Robust Gyroscope-Aided Camera Self-Calibration

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

Kuvaus

Camera calibration for estimating the intrinsic parameters and lens distortion is a prerequisite for various monocular vision applications including feature tracking and video stabilization. This application paper proposes a model for estimating the parameters on the fly by fusing gyroscope and camera data, both readily available in modern day smartphones. The model is based on joint estimation of visual feature positions, camera parameters, and the camera pose, the movement of which is assumed to follow the movement predicted by the gyroscope. Our model assumes the camera movement to be free, but continuous and differentiable, and individual features are assumed to stay stationary. The estimation is performed online using an extended Kalman filter, and it is shown to outperform existing methods in robustness and insensitivity to initialization. We demonstrate the method using simulated data and empirical data from an iPad.

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2018 21st International Conference on Information Fusion, FUSION 2018
TilaJulkaistu - 5 syyskuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Conference on Information Fusion - Cambridge, Iso-Britannia
Kesto: 10 heinäkuuta 201813 heinäkuuta 2018
Konferenssinumero: 21

Conference

ConferenceInternational Conference on Information Fusion
LyhennettäFUSION
MaaIso-Britannia
KaupunkiCambridge
Ajanjakso10/07/201813/07/2018

ID: 28605181