Automatic LIDAR building segmentation based on DGCNN and euclidean clustering

Abstract

There has been growing demand for 3D modeling from earth observations, especially for purposes of urban and regional planning and management. The results of 3D observations has slowly become the primary source of data in terms of policy determination and infrastructure planning. In this research, we presented an automatic building segmentation method that directly uses LIDAR data. Previous works have utilized the CNN method to automatically segment buildings. However, the existing body of works have relied heavily on the conversion of LIDAR data into Digital Terrain Model (DTM), Digital Surface Model (DSM), or Digital Elevation Model (DEM) formats. Those formats required conversion of LIDAR data into raster images, which poses challenges to the evaluation of building volumes. In this paper, we collected LIDAR data with unmanned aerial vehicle and directly segmented buildings utilizing the said LIDAR data. We utilized a Dynamic Graph Convolutional Neural Network (DGCNN) algorithm to separate buildings and vegetation. We then utilized Euclidean Clustering to segment each building. We found that the combination of these methods are superior to prior works in the field, with accuracy up to 95.57% and an Intersection Over Union (IOU) score of 0.85.

Dynamic Slicing and Reconstruction Algorithm for Precise Canopy Volume Estimation in 3D Citrus Tree Point Clouds

“…After finishing the ground filtering, the point cloud should be segmented by clustering using appropriate clustering algorithms in conjunction with the crop growth characteristics and the size of the test area to get each fruit tree's point cloud data. Among the frequently employed clustering algorithms are the region expanding algorithm [45], Kmean clustering [46], DBSCAN clustering [47] and Euclidean clustering [48] algorithms. The point cloud is split up by the region expanding algorithm into different regions based on the similarity between neighboring points to form point clusters with continuity.…”

Canopy Parameter Estimation of Citrus grandis var. Longanyou Based on LiDAR 3D Point Clouds

“…After filtering the ground point clouds in the test area, an appropriate clustering algorithm should be used for point cloud segmentation in combination with crop growth characteristics to obtain a point cloud data of each individual fruit tree. Clustering algorithms based on 3D point clouds mainly include the Density-Based Spatial Clustering of Application with Noise [48], K-means clustering [49], and European clustering [50]. European clustering was used to extract individual fruit trees because the C. grandis var.…”

Obstacle Detection Based on 3D Lidar Euclidean Clustering

“…Environmental sensing based on lidar is usually only interested in targets on the road surface. In order to quickly and accurately detect the location of obstacles, ground and non-ground points need to be separated before cluster detection (Miao & Tseng, 2004;Reitberger, Schnoerr, Krzystek, et al, 2009;Gamal, Wibisono, Wicaksono, et al, 2020). In this paper, the Ray Ground Filter method is adopted for ground filtration, and the flow chart of this method is as follows:…”

“…Kd tree (short for K-dimensional tree) is a data structure that divides k-dimensional data space. Euclidean clustering is a kind of clustering method which uses Kd-tree to search the nearest neighbor and takes euclidean distance as reference (Gamal, Wibisono, Wicaksono, et al, 2020). The algorithm compares the distance between two points with the clustering radius ε, and the distance smaller than the clustering radius ε is regarded as the same class.…”