Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map

TLDR

While visual scene descriptors are well studied, place description using structural information remains underexplored, and recent SLAM advances now provide dense 3D maps enabling diverse sensor‑based localization. The authors propose Scan Context, a non‑histogram‑based global descriptor derived from 3D LiDAR scans, to enable global localization using structural information. Scan Context records the 3D structure of the visible space directly, uses a similarity score to compute distances between contexts, and employs a two‑phase search algorithm that makes loop detection invariant to LiDAR viewpoint changes, allowing detection in reverse revisits and corners. Evaluation on multiple 3D LiDAR benchmark datasets demonstrates that Scan Context achieves significantly improved loop‑detection performance.

Abstract

Compared to diverse feature detectors and descriptors used for visual scenes, describing a place using structural information is relatively less reported. Recent advances in simultaneous localization and mapping (SLAM) provides dense 3D maps of the environment and the localization is proposed by diverse sensors. Toward the global localization based on the structural information, we propose Scan Context, a non-histogram-based global descriptor from 3D Light Detection and Ranging (LiDAR) scans. Unlike previously reported methods, the proposed approach directly records a 3D structure of a visible space from a sensor and does not rely on a histogram or on prior training. In addition, this approach proposes the use of a similarity score to calculate the distance between two scan contexts and also a two-phase search algorithm to efficiently detect a loop. Scan context and its search algorithm make loop-detection invariant to LiDAR viewpoint changes so that loops can be detected in places such as reverse revisit and corner. Scan context performance has been evaluated via various benchmark datasets of 3D LiDAR scans, and the proposed method shows a sufficiently improved performance.