Ahmed Ben Atitallah

Optimization and Implementation on Fpga of the DCT/IDCT Algorithm

In this paper, we present a comparison between two methods, the modified Loeffler algorithm (11 MUL and 29 ADD) and distributed arithmetic, to implement the DCT/IDCT algorithm for MPEG or H.26x video compression using VHDL description language. The implementation has been achieved on Altera Stratix EP1S10 FPGA which provides a dedicated DSP blocks required for common signal processing functions. A new solution based on this DSP blocks used to implement multipliers for the modified Loeffler algorithm in order to optimize speed and area

HW/SW Codesign of the H. 263 Video Coder

In this paper, we propose an optimized real-time H.263 video coder. The coder has been implemented in one FPGA device as HW/SW partitioned system. We made time analysis and optimization of the H.263 coder. On the basis of the achieved results, we decided for hardware implementation of the discrete cosine transform (DCT). Remaining parts were realized in software with NIOS II softcore processor. H.263 coder (NIOS II processor, DCT core) has been described by the VHDL language and implemented in Stratix EP1S10 FPGA. Finally, the coder has been tested on the Altera Stratix development board

FPGA Design of an Intra 16 × 16 Module for H.264/AVC Video Encoder

In this paper, we propose novel hardware architecture for intra 16 × 16 module for the macroblock engine of a new video coding standard H.264. To reduce the cycle of intra prediction 16 × 16, transform/quantization, and inverse quantization/inverse transform of H.264, an advanced method for different operation is proposed. This architecture can process one macroblock in 208 cycles for all cases of macroblock type by processing 4 × 4 Hadamard transform and quantization during 16 × 16 prediction. This module was designed using VHDL Hardware Description Language (HDL) and works with a 160 MHz frequency using ALTERA NIOS-II development board with Stratix II EP2S60F1020C3 FPGA. The system also includes software running on an NIOS-II processor in order to implementing the pre-processing and the post-processing functions. Finally, the execution time of our HW solution is decreased by 26% when compared with the previous work.