ORB-SLAM is a versatile and accurate SLAM solution for Monocular, Stereo and RGB-D cameras. It is able to compute
in real-time the camera trajectory and a sparse 3D reconstruction of the scene in
a wide variety of environments, ranging from small hand-held sequences of a desk to a car driven around several city blocks. It is able to
close large loops and perform global relocalisation in real-time and
from wide baselines. It includes an automatic and robust initialization from
planar and non-planar scenes. Demostrating videos, code and related publications are shown below.
We are currently able to perform semi-dense reconstructions using the accurately localised stream of keyframes from ORB-SLAM. Check our RSS 2015 paper . See the video below running in real-time in an intel core i7-4700MQ. No GPU acceleration was used. This module has not been released yet.
Raúl Mur-Artal and Juan D. Tardós. ORB-SLAM: Tracking and Mapping Recognizable Features. Robotics: Science and Systems (RSS) Workshop on Multi VIew Geometry in RObotics (MVIGRO), Berkeley, USA, July 2014. Oral presentation [pdf]