Leveraging BEV Representation for 360-degree Visual Place Recognition

TL;DR

This paper introduces a novel BEV-based approach for 360-degree visual place recognition, demonstrating improved performance through spatially aware feature extraction, deformation compensation, and rotation-invariant aggregation, validated on diverse datasets.

Contribution

It is the first to employ BEV representation in visual place recognition, integrating vision-LiDAR fusion and rotation-invariant features for enhanced accuracy.

Findings

BEV representation outperforms baseline methods in VPR tasks.

Deformable attention improves robustness to camera misalignments.

Rotation-invariant aggregation enhances recognition in varied orientations.

Abstract

This paper investigates the advantages of using Bird's Eye View (BEV) representation in 360-degree visual place recognition (VPR). We propose a novel network architecture that utilizes the BEV representation in feature extraction, feature aggregation, and vision-LiDAR fusion, which bridges visual cues and spatial awareness. Our method extracts image features using standard convolutional networks and combines the features according to pre-defined 3D grid spatial points. To alleviate the mechanical and time misalignments between cameras, we further introduce deformable attention to learn the compensation. Upon the BEV feature representation, we then employ the polar transform and the Discrete Fourier transform for aggregation, which is shown to be rotation-invariant. In addition, the image and point cloud cues can be easily stated in the same coordinates, which benefits sensor fusion for place recognition. The proposed BEV-based method is evaluated in ablation and comparative studies on two datasets, including on-the-road and off-the-road scenarios. The experimental results verify the hypothesis that BEV can benefit VPR by its superior performance compared to baseline methods. To the best of our knowledge, this is the first trial of employing BEV representation in this task.