Skip to Main content Skip to Navigation
Conference papers

End-to-end depth from motion with stabilized monocular videos

Abstract : We propose a depth map inference system from monocular videos based on a novel dataset for navigation that mimics aerial footage from gimbal stabilized monocular camera in rigid scenes. Unlike most navigation datasets, the lack of rotation implies an easier structure from motion problem which can be leveraged for different kinds of tasks such as depth inference and obstacle avoidance. We also propose an architecture for end-to-end depth inference with a fully convolutional network. Results show that although tied to camera inner parameters, the problem is locally solvable and leads to good quality depth prediction.
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01587652
Contributor : Clément Pinard <>
Submitted on : Thursday, September 14, 2017 - 3:08:22 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM

File

isprs-annals-IV-2-W3-67-2017.p...
Publisher files allowed on an open archive

Identifiers

Citation

Clément Pinard, Laure Chevalley, Antoine Manzanera, David Filliat. End-to-end depth from motion with stabilized monocular videos. International Conference on Unmanned Aerial Vehicles in Geomatics, Sep 2017, Bonn, Germany. pp.67-74, ⟨10.5194/isprs-annals-IV-2-W3-67-2017⟩. ⟨hal-01587652⟩

Share

Metrics

Record views

675

Files downloads

1032