ROCVMay 30, 2017

Efficient Decentralized Visual Place Recognition From Full-Image Descriptors

arXiv:1705.10739v138 citations
Originality Synthesis-oriented
AI Analysis

This work addresses scalability in multi-robot systems for visual place recognition, though it is incremental as it builds on prior decentralized methods.

The paper tackles the problem of decentralized visual place recognition by adapting a key-value lookup approach to full-image descriptors, resulting in a simpler system than previous methods but with limitations when deployment environments differ from training distributions.

In this paper, we discuss the adaptation of our decentralized place recognition method described in [1] to full image descriptors. As we had shown, the key to making a scalable decentralized visual place recognition lies in exploting deterministic key assignment in a distributed key-value map. Through this, it is possible to reduce bandwidth by up to a factor of n, the robot count, by casting visual place recognition to a key-value lookup problem. In [1], we exploited this for the bag-of-words method [3], [4]. Our method of casting bag-of-words, however, results in a complex decentralized system, which has inherently worse recall than its centralized counterpart. In this paper, we instead start from the recent full-image description method NetVLAD [5]. As we show, casting this to a key-value lookup problem can be achieved with k-means clustering, and results in a much simpler system than [1]. The resulting system still has some flaws, albeit of a completely different nature: it suffers when the environment seen during deployment lies in a different distribution in feature space than the environment seen during training.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes