19 November 2001 Massively parallel per-pixel-based zerotree processing architecture for real-time video compression
Author Affiliations +
In the span of a few years, mobile multimedia communication has rapidly become a significant area of research and development constantly challenging boundaries on a variety of technological fronts. Video compression, a fundamental component for most mobile multimedia applications, generally places heavy demands in terms of the required processing capacity. Hardware implementations of typical modern hybrid codecs require realisation of components such as motion compensation, wavelet transform, quantisation, zerotree coding and arithmetic coding in real-time. While the implementation of such codecs using a fast generic processor is possible, undesirable trade-offs in terms of power consumption and speed must generally be made. The improvement in power consumption that is achievable through the use of a slow-clocked massively parallel processing environment, while maintaining real-time processing speeds, should thus not be overlooked. An architecture to realise such a massively parallel solution for a zerotree entropy coder is, therefore, presented in this paper.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Geoffrey Alagoda, Alexander Mark Rassau, Kamran Eshraghian, "Massively parallel per-pixel-based zerotree processing architecture for real-time video compression", Proc. SPIE 4593, Design, Characterization, and Packaging for MEMS and Microelectronics II, (19 November 2001); doi: 10.1117/12.448851; https://doi.org/10.1117/12.448851

Back to Top