Three-Dimensional Transformation for Automatic Target Recognition Using LIDAR Data

The three-dimensional (3-D) nature and the unorganized structure of topographic LIDAR data pose several challenges for target recognition tasks. In the past, several approaches have applied two-dimensional transformations such as spin-images or Digital Elevation Maps (DEMs) as an intermediate step for analyzing the 3-D data with two-dimensional (2-D) methods. However, these techniques are computationally intensive and often sacrifice some of the overall geometrical relationship of the target points. In this paper, we present a simple and efficient 3-D spatial transformation that preserves the geometrical attributes of the LIDAR data in all its dimensions. This transformation permits the utilization of well established statistical and shape-based descriptors for the implementation of an automatic target recognition algorithm. We evaluate our transformation and analysis technique on a set of simulated LIDAR point clouds of ground vehicles with varied obstructions and noise levels. Classification results demonstrate that our approach is efficient, tolerant to scale, rotation, and robust to noise and other degradations.