|
|
Interest-Point Detection on CUDA
Ryba, Jan ; Řezníček, Ivo (referee) ; Herout, Adam (advisor)
Corner point detection is one of many functions used in computer vision for tasks such as tracking, detecting objects, comparing images and much more. Many of the algorithms are complex and require a lot of CPU time. This is where the CUDA platform comes in. CUDA kernels run parallely on graphic accelerators can rapidly decrease time needed for execution, allowing even these complex calculations to work in real time or even better. Text focuces on Moravec and Harris corner detection algorithms and their effective implementation on CUDA. Examination of potetntial and performance of CUDA platform is also importatnt.
|
|
|
The Acceleration of Communication and Manifestations of Everydayness in the Information Society. Parallel to the Approaches of Paul Virilio and Godfrey Reggio
Novotná, Eva ; Fišerová, Michaela (advisor) ; Sluková, Tereza (referee)
This thesis deals with the introduction of new technologies in the information society, which cause acceleration of aspects of everyday life. The consequence of this situation is the increased level of alienation and anonymity among people in cities. The thesis compares the view of two authors. The first one is a French writer and philosopher Paul Virilio, the other is an American director Godfrey Reggio. Both authors perceive the transformation of today's society negatively and describe the consequences arising from the introduction of new technologies. Each of them uses a different form of expression - Paul Virilio, writing and text, Godfrey Reggio, documentary films. Nevertheless, they have the same opinion on the relevant issues and come to similar conclusions. The aim of this thesis is to compare the two authors and their ideas and propose possible solutions to prevent negative consequences of acceleration of aspects of everyday life. Key words Virilio, Reggio, acceleration, technology, information society, media, communication
|
|
|
Interest-Point Detection on CUDA
Ryba, Jan ; Řezníček, Ivo (referee) ; Herout, Adam (advisor)
Corner point detection is one of many functions used in computer vision for tasks such as tracking, detecting objects, comparing images and much more. Many of the algorithms are complex and require a lot of CPU time. This is where the CUDA platform comes in. CUDA kernels run parallely on graphic accelerators can rapidly decrease time needed for execution, allowing even these complex calculations to work in real time or even better. Text focuces on Moravec and Harris corner detection algorithms and their effective implementation on CUDA. Examination of potetntial and performance of CUDA platform is also importatnt.
|
guest ::
