Target recognition for articulated and occluded objects in Synthetic Aperture Radar imagery

Recognition of articulated occluded real-world man-made objects in Synthetic Aperture Radar (SAR) imagery has not been addressed in the field of image processing and computer vision. The traditional approach to object recognition in SAR imagery (at one foot or worse resolution) typically involves template matching methods, which are not suited for these cases because articulation of occlusion changes global features like the object outline and major axis. In this paper the performance of a model-based automatic target recognition (ATR) engine with articulated and occluded objects in SAR imagery is characterized based on invariant properties of the objects. Although the approach is related to geometric hashing, it is a novel approach for recognizing objects in SAR images. The novelty and power of the approach come from a combination of a SAR specific method for recognition, taking into account azimuthal variation, articulation invariants and sensor resolution.