A Model-Driven Approach for 3D Modeling of Pylon from Airborne LiDAR Data

Abstract

Abstract:Reconstructing three-dimensional model of the pylon from LiDAR (Light Detection And Ranging) point clouds automatically is one of the key techniques for facilities management GIS system of high-voltage nationwide transmission smart grid. This paper presents a model-driven three-dimensional pylon modeling (MD3DM) method using airborne LiDAR data. We start with constructing a parametric model of pylon, based on its actual structure and the characteristics of point clouds data. In this model, a pylon is divided into three parts: pylon legs, pylon body and pylon head. The modeling approach mainly consists of four steps. Firstly, point clouds of individual pylon are detected and segmented from massive high-voltage transmission corridor point clouds automatically. Secondly, an individual pylon is divided into three relatively simple parts in order to reconstruct different parts with different strategies. Its position and direction are extracted by contour analysis of the pylon body in this stage. Thirdly, the geometric features of the pylon head are extracted, from which the head type is derived with a SVM (Support Vector Machine) classifier. After that, the head is constructed by seeking corresponding model OPEN ACCESSRemote Sens. 2015, 7 11502 from pre-build model library. Finally, the body is modeled by fitting the point cloud to planes. Experiment results on several point clouds data sets from China Southern high-voltage nationwide transmission grid from Yunnan Province to Guangdong Province show that the proposed approach can achieve the goal of automatic three-dimensional modeling of the pylon effectively.

A Heuristic Method for Power Pylon Reconstruction from Airborne LiDAR Data

“…Compared with existing pylon reconstruction methods, the proposed method has several characteristics, and shows potential in pylon reconstruction from LiDAR data. The major contributions of the proposed method mainly exist in four aspects: (1) using the statistics analysis method, which combines both the local maximum density and the minimum length, to automatically decompose a pylon into body and head which is more applicable than Li et al [1] method for various pylon types; (2) reconstructing the pylon body and head with optimal strategies, which are robust to noise and partially missing data; (3) the flow of body reconstruction method is simpler than Li et al [1], using a RANSAC based 3D line fitting method to reconstruct four principal legs of a pylon body, improving the stability of body reconstruction, which can also ensure the reconstruction accuracy; and (4) using a shape context algorithm to recognize the head type, and a Metropolis-Hastings (MH) sampler coupled with Simulated Annealing (SA) algorithm to solve the head parameters, improving the robustness of head type recognition while reducing the parameters of optimization. Meanwhile, pylon body reconstruction results and the original point cloud information are utilized in the model parameters solving process.…”

“…However, in this instance, the reconstructed models consisted of only tangled lines without correct topological relations. Chen et al [6] proposed a semiautomatic model-driven method to rebuild pylons; this method was further improved by Li and Chen et al [1]. In their work, the point cloud of a pylon was firstly decomposed into three parts according to their density features: legs, body, and head.…”

“…Although the waist planes' types are different, there are two common statistical characteristics: (1) the local maximum density used in Li et al [1]; and (2) the local minimum length. The density is defined as the number of point in each bin, and the length is the maximum distance to the center of each bin.…”

“…They firstly extract basic features, such as planes, lines, or points, and then through a combination of features and their topological relations, a complete model is reconstructed. In buildings, reconstruction usually contains two key processes: building roof edge segmentation and topological reconstruction [1]. Since plane features of buildings are more stable than point or line features, for complex roof structures with high-density point cloud data, methods based on plane segmentation is first adopted, such as ridge or edge-based and voxel-based region growing [10,11], cross-line element growth (CLEG) [12], RANSAC [13,14], classification or feature clustering [15][16][17][18]; then, point or line features are obtained method [5] belongs to data-driven while Guo's approach [2] belongs to model-driven.…”

“…Many research projects have been conducted on the 3D reconstruction from LiDAR data, and great progress has been made in modeling both natural features and man-made objects [1]. The reconstructed 3D models can be significantly applied in various areas, for example, urban planning, navigation, and emergency response [2].…”