We propose an architecture appropriate for future Light Detection and Ranging (LIDAR) active homing seeker missiles with Automatic Target Recognition (ATR) capabilities. Our proposal enhances military targeting performance by extending ATR into the 3 rd dimension. From a military and aerospace industry point of view, this is appealing as weapon effectiveness against camouflage, concealment and deception techniques can be substantially improved. Specifically, we present a missile seeker 3D ATR architecture that relies on the 3D local feature based SHOT descriptor and a dual-role pipeline with a number of pre and post-processing operations. We evaluate our architecture on a number of missile engagement scenarios in various environmental setups with the missile being under various altitudes, obliquities, distances to the target and scene resolutions. Under these demanding conditions, the recognition performance gained is highly promising. Even in the extreme case of reducing the database entries to a single template per target, our interchangeable ATR architecture still provides a highly acceptable performance. Although we focus on future intelligent missile systems, our approach can be implemented to a great range of time-critical complex systems for space, air and ground environments for military, law-enforcement, commercial and research purposes.

Heat seeking missiles pose a major threat to air-, land-and sea-based military platforms, and ongoing research into developing techniques for countering these threats is vital. In order to counter the threat, one needs to understand its performance, by developing highfidelity models of infrared missile seekers. As seeker technologies advance, the capability exists to include more sophisticated countermeasure rejection techniques, and even techniques to discriminate between different potential targets. This paper considers the application of featurebased ship classification to the acquisition process of an imaging infrared missile in a naval engagement scenario. Scale invariant interest point detectors are used to extract keypoints and descriptors from simulated infrared imagery, generated by a high-fidelity infrared seeker model. Two methods are then used to classify the descriptors into different ship classes: the Generalised Hough Transform for pose estimation, and Bayes Decision Theory using Gaussian mixtures.

No abstract