SURFER: SAR Unsupervised and Robust Feature ExtractoR

The NGA requires an automatic, unsupervised SAR feature extraction (AUFE) technique, that can ultimately be deployed for geospatial analysis, modeling, and target detection. Our proposed “SAR Unsupervised and Robust Feature ExtractoR” (SURFER) solution includes in Phase I: (1) a sound and deterministic assessment of the underlying RF phenomenology and SAR processing theoretical basis for effective, unsupervised feature clustering using attributes from SAR data, (2) an operable and demonstrable test and evaluation configuration to (a) test clustering algorithms with actual SAR data from Sentinel-1, and (b) provide clustering algorithm results from multiple algorithms that are directly associated with the theoretical basis; (3) a quantified feasibility proof, from deterministically analyzing the results from the theoretical basis and the testing or experiments; and (4) a preliminary design explicitly defining how the configuration and theoretical basis can be captured in a realized system for Phase II or beyond, to satisfy NGA requirements as well as those for other Government or commercial organizations.