DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions

TL;DR

DEVO introduces a real-time stereo visual odometry method combining depth and event cameras, achieving high accuracy and robustness in challenging environments like low light or high motion, outperforming traditional RGB-D methods.

Contribution

The paper presents a novel semi-dense visual odometry framework that integrates event-based data with depth information for improved performance in difficult conditions.

Findings

Performs comparably to RGB-D methods in normal conditions

Outperforms in high dynamics and low illumination scenarios

Validated on diverse datasets

Abstract

We present a novel real-time visual odometry framework for a stereo setup of a depth and high-resolution event camera. Our framework balances accuracy and robustness against computational efficiency towards strong performance in challenging scenarios. We extend conventional edge-based semi-dense visual odometry towards time-surface maps obtained from event streams. Semi-dense depth maps are generated by warping the corresponding depth values of the extrinsically calibrated depth camera. The tracking module updates the camera pose through efficient, geometric semi-dense 3D-2D edge alignment. Our approach is validated on both public and self-collected datasets captured under various conditions. We show that the proposed method performs comparable to state-of-the-art RGB-D camera-based alternatives in regular conditions, and eventually outperforms in challenging conditions such as high dynamics or low illumination.