Explicit Interaction for Fusion-Based Place Recognition

Fusion-based place recognition is an emerging technique jointly utilizing multi-modal perception data, to recognize previously visited places in GPS-denied scenarios for robots and autonomous vehicles. Recent fusion-based place recognition methods combine multi-modal features in implicit manners. While achieving remarkable results, they do not explicitly consider what the individual modality affords in the fusion system. Therefore, the benefit of multi-modal feature fusion may not be fully explored. In this paper, we propose a novel fusion-based network, dubbed EINet, to achieve explicit interaction of the two modalities. EINet uses LiDAR ranges to supervise more robust vision features for long time spans, and simultaneously uses camera RGB data to improve the discrimination of LiDAR point clouds. In addition, we develop a new benchmark for the place recognition task based on the nuScenes dataset. To establish this benchmark for future research with comprehensive comparisons, we introduce both supervised and self-supervised training schemes alongside evaluation protocols. We conduct extensive experiments on the proposed benchmark, and the experimental results show that our EINet exhibits better recognition performance as well as solid generalization ability compared to the state-of-the-art fusion-based place recognition approaches. Our open-source code and benchmark are released at: https://github.com/BIT-XJY/EINet.

Authors

• Jingyi Xu
• Junyi Ma
• Qi Wu 0007
• Zijie Zhou
• Yue Wang 0020
• Xieyuanli Chen
• Wenxian Yu
• Ling Pei

Keywords

• Training
• Point cloud compression
• Laser radar
• Protocols
• Benchmark testing
• Cameras
• Solids
• Rendering (computer graphics)
• Autonomous vehicles
• Intelligent robots
• Explicit Interactions
• Place Recognition
• Open-source Software
• Time Span
• Point Cloud
• Recognition Performance
• Feature Fusion
• Evaluation Protocol
• Fusion System
• LiDAR Point Clouds
• Positive Samples
• Negative Samples
• Learning Strategies
• Camera Images
• Image Sensor
• Distance Metrics
• Self-supervised Learning
• Contrastive Loss
• Global Descriptors
• Query Sample
• Camera Features
• Relative Pose
• Spherical Projection
• Time Metrics
• Triplet Loss
• Cross-modal Interactions
• Running Efficiency
• Ground Truth Position
• Large-scale Environments