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.

One of the main problems associated with vision-based SLAM is the difficulty to find high-quality and indistinguishable landmarks which are detectable across significant viewpoint changes. Most of the current visual SLAM systems utilize the feature extraction methods that have been proposed for the offline computer vision tasks, which are either too slow for a real-time SLAM or not robust enough against viewpoint changes. In this paper, we demonstrate that by incorporating the position information of the robot into the feature description, we can help the feature matching process significantly.

Discerning depth from IR stereopsis is difficult because in general IR imagery does not contain sufficient features for left-right correspondence. We investigate the production of sparse disparity maps from uncalibrated infrared stereo images and argue that a dense depth field may not be attained directly from IR stereo images, but perhaps a sparse depth field may be obtained that can be interpolated to produce a dense depth field. In our proposed technique the sparse disparity map is produced by matching the stable features, extracted from the phase congruency model. A set of Log-Gabor wavelet coefficients is used to analyze and describe the extracted features for matching. The resulted sparse disparity map is then refined by triangular and epipolar geometrical constraints. In densifying the sparse disparity map, a watershed transformation is performed on the discontinuity map of the reference image to divide the image into several segments and finally the surface of each segment is reconstructed independently by fitting a thin-plate spline to its known disparities. Experiments on a set of IR stereo pairs lend credibility to the robustness of our IR stereo matching and surface reconstruction technique