An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environments
This work addresses the need for low-overhead VPR techniques to enable robots with cheap hardware or free up resources on more powerful systems, though it is incremental as it builds on existing lightweight deep learning approaches.
The paper tackled the problem of visual place recognition (VPR) for robots with hardware constraints by proposing DrosoNet, a compact model inspired by fruit flies, and a voting mechanism using multiple classifiers. The result was state-of-the-art robustness to appearance and viewpoint changes, with evaluation on five benchmark datasets showing competitive precision-recall AUC and improved computational efficiency.
State-of-the-art visual place recognition performance is currently being achieved utilizing deep learning based approaches. Despite the recent efforts in designing lightweight convolutional neural network based models, these can still be too expensive for the most hardware restricted robot applications. Low-overhead VPR techniques would not only enable platforms equipped with low-end, cheap hardware but also reduce computation on more powerful systems, allowing these resources to be allocated for other navigation tasks. In this work, our goal is to provide an algorithm of extreme compactness and efficiency while achieving state-of-the-art robustness to appearance changes and small point-of-view variations. Our first contribution is DrosoNet, an exceptionally compact model inspired by the odor processing abilities of the fruit fly, Drosophyla melanogaster. Our second and main contribution is a voting mechanism that leverages multiple small and efficient classifiers to achieve more robust and consistent VPR compared to a single one. We use DrosoNet as the baseline classifier for the voting mechanism and evaluate our models on five benchmark datasets, assessing moderate to extreme appearance changes and small to moderate viewpoint variations. We then compare the proposed algorithms to state-of-the-art methods, both in terms of precision-recall AUC results and computational efficiency.