Event-VPR: End-to-End Weakly Supervised Network Architecture for Event-based Visual Place Recognition
This addresses the problem of robust place recognition under dramatic illumination changes or fast motions for robotics and autonomous systems, presenting a novel approach but with incremental improvements in a specific domain.
The paper tackles visual place recognition in challenging environments by proposing an end-to-end network for event cameras, achieving better performance compared to classical methods on event-based and synthetic datasets.
Traditional visual place recognition (VPR) methods generally use frame-based cameras, which is easy to fail due to dramatic illumination changes or fast motions. In this paper, we propose an end-to-end visual place recognition network for event cameras, which can achieve good place recognition performance in challenging environments. The key idea of the proposed algorithm is firstly to characterize the event streams with the EST voxel grid, then extract features using a convolution network, and finally aggregate features using an improved VLAD network to realize end-to-end visual place recognition using event streams. To verify the effectiveness of the proposed algorithm, we compare the proposed method with classical VPR methods on the event-based driving datasets (MVSEC, DDD17) and the synthetic datasets (Oxford RobotCar). Experimental results show that the proposed method can achieve much better performance in challenging scenarios. To our knowledge, this is the first end-to-end event-based VPR method. The accompanying source code is available at https://github.com/kongdelei/Event-VPR.