Abstract
Power lines are extending to complex environments (e.g., lakes and forests), and the distribution of power lines in a tower is becoming complicated (e.g., multi-loop and multi-bundle). Additionally, power line inspection is becoming heavier and more difficult. Advanced LiDAR technology is increasingly being used to solve these difficulties. Based on precise cable inspection robot (CIR) LiDAR data and the distinctive position and orientation system (POS) data, we propose a novel methodology to detect inspection objects surrounding power lines. The proposed method mainly includes four steps: firstly, the original point cloud is divided into single-span data as a processing unit; secondly, the optimal elevation threshold is constructed to remove ground points without the existing filtering algorithm, improving data processing efficiency and extraction accuracy; thirdly, a single power line and its surrounding data can be respectively extracted by a structured partition based on a POS data (SPPD) algorithm from “layer” to “block” according to power line distribution; finally, a partition recognition method is proposed based on the distribution characteristics of inspection objects, highlighting the feature information and improving the recognition effect. The local neighborhood statistics and the 3D region growing method are used to recognize different inspection objects surrounding power lines in a partition. Three datasets were collected by two CIR LIDAR systems in our study. The experimental results demonstrate that an average 90.6% accuracy and average 98.2% precision at the point cloud level can be achieved. The successful extraction indicates that the proposed method is feasible and promising. Our study can be used to obtain precise dimensions of fittings for modeling, as well as automatic detection and location of security risks, so as to improve the intelligence level of power line inspection.
Highlights
Power lines are important parts of the national power grid
It can be seen that the number of original point clouds of cable inspection robot (CIR) LiDAR is large, and the ground points with an average of 79.7% of the dataset can be quickly removed by ground point removal
The numbers of inspection object points extracted by mistake are zero, which shows that the proposed method can effectively remove ground points in datasets, and retain all meaningful point clouds closely associated with power lines in a span segment
Summary
Power lines are important parts of the national power grid. With the development of the economy, power towers and power lines are rapidly increasing. Power lines are extending into dense forests. The impact of human activities is increasing, especially in the vicinity of urban areas, and attachment objects such as kites and balloons are frequently attached to power lines that can cause security risks, as shown in Figure 1b [1]. It is very important to regularly inspect power lines to ensure their stable operation [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
