Automatic target recognition with synthetic aperture radar imagery.

摘要

Synthetic aperture radars (SARs) have become increasingly popular for a wide range of applications that require high resolution images of the Earth's surface independent of solar illumination and weather conditions. This thesis focuses on the development of an automatic target recognition (ATR) system using high resolution SAR imagery. The system achieves 98–100% recognition rates under standard operating conditions and 91–100% recognition rates under extended operating conditions when applied to the MSTAR image set; this is a substantial improvement compared to the previous 54–78% recognition rates for an earlier version of the Stanford system with synthesized XPATCH images. Typically, the system takes less than one minute to match the input image to a candidate vehicle class with Matlab programs running on a Pentium II 300 MHz machine.; An object-based recognition system is devised to identify ground vehicles in SAR images. Study of persistent scattering confirms the feasibility of implementing a SAR ATR system based on physical image features. A new generic vehicle model, parameterized by the length, width, and orientation of a target is used in a two-phase recognition process with hypothesis generation and verification aimed at addressing the combinatorial target recognition problem. In the hypothesis generation stage, a few likely candidate target classes are identified from a target database with positive evidence. The candidates are assessed using both positive and negative evidence in the hypothesis verification stage. Leading surface estimation, image alignment, Delaunay walk, recognition metrics, and interpolated templates are introduced to improve performance of the SAR ATR system.