Improved Real-Time Scan Matching Using Corner Features

Abstract

ABSTRACT:The automation of unmanned vehicle operation has gained a lot of research attention, in the last few years, because of its numerous applications. The vehicle localization is more challenging in indoor environments where absolute positioning measurements (e.g. GPS) are typically unavailable. Laser range finders are among the most widely used sensors that help the unmanned vehicles to localize themselves in indoor environments. Typically, automatic real-time matching of the successive scans is performed either explicitly or implicitly by any localization approach that utilizes laser range finders. Many accustomed approaches such as Iterative Closest Point (ICP), Iterative Matching Range Point (IMRP), Iterative Dual Correspondence (IDC), and Polar Scan Matching (PSM) handles the scan matching problem in an iterative fashion which significantly affects the time consumption. Furthermore, the solution convergence is not guaranteed especially in cases of sharp maneuvers or fast movement. This paper proposes an automated real-time scan matching algorithm where the matching process is initialized using the detected corners. This initialization step aims to increase the convergence probability and to limit the number of iterations needed to reach convergence. The corner detection is preceded by line extraction from the laser scans. To evaluate the probability of line availability in indoor environments, various data sets, offered by different research groups, have been tested and the mean numbers of extracted lines per scan for these data sets are ranging from 4.10 to 8.86 lines of more than 7 points. The set of all intersections between extracted lines are detected as corners regardless of the physical intersection of these line segments in the scan. To account for the uncertainties of the detected corners, the covariance of the corners is estimated using the extracted lines variances. The detected corners are used to estimate the transformation parameters between the successive scan using least squares. These estimated transformation parameters are used to calculate an adjusted initialization for scan matching process. The presented method can be employed solely to match the successive scans and also can be used to aid other accustomed iterative methods to achieve more effective and faster converge. The performance and time consumption of the proposed approach is compared with ICP algorithm alone without initialization in different scenarios such as static period, fast straight movement, and sharp manoeuvers.

A Novel Real-Time Reference Key Frame Scan Matching Method

“…Using Hector SLAM with single level grid cell dimension is potentially apt to get stuck in local minima. Therefore, multi-resolution map representation is used to mitigate this problem [ 28 ]. However, these multiple map levels are memory and time consuming because they are keeping different map levels in memory and simultaneously updating them, furthermore, each level takes many iterations in order to converge.…”

“…The primary challenge for the ICP algorithm is determining the correct data association between the two point clouds. While the ICP algorithm encounters problems in data association during sharp rotation and/or fast movement, the corners registration method helps the ICP improve data association even in harsh situations [ 28 ]. Occasionally there are no new references matched with previous ones, and in this case, swapping to new reference lines occurs, creating new reference key frame.…”

Panoramic Image and Three-Axis Laser Scanner Integrated Approach for Indoor 3D Mapping

“…Getting the inspiration from the image matching method, the feature-based point cloud matching algorithm is designed based on extracted feature points, lines, and planes from a raw point cloud such as [34,35]. This method employs and extends some image feature extraction methods, such as SIFT, split-and-merge algorithm, and histogram cluster.…”

Multi‐slices navigation approach for unknown 3D environments using micro aerial vehicles

“…Thus, the compact representation is much more proper for search and rescue operations because the utilized MAVs are susceptible to loss during harsh situations. For efficient 3D mapping, many probabilistic approaches such as the voxel occupancy grids (Duffy et al, 1989; Plaza‐Leiva et al., 2015), elevation map (Hadsell et al, 2009; Herbert et al, 1989), multi‐level surface maps (MLS) (Rivadeneyra et al, 2009; Triebel et al., 2006), Octomap (Hornung et al, 2013; Wurm et al, 2010), multi‐volume occupancy grid (MVOG) (Dryanovski et al, 2010), multi‐level occupancy grid (MLOG) (Tian et al., 2016), and Occupancy Elevation Grid (OEG) (Souza & Gonçalves, 2016) are used.…”