Good Feature Matching: Towards Accurate, Robust VO/VSLAM with Low Latency

TL;DR

This paper introduces an enhanced feature matching method for VSLAM that reduces latency while maintaining accuracy and robustness, bridging the gap between performance and efficiency in visual odometry systems.

Contribution

It proposes a novel active map-to-frame feature matching algorithm with optimized selection and acceleration techniques, integrated into existing VSLAM systems.

Findings

Significant latency reduction demonstrated on multiple benchmarks.

Maintains high accuracy and robustness comparable to state-of-the-art methods.

Effective in both monocular and stereo VSLAM systems.

Abstract

Analysis of state-of-the-art VO/VSLAM system exposes a gap in balancing performance (accuracy & robustness) and efficiency (latency). Feature-based systems exhibit good performance, yet have higher latency due to explicit data association; direct & semidirect systems have lower latency, but are inapplicable in some target scenarios or exhibit lower accuracy than feature-based ones. This paper aims to fill the performance-efficiency gap with an enhancement applied to feature-based VSLAM. We present good feature matching, an active map-to-frame feature matching method. Feature matching effort is tied to submatrix selection, which has combinatorial time complexity and requires choosing a scoring metric. Via simulation, the Max-logDet matrix revealing metric is shown to perform best. For real-time applicability, the combination of deterministic selection and randomized acceleration is studied. The proposed algorithm is integrated into monocular & stereo feature-based VSLAM systems. Extensive evaluations on multiple benchmarks and compute hardware quantify the latency reduction and the accuracy & robustness preservation.