Back Propagation Neural Network Approach for SAR Raw Data Compression
Synthetic Aperture Radar (SAR) is a coherent active and high-resolution microwave imaging system with diverse applications in remote sensing. A significant characteristic of this system is the generation of a large amount of data that involves major problems related to on-board data storage. The near future SAR satellite missions planned would be pushing downlink data bandwidth to prohibitive levels. Given the unprecedented volume of data that will be generated by future high-resolution SAR satellites, the use of innovative data compression techniques will be essential if economically feasible. It is proposed to first pre-process the raw data and then to apply a suitable compression technique like back-propagation neural network whose on-board implementation would be efficient both in terms of speed and power.