Global ETD Search

301	Sledování více osob ve videu z jedné kamery / Multi-Person Tracking in Video from Mono-Camera Vojvoda, Jakub January 2016 (has links) Multiple person detection and tracking is challenging problem with high application potential. The difficulty of the problem is caused mainly by complexity of scene and large variations in articulation and appearance of person. The aim of this work is to design and implement system capable of detecting and tracking people in video from static mono-camera. For this purpose, an online method for tracking has been proposed based on tracking-by-detection approach. The method combines detection, tracking and fusion of responses to achieve accurate results. The implementation was evaluated on available dataset and the results show that it is suitable to use for this task. A method for motion segmentation was proposed and implemented to improve the tracking results. Furthermore, implementation of detector based on histogram of oriented gradients was accelerated by taking advantage of graphics processing unit (GPU).
302	Akcelerace genetického algoritmu s využitím GPU / The GPU-Based Acceleration of the Genetic Algorithm Pospíchal, Petr January 2009 (has links) This thesis represents master's thesis focused on acceleration of Genetic algorithms using GPU. First chapter deeply analyses Genetic algorithms and corresponding topics like population, chromosome, crossover, mutation and selection. Next part of the thesis shows GPU abilities for unified computing using both DirectX/OpenGL with Cg and specialized GPGPU libraries like CUDA. The fourth chapter focuses on design of GPU implementation using CUDA, coarse-grained and fine-grained GAs are discussed, and completed by sorting and random number generation task accelerated by GPU. Next chapter covers implementation details -- migration, crossover and selection schemes mapped on CUDA software model. All GA elements and quality of GPU results are described in the last chapter.
303	A Physically Based Pipeline for Real-Time Simulation and Rendering of Realistic Fire and Smoke / En fysiskt baserad rörledning för realtidssimulering och rendering av realistisk eld och rök He, Yiyang January 2018 (has links) With the rapidly growing computational power of modern computers, physically based rendering has found its way into real world applications. Real-time simulations and renderings of fire and smoke had become one major research interest in modern video game industry, and will continue being one important research direction in computer graphics. To visually recreate realistic dynamic fire and smoke is a complicated problem. Furthermore, to solve the problem requires knowledge from various areas, ranged from computer graphics and image processing to computational physics and chemistry. Even though most of the areas are well-studied separately, when combined, new challenges will emerge. This thesis focuses on three aspects of the problem, dynamic, real-time and realism, to propose a solution in form of a GPGPU pipeline, along with its implementation. Three main areas with application in the problem are discussed in detail: fluid simulation, volumetric radiance estimation and volumetric rendering. The weights are laid upon the first two areas. The results are evaluated around the three aspects, with graphical demonstrations and performance measurements. Uniform grids are used with Finite Difference (FD) discretization scheme to simplify the computation. FD schemes are easy to implement in parallel, especially with ComputeShader, which is well supported in Unity engine. The whole implementation can easily be integrated into any real-world applications in Unity or other game engines that support DirectX 11 or higher. Visualization Physically Based Pipeline Real-Time Dynamic Simulation Combustion Fire Explosion Smoke Thick Smoke Computer Graphics PDE Numerical Methods Grid Based Navier-Stokes Equation Imcompressible Fluid Radiative Transfer Equation RTE Volumetric Illumination Volumetric Rendering Volumetric Global Illumination Distant Light Source Volumetric Global Shadow Local Shadow Approximation Black-body Radiation Poisson Solver Spectroscopy Fire Color Color Reproduction Tone Mapping Color Temperature Color Matching Function Tristimulus CIE Standard Observer Color Space XYZ RGB GPU GPGPU ComputeShader DirectX 12 Unity C# Computer Sciences Datavetenskap (datalogi)

Page generated in 0.0168 seconds