Show simple item record

dc.contributor.authorDing, Xen
dc.contributor.authorChen, Wen
dc.contributor.authorWassell, Ianen
dc.date.accessioned2017-08-11T12:07:11Z
dc.date.available2017-08-11T12:07:11Z
dc.date.issued2017-07-15en
dc.identifier.issn1053-587X
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/266277
dc.description.abstractTensor compressive sensing (TCS) is a multidimensional framework of compressive sensing (CS), and it is advantageous in terms of reducing the amount of storage, easing hardware implementations, and preserving multidimensional structures of signals in comparison to a conventional CS system. In a TCS system, instead of using a random sensing matrix and a predefined dictionary, the average-case performance can be further improved by employing an optimized multidimensional sensing matrix and a learned multilinear sparsifying dictionary. In this paper, we propose an approach that jointly optimizes the sensing matrix and dictionary for a TCS system. For the sensing matrix design in TCS, an extended separable approach with a closed form solution and a novel iterative nonseparable method are proposed when the multilinear dictionary is fixed. In addition, a multidimensional dictionary learning method that takes advantages of the multidimensional structure is derived, and the influence of sensing matrices is taken into account in the learning process. A joint optimization is achieved via alternately iterating the optimization of the sensing matrix and dictionary. Numerical experiments using both synthetic data and real images demonstrate the superiority of the proposed approaches.
dc.description.sponsorshipThis work was supported in part by the EPSRC Research under Grant EP/K033700/1, in part by the Natural Science Foundation of China (61671046, 61401018), and in part by the State Key Laboratory of Rail Traffic Control and Safety (RCS2016ZT014) of Beijing Jiaotong University.
dc.language.isoenen
dc.publisherIEEE
dc.subjectMultidimensional systemen
dc.subjectCompressive sensingen
dc.subjectTensor compressive sensingen
dc.subjectDictionary learningen
dc.subjectSensing matrix optimizationen
dc.titleJoint sensing matrix and sparsifying dictionary optimization for tensor compressive sensingen
dc.typeArticle
prism.endingPage3646
prism.issueIdentifier14en
prism.publicationDate2017en
prism.publicationNameIEEE Transactions on Signal Processingen
prism.startingPage3632
prism.volume65en
dc.identifier.doi10.17863/CAM.12550
dcterms.dateAccepted2017-04-23en
rioxxterms.versionofrecord10.1109/TSP.2017.2699639en
rioxxterms.versionAMen
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-07-15en
dc.contributor.orcidWassell, Ian [0000-0001-7927-5565]
dc.identifier.eissn1941-0476
rioxxterms.typeJournal Article/Reviewen
pubs.funder-project-idEPSRC (EP/K033700/1)
cam.issuedOnline2017-04-28en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record