Visual Place Recognition (VPR) is a crucial task in robotics and autonomous driving, where it identifies the geographic location of a query image by matching it with a reference database. VPR faces significant challenges, including appearance variations due to lighting, occlusion, weather, and seasonal changes, alongside the need for real-time processing under low computational cost and latency. To address these challenges, we introduce Spiking Neural Networks (SNN) into the VPR task, specifically focusing on the feature aggregation component. SNNs, with their event-driven nature, offer advantages in computational efficiency and energy consumption, making them well-suited for energy-constrained environments such as drones. Our approach transforms the feature aggregation stage of VPR into a spiking, event-driven mechanism, which maintains high recall performance while integrating seamlessly with traditional ANN-based methods. Experimental results demonstrate that our SNN-based method effectively maintains high recall performance, validating its potential in autonomous driving and other related applications.

Visual place recognition,Spiking Neural Network,Feature Aggregation,Event-Driven Mechanism