Place recognition based on matching of planar surfaces and line segments

Abstract

This paper considers the potential of using three-dimensional (3D) planar surfaces and line segments detected in depth images for place recognition. A place recognition method is presented that is based on matching sets of surface and line features extracted from depth images provided by a 3D camera to features of the same type contained in a previously created environment model. The considered environment model consists of a set of local models representing particular locations in the modeled environment. Each local model consists of planar surface segments and line segments representing the edges of objects in the environment. The presented method is designed for indoor and urban environments. A computationally efficient pose hypothesis generation approach is proposed that ranks the features according to their potential contribution to the pose information, thereby reducing the time needed for obtaining accurate pose estimation. Furthermore, a robust probabilistic method for selecting the best pose hypothesis is proposed that allows matching of partially overlapping point clouds with gross outliers. The proposed approach is experimentally tested on a benchmark dataset containing depth images acquired in the indoor environment with changes in lighting conditions and the presence of moving objects. A comparison of the proposed method to FAB-MAP and DLoopDetector is reported.

Indoor Relocalization in Challenging Environments With Dual-Stream Convolutional Neural Networks

“…Cupec at el. [12] extracted robust line segments and planar surface segments as primitive features instead of feature points to recognize places. The system performed robustly even in some appearance changed environments.…”

Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction

“…Several researches [41,42,38,20] used visual features to identify loop closures, but they showed failure cases under pose variations as well as when revisiting poorly textured regions. Therefore, some researches [34,14,11,9] focused on solving this problem with geometric features. Assuming loop closures are given from a set of accurate correspondences, the pose graph optimization scheme has been widely employed [41,42,38,20,9] owning to its real-time performance.…”

Scene structure registration for localization and mapping

“…The technique we propose here is an extension of our previous work in [1], which can be seen as a combined geometric-photometric global descriptor where the scene is described by a set of neighbouring planar patches which capture information about the scene's global set-up. A recent work which is based on matching a set of planar patches and line segments is described in [11], however it is restricted to match images, in a similar fashion to the SLAM solution of [12], and does not exploit the fact that planar patches can be used to build a piecewise continuous representation using a graph. In contrast to previous registration approaches, our method is not limited to image registration, and therefore it can be applied to different sensors and can use information of several images or video sequences.…”

“…as it can happen in a staircase. A nice strategy to balance the two factors above is presented in [11] with the information content factor. This factor was defined according to both the uncertainty and the distribution of normal vectors of the set of planar patches, resulting in the following value of scene's planar information…”