Mapping inaccessible sites in great detail, and doing it 120 times faster? The new 3D image processing technology developed at iMinds-KU Leuven makes it possible. The technology is particularly useful to map locations that are either difficult to access – think of narrow catacombs and sewers – or entail health and safety risks, such as nuclear power plants that require inspection after a catastrophe.
Self-driving robots are increasingly being used to map locations that are either difficult to access or entail safety risks. “But these self-driving robots still have a lot of issues,” says Professor Luc Van Gool (iMinds – KU Leuven). “For example, the use of traditional imaging techniques such as HD video is often impossible because the robots are literally stumbling around in poorly lit areas – all while laser technology is still very expensive.”
That is why, in the context of the European ROVINA project, the iMinds – KU Leuven researchers developed new, affordable technologies to create good-quality images. Their approach even works in difficult circumstances, for instance in the dark Catacombs of Priscilla in Rome. The researchers combined the images with 3D reconstruction software to create lifelike, realistically coloured 3D images.
“It feels like you’re actually walking through the Catacombs of Priscilla in Rome. You can even zoom in on the tiniest details, such as the lichen on the stones or the ancient cement work.”
To take good-quality photographs in the dark catacombs, the scientists developed an array of seven cameras and a special light configuration for the self-driving ROVINA robot. “We were able to collect good source material that can be used by our 3D image reconstruction software. This is a first important breakthrough. But even more significantly, we have also improved our intelligent image processing algorithms. We can now construct realistic, large-scale 3D models, based on a gigantic amount of data,” Professor Van Gool explains. “Particularly striking is the amount of detail we can get out of our 3D models. It feels like you’re actually walking through the Catacombs of Priscilla. You can also zoom in on the tiniest details, such as the lichen on the stones or the ancient cement work.”
“Our algorithms are over 120 times faster than existing methods,” adds researcher Marc Proesmans (iMinds – KU Leuven). “What used to take more than 120 days can now be done in just one day.” This makes the technology very useful for projects such as ROVINA, for which over 600 metres of passages had to be mapped.
Opening up cultural heritage that is difficult to access is just one possible application. “We can use our findings in any situation that requires an accurate 3D replication of what a robot ‘sees’. Gaming is one example. But this is also an important step forward in the development of self-driving cars. After all, a self-driving car needs to be able to estimate accurately, and in real time, where it is located. GPS – which has an accuracy of a few metres – is not sufficient for this purpose. With our technology, the car would ‘observe’ its surroundings and use the resulting data to locate its position with an accuracy of a couple of centimetres. As such, we are inching closer to a world in which fully autonomous cars are a reality,” Professor Van Gool concludes.
Source: iMinds (with minor adaptions) and KU Leuven