Robust Monocular Edge Visual Odometry through Coarse-to-Fine Data Association

TL;DR

This paper introduces a monocular visual odometry system that robustly tracks and maps using edge features, incorporating a novel data association method and uncertainty analysis to improve performance under lighting changes and large motions.

Contribution

It presents a new edge-guided data association pipeline with probabilistic search and confidence metrics, enhancing robustness and efficiency in monocular visual odometry.

Findings

Outperforms state-of-the-art algorithms on benchmark datasets.

Robust under illumination changes and large camera motions.

Reduces search space and improves mapping confidence.

Abstract

In this work, we propose a monocular visual odometry framework, which allows exploiting the best attributes of edge feature for illumination-robust camera tracking, while at the same time ameliorating the performance degradation of edge mapping. In the front-end, an ICP-based edge registration can provide robust motion estimation and coarse data association under lighting changes. In the back-end, a novel edge-guided data association pipeline searches for the best photometrically matched points along geometrically possible edges through template matching, so that the matches can be further refined in later bundle adjustment. The core of our proposed data association strategy lies in a point-to-edge geometric uncertainty analysis, which analytically derives (1) the probabilistic search length formula that significantly reduces the search space for system speed-up and (2) the geometrical confidence metric for mapping degradation detection based on the predicted depth uncertainty. Moreover, match confidence based patch size adaption strategy is integrated into our pipeline, connecting with other components, to reduce the matching ambiguity. We present extensive analysis and evaluation of our proposed system on synthetic and real-world benchmark datasets under the influence of illumination changes and large camera motions, where our proposed system outperforms current state-of-art algorithms.