Bi-directional Loop Closure for Visual SLAM

TL;DR

This paper introduces a bi-directional loop closure method for visual SLAM, enabling relocalization in reverse directions and reducing odometry drift, validated through extensive outdoor and indoor experiments.

Contribution

It presents the first approach for bi-directional loop closure detection in visual SLAM, including data selection, CNN training, and comprehensive empirical evaluation.

Findings

Effective in relocalizing in reverse directions

Reduces long-term odometry drift

Outperforms existing uni-directional methods

Abstract

A key functional block of visual navigation system for intelligent autonomous vehicles is Loop Closure detection and subsequent relocalisation. State-of-the-Art methods still approach the problem as uni-directional along the direction of the previous motion. As a result, most of the methods fail in the absence of a significantly similar overlap of perspectives. In this study, we propose an approach for bi-directional loop closure. This will, for the first time, provide us with the capability to relocalize to a location even when traveling in the opposite direction, thus significantly reducing long-term odometry drift in the absence of a direct loop. We present a technique to select training data from large datasets in order to make them usable for the bi-directional problem. The data is used to train and validate two different CNN architectures for loop closure detection and subsequent regression of 6-DOF camera pose between the views in an end-to-end manner. The outcome packs a considerable impact and aids significantly to real-world scenarios that do not offer direct loop closure opportunities. We provide a rigorous empirical comparison against other established approaches and evaluate our method on both outdoor and indoor data from the FinnForest dataset and PennCOSYVIO dataset.