Stereo Event-based Visual-Inertial Odometry

TL;DR

This paper introduces the first visual-inertial odometry system for stereo event-based cameras, leveraging an Error-State Kalman Filter to achieve real-time, accurate pose estimation in challenging scenes.

Contribution

It presents a novel stereo event-based visual-inertial odometry method using ESKF, combining edge alignment and IMU data, with improved accuracy over existing methods.

Findings

Achieves real-time performance on standard CPU

Outperforms state-of-the-art stereo event-based visual odometry

Validated on public datasets with 6-DoF motion

Abstract

Event-based cameras are new type vision sensors whose pixels work independently and respond asynchronously to brightness change with microsecond resolution, instead of providing standard intensity frames. Compared with traditional cameras, event-based cameras have low latency, no motion blur, and high dynamic range (HDR), which provide possibilities for robots to deal with some challenging scenes. We propose a visual-inertial odometry for stereo event-based cameras based on Error-State Kalman Filter (ESKF). The visual module updates the pose relies on the edge alignment of a semi-dense 3D map to a 2D image, and the IMU module updates pose by median integral. We evaluate our method on public datasets with general 6-DoF motion and compare the results against ground truth. We show that our proposed pipeline provides improved accuracy over the result of the state-of-the-art visual odometry for stereo event-based cameras, while running in real-time on a standard CPU (low-resolution cameras). To the best of our knowledge, this is the first published visual-inertial odometry for stereo event-based cameras.