Abstract: Disclosed are example embodiments of a method and system to reduce re-transmission requirements of a compress media transferring system implemented in a network where packet loss could be possible. An extended header for each transmitted packet can indicate the priority of the packet and endpoints can determine if a re-transmission of a missing packet is desired. Buffering of packets at different hops in a multi-hop system could allow for the retransmission request to be satisfied by a more recent hop than the original system transmitting the video packet. In one embodiment three levels of priority are established to achieve a reliable frame rate of 30 frames per second by compressing the first and second levels at 7.5 frames per second and a third level at 15 frames per second.

Abstract: A motion estimator uses many parallel Arithmetic-Logic-Unit (ALU) processors to simultaneously perform searches in many directions from a starting point. Each processor follows a different path outward from the starting point, generating sum-of-absolute differences (SADs) for each point in the path. A best SAD for the path is kept, along with an index into motion vector tables containing X,Y points for all paths. Current and best SAD's, thresholds, and indexes are stored in an ALU dedicated memory. When the number of best SAD's meeting thresholds exceeds a target, the current search-level ends. The index of the overall best SAD locates a new starting point, and a next-denser search-level is performed in the same manner, but over a smaller search area. Each processor calculates SAD's for one 16×16 macroblock, four 8×8 blocks, and 16 4×4 blocks and the net best SAD of these 3 types determines partitioning.

Abstract: A motion estimator uses many parallel Arithmetic-Logic-Unit (ALU) processors to simultaneously perform searches in many directions from a starting point. Each processor follows a different path outward from the starting point, generating sum-of-absolute differences (SADs) for each point in the path. A best SAD for the path is kept, along with an index into motion vector tables containing X,Y points for all paths. Current and best SAD's, thresholds, and indexes are stored in an ALU dedicated memory. When the number of best SAD's meeting thresholds exceeds a target, the current search-level ends. The index of the overall best SAD locates a new starting point, and a next-denser search-level is performed in the same manner, but over a smaller search area. Each processor calculates SAD's for one 16×16 macroblock, four 8×8 blocks, and 16 4×4 blocks and the net best SAD of these 3 types determines partitioning.