Parallel programming in SAR imaging processing

Abstract

Synthetic aperture radar (SAR) imaging processing is a complex operation that requires a large amount of floating point computations. It is very time-consuming to convert SAR raw data into imagery on microcomputers. The authors have successively developed SAR processors using two kinds of computers-JN3AR of distributed memory multiprocessor architecture (made in China), and SGI Origin 200 of scalable shared memory multiprocessor architecture. The SAR imaging efficiency has been greatly improved.