Exact Acceleration of Linear Object Detectors View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2012

AUTHORS

Charles Dubout , François Fleuret

ABSTRACT

We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. The main bottleneck of many of those systems is the computational cost of the convolutions between the multiple rescalings of the image to process, and the linear filters. We make use of properties of the Fourier transform and of clever implementation strategies to obtain a speedup factor proportional to the filters’ sizes. The gain in performance is demonstrated on the well known Pascal VOC benchmark, where we accelerate the speed of said convolutions by an order of magnitude. More... »

PAGES

301-311

References to SciGraph publications

Book

TITLE

Computer Vision – ECCV 2012

ISBN

978-3-642-33711-6
978-3-642-33712-3

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_22

DOI

http://dx.doi.org/10.1007/978-3-642-33712-3_22

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1049381146


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/2008/0801", 
        "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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Idiap Research Institute", 
          "id": "https://www.grid.ac/institutes/grid.482253.a", 
          "name": [
            "Idiap Research Institute, Centre du Parc, Rue Marconi 19, CH - 1920\u00a0Martigny, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dubout", 
        "givenName": "Charles", 
        "id": "sg:person.016577465751.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016577465751.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Idiap Research Institute", 
          "id": "https://www.grid.ac/institutes/grid.482253.a", 
          "name": [
            "Idiap Research Institute, Centre du Parc, Rue Marconi 19, CH - 1920\u00a0Martigny, Switzerland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fleuret", 
        "givenName": "Fran\u00e7ois", 
        "id": "sg:person.01160624137.87", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01160624137.87"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/b:visi.0000042934.15159.49", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022591804", 
          "https://doi.org/10.1023/b:visi.0000042934.15159.49"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-77343-6_14", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030117416", 
          "https://doi.org/10.1007/978-3-540-77343-6_14"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-77343-6_14", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030117416", 
          "https://doi.org/10.1007/978-3-540-77343-6_14"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jproc.2004.840301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061296364"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tc.1983.1676307", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061532958"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2009.167", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743745"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2008.4587586", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093337684"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2005.177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093997066"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206693", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094033212"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icpr.2008.4761638", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094604775"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5539906", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095781329"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.24.68", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099341273"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. The main bottleneck of many of those systems is the computational cost of the convolutions between the multiple rescalings of the image to process, and the linear filters. We make use of properties of the Fourier transform and of clever implementation strategies to obtain a speedup factor proportional to the filters\u2019 sizes. The gain in performance is demonstrated on the well known Pascal VOC benchmark, where we accelerate the speed of said convolutions by an order of magnitude.", 
    "editor": [
      {
        "familyName": "Fitzgibbon", 
        "givenName": "Andrew", 
        "type": "Person"
      }, 
      {
        "familyName": "Lazebnik", 
        "givenName": "Svetlana", 
        "type": "Person"
      }, 
      {
        "familyName": "Perona", 
        "givenName": "Pietro", 
        "type": "Person"
      }, 
      {
        "familyName": "Sato", 
        "givenName": "Yoichi", 
        "type": "Person"
      }, 
      {
        "familyName": "Schmid", 
        "givenName": "Cordelia", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-33712-3_22", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-33711-6", 
        "978-3-642-33712-3"
      ], 
      "name": "Computer Vision \u2013 ECCV 2012", 
      "type": "Book"
    }, 
    "name": "Exact Acceleration of Linear Object Detectors", 
    "pagination": "301-311", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-33712-3_22"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "eb3e133625ced8fdef9ef9b7b306a8ace047b26ea80a13be4f78349d304773b5"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1049381146"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-33712-3_22", 
      "https://app.dimensions.ai/details/publication/pub.1049381146"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T13:31", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8664_00000274.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-642-33712-3_22"
  }
]
 

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.10.1007/978-3-642-33712-3_22'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_22'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_22'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_22'


 

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

127 TRIPLES      23 PREDICATES      38 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-33712-3_22 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nec55c0182a57419cb43cdd44b0320ae0
4 schema:citation sg:pub.10.1007/978-3-540-77343-6_14
5 sg:pub.10.1023/b:visi.0000042934.15159.49
6 https://doi.org/10.1109/cvpr.2005.177
7 https://doi.org/10.1109/cvpr.2008.4587586
8 https://doi.org/10.1109/cvpr.2009.5206693
9 https://doi.org/10.1109/cvpr.2010.5539906
10 https://doi.org/10.1109/icpr.2008.4761638
11 https://doi.org/10.1109/jproc.2004.840301
12 https://doi.org/10.1109/tc.1983.1676307
13 https://doi.org/10.1109/tpami.2009.167
14 https://doi.org/10.5244/c.24.68
15 schema:datePublished 2012
16 schema:datePublishedReg 2012-01-01
17 schema:description We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. The main bottleneck of many of those systems is the computational cost of the convolutions between the multiple rescalings of the image to process, and the linear filters. We make use of properties of the Fourier transform and of clever implementation strategies to obtain a speedup factor proportional to the filters’ sizes. The gain in performance is demonstrated on the well known Pascal VOC benchmark, where we accelerate the speed of said convolutions by an order of magnitude.
18 schema:editor Ne06a637a11ec4408b3945225c500daa6
19 schema:genre chapter
20 schema:inLanguage en
21 schema:isAccessibleForFree true
22 schema:isPartOf Nd1a6d47aa2ba4f7c8c91947b903c0d3c
23 schema:name Exact Acceleration of Linear Object Detectors
24 schema:pagination 301-311
25 schema:productId N49c6b07037604675bee5b0a7fd89d441
26 N92650ecc799a4c5f8ef1e77e38191c20
27 Nc7cf15f0e8fe4bb9b60a8a3e6d8ae5b9
28 schema:publisher Nffb488b37a5c447fb13e8e8a45a9948e
29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049381146
30 https://doi.org/10.1007/978-3-642-33712-3_22
31 schema:sdDatePublished 2019-04-15T13:31
32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
33 schema:sdPublisher N6b923fce32604bacae3fa7a006dc8515
34 schema:url http://link.springer.com/10.1007/978-3-642-33712-3_22
35 sgo:license sg:explorer/license/
36 sgo:sdDataset chapters
37 rdf:type schema:Chapter
38 N31f9c36509294da5afaf42bb38501f02 schema:familyName Sato
39 schema:givenName Yoichi
40 rdf:type schema:Person
41 N49c6b07037604675bee5b0a7fd89d441 schema:name doi
42 schema:value 10.1007/978-3-642-33712-3_22
43 rdf:type schema:PropertyValue
44 N57291aa2326b4812b6d9fa241dff8e8a schema:familyName Lazebnik
45 schema:givenName Svetlana
46 rdf:type schema:Person
47 N6136345e0d404ad7bc77d47de11ed1bb rdf:first Nf6bf398bc5e74722abb210b5504372aa
48 rdf:rest rdf:nil
49 N6b923fce32604bacae3fa7a006dc8515 schema:name Springer Nature - SN SciGraph project
50 rdf:type schema:Organization
51 N92650ecc799a4c5f8ef1e77e38191c20 schema:name readcube_id
52 schema:value eb3e133625ced8fdef9ef9b7b306a8ace047b26ea80a13be4f78349d304773b5
53 rdf:type schema:PropertyValue
54 Nc7cf15f0e8fe4bb9b60a8a3e6d8ae5b9 schema:name dimensions_id
55 schema:value pub.1049381146
56 rdf:type schema:PropertyValue
57 Nc8b00fb70a744429860b64c9d1f12a4d rdf:first N57291aa2326b4812b6d9fa241dff8e8a
58 rdf:rest Nfef7365b310e4a7aa6f0454fe7dc321f
59 Nd1a6d47aa2ba4f7c8c91947b903c0d3c schema:isbn 978-3-642-33711-6
60 978-3-642-33712-3
61 schema:name Computer Vision – ECCV 2012
62 rdf:type schema:Book
63 Nde28651360a9461b8178f0d713b55d8c schema:familyName Perona
64 schema:givenName Pietro
65 rdf:type schema:Person
66 Ne06a637a11ec4408b3945225c500daa6 rdf:first Ne203a670abef4d7f820ea4053cad2e8e
67 rdf:rest Nc8b00fb70a744429860b64c9d1f12a4d
68 Ne203a670abef4d7f820ea4053cad2e8e schema:familyName Fitzgibbon
69 schema:givenName Andrew
70 rdf:type schema:Person
71 Nec55c0182a57419cb43cdd44b0320ae0 rdf:first sg:person.016577465751.46
72 rdf:rest Nf771b85e9d7246b29c2174c873544336
73 Nf6bf398bc5e74722abb210b5504372aa schema:familyName Schmid
74 schema:givenName Cordelia
75 rdf:type schema:Person
76 Nf771b85e9d7246b29c2174c873544336 rdf:first sg:person.01160624137.87
77 rdf:rest rdf:nil
78 Nfd9c3e5f0ef34d8e9ecc52597bfe442b rdf:first N31f9c36509294da5afaf42bb38501f02
79 rdf:rest N6136345e0d404ad7bc77d47de11ed1bb
80 Nfef7365b310e4a7aa6f0454fe7dc321f rdf:first Nde28651360a9461b8178f0d713b55d8c
81 rdf:rest Nfd9c3e5f0ef34d8e9ecc52597bfe442b
82 Nffb488b37a5c447fb13e8e8a45a9948e schema:location Berlin, Heidelberg
83 schema:name Springer Berlin Heidelberg
84 rdf:type schema:Organisation
85 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
86 schema:name Information and Computing Sciences
87 rdf:type schema:DefinedTerm
88 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
89 schema:name Artificial Intelligence and Image Processing
90 rdf:type schema:DefinedTerm
91 sg:person.01160624137.87 schema:affiliation https://www.grid.ac/institutes/grid.482253.a
92 schema:familyName Fleuret
93 schema:givenName François
94 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01160624137.87
95 rdf:type schema:Person
96 sg:person.016577465751.46 schema:affiliation https://www.grid.ac/institutes/grid.482253.a
97 schema:familyName Dubout
98 schema:givenName Charles
99 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016577465751.46
100 rdf:type schema:Person
101 sg:pub.10.1007/978-3-540-77343-6_14 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030117416
102 https://doi.org/10.1007/978-3-540-77343-6_14
103 rdf:type schema:CreativeWork
104 sg:pub.10.1023/b:visi.0000042934.15159.49 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022591804
105 https://doi.org/10.1023/b:visi.0000042934.15159.49
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1109/cvpr.2008.4587586 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093337684
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/cvpr.2009.5206693 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094033212
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1109/cvpr.2010.5539906 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095781329
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1109/icpr.2008.4761638 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094604775
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1109/jproc.2004.840301 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061296364
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1109/tc.1983.1676307 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061532958
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1109/tpami.2009.167 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743745
122 rdf:type schema:CreativeWork
123 https://doi.org/10.5244/c.24.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099341273
124 rdf:type schema:CreativeWork
125 https://www.grid.ac/institutes/grid.482253.a schema:alternateName Idiap Research Institute
126 schema:name Idiap Research Institute, Centre du Parc, Rue Marconi 19, CH - 1920 Martigny, Switzerland
127 rdf:type schema:Organization
 




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


...