A robust aim point tracking algorithm for 3-D laser radar imagery

In this work, we present a controlled active vision tracking scheme that makes use of 3-D range data and 2-D reflectance data collected with a 3-D Laser Radar (3DLADAR) system. Specifically, our algorithm employs the Active Contour Framework along with a detection algorithm involving feedback to effectively maintain visual tracking of an object in adverse scenarios. As opposed to typical 2D systems, in which tracking is limited by a lack of contrast, 3DLADAR provides the capability to improve aim point tracking by encoding depth information so that the scene can be resolved for all spatial dimensions. We demonstrate the proposed algorithm both qualitatively and quantitatively on several challenging tracking scenarios.