Show simple item record

dc.contributor.advisorÇetin, A. Enisen_US
dc.contributor.authorGünay, Osmanen_US
dc.date.accessioned2016-04-25T06:08:12Z
dc.date.available2016-04-25T06:08:12Z
dc.date.copyright2015-05
dc.date.issued2015-05
dc.date.submitted13-05-2015
dc.identifier.urihttp://hdl.handle.net/11693/28973
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (leaves 102-117).en_US
dc.descriptionThesis (Ph. D.): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2015.en_US
dc.description.abstractWe propose various image and video processing algorithms for wild re surveillance. The proposed methods include; classi er fusion, online learning, real-time feature extraction, image registration and optimization. We develop an entropy functional based online classi er fusion framework. We use Bregman divergences as the distance measure of the projection operator onto the hyperplanes describing the output decisions of classi ers. We test the performance of the proposed system in a wild re detection application with stationary cameras that scan prede ned preset positions. In the second part of this thesis, we investigate di erent formulations and mixture applications for passive-aggressive online learning algorithms. We propose a classi er fusion method that can be used to increase the performance of multiple online learners or the same learners trained with di erent update parameters. We also introduce an aerial wild re detection system to test the real-time performance of the analyzed algorithms. In the third part of the thesis we propose a real-time dynamic texture recognition method using random hyperplanes and deep neural networks. We divide dynamic texture videos into spatio-temporal blocks and extract features using local binary patterns (LBP). We reduce the computational cost of the exhaustive LBP method by using randomly sampled subset of pixels in the block. We use random hyperplanes and deep neural networks to reduce the dimensionality of the nal feature vectors. We test the performance of the proposed method in a dynamic texture database. We also propose an application of the proposed method in real-time detection of ames in infrared videos. Using the same features we also propose a fast wild re detection system using pan-tilt-zoom cameras and panoramic background subtraction. We use a hybrid method consisting of speeded-up robust features and mutual information to register consecutive images and form the panorama. The next step for multi-modal surveillance applications is the registration of images obtained with di erent devices. We propose a multi-modal image registration algorithm for infrared and visible range cameras. A new similarity measure is described using log-polar transform and mutual information to recover rotation and scale parameters. Another similarity measure is introduced using mutual information and redundant wavelet transform to estimate translation parameters. The new cost function for translation parameters is minimized using a novel lifted projections onto convex sets method.en_US
dc.description.statementofresponsibilityby Osman Günayen_US
dc.format.extentxix, 142 leaves : illustrations, charts.en_US
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectProjections onto convex setsen_US
dc.subjectClassi er fusionen_US
dc.subjectOnline learningen_US
dc.subjectEntropy maximizationen_US
dc.subjectWild re detectionen_US
dc.subjectAdaptive lteringen_US
dc.subjectLMSen_US
dc.subjectBregman divergenceen_US
dc.subjectImage processingen_US
dc.subjectInfrareden_US
dc.subjectMutual informationen_US
dc.subjectWavelet transformen_US
dc.subjectImage registrationen_US
dc.subjectLog-polar transformen_US
dc.subjectSupporting hyperplanesen_US
dc.titleVideo processing algorithms for wildfire surveillanceen_US
dc.title.alternativeOrman yangını gözetleme amaçlı video işleme algoritmalarıen_US
dc.typeThesisen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.publisherBilkent Universityen_US
dc.description.degreePh.D.en_US
dc.identifier.itemidB150074
dc.embargo.release2017-13-05


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record