Mining of Moving Objects from Time-Series Images and its Application to Satellite Weather Imagery View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2002-07

AUTHORS

Rie Honda, Shuai Wang, Tokio Kikuchi, Osamu Konishi

ABSTRACT

The framework of mining of moving objects from image data sequence is presented. Scenes are first clustered and labeled by using two-stage SOM that is modified to recognize images including similar moving objects as the same cluster, and that well recognizes scenes including prominent objects. After extraction of images which include prominent objects based on clustering result, the position and the shape of objects are approximated by using mixture gaussian model via EM algorithm, providing the adequate or larger number of components. By adopting the average of the data points in the smaller blocks as the initial parameters, the solutions are stabilized and the identification of components among time-series images and the tracking of a specific object become easier.This framework is applied to a four-year (ranging from 1997 to 2000) dataset of cloud images taken by Japanese weather satellite GMS-5 to evaluate its performance. Modified SOM method well classifies scenes which include prominent moving object, and seasonal variation tendency is detected in the cluster ID sequence. The result of object detection via EM algorithm for summer-type images including clear cloud masses such as typhoons shows that this approach well approximate the adequate distribution of cloud masses in many cases. Objects in the very irregular shapes are also well represented as the mixtures of gaussians.The extracted object information, together with the scene clustering result, is expected to offer us a rich source for knowledge discovery of video datasets. This approach is one of the effective ways of mining video images whose characteristics are unknown in advance, and thus applicable to the various type of applications. More... »

PAGES

79-93

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1015516504614

DOI

http://dx.doi.org/10.1023/a:1015516504614

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1047427472


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": "Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan", 
          "id": "http://www.grid.ac/institutes/grid.278276.e", 
          "name": [
            "Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Honda", 
        "givenName": "Rie", 
        "id": "sg:person.011505570273.04", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011505570273.04"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Anritsu Engineering Co., Ltd., Tamura-cyo 8-5, 243-001, Atsugi, Kanagawa, Japan", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Anritsu Engineering Co., Ltd., Tamura-cyo 8-5, 243-001, Atsugi, Kanagawa, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Shuai", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan", 
          "id": "http://www.grid.ac/institutes/grid.278276.e", 
          "name": [
            "Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kikuchi", 
        "givenName": "Tokio", 
        "id": "sg:person.014061245035.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014061245035.45"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Complex Systems, Future, University of Hakodate, 116-2 Kamedanakano-cho, 041-8655, Hakodate, Hokkaido, Japan", 
          "id": "http://www.grid.ac/institutes/grid.443610.4", 
          "name": [
            "Department of Complex Systems, Future, University of Hakodate, 116-2 Kamedanakano-cho, 041-8655, Hakodate, Hokkaido, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Konishi", 
        "givenName": "Osamu", 
        "id": "sg:person.012546024511.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012546024511.40"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/3-540-45884-0_26", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050948716", 
          "https://doi.org/10.1007/3-540-45884-0_26"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007400206189", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048353463", 
          "https://doi.org/10.1023/a:1007400206189"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-44794-6_17", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037092098", 
          "https://doi.org/10.1007/3-540-44794-6_17"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45884-0_29", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025313127", 
          "https://doi.org/10.1007/3-540-45884-0_29"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2002-07", 
    "datePublishedReg": "2002-07-01", 
    "description": "The framework of mining of moving objects from image data sequence is presented. Scenes are first clustered and labeled by using two-stage SOM that is modified to recognize images including similar moving objects as the same cluster, and that well recognizes scenes including prominent objects. After extraction of images which include prominent objects based on clustering result, the position and the shape of objects are approximated by using mixture gaussian model via EM algorithm, providing the adequate or larger number of components. By adopting the average of the data points in the smaller blocks as the initial parameters, the solutions are stabilized and the identification of components among time-series images and the tracking of a specific object become easier.This framework is applied to a four-year (ranging from 1997 to 2000) dataset of cloud images taken by Japanese weather satellite GMS-5 to evaluate its performance. Modified SOM method well classifies scenes which include prominent moving object, and seasonal variation tendency is detected in the cluster ID sequence. The result of object detection via EM algorithm for summer-type images including clear cloud masses such as typhoons shows that this approach well approximate the adequate distribution of cloud masses in many cases. Objects in the very irregular shapes are also well represented as the mixtures of gaussians.The extracted object information, together with the scene clustering result, is expected to offer us a rich source for knowledge discovery of video datasets. This approach is one of the effective ways of mining video images whose characteristics are unknown in advance, and thus applicable to the various type of applications.", 
    "genre": "article", 
    "id": "sg:pub.10.1023/a:1015516504614", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1327483", 
        "issn": [
          "0925-9902", 
          "1573-7675"
        ], 
        "name": "Journal of Intelligent Information Systems", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "19"
      }
    ], 
    "keywords": [
      "time-series images", 
      "framework of mining", 
      "similar moving objects", 
      "image data sequence", 
      "prominent objects", 
      "extraction of images", 
      "mixture Gaussian model", 
      "types of applications", 
      "mixture of Gaussians", 
      "knowledge discovery", 
      "video dataset", 
      "shape of objects", 
      "object detection", 
      "Moving Objects", 
      "EM algorithm", 
      "object information", 
      "two-stage SOM", 
      "video images", 
      "cloud images", 
      "specific objects", 
      "data sequence", 
      "scene", 
      "same cluster", 
      "SOM method", 
      "small blocks", 
      "mining", 
      "images", 
      "objects", 
      "algorithm", 
      "dataset", 
      "initial parameters", 
      "data points", 
      "Gaussian model", 
      "framework", 
      "large number", 
      "effective way", 
      "applications", 
      "tracking", 
      "SOM", 
      "ID sequence", 
      "information", 
      "imagery", 
      "extraction", 
      "performance", 
      "Gaussian", 
      "detection", 
      "rich source", 
      "identification of components", 
      "four-year dataset", 
      "GMS-5", 
      "solution", 
      "way", 
      "results", 
      "block", 
      "clusters", 
      "discovery", 
      "sequence", 
      "model", 
      "components", 
      "adequate distribution", 
      "method", 
      "advances", 
      "irregular shape", 
      "number", 
      "point", 
      "shape", 
      "identification", 
      "position", 
      "parameters", 
      "source", 
      "cloud mass", 
      "types", 
      "characteristics", 
      "typhoons", 
      "cases", 
      "variation tendency", 
      "distribution", 
      "average", 
      "tendency", 
      "mass", 
      "mixture", 
      "approach"
    ], 
    "name": "Mining of Moving Objects from Time-Series Images and its Application to Satellite Weather Imagery", 
    "pagination": "79-93", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1047427472"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1015516504614"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1015516504614", 
      "https://app.dimensions.ai/details/publication/pub.1047427472"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-05-20T07:22", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/article/article_356.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1023/a:1015516504614"
  }
]
 

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.10.1023/a:1015516504614'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/a:1015516504614'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1015516504614'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1015516504614'


 

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

182 TRIPLES      22 PREDICATES      112 URIs      100 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1015516504614 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nb82118fc743c435daf3161521ee62b9f
4 schema:citation sg:pub.10.1007/3-540-44794-6_17
5 sg:pub.10.1007/3-540-45884-0_26
6 sg:pub.10.1007/3-540-45884-0_29
7 sg:pub.10.1023/a:1007400206189
8 schema:datePublished 2002-07
9 schema:datePublishedReg 2002-07-01
10 schema:description The framework of mining of moving objects from image data sequence is presented. Scenes are first clustered and labeled by using two-stage SOM that is modified to recognize images including similar moving objects as the same cluster, and that well recognizes scenes including prominent objects. After extraction of images which include prominent objects based on clustering result, the position and the shape of objects are approximated by using mixture gaussian model via EM algorithm, providing the adequate or larger number of components. By adopting the average of the data points in the smaller blocks as the initial parameters, the solutions are stabilized and the identification of components among time-series images and the tracking of a specific object become easier.This framework is applied to a four-year (ranging from 1997 to 2000) dataset of cloud images taken by Japanese weather satellite GMS-5 to evaluate its performance. Modified SOM method well classifies scenes which include prominent moving object, and seasonal variation tendency is detected in the cluster ID sequence. The result of object detection via EM algorithm for summer-type images including clear cloud masses such as typhoons shows that this approach well approximate the adequate distribution of cloud masses in many cases. Objects in the very irregular shapes are also well represented as the mixtures of gaussians.The extracted object information, together with the scene clustering result, is expected to offer us a rich source for knowledge discovery of video datasets. This approach is one of the effective ways of mining video images whose characteristics are unknown in advance, and thus applicable to the various type of applications.
11 schema:genre article
12 schema:inLanguage en
13 schema:isAccessibleForFree false
14 schema:isPartOf N121789d0fcae408e8ec82b9cf268803a
15 N1d21d19f75ca4b19a59294ba1dfaebaa
16 sg:journal.1327483
17 schema:keywords EM algorithm
18 GMS-5
19 Gaussian
20 Gaussian model
21 ID sequence
22 Moving Objects
23 SOM
24 SOM method
25 adequate distribution
26 advances
27 algorithm
28 applications
29 approach
30 average
31 block
32 cases
33 characteristics
34 cloud images
35 cloud mass
36 clusters
37 components
38 data points
39 data sequence
40 dataset
41 detection
42 discovery
43 distribution
44 effective way
45 extraction
46 extraction of images
47 four-year dataset
48 framework
49 framework of mining
50 identification
51 identification of components
52 image data sequence
53 imagery
54 images
55 information
56 initial parameters
57 irregular shape
58 knowledge discovery
59 large number
60 mass
61 method
62 mining
63 mixture
64 mixture Gaussian model
65 mixture of Gaussians
66 model
67 number
68 object detection
69 object information
70 objects
71 parameters
72 performance
73 point
74 position
75 prominent objects
76 results
77 rich source
78 same cluster
79 scene
80 sequence
81 shape
82 shape of objects
83 similar moving objects
84 small blocks
85 solution
86 source
87 specific objects
88 tendency
89 time-series images
90 tracking
91 two-stage SOM
92 types
93 types of applications
94 typhoons
95 variation tendency
96 video dataset
97 video images
98 way
99 schema:name Mining of Moving Objects from Time-Series Images and its Application to Satellite Weather Imagery
100 schema:pagination 79-93
101 schema:productId N610414d70ecf43328721a41e6f2df014
102 N68ddb482d9fa45fbbabeed759c77a223
103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047427472
104 https://doi.org/10.1023/a:1015516504614
105 schema:sdDatePublished 2022-05-20T07:22
106 schema:sdLicense https://scigraph.springernature.com/explorer/license/
107 schema:sdPublisher N404a24383160436d9e8d5cbc17a2b7ee
108 schema:url https://doi.org/10.1023/a:1015516504614
109 sgo:license sg:explorer/license/
110 sgo:sdDataset articles
111 rdf:type schema:ScholarlyArticle
112 N121789d0fcae408e8ec82b9cf268803a schema:volumeNumber 19
113 rdf:type schema:PublicationVolume
114 N1d21d19f75ca4b19a59294ba1dfaebaa schema:issueNumber 1
115 rdf:type schema:PublicationIssue
116 N404a24383160436d9e8d5cbc17a2b7ee schema:name Springer Nature - SN SciGraph project
117 rdf:type schema:Organization
118 N4169e36df99a4eff9c93c43504012cbd schema:affiliation grid-institutes:None
119 schema:familyName Wang
120 schema:givenName Shuai
121 rdf:type schema:Person
122 N610414d70ecf43328721a41e6f2df014 schema:name doi
123 schema:value 10.1023/a:1015516504614
124 rdf:type schema:PropertyValue
125 N68ddb482d9fa45fbbabeed759c77a223 schema:name dimensions_id
126 schema:value pub.1047427472
127 rdf:type schema:PropertyValue
128 Nb61e33a97fc143dab42a01abb83e0ff8 rdf:first sg:person.014061245035.45
129 rdf:rest Nc1b0638cdccb4db98527c3a6ef2715f3
130 Nb82118fc743c435daf3161521ee62b9f rdf:first sg:person.011505570273.04
131 rdf:rest Nd5eab40498864c848ba4b1a13627bfa3
132 Nc1b0638cdccb4db98527c3a6ef2715f3 rdf:first sg:person.012546024511.40
133 rdf:rest rdf:nil
134 Nd5eab40498864c848ba4b1a13627bfa3 rdf:first N4169e36df99a4eff9c93c43504012cbd
135 rdf:rest Nb61e33a97fc143dab42a01abb83e0ff8
136 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
137 schema:name Information and Computing Sciences
138 rdf:type schema:DefinedTerm
139 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
140 schema:name Artificial Intelligence and Image Processing
141 rdf:type schema:DefinedTerm
142 sg:journal.1327483 schema:issn 0925-9902
143 1573-7675
144 schema:name Journal of Intelligent Information Systems
145 schema:publisher Springer Nature
146 rdf:type schema:Periodical
147 sg:person.011505570273.04 schema:affiliation grid-institutes:grid.278276.e
148 schema:familyName Honda
149 schema:givenName Rie
150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011505570273.04
151 rdf:type schema:Person
152 sg:person.012546024511.40 schema:affiliation grid-institutes:grid.443610.4
153 schema:familyName Konishi
154 schema:givenName Osamu
155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012546024511.40
156 rdf:type schema:Person
157 sg:person.014061245035.45 schema:affiliation grid-institutes:grid.278276.e
158 schema:familyName Kikuchi
159 schema:givenName Tokio
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014061245035.45
161 rdf:type schema:Person
162 sg:pub.10.1007/3-540-44794-6_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037092098
163 https://doi.org/10.1007/3-540-44794-6_17
164 rdf:type schema:CreativeWork
165 sg:pub.10.1007/3-540-45884-0_26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050948716
166 https://doi.org/10.1007/3-540-45884-0_26
167 rdf:type schema:CreativeWork
168 sg:pub.10.1007/3-540-45884-0_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025313127
169 https://doi.org/10.1007/3-540-45884-0_29
170 rdf:type schema:CreativeWork
171 sg:pub.10.1023/a:1007400206189 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048353463
172 https://doi.org/10.1023/a:1007400206189
173 rdf:type schema:CreativeWork
174 grid-institutes:None schema:alternateName Anritsu Engineering Co., Ltd., Tamura-cyo 8-5, 243-001, Atsugi, Kanagawa, Japan
175 schema:name Anritsu Engineering Co., Ltd., Tamura-cyo 8-5, 243-001, Atsugi, Kanagawa, Japan
176 rdf:type schema:Organization
177 grid-institutes:grid.278276.e schema:alternateName Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan
178 schema:name Department of Mathematics and Information Science, Kochi University, 2-5-1, Akebono-cho, 780-8520, Kochi, Japan
179 rdf:type schema:Organization
180 grid-institutes:grid.443610.4 schema:alternateName Department of Complex Systems, Future, University of Hakodate, 116-2 Kamedanakano-cho, 041-8655, Hakodate, Hokkaido, Japan
181 schema:name Department of Complex Systems, Future, University of Hakodate, 116-2 Kamedanakano-cho, 041-8655, Hakodate, Hokkaido, Japan
182 rdf:type schema:Organization
 




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


...