This paper presents a hardware implementation of the Hough technique applied to the tasks of irregular colour and grey-level pattern recognition. The presented method is based on the Hough Transform with a parameter space defined by translation, rotation and scaling operations. An essential element of this method is the generalisation of the Hough Transform for grey level and colour images. The technique simplifies the application of the Hough Transform to irregular patterns recognition tasks. The hardware implementation accelerates the calculations considerably and may be used in computer vision systems, for example, in a robotic system.
This paper presents an application of the Hough Transform to the tasks of learning and identifying irregular patterns in a computer vision system. The method presented is based on the Hough Transform with a parameter space defined by translation, rotation and scaling operations. A fundamental element of this method is the generalisation of the Hough Transform for grey-level and colour images. The technique may be used in a robotic system, identification system or for image analysis.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The paper presents an application of the Hough Transform to the tasks of learning and identifying irregular patterns in computer vision systems. The method presented is based on the Hough Transform with a parameter space defined by translation, rotation and scaling operations. An essential element of this method is the generalisation of the Hough Transform for grey-level images. The technique simplifies application of the Hough Transform to pattern recognition tasks as well as accelerates the calculations considerably. The technique could be used, for example, in a robotic system or for image analysis.
W artykule przedstawiono implementację techniki rozpoznawania wzorców nieregularnych przy zastosowaniu technologii CUDA. Zasygnalizowano możliwości współczesnych procesorów graficznych firmy NVIDIA o architekturze Fermi. Przytoczono podstawowe reguły programowania w C UDA. Dokonano wyboru metody segmentacji wzorcami nieregularnymi opartej na transformacie Hougha, jako odpowiedniej do wykorzystania potencjału procesora graficznego. Opisano kluczowe fragmenty implementacji. Dokonano weryfikacji działania w zakresie szybkości i poprawności obliczeń.
EN
An implementation of an irregular pattern recognition technique with the use of the CUDA technology is presented in the paper. The potential of the contemporary NVIDIA's graphics processing units based on the Fermi architecture is emphasized. Basic rules of the CUDA programming are described. The Hough method for irregular patterns segmentation, as suitable for the implementation, has been chosen. Parts of the written program crucial to the CUDA technology are explained. The implementation has been verified for the sake of speed and correctness.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.