An Efficient Index for Visual Search in Appearance-based SLAM
This addresses efficiency for real-time appearance-based SLAM systems, though it appears incremental as it builds on existing BoW and graph-based methods.
The paper tackles the computational expense of vector-quantization in visual bag-of-words search for SLAM by proposing a graph-based nearest neighbor search method, showing it outperforms state-of-the-art approaches with experimental speedups.
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.