Automatic Detection and Characterisation of Power Lines and Their Surroundings Using Lidar Data

Abstract

<p><strong>Abstract.</strong> Light Detection and Ranging (LiDAR) is nowadays one of the most used tools to obtain geospatial data. In this paper, a method to detect and characterise power lines of both high and low voltage and their surroundings from 3D LiDAR point clouds exclusively is proposed. First, to identify points of the power lines a global search of candidate points is carried out based on the height of each point compared to its neighbours. Then, the Hough Transform (HT) is applied on the set of candidate points to extract the catenaries that belong to each power line, allowing the identification of each conductor individually. Finally, conductors located on the same power line are grouped, their geometric characteristics analysed, and the quantitative features of the surroundings are computed. A very high accuracy of power line classification is reached with these methods, while the computational time is optimised by efficient memory usage and parallel implementation of the code.</p>

Seperating Power Line Using Lidar Point Elevation and Intensity

“…Make a triangle from the selected sample set satisfying the condition (1) The smallest angle in each triangle needs to be maximized; (2) There is not any point of the triangle inside the circumcircle of any triangle in the grid; (3) Points lying on the Euclidean plane [12] [18]. At the surface interpolation step, each face of the triangle will characterize the geometry of that surface area [13]. Therefore, for each triangle in TIN, every point on its face (including the three vertices of the triangle) is always represented through a plane.…”

“…Therefore, for each triangle in TIN, every point on its face (including the three vertices of the triangle) is always represented through a plane. Therefore, the equation of the triangle face in TIN is expressed [13]:…”

Archives of Civil Engineering

“…The issues of linear object detection based on photogrammetric and laser data have been discussed in many publications. The authors use complex mathematical methods based on: wavelet analysis [1], neural network algorithms [2], Radon transformations [3], Hough transform [4], RANSAC method [5], [6], height differences [7] or classification methods such as Random Forest [2] or Support Vector Machines (SVM) [8]. In their studies, the authors focus on developing an optimal algorithm for linear object detection.…”