Multimodal image analysis for power line inspection

Jalil B., Leone G. R., Martinelli M., Moroni D., Pascali M. A., Salvetti O.

RGB Images  Machine Learning  Wire detection  Insulators  Unmanned Aerial Vehicles  Infrared Images  Image analysis 

he use of Unmanned Aerial Vehicles (UAVs) for environmental and industrial monitoring is constantly growing. At the same time, the demand for fast and robust algorithms for the analysis of the data acquired by drones during the inspections has increased. In this paper we provide a concise survey about a peculiar case study: the monitoring of the high-voltage power grid which includes: (i) the detection of the power lines and of the electric towers along with their components more subject to wear and tear; (ii) the diagnosis of maintenance status. In this work different algorithms from image processing are applied to visible and infrared thermal data, to track the power lines and to detect faults and anomalies. We applied Canny edge detection to identify significant transition followed by Hough transform to highlight power lines. The method significantly identify edges from the set of frames with good accuracy. The paper concludes with the description of the current work, which has been carried out in a research project, namely SCIADRO.

Source: ICPRAI 2018 - International Conference on Pattern Recognition and Artificial Intelligence, pp. 592–596, Montreal, Canada, 14-17 May 2018