A Minimal Subset Approach for Informed Keyframe Sampling in Large-Scale SLAM
Nikolaos Stathoulopoulos, Christoforos Kanellakis, George Nikolakopoulos
AI summary
Problem
Loop closure detection in large-scale SLAM scales quadratically with keyframes, causing prohibitive computational delays, high memory usage, and increased false positives that degrade mapping accuracy.
Approach
MSA employs a sliding window optimization in feature space to jointly minimize keyframe redundancy and preserve essential information, automatically selecting a minimal keyframe subset for real-time loop closure and pose graph optimization.
Key results
- Reduces false positive rates in place recognition compared to entropy-based baselines
- Achieves superior absolute and relative trajectory errors in metric localization
- Significantly lowers memory usage and computational overhead during loop closure detection
- Eliminates manual parameter tuning while maintaining consistent performance across diverse datasets
Why it matters
Enables scalable, real-time SLAM for large-scale missions by balancing computational efficiency with high localization and place recognition accuracy.
Abstract
Typical LiDAR SLAM architectures feature a front- end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale mis- sions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. Evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational over- head during loop closure detection and pose graph optimization.