Wide Area Video Motion Blur Elimination

This Small Business Technology Transfer Phase-II project will design, develop and integrate an effective and efficient motion blur elimination algorithm to Autonomous Real-time Ground Ubiquitous Surveillance - Imaging System (ARGUS-IS) system by optimizing and implementing the algorithm proposed during the Phase-I investigation to FPGA. In addition, an image enhancement toolkit for ground station video enhancement will be developed. High performance parallel architectures will be investigated and designed to enable real-time operation of such a toolkit. The key innovations in the proposed effort are: 1) a novel efficient algorithm for non-Linear Shift-Invariant (LSI) motion blur elimination, and 2) an efficient and optimized FPGA implementation of the deblurring module for ARGUS-IS system. The Phase-II effort will build on the achievements of the Phase-I investigation in further refining and optimizing the proposed blur elimination algorithm with regard to both quality and computational complexity. In particular, emphasis will be on a real-time FPGA implementation of the algorithm to meet the system and integration requirements of the ARGUS-IS system. The Phase-II effort will include: development of the enabling algorithms, FPGA implementation, support for system integration, demonstration of the proof of concept, computational complexity analysis and quantitative evaluation of the proposed technologies.