As the electric companies need to assure the reliability of their services, power line management gains importance during the last years. Many of them rely on LiDAR scanning of their assets to obtain the status of their power line corridors and determine possible risks. In this paper, a novel sevenfold staged pipeline is introduced to classify pylon and wire points and model the conductors. Wire points are subdivided into three categories: shield, common conductor and chain. Pylons of two different types are taken into account: suspension and anchor. For the first case, insulator strains are also identified and separated. Wire points are segmented as individual conductors and a 3D-wise model based on the catenary equation is generated for each conductor using particle swarm optimization. Tests have been conducted on a set with 25 point cloud files to assess the accuracy and correctness of the results given by the proposed pipeline.
A sample point cloud file from the test set described in the article can be downloaded by clicking on the following image:
The point cloud comes in .mat format, accesible for Octave and Matlab IDEs, and it is represented as a matrix whose rows represent a point and whose columns represent:
- Anonymized X coordinate (meters)
- Anonymized Y coordinate (meters)
- Anonymized Z coordinate (meters)
- Intensity/Reflectivity value
- Ground truth classification
- Return value
The total number of points in this dataset is of 1472784. The results of classification of our method for this particular sample are the ones in the following table:
|Points||Detected||Non detected||False Positives||Accuracy (%)|
Furthermore, the results of identification of catenaries and insulators for this sample are introduced in the following table:
|Total||Detected||Partial||Split||Over detected||Non detected||Error (cm)|
In case you are interested in comparing your results with our results for the whole dataset, please contact us! Our contact emails are linked to our names.
The first author wants to thank the Vicerrectorado de Investigación, Innovación y Transferencia of the Universidad de Las Palmas de Gran Canaria for its grant "Programa de personal investigador predoctoral en formación 2015", which made possible this work.