Plane detection in 3D point cloud using octree‐balanced density down‐sampling and iterative adaptive plane extraction

Abstract

In this paper, a new technique for plane detection from 3D point clouds is proposed. The algorithm depends on two concepts to balance between high-accuracy and fast performance. The first is the use of a new fast octree-based balanced density down-sampling technique to reduce the number of points. The second is the fact that the number of planes in any dataset is much less than the number of the points. Random points are examined to find the 3D planes. To increase the accuracy, the system utilizes an adaptive plane extraction technique to overcome data noise. Initially, the point cloud is subdivided using octree into small cubes with a limited number of points. Then the cubes are down-sampled based on the local density of each cube. The points are explored randomly for finding a planar surface by applying principal component analysis (PCA) on the points' spherical neighborhood obtained by the down-sampled octree structure. The adaptive plane extraction is used to adjust the plane orientation to find the best position that includes the maximum number of points. Experimental results demonstrate that the proposed algorithm is capable of processing large amounts of data efficiently to produce accurate results that are robust to noise.

Painting Path Planning for a Painting Robot with a RealSense Depth Sensor

“…The D415 camera is also in line with results obtained from other cameras in the scientific literature and surpasses their performance when considering filtered data. El-Sayed et al [32] proposed a new method for plane detection from 3D point clouds. The method is contingent on two concepts to achieve a balance between high-accuracy and fast performance.…”

“…The wall extraction algorithm is based on real-time, appearance-based mapping (RTAB-Map) [23][24][25][26][27] and a random sample consensus model (RANSAC) [28,29]. The input point cloud is formed via an RTAB-Map algorithm using zig-zag robot movements along with a built-in RealSense depth camera by merging recorded point clouds during movement [30][31][32]. Further, before extracting the RANSAC algorithm, the initial step is to apply a statistical filter [30] to remove most of the outliers from the captured point clouds.…”

Robust 3-D Plane Segmentation From Airborne Point Clouds Based on Quasi-A-Contrario Theory

“…Region growing-based methods are mostly implemented with alternative and iterative processes [12]- [16]. In each iteration, one or more seed points are selected from the point cloud based on the curvature of each point; then, the neighboring points (determined by the k-nearest neighborhood (KNN) algorithm mostly) of each seed point are examined to extend the growing region based on some predefined similarity criteria (e.g., normal vector, curvature).…”

Advanced Methods for Point Cloud Processing and Simplification

“…The achieved results prove the concept of usability for the urban environment point clouds even if there is space for improving the detection of some regular objects with curved surfaces. The octree-based approach, with a combination of PCA analysis, is presented in reference [6]. Results are compared with other detection algorithms such as a 3D Kernel-based Hough Transform (3D-KHT) or the classical Random Sample Consensus (RANSAC).…”