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

这个小企业创新研究（SBIR）第一阶段项目提议开发一种基于离散小波变换（DWT）的新型图像压缩/信号分解算法的硬件实现。这种完全并行的、低功耗的、可扩展的、多分辨率的实现特别适合使用在无线通信信道上的低比特率应用，如下一代支持web的手机。这种特殊的实现是小波变换的高效实现，并利用了一种新的重叠状态小波分解算法，该算法最大限度地减少了内存使用和处理器间通信开销。在接下来的十年里，消费者对快速移动语音和IP通信的需求在日益集成的地面和卫星无线电系统上不断上升，这些系统受到有限的电磁频谱分配的困扰，这就要求在低比特率下追求和开发更好的压缩算法。作为广泛研究的结果，变换编码技术实际上已经主导了迄今为止提出的每一个图像和视频编码方案。因此，高效的基于软件和硬件的转换编码系统设计和实现已经成为学术和商业研究中心的一个高优先级目标。

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 bothacademic and commercial research centers.