%0 Conference Proceedings %T Generic edgelet-based tracking of 3D objects in real-time %+ Département Intelligence Ambiante et Systèmes Interactifs (DIASI) %+ Institut Pascal (IP) %A Loesch, A. %A Bourgeois, S. %A Gay-Bellile, V. %A Dhome, M. %Z Conference of IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015 ; Conference Date: 28 September 2015 Through 2 October 2015; Conference Code:117884 %< avec comité de lecture %B 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) %C Hamburg, Germany %I Institute of Electrical and Electronics Engineers Inc. %V 2015-December %P 6059-6066 %8 2015-09-02 %D 2015 %R 10.1109/IROS.2015.7354240 %K Cameras %K Computer aided design %K Intelligent robots %K Video streaming %K Analysis by synthesis %K CAD modeling %K Camera localization %K Graphics hardware %K Manual intervention %K SLAM algorithm %K Synthetic and real data %K Tracking solutions %K Three dimensional computer graphics %Z Engineering Sciences [physics]Conference papers %X This paper addresses the challenging issue of real-time camera localization relative to any object that have texture or not, sharp edges or occluding contours. 3D contour points, dynamically extracted from a CAD model by Analysis-by-Synthesis on the graphics hardware, are combined with a keyframe-based SLAM algorithm to estimate camera poses. Our tracking solution is accurate, robust to sudden motions and to occlusions, as demonstrated on synthetic and real data. This solution is also easy to deploy since it only uses an RGB camera and a CAD model of the object of interest, requires no manual intervention on this model and runs on a consumer tablet at a frequency of 40Hz on a HD video-stream. Videos are available as supplemental material. %G English %L cea-01813725 %U https://cea.hal.science/cea-01813725 %~ CEA %~ PRES_CLERMONT %~ CNRS %~ UNIV-BPCLERMONT %~ INSTITUT_PASCAL %~ DRT %~ CEA-UPSAY %~ UNIV-PARIS-SACLAY %~ CEA-UPSAY-SACLAY %~ LIST %~ GS-COMPUTER-SCIENCE %~ TEST3-HALCNRS