Semantic Intelligent Understanding and Knowledge Generation of Target Features for SAR Images

Synthetic Aperture Radar (SAR) has been widely used in all kinds of earth observation and reconnaissance. However, the characteristics such as speckle noise, perspective contraction, top and bottom inversion and so on make the information extraction of SAR images difficult. The existing effective knowledge acquisition method knowledge graph is difficult to solve the problem of the knowledge extraction for the electromagnetic scattering characteristic data based on images and signals. This paper proposes a method to intelligently understand the semantic information of target features and to generate characteristic knowledge from SAR images. Experimental results verify the effectiveness of the proposed method for vehicle target regonition, analysis, and understanding.