RGB-D-E: Event Camera Calibration for Fast 6-DOF Object Tracking

TL;DR

This paper introduces a novel RGB-D-E system combining event-based and traditional sensors to enhance 6-DOF object tracking speed and robustness for augmented reality, leveraging deep learning for high-frequency data processing.

Contribution

It is the first to integrate event-based cameras with RGB-D sensors for fast 6-DOF object tracking, improving robustness and speed in AR applications.

Findings

Significant improvement in tracking robustness.

Enhanced speed of 3D object tracking.

Effective combination of event-based and RGB-D data.

Abstract

Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth) which impose a high data bandwidth and power usage. With the necessity for low power and more responsive augmented reality systems, using solely frame-based sensors imposes limits to the various algorithms that needs high frequency data from the environement. As such, event-based sensors have become increasingly popular due to their low power, bandwidth and latency, as well as their very high frequency data acquisition capabilities. In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom. This application requires handling very high object speed to convey compelling AR experiences. To this end, we propose a new system which combines a recent RGB-D sensor (Kinect Azure) with an event camera (DAVIS346). We develop a deep learning approach, which combines an existing RGB-D network along with a novel event-based network in a cascade fashion, and demonstrate that our approach significantly improves the robustness of a state-of-the-art frame-based 6-DOF object tracker using our RGB-D-E pipeline.