Skip to Main content Skip to Navigation
Conference papers

Synchronisation et auto-étalonnage de plusieurs caméras fixées sur un casque

Abstract : This paper proposes methods that synchronize and self-calibrate helmet-held consumer cameras, without the use of a calibration pattern. The main assumption is that the cameras have the same setting (frequency, image resolution, field-of-view, roughly equiangular). First the synchronization is done using the fact that all cameras have the same rotation motion at the same time. Second, all extrinsic and intrinsic parameters are refined using Structure-from-Motion and bundle adjustment. Our experiments include both quantitative evaluation and urban videos acquired by a DIY multi-camera (4 GoPro cameras mounted on a helmet) that provides a 360 degree field-of-view in the horizontal plane.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01635426
Contributor : Maxime Lhuillier <>
Submitted on : Wednesday, November 15, 2017 - 10:48:50 AM
Last modification on : Tuesday, October 9, 2018 - 9:44:11 AM
Document(s) archivé(s) le : Friday, February 16, 2018 - 12:41:45 PM

File

pRfia16.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01635426, version 1

Citation

Thanh-Tin Nguyen, Maxime Lhuillier. Synchronisation et auto-étalonnage de plusieurs caméras fixées sur un casque. Congrès francophone AFRIF-AFIA de reconnaissance des formes et d'intelligence artificielle, Jun 2016, Clermont Ferrand, France. ⟨hal-01635426⟩

Share

Metrics

Record views

116

Files downloads

202