Pose Independent Target Recognition System Using Pulsed Ladar Imagery

Although a number of object recognition techniques have been developed to process LADAR scanned terrain scenes, these techniques have had limited success in target discrimination in part due to low-resolution data and limits in available computation power. We present a pose-independent Automatic Target Detection and Recognition System that uses data from an airborne 3D imaging Ladar sensor. The Automatic Target Recognition system uses geometric shape and size signatures from target models to detect and recognize targets under heavy canopy and camouflage cover in extended terrain scenes. A method for data integration was developed to register multiple scene views to obtain a more complete 3D surface signature of a target. Automatic target detection was performed using the general approach of "3D cueing," which determines and ranks regions of interest within a large-scale scene based on the likelihood that they contain the respective target. Each region of interest is then passed to an ATR algorithm to accurately identify the target from among a library of target models. Automatic target recognition was performed using spin-image surface matching, a pose-independent algorithm that determines correspondences between a scene and a target of interest. Given a region of interest within a large-scale scene, the ATR algorithm either identifies the target from among a library of 10 target models or reports a "none of the above" outcome. The system performance was demonstrated on five measured scenes with targets both out in the open and under heavy canopy cover, where the target occupied between 1 to 10% of the scene by volume. The ATR section of the system was successfully demonstrated for twelve measured data scenes with targets both out in the open and under heavy canopy and camouflage cover. Correct target identification was also demonstrated for targets with multiple movable parts that are in arbitrary orientations. The system achieved a high recognition rate (over 99%) along with a low false alarm rate (less than 0.01%) The contributions of this thesis research are: 1) 1 implemented a novel technique for reconstructing multiple-view 3D Ladar scenes. 2) I demonstrated that spin-image-based detection and recognition is feasible for terrain data collected in the field with a sensor that may be used in a tactical situation and 3) I demonstrated recognition of articulated objects, with multiple movable parts. Immediate benefits of the presented work will be to the area of Automatic Target Recognition of military ground vehicles, where the vehicles of interest may include articulated components with variable position relative to the body, and come in many possible configurations. Other application areas include human detection and recognition for Homeland Security, and registration of large or extended terrain scenes.