Exploitation of multi-camera configurations for visual surveillance

In this paper, we propose novel methods for background modeling, occlusion. handling and event recognition by using multi-camera configurations. Homography-related positions are utilized to construct a mixture of multivariate Gaussians to generate a background model for each pixel of the reference camera. Occlusion handling is achieved by generation of the top-view via trifocal tensors, as a result of matching over-segmented regions instead of pixels. The resulting graph is segmented into objects after determining the minimum spanning tree of this graph. Tracking of multiview data is obtained by utilizing measurements across the views in case of occlusions. Finally, the resulting trajectories are classified by GM-HMMs, yielding better results for using all different trajectories of the same object together.


Turgay, Emre; Akar, Gözde (2009-11-10)
In this paper a novel direction adaptive super-resolution (SR) image reconstruction method is proposed. The proposed maximum a-posteriori (MAP) based estimator uses gradient direction for optimal noise reduction while preserving the edges. Compared to the other edge-preserving methods, the proposed algorithm uses gradient direction in addition to the gradient amplitude for optimum regularization. The method comprises a gradient amplitude and direction estimation stage where a gradient direction map is obtai...
Piecewise-planar 3D reconstruction in rate-distortion sense
Imre, Evren; Gueduekbay, Ugur; Alatan, Abdullah Aydın (2007-05-09)
In this paper, a novel rate-distortion optimization inspired 3D piecewise-planar reconstruction algorithm is proposed. The algorithm refines a coarse 3D triangular mesh, by inserting vertices in a way to minimize the intensity difference between an image and its prediction. The preliminary experiments on synthetic and real data indicate the validity of the proposed approach.
Geospatial Object Recognition From High Resolution Satellite Imagery
Ergul, Mustafa; Alatan, Abdullah Aydın (2013-01-01)
In this paper, a novel automatic geo-spatial object recognition algorithm from high resolution satellite imagery is proposed. The proposed algorithm consists of two main steps; the generation of hypothesis with a local feature based algorithm and verification step with a shape based approach. The superiority of this method is the ability of minimization of false alarm number in the recognition and this is because object shape includes more characteristic and discriminative information about object identity ...
Durgun, Ahmet Cemal; Kuzuoğlu, Mustafa (2009-01-01)
In this paper, a novel algorithm for computing Physical Optics (PO) integrals is introduced. In this method, the integration problem is converted to an inverse problem by Levin's integration algorithm. Furthermore, the singularities, that are possible to occur in the applications of Levin's method, are handled by employing trapezoidal rule together with Levin's method. Finally, the computational accuracy of this new method is checked for some radar cross section (RCS) estimation problems performed on flat, ...
Implementation of turbulence models on 2d hybrid grids using an explicit/implicit multigrid algorithm
Yılmaz, Ali Emre; Tuncer, İsmail Hakkı; Department of Aerospace Engineering (2011)
In this thesis study, implementation, numerical stability and convergence rate issues of turbulence modeling are explored. For this purpose, a one equation turbulence model, Spalart-Allmaras, and a two-equation turbulence model, SST k-w, are adapted to an explicit, cell centered, finite volume method based, structured / hybrid multi grid flow solver, SENSE2D, developed at TUBITAK-SAGE. Governing equations for both the flow and the turbulence are solved in a loosely coupled manner, however, each set of equat...
Citation Formats
O. Akman, A. A. Alatan, and T. Çiloğlu, “Exploitation of multi-camera configurations for visual surveillance,” 2008, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/49126.