File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Fast motion detection from airborne videos using graphics processing unit

TitleFast motion detection from airborne videos using graphics processing unit
Authors
Keywordsmotion detection
principal component analysis
complete unified device architecture
graphics processing unit
optical flow
Issue Date2012
PublisherSPIE - International Society for Optical Engineering. The Journal's web site is located at https://www.spiedigitallibrary.org/journals/journal-of-applied-remote-sensing
Citation
Journal of Applied Remote Sensing, 2012, v. 6, n. 1, article no. 061505 How to Cite?
AbstractIn our previous work, we proposed a joint optical flow and principal component analysis (PCA) approach to improve the performance of optical flow based detection, where PCA is applied on the calculated two-dimensional optical flow image, and motion detection is accomplished by a metric derived from the two eigenvalues. To reduce the computational time when processing airborne videos, parallel computing using graphic processing unit (GPU) is implemented on NVIDIA GeForce GTX480. Experimental results demonstrate that our approach can efficiently improve detection performance even with dynamic background, and processing time can be greatly reduced with parallel computing on GPU. © 2012 Society of Photo-Optical Instrumentation Engineers.
Persistent Identifierhttp://hdl.handle.net/10722/265485
ISSN
2023 Impact Factor: 1.4
2023 SCImago Journal Rankings: 0.409
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiu, Kui-
dc.contributor.authorMa, Ben-
dc.contributor.authorDu, Qian-
dc.contributor.authorChen, Genshe-
dc.date.accessioned2018-12-03T01:20:48Z-
dc.date.available2018-12-03T01:20:48Z-
dc.date.issued2012-
dc.identifier.citationJournal of Applied Remote Sensing, 2012, v. 6, n. 1, article no. 061505-
dc.identifier.issn1931-3195-
dc.identifier.urihttp://hdl.handle.net/10722/265485-
dc.description.abstractIn our previous work, we proposed a joint optical flow and principal component analysis (PCA) approach to improve the performance of optical flow based detection, where PCA is applied on the calculated two-dimensional optical flow image, and motion detection is accomplished by a metric derived from the two eigenvalues. To reduce the computational time when processing airborne videos, parallel computing using graphic processing unit (GPU) is implemented on NVIDIA GeForce GTX480. Experimental results demonstrate that our approach can efficiently improve detection performance even with dynamic background, and processing time can be greatly reduced with parallel computing on GPU. © 2012 Society of Photo-Optical Instrumentation Engineers.-
dc.languageeng-
dc.publisherSPIE - International Society for Optical Engineering. The Journal's web site is located at https://www.spiedigitallibrary.org/journals/journal-of-applied-remote-sensing-
dc.relation.ispartofJournal of Applied Remote Sensing-
dc.subjectmotion detection-
dc.subjectprincipal component analysis-
dc.subjectcomplete unified device architecture-
dc.subjectgraphics processing unit-
dc.subjectoptical flow-
dc.titleFast motion detection from airborne videos using graphics processing unit-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1117/1.JRS.6.061505-
dc.identifier.scopuseid_2-s2.0-84862091779-
dc.identifier.volume6-
dc.identifier.issue1-
dc.identifier.spagearticle no. 061505-
dc.identifier.epagearticle no. 061505-
dc.identifier.isiWOS:000304036500001-
dc.identifier.issnl1931-3195-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats