Computing in Engineering New algorithms tell smart glasses where they are
Poring over blueprints and searching for manuals might soon become a thing of the past. Augmented Reality could facilitate maintenance and repair work in buildings.
Augmented Reality applications might significantly facilitate maintenance and repair work as technicians could use intelligent goggles to navigate to the respective location, where the glasses then indicate the required tasks step by step. In order for this to work, the devices must be able to calculate their exact position in the room and understand what they are seeing at any given time. At the Chair of Computing in Engineering in Bochum, the team headed by Professor Markus König is developing algorithms that make all this possible without any manual calibration being required. Rubin, the science magazine at Ruhr-Universität Bochum, published a report on that project.
The algorithm made in Bochum requires a digital building model. It compares the image recorded by the smart glasses with the model. To this end, the person wearing the glasses only has to turn around once in the room, in order to provide the glasses with as much visual information on their surroundings as possible. The algorithm rotates and moves the digital model until it overlaps with the surroundings. If necessary, it does so pixel by pixel by pixel; depth information such as is recorded by modern cameras is very helpful in the process.
Manual calibration required in the past
Traditional methods have required manual calibration, which is achieved with the aid of at least two dots applied in different points in the room and recorded in a digital model: when the user wearing the smart glasses enters the room, he has to input the information on the dots’ position into the system, in order for it to calculate his three-dimensional position in the room.
With their algorithm, the researchers from Bochum are not only able to automatically determine the glasses’ position in the room, but also in the entire building. Using the manual dot calibration method, this would only be possible if the user frequently recalibrated the glasses or if he used a large number of dots.
Optimisation for lower computational power
Automated calibration has currently an accuracy of 20 centimetres, which is enough to navigate around a room. For other applications, the Bochum researchers intend to optimise the algorithm.
One of the group’s main concerns is to ensure that the algorithm works automatically and in real time – as it already does when run on a Smartphone. Smart glasses have lower computational power than phones, however, which means that the application has to become more efficient in order to operate smoothly.