Memory Management for Real-Time Appearance-Based Loop Closure Detection

TL;DR

This paper introduces a memory management technique for real-time appearance-based loop closure detection in SLAM, ensuring consistent processing times regardless of map size, and demonstrates its effectiveness on standard datasets.

Contribution

A novel memory management method enabling scalable, real-time loop closure detection in large-scale SLAM systems, maintaining fixed computation times.

Findings

Maintains fixed processing time per observation

Demonstrates scalability on multiple datasets

Effective in large-scale, long-term SLAM scenarios

Abstract

Loop closure detection is the process involved when trying to find a match between the current and a previously visited locations in SLAM. Over time, the amount of time required to process new observations increases with the size of the internal map, which may influence real-time processing. In this paper, we present a novel real-time loop closure detection approach for large-scale and long-term SLAM. Our approach is based on a memory management method that keeps computation time for each new observation under a fixed limit. Results demonstrate the approach's adaptability and scalability using four standard data sets.