Deep Visual Odometry with Events and Frames

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pellerito, Roberto, Cannici, Marco, Gehrig, Daniel, Belhadj, Joris, Dubois-Matra, Olivier, Casasco, Massimo, Scaramuzza, Davide
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929493436792832
author Pellerito, Roberto
Cannici, Marco
Gehrig, Daniel
Belhadj, Joris
Dubois-Matra, Olivier
Casasco, Massimo
Scaramuzza, Davide
author_facet Pellerito, Roberto
Cannici, Marco
Gehrig, Daniel
Belhadj, Joris
Dubois-Matra, Olivier
Casasco, Massimo
Scaramuzza, Davide
contents Visual Odometry (VO) is crucial for autonomous robotic navigation, especially in GPS-denied environments like planetary terrains. To improve robustness, recent model-based VO systems have begun combining standard and event-based cameras. While event cameras excel in low-light and high-speed motion, standard cameras provide dense and easier-to-track features. However, the field of image- and event-based VO still predominantly relies on model-based methods and is yet to fully integrate recent image-only advancements leveraging end-to-end learning-based architectures. Seamlessly integrating the two modalities remains challenging due to their different nature, one asynchronous, the other not, limiting the potential for a more effective image- and event-based VO. We introduce RAMP-VO, the first end-to-end learned image- and event-based VO system. It leverages novel Recurrent, Asynchronous, and Massively Parallel (RAMP) encoders capable of fusing asynchronous events with image data, providing 8x faster inference and 33% more accurate predictions than existing solutions. Despite being trained only in simulation, RAMP-VO outperforms previous methods on the newly introduced Apollo and Malapert datasets, and on existing benchmarks, where it improves image- and event-based methods by 58.8% and 30.6%, paving the way for robust and asynchronous VO in space.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09947
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep Visual Odometry with Events and Frames
Pellerito, Roberto
Cannici, Marco
Gehrig, Daniel
Belhadj, Joris
Dubois-Matra, Olivier
Casasco, Massimo
Scaramuzza, Davide
Computer Vision and Pattern Recognition
Visual Odometry (VO) is crucial for autonomous robotic navigation, especially in GPS-denied environments like planetary terrains. To improve robustness, recent model-based VO systems have begun combining standard and event-based cameras. While event cameras excel in low-light and high-speed motion, standard cameras provide dense and easier-to-track features. However, the field of image- and event-based VO still predominantly relies on model-based methods and is yet to fully integrate recent image-only advancements leveraging end-to-end learning-based architectures. Seamlessly integrating the two modalities remains challenging due to their different nature, one asynchronous, the other not, limiting the potential for a more effective image- and event-based VO. We introduce RAMP-VO, the first end-to-end learned image- and event-based VO system. It leverages novel Recurrent, Asynchronous, and Massively Parallel (RAMP) encoders capable of fusing asynchronous events with image data, providing 8x faster inference and 33% more accurate predictions than existing solutions. Despite being trained only in simulation, RAMP-VO outperforms previous methods on the newly introduced Apollo and Malapert datasets, and on existing benchmarks, where it improves image- and event-based methods by 58.8% and 30.6%, paving the way for robust and asynchronous VO in space.
title Deep Visual Odometry with Events and Frames
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.09947