Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling

TL;DR

Locus is a novel LiDAR-based place recognition method that encodes topological and temporal scene information, using second-order pooling to generate robust, discriminative global descriptors for large-scale environments.

Contribution

It introduces a new approach combining topological, temporal, and higher-order pooling features for improved place recognition in LiDAR data.

Findings

Outperforms state-of-the-art on KITTI dataset

Robust against occlusions and viewpoint changes

Effective in large-scale environments

Abstract

Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D LiDAR point clouds in large-scale environments. We propose a method for extracting and encoding topological and temporal information related to components in a scene and demonstrate how the inclusion of this auxiliary information in place description leads to more robust and discriminative scene representations. Second-order pooling along with a non-linear transform is used to aggregate these multi-level features to generate a fixed-length global descriptor, which is invariant to the permutation of input features. The proposed method outperforms state-of-the-art methods on the KITTI dataset. Furthermore, Locus is demonstrated to be robust across several challenging situations such as occlusions and viewpoint changes in 3D LiDAR point clouds. The open-source implementation is available at: https://github.com/csiro-robotics/locus .