A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition
This addresses the scalability and compute challenges in VPR for applications like robotics and autonomous systems, though it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of scaling compute and improving performance in Visual Place Recognition (VPR) by proposing Hyperdimensional One Place Signatures (HOPS), which fuses descriptors from multiple reference sets under different conditions, resulting in consistently improved recall performance across all evaluated methods and datasets by large margins.
Visual Place Recognition (VPR) enables coarse localization by comparing query images to a reference database of geo-tagged images. Recent breakthroughs in deep learning architectures and training regimes have led to methods with improved robustness to factors like environment appearance change, but with the downside that the required training and/or matching compute scales with the number of distinct environmental conditions encountered. Here, we propose Hyperdimensional One Place Signatures (HOPS) to simultaneously improve the performance, compute and scalability of these state-of-the-art approaches by fusing the descriptors from multiple reference sets captured under different conditions. HOPS scales to any number of environmental conditions by leveraging the Hyperdimensional Computing framework. Extensive evaluations demonstrate that our approach is highly generalizable and consistently improves recall performance across all evaluated VPR methods and datasets by large margins. Arbitrarily fusing reference images without compute penalty enables numerous other useful possibilities, three of which we demonstrate here: descriptor dimensionality reduction with no performance penalty, stacking synthetic images, and coarse localization to an entire traverse or environmental section.