An area-efficient IDCT architecture for multiple video standards

In this paper, we introduce a unified 1-D IDCT architecture for a video decoder supporting multiple standards including AVS, VC-1, MPEG-4 and H.264. The low-cost architecture is implemented by the method of matrix decomposition and sharing resources such as adders and shifters as far as possible. We make use of the coefficients in AVS and VC-1 to reduce the complexity of IDCT based on MPEG-4 greatly. And multipliers are replaced by shifters and adders, which are much more area-efficient. Researching on the relationship of coefficients among AVS, VC-1, and MPEG-4, we propose a low-cost hardware sharing architectures requiring lower hardware cost than that of the individual and separate implementations.