基于DSP的2维离散小波变换快速实现(英文)  

Implementation of 2-D Fast Discrete Wavelet Transform Based on DSP

作　　者：陈鹏[1] 赵振纲[1] 

机构地区：[1]北京邮电大学信息工程学院,北京100876

出　　处：《科学技术与工程》2007年第20期5241-5245,共5页Science Technology and Engineering

摘　　要：小波域的图像处理技术已经广泛应用于各种领域,但2维离散小波变换的实现通常需要耗费大量时间和存储空间,在许多实时环境中,极大地降低了系统的效率和性能。为了充分利用计算资源文中利用数字信号处理器TMS320C6416T双向循环寻址和流水线技术的硬件特性,给出一种高速实现的方案。实验结果表明,卷积模式下的离散小波变换的快速实现能够满足实时处理的要求,并为今后的研究指明了应用前景。Image processing in wavelet domain has been adopted broadly in various fields. But the implementation of 2-D Discrete Wavelet Transform （2-D DWT） usually consumes lots of time and memory resources, which degrades its efficiency and performance fundamentally in many time critical environments. To make most. of the computing resources, hardware support specified for signal processing is introduced. Bidirectional circular addressing and pipelined program structure based on TMS320C6416T DSP were studied. Experimental results demonstrate that the DWT algorithm under convolution mode is capable of satisfying real-time requirements and therefore paves the way for future application.

关 键 词：离散小波变换 并行 循环寻址 数字信号处理器 

分 类 号：TN911.72[电子电信—通信与信息系统]