In this work, we present a new lossy video compression scheme, based on the use of the 3D Fast Wavelet Transform (3D-FWT). This encoder achieves high compression ratio and a quality excellent from the point of medical view, because there are no differences between the original and the reconstructed video. On the other hand, we propose several techniques to allow the real-time video compression and transmission of the 3D-FWT in single processor architectures. We mitigate the memory problem by exploiting the memory hierarchy of the processor using the blocking techniques. We also put forward the reuse of previous computations in order to decrease the number of memory accesses and floating point operations. (Párrafo extraído del texto a modo de resumen)
© 2001-2024 Fundación Dialnet · Todos los derechos reservados