Video target tracking by using competitive neural networks

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorAraujo, Ernesto
dc.creatorSilva, Cassiano R.
dc.creatorSampaio, Daniel J.B.S.
dc.date2014-05-27T11:23:49Z
dc.date2016-10-25T18:26:37Z
dc.date2014-05-27T11:23:49Z
dc.date2016-10-25T18:26:37Z
dc.date2008-12-01
dc.date.accessioned2017-04-06T01:34:40Z
dc.date.available2017-04-06T01:34:40Z
dc.identifierWSEAS Transactions on Signal Processing, v. 4, n. 8, p. 420-431, 2008.
dc.identifier1790-5022
dc.identifierhttp://hdl.handle.net/11449/70830
dc.identifierhttp://acervodigital.unesp.br/handle/11449/70830
dc.identifier2-s2.0-58249104081
dc.identifierhttp://www.wseas.us/e-library/transactions/signal/2008/28-145.pdf
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/891897
dc.descriptionA target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.
dc.languageeng
dc.relationWSEAS Transactions on Signal Processing
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectComputational intelligence
dc.subjectImage motion
dc.subjectNeural network
dc.subjectTarget tracking
dc.subjectVideo digital camera
dc.subjectArtificial intelligence
dc.subjectCameras
dc.subjectComputer graphics
dc.subjectDigital cameras
dc.subjectImage analysis
dc.subjectImage enhancement
dc.subjectIntelligent control
dc.subjectLearning algorithms
dc.subjectTargets
dc.subjectTracking (position)
dc.subjectVegetation
dc.subjectVideo cameras
dc.subjectColored images
dc.subjectCompetitive learnings
dc.subjectCompetitive neural networks
dc.subjectDigital sequences
dc.subjectMoving targets
dc.subjectPre-processing
dc.subjectReal times
dc.subjectReal worlds
dc.subjectSequence of images
dc.subjectTracking algorithms
dc.subjectVideo target tracking
dc.subjectWinning neurons
dc.subjectNeural networks
dc.titleVideo target tracking by using competitive neural networks
dc.typeOtro


Este ítem pertenece a la siguiente institución