The missing link to faster, cheaper, and more accurate 3D mapping

Three-dimensional (3D) mapping is a very useful tool for monitoring construction sites, tracking the effects of climate change on ecosystems, and verifying road and bridge safety. However, the technology currently used to automate the mapping process is limited, making the process time-consuming and costly.

The method is described in a paper published in the ISPRS Journal of Photogrammetry and Remote Sensing by Davide Cucci, a senior research associate at the Research Center for Statistics of the Geneva School of Economics and Management of the University of Geneva who regularly collaborates with Topo, Jan Skaloud, and Aurélien Brun, lead author and recent Master’s graduate from EPFL and recipient of an award from the Western Switzerland Association of Surveyor Engineers (IGSO).

Missing the point

LiDAR laser scanners beam millions of pulses of light on surfaces to create high-resolution digital twins—computer-based replicas of objects or landscapes—that can be used in architecture, road systems and manufacturing, for example. Lasers are particularly effective at collecting spatial data since they don’t depend on ambient light, can collect accurate data at large distances and can essentially see through vegetation. But lasers’ accuracy is often lost when they’re mounted on drones or other moving vehicles, especially in areas with numerous obstacles like dense cities, underground infrastructure sites, and places where GPS signals are interrupted. This results in gaps and misalignments in the datapoints used to generate 3D maps (also known as laser-point clouds), and can lead to double vision of scanned objects. These errors must be corrected manually before a map can be used.

“For the time being, there is no way to generate perfectly aligned 3D maps without a manual data-correction step,” Cucci says. “Many semi-automatic methods are being investigated to address this issue, but ours has the advantage of resolving the issue directly at the scanner level, where measurements are taken, eliminating the need to make corrections later. It is also entirely software-driven, allowing end users to implement it quickly and seamlessly.”

On the road to automation

The Topo method makes use of recent advances in artificial intelligence to detect when an object has been scanned multiple times from various angles. To correct gaps and misalignments in the laser-point cloud, the method involves selecting correspondences and inserting them into what is known as a Dynamic Network.

“We’re bringing more automation to 3D mapping technology,” says Skaloud, “which will go a long way toward improving its efficiency and productivity and allowing for a much broader range of applications.”


Source Link


Leave a Reply

Your email address will not be published.

Previous post The battle for dominance in satellite internet is heating up
Next post Review of the Google Nest Camera with Tata Play Secure+: Someone is standing at the door