Muhammad Martuza

Learn More
The current trend of digital convergence leads to the need of the video decoder that should support multiple video standards such as, H.264/AVC, JPEG, MPEG-2, VC-1, and AVS on a single platform. In this paper, we present a resource-shared architecture of multiple transforms to support all five video codecs. The architecture is based on a new(More)
The current trend of digital convergence leads to the need of the video decoder that should support multiple video standards such as, H.264/AVC, JPEG, MPEG-2/4, VC-1, and AVS on a single platform. In this paper, we present a cost-sharing architecture of multiple transforms to support all five popular video codecs. The architecture is based on a new(More)
The paper presents a hybrid algorithm to compute the 8×8 Integer Inverse Discrete Cosine Transform (IDCT) of multiple modern codecs - AVS, VC-1, H.264/AVC, JPEG and MPEG-2. Based on the symmetric structure of the matrices and the similarity in matrix operation, we develop a factorizing algorithm to compute the 8×8 IDCT of first three(More)
In this brief, we present a reconfigurable architecture to implement variable block-size transforms (8-point, 16-point and 32-point) in HEVC. The scheme is based on internal sharing and reuse of transform coefficients and uses a novel two-level grouping strategy exploiting the mirror symmetry and mirror anti-symmetry of the coefficients. Additionally, we(More)
The state of the art video standard H.264/AVC is very popular worldwide for its efficient coding techniques. But recently the ITU-T Video Coding Experts Group (VCEG) and ISO/IEC Moving Picture Expert Group (MPEG) have been jointly developing the next generation video standard, called High Efficiency Video Coding (HEVC) which is expected to be more efficient(More)
The paper presents a cost-shared architecture to compute multiple integer discrete cosine transform (Int-DCT) of four video codecs—AVS, H.264/AVC, VC-1 and HEVC (under development). Based on the symmetric structure of the matrices and the similarity in matrix operation, we develop a generalized “decompose and share” algorithm to compute both 4 × 4 and 8 × 8(More)
  • 1