Skip to Main content Skip to Navigation

Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera

Abstract : Customer unmanned aerial vehicles (UAVs) are mainly flying cameras. They democratized aerial footage, but with thei success came security concerns.This works aims at improving UAVs security with obstacle avoidance, while keeping a smooth flight. In this context, we use only one stabilized camera, because of weight and cost incentives.For their robustness in computer vision and thei capacity to solve complex tasks, we chose to use convolutional neural networks (CNN). Our strategy is based on incrementally learning tasks with increasing complexity which first steps are to construct a depth map from the stabilized camera. This thesis is focused on studying ability of CNNs to train for this task.In the case of stabilized footage, the depth map is closely linked to optical flow. We thus adapt FlowNet, a CNN known for optical flow, to output directly depth from two stabilized frames. This network is called DepthNet.This experiment succeeded with synthetic footage, but is not robust enough to be used directly on real videos. Consequently, we consider self supervised training with real videos, based on differentiably reproject images. This training method for CNNs being rather novel in literature, a thorough study is needed in order not to depend too moch on heuristics.Finally, we developed a depth fusion algorithm to use DepthNet efficiently on real videos. Multiple frame pairs are fed to DepthNet to get a great depth sensing range.
Complete list of metadata

Cited literature [148 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Thursday, September 12, 2019 - 3:49:08 PM
Last modification on : Wednesday, May 11, 2022 - 3:20:03 PM
Long-term archiving on: : Saturday, February 8, 2020 - 10:15:24 AM


Version validated by the jury (STAR)


  • HAL Id : tel-02285215, version 1



Clément Pinard. Robust Learning of a depth map for obstacle avoidance with a monocular stabilized flying camera. Computer Vision and Pattern Recognition [cs.CV]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLY003⟩. ⟨tel-02285215⟩



Record views


Files downloads