Distributed 3D-Map Matching and Merging on Resource-Limited Platforms Using Tomographic Features

Halil Utku Unlu, Anthony Tzes, Prashanth Krishnamurthy, Farshad Khorrami

Abstract: A fast, robust, resource-efficient, and distributed 3D map matching and merging algorithm utilizing extracted tomographic features is studied. Instead of depending on 3D features and descriptors, 2D features are extracted from 2D projections of horizontal sections of gravity-aligned local maps and matched with slices from the other map at different height differences, enabling the estimation of four degrees of freedom. The proposed algorithm is observed to provide order-of-magnitude improvements in memory and time efficiency over state-of-the-art feature extraction and registration pipelines, rendering it useful for near real-time map merging tasks in resource-limited platforms (e.g. UAVs).