A Fast Voxel-Based Indicator for Change Detection Using Low Resolution Octrees

Abstract

<p><strong>Abstract.</strong> This paper proposes a change detection approach that uses a low-resolution octree enhanced with Gaussian kernels to describe free and occupied space. This so-called Gaussian Occupancy Octree is derived from range measurements and used to represent spatial information for a single epoch. Changes between epochs are encoded using a Delta Octree. A qualitative and quantitative evaluation of the proposed approach shows that its advantages are a fast runtime and the ability to make a statement about the re-exploration of space. An evaluation of the classification accuracy shows that our approach tents towards correct classifications with an overall accuracy of 51.5 %, but is also systematically biased towards the appearance of occupied space.</p>

Development and Testing of Octree-Based Intra-Voxel Statistical Inference to Enable Real-Time Geotechnical Monitoring of Large-Scale Underground Spaces with Mobile Laser Scanning Data

“…The loss of accuracy remains a concern, especially in safety-critical monitoring applications. Gehrung et al [68] address this in urban datasets by supplementing voxels with a local spatial data representation in the form of a Shortcomings of voxel-based representations include their susceptibility to discretization artifacts created when large, open scenes are not sufficiently observed and a loss in accuracy compared to the original point cloud data [66,67]. Underground mine envi-ronments present fewer discretization challenges due to their confined nature, high MLS sampling rates, and high point cloud density.…”

“…The loss of accuracy remains a concern, especially in safety-critical monitoring applications. Gehrung et al [68] address this in urban datasets by supplementing voxels with a local spatial data representation in the form of a three-dimensional Gaussian kernel. In a later version of their method, they detected the appearance and disappearance of objects like pedestrians and cars using a voxel edge length of 0.5 m [69].…”

Three Dimensional Change Detection Using Point Clouds: A Review

“…Each point is scanned independently, and its distance to adjacent points is not always fixed, as shown in Figure 1b, which makes their spatial structuration complex. In analogy to images where pixels are represented on a two-dimensional grid, and the space between two adjacent pixels is always fixed, the point cloud is sometimes transformed into voxels to facilitate processing [39,65].…”

“…The 3D CD methods can be subdivided into Point-Based (PBCD), Object-Based (OBCD) [36][37][38], and Voxel-Based (VBCD) [39][40][41]. OBCD allows the detection of changes at an object level (segment or clusters that group a set of homogeneous points, or an instance that belongs to a known object class, like tree, car, building, etc.).…”

“…CD of large and outdoor scene point clouds faces many challenges, including incomplete data, noise, artifacts caused by temporary or moving objects, and cross-source point clouds captured by different sensor types. To address these challenges, many studies have proposed different methods to use voxels and objects as basic units for change detection [38][39][40].…”