The project SuperPower developed thanks to I-NERGY first open call has developed super-resolution algorithms to double the pixels in an image using Convolutional Neural Networks. These datasets consist of two subsets of original photos of high-voltage power lines and the enhanced photos using superresolution.

Over 5 million kilometers of power lines deliver energy to European societies. To ensure that they are good maintained, they are required by law to be regularly inspected. Currently, the main means to perform such inspection services are: 1) On-foot inspections and 2) Crewed helicopters. Our goal is to replace such means for long-range drones. These aircraft can save up to 94% costs and perform these operations with no human risks and no emissions.

However, these aircraft cannot carry much weight due to regulatory constraints. This means that these aircraft must carry low-weight sensors that not have as much resolution as the one that crewed helicopter’s sensors have. That is why the goal of the SuperPower project (I-NERGY Open Call I) has been developing super-resolution technologies to apply them to the imagery captured by our long-range drones.

With superresolution, we are able to capture photos with the same quality (2 - 5 mm. per pixel GSD) as helicopters while using much lighter cameras. This is enabling our long-range inspection services to compete with these aircraft which are expensive (150 € per kilometer inspected), pollutant (50 liters per 100 km. flown) and have human risks.