SBIR Phase I: Parallel Hardware Implementation of the Split and Merge Discrete Wavelet Transform for Wireless Communication

Mosaix, Llc, Monrovia CA

Investigators

Abstract

This Small Business Innovative Research (SBIR) Phase I project proposes to develop the hardware implementation of a novel image compression/signal decomposition algorithm based on the discrete wavelet transform (DWT). This fully parallel, low-power, scalable, multi-resolution implementation is particularly well suited for use in reduced bit-rate applications over wireless communication channels as found in the next generation of web enabled cell phones. This particular implementation is a highly efficient implementation of the wavelet transform and makes use of a novel overlap state wavelet decomposition algorithm that minimizes both memory usage and interprocessor communication overhead. Over the next decade, spiraling consumer demand for fast mobile communication of voice and IP over increasingly integrated terrestrial and satellite-based radio systems plagued by a limited electromagnetic spectrum allocation necessitates the pursuit and development of better compression algorithms at low bit-rates. As a consequence of extensive research, transform-coding techniques has come to virtually dominate every single image and video coding scheme proposed to-date. Consequently, efficient software and hardware based transform coding system designs and implementations have become a high priority objective at both academic and commercial research centers.