Robust temporal activity templates using higher order statistics.
Identifieur interne : 000360 ( PubMed/Corpus ); précédent : 000359; suivant : 000361Robust temporal activity templates using higher order statistics.
Auteurs : Alexia Briassouli ; Ioannis KompatsiarisSource :
- IEEE transactions on image processing : a publication of the IEEE Signal Processing Society [ 1941-0042 ] ; 2009.
English descriptors
- KwdEn :
- MESH :
- methods : Image Processing, Computer-Assisted, Video Recording.
- physiology : Motor Activity, Movement.
- Humans, Models, Statistical, Normal Distribution.
Abstract
A robust, theoretically founded approach for the extraction of temporal templates corresponding to areas of motion in video, is presented. Higher order statistics (kurtosis) are employed to extract activity areas, i.e., binary masks indicating which pixels in a video are active. The application of the kurtosis on illumination changes modeled as Gaussians and mixture of Gaussians is shown to be sensitive to outliers for both models, thus correctly localizing active pixels. Activity areas are compared to existing, difference-based temporal templates, known as motion energy images, and the robustness of both categories of temporal templates to additive noise is analyzed theoretically. Experiments with numerous real videos with additive noise, both indoors and outdoors, are conducted to compare the robustness of the activity areas and motion energy images, and their temporal extensions, the activity history areas, and motion history images. As expected from the theoretical analysis, the kurtosis-based activity areas prove to be more robust than the difference-based templates. Challenging videos containing occlusions, varying backgrounds, and shadows are also examined, and it is shown that the proposed approach outperforms the difference-based method for these cases, as well, consistently providing reliable localization of activity under a wide range of difficult circumstances. The proposed approach provides good results at a very low computational cost, and without requiring prior knowledge about the scene, nor training of any kind.
DOI: 10.1109/TIP.2009.2029595
PubMed: 19666336
Links to Exploration step
pubmed:19666336Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Robust temporal activity templates using higher order statistics.</title>
<author><name sortKey="Briassouli, Alexia" sort="Briassouli, Alexia" uniqKey="Briassouli A" first="Alexia" last="Briassouli">Alexia Briassouli</name>
<affiliation><nlm:affiliation>Informatics and Telematics Institute, CERTH-ITI, Thessaloniki, Greece. abria@iti.gr</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Kompatsiaris, Ioannis" sort="Kompatsiaris, Ioannis" uniqKey="Kompatsiaris I" first="Ioannis" last="Kompatsiaris">Ioannis Kompatsiaris</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2009">2009</date>
<idno type="doi">10.1109/TIP.2009.2029595</idno>
<idno type="RBID">pubmed:19666336</idno>
<idno type="pmid">19666336</idno>
<idno type="wicri:Area/PubMed/Corpus">000360</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000360</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Robust temporal activity templates using higher order statistics.</title>
<author><name sortKey="Briassouli, Alexia" sort="Briassouli, Alexia" uniqKey="Briassouli A" first="Alexia" last="Briassouli">Alexia Briassouli</name>
<affiliation><nlm:affiliation>Informatics and Telematics Institute, CERTH-ITI, Thessaloniki, Greece. abria@iti.gr</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Kompatsiaris, Ioannis" sort="Kompatsiaris, Ioannis" uniqKey="Kompatsiaris I" first="Ioannis" last="Kompatsiaris">Ioannis Kompatsiaris</name>
</author>
</analytic>
<series><title level="j">IEEE transactions on image processing : a publication of the IEEE Signal Processing Society</title>
<idno type="eISSN">1941-0042</idno>
<imprint><date when="2009" type="published">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Humans</term>
<term>Image Processing, Computer-Assisted (methods)</term>
<term>Models, Statistical</term>
<term>Motor Activity (physiology)</term>
<term>Movement (physiology)</term>
<term>Normal Distribution</term>
<term>Video Recording (methods)</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Image Processing, Computer-Assisted</term>
<term>Video Recording</term>
</keywords>
<keywords scheme="MESH" qualifier="physiology" xml:lang="en"><term>Motor Activity</term>
<term>Movement</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Humans</term>
<term>Models, Statistical</term>
<term>Normal Distribution</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A robust, theoretically founded approach for the extraction of temporal templates corresponding to areas of motion in video, is presented. Higher order statistics (kurtosis) are employed to extract activity areas, i.e., binary masks indicating which pixels in a video are active. The application of the kurtosis on illumination changes modeled as Gaussians and mixture of Gaussians is shown to be sensitive to outliers for both models, thus correctly localizing active pixels. Activity areas are compared to existing, difference-based temporal templates, known as motion energy images, and the robustness of both categories of temporal templates to additive noise is analyzed theoretically. Experiments with numerous real videos with additive noise, both indoors and outdoors, are conducted to compare the robustness of the activity areas and motion energy images, and their temporal extensions, the activity history areas, and motion history images. As expected from the theoretical analysis, the kurtosis-based activity areas prove to be more robust than the difference-based templates. Challenging videos containing occlusions, varying backgrounds, and shadows are also examined, and it is shown that the proposed approach outperforms the difference-based method for these cases, as well, consistently providing reliable localization of activity under a wide range of difficult circumstances. The proposed approach provides good results at a very low computational cost, and without requiring prior knowledge about the scene, nor training of any kind.</div>
</front>
</TEI>
<pubmed><MedlineCitation Owner="NLM" Status="MEDLINE"><PMID Version="1">19666336</PMID>
<DateCreated><Year>2009</Year>
<Month>11</Month>
<Day>12</Day>
</DateCreated>
<DateCompleted><Year>2010</Year>
<Month>01</Month>
<Day>15</Day>
</DateCompleted>
<Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1941-0042</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>18</Volume>
<Issue>12</Issue>
<PubDate><Year>2009</Year>
<Month>Dec</Month>
</PubDate>
</JournalIssue>
<Title>IEEE transactions on image processing : a publication of the IEEE Signal Processing Society</Title>
<ISOAbbreviation>IEEE Trans Image Process</ISOAbbreviation>
</Journal>
<ArticleTitle>Robust temporal activity templates using higher order statistics.</ArticleTitle>
<Pagination><MedlinePgn>2756-68</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1109/TIP.2009.2029595</ELocationID>
<Abstract><AbstractText>A robust, theoretically founded approach for the extraction of temporal templates corresponding to areas of motion in video, is presented. Higher order statistics (kurtosis) are employed to extract activity areas, i.e., binary masks indicating which pixels in a video are active. The application of the kurtosis on illumination changes modeled as Gaussians and mixture of Gaussians is shown to be sensitive to outliers for both models, thus correctly localizing active pixels. Activity areas are compared to existing, difference-based temporal templates, known as motion energy images, and the robustness of both categories of temporal templates to additive noise is analyzed theoretically. Experiments with numerous real videos with additive noise, both indoors and outdoors, are conducted to compare the robustness of the activity areas and motion energy images, and their temporal extensions, the activity history areas, and motion history images. As expected from the theoretical analysis, the kurtosis-based activity areas prove to be more robust than the difference-based templates. Challenging videos containing occlusions, varying backgrounds, and shadows are also examined, and it is shown that the proposed approach outperforms the difference-based method for these cases, as well, consistently providing reliable localization of activity under a wide range of difficult circumstances. The proposed approach provides good results at a very low computational cost, and without requiring prior knowledge about the scene, nor training of any kind.</AbstractText>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Briassouli</LastName>
<ForeName>Alexia</ForeName>
<Initials>A</Initials>
<AffiliationInfo><Affiliation>Informatics and Telematics Institute, CERTH-ITI, Thessaloniki, Greece. abria@iti.gr</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Kompatsiaris</LastName>
<ForeName>Ioannis</ForeName>
<Initials>I</Initials>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
<PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2009</Year>
<Month>08</Month>
<Day>07</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>IEEE Trans Image Process</MedlineTA>
<NlmUniqueID>9886191</NlmUniqueID>
<ISSNLinking>1057-7149</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList><MeshHeading><DescriptorName MajorTopicYN="N" UI="D006801">Humans</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D007091">Image Processing, Computer-Assisted</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="Y" UI="D015233">Models, Statistical</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D009043">Motor Activity</DescriptorName>
<QualifierName MajorTopicYN="N" UI="Q000502">physiology</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D009068">Movement</DescriptorName>
<QualifierName MajorTopicYN="N" UI="Q000502">physiology</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D016011">Normal Distribution</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D014741">Video Recording</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
</MeshHeadingList>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="aheadofprint"><Year>2009</Year>
<Month>8</Month>
<Day>07</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2009</Year>
<Month>8</Month>
<Day>12</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2009</Year>
<Month>8</Month>
<Day>12</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2010</Year>
<Month>1</Month>
<Day>16</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="doi">10.1109/TIP.2009.2029595</ArticleId>
<ArticleId IdType="pubmed">19666336</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/TelematiV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000360 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000360 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= TelematiV1 |flux= PubMed |étape= Corpus |type= RBID |clé= pubmed:19666336 |texte= Robust temporal activity templates using higher order statistics. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:19666336" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a TelematiV1
![]() | This area was generated with Dilib version V0.6.31. | ![]() |