Method for evaluating performance of heterogeneous SAR (synthetic aperture radar) image feature matching algorithm

Abstract

The invention discloses a method for evaluating performance of heterogeneous SAR (synthetic aperture radar) image feature matching algorithms. The method comprises the following steps of 1) preparing an edge feature reference map based on the ROC classification decision criterion; 2) performing quantitative evaluation based on edge similarity measurement; 3) performing selection and optimization on SAR image evaluation indicators; and 4) performing qualitative evaluation based on an SVM evaluation model. The invention helps to shorten a development cycle of image matching of precision-guided weapon systems, reduce a period and times of outfield field experiment flights, realize automatic selection and optimization of the matching algorithms, and at the same time save many field experiment funds, human resources and material resources.

Description

Technical field [0001] The invention belongs to the field of remote sensing navigation, and specifically relates to a performance evaluation method of a heterogeneous SAR scene feature matching algorithm. Background technique [0002] Scene matching is a high-precision assisted navigation technology that collects real-time maps of a predetermined area during flight and compares them with reference maps pre-stored in the aircraft to obtain the current accurate position of the aircraft. Scene matching has the advantages of having nothing to do with voyage, high terminal guidance accuracy, and strong autonomy. It has a wide range of applications in aircraft integrated navigation. Compared with traditional visible light imaging and other methods, Synthetic Aperture Radar (SAR) has the characteristics of high resolution, all-weather and all-weather imaging, and its application in scene matching terminal guidance is of great significance. Considering the limitations of reconnaissance ...

AI Technical Summary

Problems solved by technology

Some studies divide the algorithm performance evaluation into two parts: test experiment and result analysis, but the structure of the evaluation system is simple and the function is single; The relationship between index systems; some inspected several measures in multimodal image registration, including entropy measure, PIU measure and improved PIU measure, and analyzed their differences in effectiveness and adaptability; some Some put forward five evaluation indicators of accuracy, robustness, automation, real-time and reliability, and discussed the evaluation timing; some combined DSP software and hardware technology with PC human-computer interaction technology to build a scene based on DSP platform The matching algorithm evaluates the environment, but it is only a simple framework, without establishing an evaluation model, but directly displays the evaluation results through matching probability, etc.

Images