Densifying SLAM for UAV Navigation by Fusion of Monocular Depth Prediction
Authors:
- 10 February 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 225-229
Abstract
Simultaneous Localization and Mapping (SLAM) research has reached a level of maturity enabling systems to build autonomously an accurate sparse map of the environment while localizing themselves in that map. At the same time, the use of deep learning has recently brought great improvements in Monocular Depth Prediction (MDP). Some applications such as autonomous drone navigation and obstacle avoidance require dense structure information and cannot only rely on sparse SLAM representation. We propose to densify a state-of-the-art SLAM algorithm using deep learning-based dense MDP at keyframe rate. Towards this goal, we describe a scale recovery from SLAM landmarks by minimizing a depth error metric combined with a multi-view depth refinement using a volumetric approach. We conclude with experiments that attest the added value of our approach in terms of depth estimation.Keywords
This publication has 17 references indexed in Scilit:
- Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image2018
- Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- DeMoN: Depth and Motion Network for Learning Monocular Stereo2017
- Unsupervised Learning of Depth and Ego-Motion from Video2017
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue2016
- The EuRoC micro aerial vehicle datasetsThe International Journal of Robotics Research, 2016
- Rescue robots at earthquake-hit Mirandola, Italy: A field report2012
- A benchmark for the evaluation of RGB-D SLAM systems2012
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012