1 / 4

Pablo F. Alcantarilla , Luis M. Bergasa

Pablo F. Alcantarilla , Luis M. Bergasa Department of Electronics, University of Alcalá, Madrid, Spain Olivier Stasse, Sebastien Druon Joint Robotics Laboratory, CNRS-AIST, Tsukuba, Japan Frank Dellaert School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA

Download Presentation

Pablo F. Alcantarilla , Luis M. Bergasa

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Pablo F. Alcantarilla, Luis M. Bergasa Department of Electronics, University of Alcalá, Madrid, Spain Olivier Stasse, Sebastien Druon Joint Robotics Laboratory, CNRS-AIST, Tsukuba, Japan Frank Dellaert School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA Submission to Autonomous Robots

  2. STEREO VISUAL SLAM • We learn a 3D map of the environment, by means of stereo visual SLAM techniques

  3. MONOCULAR VISION-BASED LOCALIZATION • Monocular Vision-Based Localization given a prior 3D map and camera poses from a previous 3D reconstruction • We perform Visibility Prediction to predict the most highly visible 3D points given a prior camera pose • Then, we establish 2D-3D correspondences between detected 2D features and 3D map elements • Finally, after data association we solve the PnP problem and estimate the localization of the robot in the map

  4. LOCALIZATION EXPERIMENTS O Detected 2D Features + Visible 3D Map Points Re-Projections Inlier PnP problem Outlier PnP problem + Predicted Visible 3D Points + 3D Map Points RGB Camera Pose Robot Trajectory

More Related