Tag: parallel architectures

 
+

Architectures for Finite Radon Transform

Two VLSI architectures for the finite Radon transform are presented. The first is a reference architecture using memory blocks and the second is a memoryless architecture. The proposed architectures use 7×7 size image blocks and are prototyped for processing the CIF image sequence. The simulation and synthesis results show that the core speeds of the two proposed architectures are around 100 and 82 MHz, respectively.

Published in:

Electronics Letters (Volume:40 , Issue: 15 )

 

C. A. Rahman and W. Badawy, “Architectures for Finite Radon Transform“, The IEE Electronics Letters, Vol. 40, Issue 15, July 2004, pp. 931-932.

 

+

An Affine Based Algorithm and SIMD Architecture for Video Compression with Low Bit-rate Applications

This paper presents a new affine-based algorithm and SIMD architecture for video compression with low bit rate applications. The proposed algorithm is used for mesh-based motion estimation and it is named mesh-based square-matching algorithm (MB-SMA). The MB-SMA is a simplified version of the hexagonal matching algorithm [1]. In this algorithm, right-angled triangular mesh is used to benefit from a multiplication free algorithm presented in [2] for computing the affine parameters. The proposed algorithm has lower computational cost than the hexagonal matching algorithm while it produces almost the same peak signal-to-noise ratio (PSNR) values. The MB-SMA outperforms the commonly used motion estimation algorithms in terms of computational cost, efficiency and video quality (i.e., PSNR). The MB-SMA is implemented using an SIMD architecture in which a large number of processing elements has been embedded with SRAM blocks to utilize the large internal memory bandwidth. The proposed architecture needs 26.9 ms to process one CIF video frame. Therefore, it can process 37 CIF frames/s. The proposed architecture has been prototyped using Taiwan Semiconductor Manufacturing Company (TSMC) 0.18-μm CMOS technology and the embedded SRAMs have been generated using Virage Logic memory compiler.

Published in:

Circuits and Systems for Video Technology, IEEE Transactions on (Volume:16 , Issue: 4 )

Back to a complete list of Peer-Reviewed Journal Papers

Mohammed Sayed , Wael Badawy, “An Affine Based Algorithm and SIMD Architecture for Video Compression with Low Bit-rate Applications“, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 16, Issue 4, pp. 457-471, April 2006. Abstract