Occupancy Grid Map Estimation Based on Visual SLAM and Ground Segmentation

Abstract

Feature-based SLAM is efficient, fast, and can offer an accurate localization system; on the other hand, the map produced is a sparse representation of the environment, limiting path planning activities and reducing robotic autonomy. We extend this mapping stage to build an occupancy grid map given the sparse point cloud. Our method uses the pose estimation from the SLAM system, its sparse map, and an image segmentation technique. Tests made in synthetic and real-world environments demonstrate maps with high precision and excellent coverage. Furthermore, the application can run in conjunction with the SLAM system in real-time while requiring a low memory footprint. Finally, the map generated represents high-level information that allows a link between a feature-based SLAM and navigation tasks.