Super-resolution Services for power line drone inspections
Generating good quality data in power line inspection to enable the use of AI technologies to automate the power line inspection process using drones
Power lines require regular inspections to guarantee their structural health. This process has been completely manual up until now when artificial intelligence is enabling the automation of this process. Nevertheless, the process is highly dependent on the quality of the input data, that is, visual images captured by an aerial vehicle. While crewed helicopters carry heavy cameras that enables to capture high-resolution data, drones do not have such payload capacity and therefore, the quality of the images captured can be drastically worse than helicopters. To be able to compete with crewed helicopters in data quality without needing to carry heavier cameras, we have developed super-resolution technologies to automatically enhanced the quality of the images captured by drones.
The service aims to automatically double the number of pixels in an image. As it can be seen in the demo video the service follows this process:
-The client captures the visual data in .jpg format using drones.
-The client transfers the data from the drones to a computer where the data is uploaded into the cloud and sent to our team. In this prototype we used OneDrive for simplicity but other platforms are available on demand.
-Our team receives the data, and stores it in an input folder. After that, the team executes the super-resolution algorithms developed in the project to obtain the enhanced photos in an output folder.
-The output data is sent back to the client using the demanded service.
With this service, we aim to provide image enhancement service to companies that inspect power lines using super-resolution. This technology enables us to process images to double the number of pixels using AI. This way, the processing of the images by AI or humans can be performed by detecting smaller defects thus detecting such defects earlier. Consequently, with this technology, we aim to improve the safety of the grid enhancing the predictive maintenance processes.
This project has received funding from the European Union's Horizon 2020 research and innovation programme within the framework of the I-NERGY Project, funded under grant agreement No 101016508