Abstract
A novel scheme to compute energy on‐the‐fly and thereby control the quality of the image frames dynamically is presented along with its FPGA implementation. This scheme is suitable for incorporation in image compression systems such as video encoders. In this new scheme, processing is automatically stopped when the desired quality is achieved for the image being processed by using a concept called pruning. Pruning also increases the processing speed by a factor of more than two when compared to the conventional method of processing without pruning. An MPEG‐2 encoder implemented using this scheme is capable of processing good quality monochrome and color images of sizes up to 1024 × 768 pixels at the rate of 42 and 28 frames per second, respectively, with a compression ratio of over 17:1. The encoder is also capable of working in the fixed pruning level mode with user programmable features.
Highlights
Image processing applications such as high definition television, video conferencing, computer communication, etc. require large storage and high speed channels for handling huge volumes of image data
The basic operations that bring about image compression, namely, the Discrete Cosine Transform (DCT), Quantization (Q) and Variable Length Coding (VLC) are, common to all these standards
The processing time of DCTQ is 800 ns for PL0 because the first DC coefficient is issued at the twentieth clock cycle owing to high pipelining inherent in the design
Summary
Image processing applications such as high definition television, video conferencing, computer communication, etc. require large storage and high speed channels for handling huge volumes of image data. In order to reduce the processing time of still pictures, a modified adaptive pruning technique [8] was introduced at the DCT stage itself This method, is not suitable for implementation on FPGAs both from the quality and exacting speed considerations encountered in motion pictures. The present work considerably reduces these limitations by evaluating the image quality dynamically as DCT coefficients are being computed. The present design implemented on FPGAs is capable of throughputs of 50 Mbps meeting MPEG 2 standards [9] for processing I frames including the header and color information It has the following advantageous feature: while computing the (n þ 1)th block of DCTQ by the DCT and Quantization processor, the nth block of VLC can be executed in parallel since the nth block of DCTQ is already available. The sum of the squares of all the DCT coefficients or the spatial data values is the energy of the block, i.e
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
