Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?
This work addresses the problem of adapting ground-based visual place recognition methods for aerial robots, which face unique challenges like viewpoint variation and resource constraints, and is incremental in nature.
The paper evaluated 8 state-of-the-art visual place recognition techniques on 2 aerial datasets, focusing on matching performance, processing power consumption, and memory requirements to assess their applicability to aerial robotics.
Visual Place Recognition (VPR) has seen significant advances at the frontiers of matching performance and computational superiority over the past few years. However, these evaluations are performed for ground-based mobile platforms and cannot be generalized to aerial platforms. The degree of viewpoint variation experienced by aerial robots is complex, with their processing power and on-board memory limited by payload size and battery ratings. Therefore, in this paper, we collect $8$ state-of-the-art VPR techniques that have been previously evaluated for ground-based platforms and compare them on $2$ recently proposed aerial place recognition datasets with three prime focuses: a) Matching performance b) Processing power consumption c) Projected memory requirements. This gives a birds-eye view of the applicability of contemporary VPR research to aerial robotics and lays down the the nature of challenges for aerial-VPR.