Comparing Representations in Tracking for Event Camera-based SLAM

TL;DR

This paper compares and enhances event camera-based SLAM tracking by integrating time surface and event map representations, evaluating their strengths and limitations across diverse scenarios.

Contribution

It introduces a hybrid tracker that adaptively switches between representations based on degeneracy evaluation, improving robustness in event camera SLAM.

Findings

Hybrid tracker outperforms single-representation methods.

Representation limitations vary with scene and motion.

Adaptive switching enhances tracking robustness.

Abstract

This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM). Based on the original TS-based tracker, we make use of these two representations' complementary strengths to develop an enhanced version. The proposed tracker consists of a general strategy to evaluate the optimization problem's degeneracy online and then switch proper representations. Both TS and EM are motion- and scene-dependent, and thus it is important to figure out their limitations in tracking. We develop six tracker variations and conduct a thorough comparison of them on sequences covering various scenarios and motion complexities. We release our implementations and detailed results to benefit the research community on event cameras: https: //github.com/gogojjh/ESVO_extension.