File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Block-wise motion detection using compressive imaging system

TitleBlock-wise motion detection using compressive imaging system
Authors
KeywordsCompressive imaging
Feature-specific imaging
Motion detection
Gaussian mixture model
Tracking
Issue Date2011
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/optcom
Citation
Optics Communications, 2011, v. 284 n. 5, p. 1170-1180 How to Cite?
AbstractA block-wise motion detection strategy based on compressive imaging, also referred to as feature-specific imaging (FSI), is described in this work. A mixture of Gaussian distributions is used to model the background in a scene. Motion is detected in individual object blocks using feature measurements. Gabor, Hadamard binary and random binary features are studied. Performance of motion detection methods using pixel-wise measurements is analyzed and serves as a baseline for comparison with motion detection techniques based on compressive imaging. ROC (Receiver Operation Characteristic) curves and AUC (Area Under Curve) metrics are used to quantify the algorithm performance. Because a FSI system yields a larger measurement SNR (Signal-to-Noise Ratio) than a traditional system, motion detection methods based on the FSI system have better performance. We show that motion detection algorithms using Hadamard and random binary features in a FSI system yields AUC values of 0.978 and 0.969 respectively. The pixel-based methods are only able to achieve a lower AUC value of 0.627. © 2010 Elsevier B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/139225
ISSN
2015 Impact Factor: 1.48
2015 SCImago Journal Rankings: 0.778
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorKe, Jen_US
dc.contributor.authorAshok, Aen_US
dc.contributor.authorNeifeld, MAen_US
dc.date.accessioned2011-09-23T05:47:23Z-
dc.date.available2011-09-23T05:47:23Z-
dc.date.issued2011en_US
dc.identifier.citationOptics Communications, 2011, v. 284 n. 5, p. 1170-1180en_US
dc.identifier.issn0030-4018-
dc.identifier.urihttp://hdl.handle.net/10722/139225-
dc.description.abstractA block-wise motion detection strategy based on compressive imaging, also referred to as feature-specific imaging (FSI), is described in this work. A mixture of Gaussian distributions is used to model the background in a scene. Motion is detected in individual object blocks using feature measurements. Gabor, Hadamard binary and random binary features are studied. Performance of motion detection methods using pixel-wise measurements is analyzed and serves as a baseline for comparison with motion detection techniques based on compressive imaging. ROC (Receiver Operation Characteristic) curves and AUC (Area Under Curve) metrics are used to quantify the algorithm performance. Because a FSI system yields a larger measurement SNR (Signal-to-Noise Ratio) than a traditional system, motion detection methods based on the FSI system have better performance. We show that motion detection algorithms using Hadamard and random binary features in a FSI system yields AUC values of 0.978 and 0.969 respectively. The pixel-based methods are only able to achieve a lower AUC value of 0.627. © 2010 Elsevier B.V. All rights reserved.-
dc.languageengen_US
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/optcom-
dc.relation.ispartofOptics Communicationsen_US
dc.rightsNOTICE: this is the author’s version of a work that was accepted for publication in Optics Communications. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Optics Communications, 2011, v. 284 n. 5, p. 1170-1180. DOI: 10.1016/j.optcom.2010.11.028-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectCompressive imaging-
dc.subjectFeature-specific imaging-
dc.subjectMotion detection-
dc.subjectGaussian mixture model-
dc.subjectTracking-
dc.titleBlock-wise motion detection using compressive imaging systemen_US
dc.typeArticleen_US
dc.identifier.emailKe, J: junke@eee.hku.hken_US
dc.description.naturepostprint-
dc.identifier.doi10.1016/j.optcom.2010.11.028-
dc.identifier.scopuseid_2-s2.0-78751641943-
dc.identifier.hkuros192220en_US
dc.identifier.volume284en_US
dc.identifier.issue5-
dc.identifier.spage1170en_US
dc.identifier.epage1180en_US
dc.identifier.isiWOS:000287179500010-
dc.publisher.placeNetherlands-
dc.identifier.citeulike8341375-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats