Multiresolution surface feature analysis for automatic target identification based on laser radar images

Automatic target recognition based on range image data acquired with laser radar imagers is a research topic that is of great interest to both the defense and manufacturing industries. A hybrid approach using both models and features for automatic target identification/recognition within laser radar images is presented. The multiscale and geometrical features are developed and deployed as input parameters for the proposed classification method. The experimental results show that the proposed method has achieved a satisfactory target classification.