Customer :	Energy
Category :	Computer Vision
Tags :	image analysis

Target: extract and analyse video footage from cameras on pylons in order to identify anomalies and patterns with a view to implementing predictive maintenance systems.

Data:
▪ Video footage from cameras on masts
▪ Hourly average information of variables collected by sensors

Implemented algorithms
▪  Algorithms for extracting images with potential discharges
▪  Algorithm based on neural networks for event location and intensity evaluation
▪  Algorithm based on optical flow techniques for image stabilization and discharge detection

Implemented interfaces
▪ Release of a docker containing extractor software for video and frame with potential discharges
▪ Release of a docker containing software for the analysis of frame with potential discharges
▪ Interface (webapp) for the end-user to analyse the results

This work has been financed by the Research Fund for the Italian Electrical System under the Contract Agreement between RSE S.p.A. and the Ministry of Economic Development – General Directorate for the Electricity Market, Renewable Energy and Energy Efficiency, Nuclear Energy in compliance with the Decree of April 16th, 2018