The two-dimensional Discrete Wavelet Transform (2D DWT) has become very popular as the basis of many recent image processing and compression techniques [1]. The 2D DWT has proved its efficiency in most application fields ranging from general-purpose multimedia to medical or satelite imaging. As a consequence, the forthcoming JPEG2000 standard for still image coding will feature the DWT as the first step of its compression scheme. Some applications, such as satelite imaging, require real-time on-the-fly image compression and transmission. Hardware implementation of a complete image compression scheme is a challenging benchmark for a System-on-Chip (SoC) approach, based on integrating and interfacing several blocks, or so-called Virtual Components (VC), each of which implements a given stage of the compression algorithm. In this paper, we introduce a first experiment consisting of designing a reusable 2D DWT virtual component. This component is described at the behavioral (algorithmic) level and the integration flow is based on a commercial high-level synthesis (HLS) tool.
[1]
Daniel D. Gajski,et al.
High ― Level Synthesis: Introduction to Chip and System Design
,
1992
.
[2]
I. Daubechies,et al.
Factoring wavelet transforms into lifting steps
,
1998
.
[3]
Catherine Lambert-Nebout,et al.
Status of onboard image compression for CNES space missions
,
1999,
Optics & Photonics.
[4]
G..
A Theory for Multiresolution Signal Decomposition : The Wavelet Representation
,
2004
.
[5]
Birgit Wirtz,et al.
Reuse Methodology Manual For System On A Chip Designs
,
2016
.