AI interprets drone footage in real-time
Video shot during an autonomous drone inspection has been interpreted in real-time in a move that could lead to tank inspections becoming safer and more efficient.
A drone developed by Scout Drone Inspection successfully inspected a 19.4m high oil tank onboard Floating Production, Storage and Offloading vessel Petrojarl Varg, while the drone footage was interpreted in real-time by an algorithm developed by DNV GL to detect cracks in the structure.
“We’ve been working with drone surveys since 2015,” said Geir Fuglerud, director of offshore classification at DNV GL – Maritime. “This latest test showcases the next step in automation, using AI to analyse live video.”
The drone uses LiDAR to navigate inside the tank and create a 3-D map. All images and video is accurately geo-tagged with position data.
Eventually the camera and algorithm will be able to detect anomalies below the surface such as corrosion and structural deformations.
Using a drone in combination with an algorithm to gather and analyze video footage can significantly reduce survey times and staging costs, while at the same time improving surveyor safety.
During the test, the drone was controlled by a pilot using the drone’s flight assistance functions, but as the technology matures it will be able to navigate more and more autonomously.
Altera Infrastructure hosted the test on Petrojarl Varg.
By Rebecca Jeffrey
Related Articles
OTHER NEWS
MARINE RENEWABLES
ACCESSORIES & EQUIPMENT