Research on Local Image Feature Description and Fusion Mechanism Based on Machine Learning View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2012-2015

FUNDING AMOUNT

240000 CNY

ABSTRACT

Local image descriptors construction and matching is a fundamental problem in computer vision, and has a profound influence on the related applications, such as object recognition, 3D reconstruction and image retrieval. To alleviate the shortcomings of the traditional methods for local descriptor construction, this proposal aims to propose data-driven methods for constructing local descriptor based on machine learning. Meanwhile, it also studies multiple descriptors fusion strategies to further improve their performance. The key issues include: (1) Modeling the local image description as a process of low-level feature extraction followed by feature pooling, then focused on the research of low-level feature extraction and feature pooling methods through machine learning;(2) Modeling the local image description as a process of dimension reduction or feature selection, then research on the methods for robustly converting images into vectors based on invariants, and research on the subspace learning as well as feature section methods for feature matching;(3) Research on the application of machine learning for multiple descriptors fusion in feature-level and in decision-level respectively. The outcomes would enrich methodology and provide novel ideas for feature description, feature matching, feature fusion and machi More... »

URL

http://npd.nsfc.gov.cn/projectDetail.action?pid=61203277

Related SciGraph Publications

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/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "amount": {
      "currency": "CNY", 
      "type": "MonetaryAmount", 
      "value": "240000"
    }, 
    "description": "Local image descriptors construction and matching is a fundamental problem in computer vision, and has a profound influence on the related applications, such as object recognition, 3D reconstruction and image retrieval. To alleviate the shortcomings of the traditional methods for local descriptor construction, this proposal aims to propose data-driven methods for constructing local descriptor based on machine learning. Meanwhile, it also studies multiple descriptors fusion strategies to further improve their performance. The key issues include: (1) Modeling the local image description as a process of low-level feature extraction followed by feature pooling, then focused on the research of low-level feature extraction and feature pooling methods through machine learning;(2) Modeling the local image description as a process of dimension reduction or feature selection, then research on the methods for robustly converting images into vectors based on invariants, and research on the subspace learning as well as feature section methods for feature matching;(3) Research on the application of machine learning for multiple descriptors fusion in feature-level and in decision-level respectively. The outcomes would enrich methodology and provide novel ideas for feature description, feature matching, feature fusion and machi", 
    "endDate": "2015-12-30T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.419696.5", 
      "type": "Organization"
    }, 
    "id": "sg:grant.7010886", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "7010886"
        ]
      }, 
      {
        "name": "nsfc_id", 
        "type": "PropertyValue", 
        "value": [
          "61203277"
        ]
      }
    ], 
    "inLanguage": [
      "zh"
    ], 
    "keywords": [
      "METHODS", 
      "vector", 
      "feature selection", 
      "key issues", 
      "proposal", 
      "low-level feature extraction", 
      "research", 
      "fundamental problem", 
      "profound influence", 
      "performance", 
      "application", 
      "feature section methods", 
      "data", 
      "object recognition", 
      "local image description", 
      "related applications", 
      "feature-level", 
      "fusion mechanism", 
      "multiple descriptors fusion", 
      "methodology", 
      "process", 
      "novel idea", 
      "outcome", 
      "feature fusion", 
      "machine learning;(2", 
      "invariant", 
      "multiple descriptors fusion strategies", 
      "3D reconstruction", 
      "computer vision", 
      "subspace learning", 
      "feature matching", 
      "machine", 
      "shortcomings", 
      "features", 
      "feature description", 
      "image retrieval", 
      "traditional methods", 
      "matching", 
      "Local image descriptors construction", 
      "images", 
      "machine learning", 
      "machi", 
      "dimension reduction", 
      "decision-level", 
      "local descriptors", 
      "Local Image Feature Description", 
      "feature matching;(3", 
      "local descriptor construction"
    ], 
    "name": "Research on Local Image Feature Description and Fusion Mechanism Based on Machine Learning", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.429126.a", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.429126.a", 
          "name": "Institute of Automation, Chinese Academy of Sciences", 
          "type": "Organization"
        }, 
        "familyName": "Fan", 
        "givenName": "Bin", 
        "id": "sg:person.011540730761.41", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.011540730761.41", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.7010886"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:42", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsfc_projects_3.xml.gz", 
    "startDate": "2012-12-31T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://npd.nsfc.gov.cn/projectDetail.action?pid=61203277"
  }
]
 

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/grant.7010886'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.7010886'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.7010886'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.7010886'


 

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

92 TRIPLES      19 PREDICATES      70 URIs      62 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.7010886 schema:about anzsrc-for:2208
2 schema:amount N92895bfebbc84597a0f62e48ebcfa714
3 schema:description Local image descriptors construction and matching is a fundamental problem in computer vision, and has a profound influence on the related applications, such as object recognition, 3D reconstruction and image retrieval. To alleviate the shortcomings of the traditional methods for local descriptor construction, this proposal aims to propose data-driven methods for constructing local descriptor based on machine learning. Meanwhile, it also studies multiple descriptors fusion strategies to further improve their performance. The key issues include: (1) Modeling the local image description as a process of low-level feature extraction followed by feature pooling, then focused on the research of low-level feature extraction and feature pooling methods through machine learning;(2) Modeling the local image description as a process of dimension reduction or feature selection, then research on the methods for robustly converting images into vectors based on invariants, and research on the subspace learning as well as feature section methods for feature matching;(3) Research on the application of machine learning for multiple descriptors fusion in feature-level and in decision-level respectively. The outcomes would enrich methodology and provide novel ideas for feature description, feature matching, feature fusion and machi
4 schema:endDate 2015-12-30T00:00:00Z
5 schema:funder https://www.grid.ac/institutes/grid.419696.5
6 schema:identifier Nabcaebad062b47eb98bdb6c3f7001ee9
7 Nc524cc00354e4ae2b23ae6e78bdb3f5d
8 schema:inLanguage zh
9 schema:keywords 3D reconstruction
10 Local Image Feature Description
11 Local image descriptors construction
12 METHODS
13 application
14 computer vision
15 data
16 decision-level
17 dimension reduction
18 feature description
19 feature fusion
20 feature matching
21 feature matching;(3
22 feature section methods
23 feature selection
24 feature-level
25 features
26 fundamental problem
27 fusion mechanism
28 image retrieval
29 images
30 invariant
31 key issues
32 local descriptor construction
33 local descriptors
34 local image description
35 low-level feature extraction
36 machi
37 machine
38 machine learning
39 machine learning;(2
40 matching
41 methodology
42 multiple descriptors fusion
43 multiple descriptors fusion strategies
44 novel idea
45 object recognition
46 outcome
47 performance
48 process
49 profound influence
50 proposal
51 related applications
52 research
53 shortcomings
54 subspace learning
55 traditional methods
56 vector
57 schema:name Research on Local Image Feature Description and Fusion Mechanism Based on Machine Learning
58 schema:recipient N7f0b9ebea414452d9dd16a48760a167a
59 sg:person.011540730761.41
60 https://www.grid.ac/institutes/grid.429126.a
61 schema:sameAs https://app.dimensions.ai/details/grant/grant.7010886
62 schema:sdDatePublished 2019-03-07T12:42
63 schema:sdLicense https://scigraph.springernature.com/explorer/license/
64 schema:sdPublisher N9b92c5759e664e0d988d2739ac2e64b2
65 schema:startDate 2012-12-31T00:00:00Z
66 schema:url http://npd.nsfc.gov.cn/projectDetail.action?pid=61203277
67 sgo:license sg:explorer/license/
68 sgo:sdDataset grants
69 rdf:type schema:MonetaryGrant
70 N7f0b9ebea414452d9dd16a48760a167a schema:member sg:person.011540730761.41
71 schema:roleName PI
72 rdf:type schema:Role
73 N92895bfebbc84597a0f62e48ebcfa714 schema:currency CNY
74 schema:value 240000
75 rdf:type schema:MonetaryAmount
76 N9b92c5759e664e0d988d2739ac2e64b2 schema:name Springer Nature - SN SciGraph project
77 rdf:type schema:Organization
78 Nabcaebad062b47eb98bdb6c3f7001ee9 schema:name dimensions_id
79 schema:value 7010886
80 rdf:type schema:PropertyValue
81 Nc524cc00354e4ae2b23ae6e78bdb3f5d schema:name nsfc_id
82 schema:value 61203277
83 rdf:type schema:PropertyValue
84 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
85 rdf:type schema:DefinedTerm
86 sg:person.011540730761.41 schema:affiliation https://www.grid.ac/institutes/grid.429126.a
87 schema:familyName Fan
88 schema:givenName Bin
89 rdf:type schema:Person
90 https://www.grid.ac/institutes/grid.419696.5 schema:Organization
91 https://www.grid.ac/institutes/grid.429126.a schema:name Institute of Automation, Chinese Academy of Sciences
92 rdf:type schema:Organization
 




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


...