Enhancing 6D visual relocalisation with depth cameras

Jose Martinez Carranza, Andrew Calway, Walterio Mayol-Cuevas, Enhancing 6D visual relocalisation with depth cameras. International Conference on Intelligent Robots and Systems IROS. November 2013. No electronic version available.


Relocalisation in 6D is relevant to a variety of Robotics applications and in particular to agile cameras ex- ploring a 3D environment. While the geometry and appearance has been used by several relocalisation systems before, we are interested in using 3D information to assist faster robust pose estimation. Our approach rapidly searches for a reduced number of visual descriptors previously observed and stored in a database, that can be used to effectively compute the camera pose corresponding to the current view. We propose to guide the search by means of constructing validated sets using a 3D test involving the depth information obtained with an RGB- D or stereo camera. Our experiments demonstrate that this guided search returns a compact quality set that works better for the camera pose estimation stage than when using a typical 1-Nearest-Neighbour search over the candidate descriptors. The improvements are observed in terms of percentage of relocalised frames and speed, where the latter goes up to two order of magnitude w.r.t. the conventional search.

Bibtex entry.

Contact details

Publication Admin