5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      UAV Pose Estimation using Cross-view Geolocalization with Satellite Imagery

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          We propose an image-based cross-view geolocalization method that estimates the global pose of a UAV with the aid of georeferenced satellite imagery. Our method consists of two Siamese neural networks that extract relevant features despite large differences in viewpoints. The input to our method is an aerial UAV image and nearby satellite images, and the output is the weighted global pose estimate of the UAV camera. We also present a framework to integrate our cross-view geolocalization output with visual odometry through a Kalman filter. We build a dataset of simulated UAV images and satellite imagery to train and test our networks. We show that our method performs better than previous camera pose estimation methods, and we demonstrate our networks ability to generalize well to test datasets with unseen images. Finally, we show that integrating our method with visual odometry significantly reduces trajectory estimation errors.

          Related collections

          Most cited references14

          • Record: found
          • Abstract: not found
          • Article: not found

          ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              SVO: Fast semi-direct monocular visual odometry

                Bookmark

                Author and article information

                Journal
                16 September 2018
                Article
                1809.05979
                76bdaec6-bff0-4b33-b0d9-578942f01b1d

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                Submitted as contributed paper to ICRA 2019
                cs.RO

                Robotics
                Robotics

                Comments

                Comment on this article