rdf:type schema:Person
131 Nd2964e6de9814d3aabd399c3e8dbcc61 rdf:first sg:person.010060055125.29
132 rdf:rest rdf:nil
133 Nebcbe1f8338b4b5582e85654230fa982 rdf:first sg:person.016177133725.13
134 rdf:rest Nd2964e6de9814d3aabd399c3e8dbcc61
135 Nfadfd9571fa649f685e8d574fea3c32a rdf:first N67eb4a07102e489699a2f89519020e52
136 rdf:rest rdf:nil
137 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
138 schema:name Information and Computing Sciences
139 rdf:type schema:DefinedTerm
140 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
141 schema:name Artificial Intelligence and Image Processing
142 rdf:type schema:DefinedTerm
143 sg:person.010060055125.29 schema:affiliation grid-institutes:grid.8684.2
144 schema:familyName Paletta
145 schema:givenName Lucas
146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29
147 rdf:type schema:Person
148 sg:person.010257616672.34 schema:affiliation grid-institutes:grid.8684.2
149 schema:familyName Seifert
150 schema:givenName Christin
151 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34
152 rdf:type schema:Person
153 sg:person.011015636117.31 schema:affiliation grid-institutes:grid.8684.2
154 schema:familyName Fritz
155 schema:givenName Gerald
156 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31
157 rdf:type schema:Person
158 sg:person.016177133725.13 schema:affiliation grid-institutes:grid.8684.2
159 schema:familyName Kumar
160 schema:givenName Manish
161 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016177133725.13
162 rdf:type schema:Person
163 grid-institutes:grid.8684.2 schema:alternateName Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
164 schema:name Institute of Digital Image Processing, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
165 rdf:type schema:Organization
 




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


...