Input Based Resource Allocation in Motion Estimation using Re-configurable Architecture
S. Suhasini, J. Lavanya, M. Parameswari, G. Manikandan, S. Gracia Nissi
Abstract
Reconfigurable engineering can dynamically assign the assets during runtime. It tends to be adequately utilized in computationally escalated applications like media processing. In media processing, video compression is one of the most computationally intensive applications. ME is the basic undertaking in video pressure as it devours enormous measure of computational time for finding the best block match by calculating Sum of Absolute Difference (S AD) of different blocks in successive video frames. To overcome this problem, its inherent parallel execution nature is analysed and mapped into customized parallel reconfigurable engineering to adequately deal with the force and asset usage by unique reconfiguration. Application of reconfigurations in the hardware for block matching and comparator modules based on the level of motion in the input video can produce substantial optimization in terms of power and resource utilization.