An Efficient Index for Visual Search in Appearance-based SLAM

TL;DR

This paper introduces a graph-based nearest neighbor search method to accelerate vector-quantization in appearance-based SLAM, enabling real-time performance with minimal additional computational cost.

Contribution

It presents a novel integration of GNNS into BoW-based SLAM, significantly improving speed over existing methods with efficient index construction.

Findings

GNNS outperforms state-of-the-art search methods in speed.

The k-NN graph can be built with minimal extra cost during vocabulary creation.

Sequential image acquisition allows for further speedup in GNNS search.

Abstract

Vector-quantization can be a computationally expensive step in visual bag-of-words (BoW) search when the vocabulary is large. A BoW-based appearance SLAM needs to tackle this problem for an efficient real-time operation. We propose an effective method to speed up the vector-quantization process in BoW-based visual SLAM. We employ a graph-based nearest neighbor search (GNNS) algorithm to this aim, and experimentally show that it can outperform the state-of-the-art. The graph-based search structure used in GNNS can efficiently be integrated into the BoW model and the SLAM framework. The graph-based index, which is a k-NN graph, is built over the vocabulary words and can be extracted from the BoW's vocabulary construction procedure, by adding one iteration to the k-means clustering, which adds small extra cost. Moreover, exploiting the fact that images acquired for appearance-based SLAM are sequential, GNNS search can be initiated judiciously which helps increase the speedup of the quantization process considerably.