Automatic target recognition using passive infrared and laser radar sensors

A probe based approach combined with image modeling is used to recognize targets in passive Forward Looking Infrared (FLIR) and laser radar (LADAR) imagery. A probe is a mathematical function which operates locally on pixel values and produces output that is directly usable by an algorithm. An empirical probability density function of the probe values is obtained from a local region of the image, and used to estimate the probability that a target of known shape is present. Target shape information is obtained from three dimensional Computer Aided Design (CAD) models. Knowledge of the probe values along with probe probability density functions and target shape information allows the likelihood ratio between a target hypothesis and background hypothesis to be written. The generalized likelihood ratio test is used to accept one of the target poses or to choose the background hypothesis. The dissertation presents an image model for infrared images, the resulting recognition algorithm, and experimental results on real and synthetic FLIR imagery. An image model and recognition algorithm for resolved range and ambiguous range LADAR imagery is also presented, along with experimental results. A fusion recognition algorithm using collocated passive infrared and laser radar sensors is presented. Experimental results for the fusion algorithm are presented, along with results from the separate passive FLIR and LADAR algorithms, for comparison purposes. An algorithm, based on probes, for the registration of imagery from different sensor types is also presented. Registration results are shown for FLIR-LADAR, FLIR and synthetic aperature radar (SAR), and FLIR-TV sensors. FLIR-SAR registration is used to allow SAR cueing of the FLIR recognition algorithm, resulting in improved performance.