Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization

Bruno Berenguel-Baeta, Antoine N. André, Guillaume Caron, Jesus Bermudez-Cameo, Jose J. Guerrero; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 6445-6448

Abstract

In this article we present a visual gyroscope based on equirectangular panoramas. We propose a new pipeline where we leverage the advantages of the combination of three different methods to obtain a fast and accurate estimation of the attitude of the camera. We quantitatively and qualitatively validate our method on two image sequences taken with a 360 dual-fisheye camera mounted on different aerial vehicles.

Related Material

[pdf]
[bibtex]
@InProceedings{Berenguel-Baeta_2023_CVPR, author = {Berenguel-Baeta, Bruno and Andr\'e, Antoine N. and Caron, Guillaume and Bermudez-Cameo, Jesus and Guerrero, Jose J.}, title = {Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {6445-6448} }