Show simple item record

dc.contributor.authorKim, Kihwanen_US
dc.date.accessioned2013-06-15T02:58:28Z
dc.date.available2013-06-15T02:58:28Z
dc.date.issued2012-01-06en_US
dc.identifier.urihttp://hdl.handle.net/1853/47729
dc.description.abstractAnalysis and visualization of dynamic scenes is often constrained by the amount of spatio-temporal information available from the environment. In most scenarios, we have to account for incomplete information and sparse motion data, requiring us to employ interpolation and approximation methods to fill for the missing information. Scattered data interpolation and approximation techniques have been widely used for solving the problem of completing surfaces and images with incomplete input data. We introduce approaches for such data interpolation and approximation from limited sensors, into the domain of analyzing and visualizing dynamic scenes. Data from dynamic scenes is subject to constraints due to the spatial layout of the scene and/or the configurations of video cameras in use. Such constraints include: (1) sparsely available cameras observing the scene, (2) limited field of view provided by the cameras in use, (3) incomplete motion at a specific moment, and (4) varying frame rates due to different exposures and resolutions. In this thesis, we establish these forms of incompleteness in the scene, as spatio-temporal uncertainties, and propose solutions for resolving the uncertainties by applying scattered data approximation into a spatio-temporal domain. The main contributions of this research are as follows: First, we provide an efficient framework to visualize large-scale dynamic scenes from distributed static videos. Second, we adopt Radial Basis Function (RBF) interpolation to the spatio-temporal domain to generate global motion tendency. The tendency, represented by a dense flow field, is used to optimally pan and tilt a video camera. Third, we propose a method to represent motion trajectories using stochastic vector fields. Gaussian Process Regression (GPR) is used to generate a dense vector field and the certainty of each vector in the field. The generated stochastic fields are used for recognizing motion patterns under varying frame-rate and incompleteness of the input videos. Fourth, we also show that the stochastic representation of vector field can also be used for modeling global tendency to detect the region of interests in dynamic scenes with camera motion. We evaluate and demonstrate our approaches in several applications for visualizing virtual cities, automating sports broadcasting, and recognizing traffic patterns in surveillance videos.en_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectSurveillance applicationen_US
dc.subjectDynamic scene analysisen_US
dc.subjectScattered data approximationen_US
dc.subjectDynamic scene visualizationen_US
dc.subjectMultivew analysisen_US
dc.subjectVideo analysisen_US
dc.subjectScattered data interpolationen_US
dc.subject.lcshComputer vision
dc.subject.lcshImage processing
dc.subject.lcshInterpolation
dc.subject.lcshElectronic surveillance
dc.subject.lcshVideo surveillance
dc.titleSpatio-temporal data interpolation for dynamic scene analysisen_US
dc.typeDissertationen_US
dc.description.degreePhDen_US
dc.contributor.departmentComputingen_US
dc.description.advisorCommittee Chair: Essa, Irfan; Committee Member: Hodgins, Jessica; Committee Member: Rehg, James Matthew; Committee Member: Starner, Thad; Committee Member: Turk, Gregen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record