MRS-VPR: a multi-resolution sampling based global visual place recognition method
This work addresses a bottleneck in visual navigation for robotics by offering an incremental improvement over SeqSLAM for more efficient loop closure detection.
The paper tackles the problem of inefficient sequential matching in visual place recognition for long-term navigation by proposing MRS-VPR, a multi-resolution sampling-based method that improves matching efficiency and accuracy, particularly when test sequences are smaller than reference ones, with experiments showing it outperforms SeqSLAM without losing accuracy.
Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions and changing viewpoints. It depends on a brute-force, time-consuming sequential matching method. We propose MRS-VPR, a multi-resolution, sampling-based place recognition method, which can significantly improve the matching efficiency and accuracy in sequential matching. The novelty of this method lies in the coarse-to-fine searching pipeline and a particle filter-based global sampling scheme, that can balance the matching efficiency and accuracy in the long-term navigation task. Moreover, our model works much better than SeqSLAM when the testing sequence has a much smaller scale than the reference sequence. Our experiments demonstrate that the proposed method is efficient in locating short temporary trajectories within long-term reference ones without losing accuracy compared to SeqSLAM.