Skip to Main content Skip to Navigation
Journal articles

Direct model based visual tracking and pose estimation using mutual information

Guillaume Caron 1 Amaury Dame 2 Eric Marchand 3 
3 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : This paper deals with model-based pose estimation (or camera localization). The model is rendered as a virtual image and we propose a direct approach that takes into account the image as a whole. For this, we consider a sim- ilarity measure, the mutual information. Mutual information is a measure of the quantity of information shared by two signals (or two images in our case). Exploiting this measure allows our method to deal with different image modalities (real and synthetic). Furthermore, it handles occlusions and illu- mination changes. Results with synthetic (benchmark) and real image sequences, with static or mobile camera, demonstrate the robustness of the method and its ability to produce stable and precise pose estimations.
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download
Contributor : Eric Marchand Connect in order to contact the contributor
Submitted on : Thursday, October 31, 2013 - 6:23:37 PM
Last modification on : Thursday, January 20, 2022 - 4:20:33 PM
Long-term archiving on: : Saturday, February 1, 2014 - 4:31:18 AM


Files produced by the author(s)



Guillaume Caron, Amaury Dame, Eric Marchand. Direct model based visual tracking and pose estimation using mutual information. Image and Vision Computing, Elsevier, 2014, 32 (1), pp.54-63. ⟨10.1016/j.imavis.2013.10.007⟩. ⟨hal-00879104⟩



Record views


Files downloads