SegMatch: Segment based loop-closure for 3D point clouds

Abstract

Loop-closure detection on 3D data is a challenging task that has been commonly approached by adapting image-based solutions. Methods based on local features suffer from ambiguity and from robustness to environment changes while methods based on global features are viewpoint dependent. We propose SegMatch, a reliable loop-closure detection algorithm based on the matching of 3D segments. Segments provide a good compromise between local and global descriptions, incorporating their strengths while reducing their individual drawbacks. SegMatch does not rely on assumptions of "perfect segmentation", or on the existence of "objects" in the environment, which allows for reliable execution on large scale, unstructured environments. We quantitatively demonstrate that SegMatch can achieve accurate localization at a frequency of 1Hz on the largest sequence of the KITTI odometry dataset. We furthermore show how this algorithm can reliably detect and close loops in real-time, during online operation. In addition, the source code for the SegMatch algorithm will be made available after publication.

8 pages, 8 figures

Cited by in corpus (25)

• RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation
• 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
• Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
• OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition
• SegMap: Segment-based mapping and localization using data-driven descriptors
• Keyframe-based monocular SLAM: design, survey, and future directions
• LocNet: Global localization in 3D point clouds for mobile vehicles
• Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
• Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling
• OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
• MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
• Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU
• Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation
• 3D Multi-Robot Patrolling with a Two-Level Coordination Strategy
• Augmenting Visual Place Recognition with Structural Cues
• Benchmarking Particle Filter Algorithms for Efficient Velodyne-Based Vehicle Localization
• Applications of Spiking Neural Networks in Visual Place Recognition
• Optimized SC-F-LOAM: Optimized Fast LiDAR Odometry and Mapping Using Scan Context
• Redundant Perception and State Estimation for Reliable Autonomous Racing
• GraffMatch: Global Matching of 3D Lines and Planes for Wide Baseline LiDAR Registration
• RecNet: An Invertible Point Cloud Encoding through Range Image Embeddings for Multi-Robot Map Sharing and Reconstruction
• LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks
• Data-driven Policy Transfer with Imprecise Perception Simulation
• Converting Depth Images and Point Clouds for Feature-based Pose Estimation
• Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAM