MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

12 Apr 2021  ·  Jacek Komorowski, Monika Wysoczanska, Tomasz Trzcinski ·

We introduce a discriminative multimodal descriptor based on a pair of sensor readings: a point cloud from a LiDAR and an image from an RGB camera. Our descriptor, named MinkLoc++, can be used for place recognition, re-localization and loop closure purposes in robotics or autonomous vehicles applications. We use late fusion approach, where each modality is processed separately and fused in the final part of the processing pipeline. The proposed method achieves state-of-the-art performance on standard place recognition benchmarks. We also identify dominating modality problem when training a multimodal descriptor. The problem manifests itself when the network focuses on a modality with a larger overfit to the training data. This drives the loss down during the training but leads to suboptimal performance on the evaluation set. In this work we describe how to detect and mitigate such risk when using a deep metric learning approach to train a multimodal neural network. Our code is publicly available on the project website: https://github.com/jac99/MinkLocMultimodal.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Retrieval Oxford RobotCar (LiDAR 4096 points) MinkLoc++ (LiDAR only) recall@top1% 98.2 # 8
recall@top1 93.9 # 8
Visual Place Recognition Oxford RobotCar (LiDAR 4096 points+RGB) MinkLoc++ (LiDAR+RGB) recall@top1% 99.1 # 1
recall@top1 96.7 # 1


No methods listed for this paper. Add relevant methods here