Volume IV-2/W3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W3, 49-57, 2017
https://doi.org/10.5194/isprs-annals-IV-2-W3-49-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W3, 49-57, 2017
https://doi.org/10.5194/isprs-annals-IV-2-W3-49-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.

  18 Aug 2017

18 Aug 2017

SQUEEZEPOSENET: IMAGE BASED POSE REGRESSION WITH SMALL CONVOLUTIONAL NEURAL NETWORKS FOR REAL TIME UAS NAVIGATION

M. S. Müller, S. Urban, and B. Jutzi M. S. Müller et al.
  • Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

Keywords: Pose Estimation, Navigation, Convolutional Neural Networks, Image-Based, UAV, UAS

Abstract. The number of unmanned aerial vehicles (UAVs) is increasing since low-cost airborne systems are available for a wide range of users. The outdoor navigation of such vehicles is mostly based on global navigation satellite system (GNSS) methods to gain the vehicles trajectory. The drawback of satellite-based navigation are failures caused by occlusions and multi-path interferences. Beside this, local image-based solutions like Simultaneous Localization and Mapping (SLAM) and Visual Odometry (VO) can e.g. be used to support the GNSS solution by closing trajectory gaps but are computationally expensive. However, if the trajectory estimation is interrupted or not available a re-localization is mandatory. In this paper we will provide a novel method for a GNSS-free and fast image-based pose regression in a known area by utilizing a small convolutional neural network (CNN). With on-board processing in mind, we employ a lightweight CNN called SqueezeNet and use transfer learning to adapt the network to pose regression. Our experiments show promising results for GNSS-free and fast localization.