Leaving Flatland: Realtime 3D Stereo Semantic Reconstruction

We report our first experiences with Leaving Flatland, an exploratory project which studies the key challenges in closing the loop on autonomous perception and action in challenging terrain. A primary objective of the project is to demonstrate the acquisition and processing of robust 3D geometric model maps from stereo data and Visual Odometry techniques. The 3D geometric model is used to infer different terrain types and construct a 3D semantic model which can be used for path planning or teleoperation. This paper presents the set of methods and techniques used for building such a model, and provides insight on the mathematical optimizations used for obtaining realtime processing. To validate our approach, we show results obtained on multiple datasets and perform a comparison with other similar initiatives.