Datacadabra

Cases

GIS maps
mobile mapping autos

BeeXact specializes in transforming camera images into map data. For example, the company maps large areas with cameras and 3D scanners. The resulting information is processed for a variety of purposes in infrastructure, such as mapping roads for fiber optic networks, or inner cities for maintenance.

Demand

BeeXact uses "mobile mapping cars. These cars take camera images of the environment, such as houses and streets, and then transmit this information. BeeXact wanted to automate the transformation of the camera images into GIS maps. This allows "ground cover" (pavers, paving stones, grass) to be mapped more quickly. With this information, contractors, among others, are supported in the construction of a fiber optic network. Where previously camera images had to be viewed by humans and ground cover was entered manually, Datacadabra figured that with the use of AI this could be done more efficiently.

The process

Datacadabra has investigated the best methods for automatically transforming camera images into 2D BGT (Basisregistratie Grootschalige Topografie) polygons. Freely translated, this means that the camera images are converted to a 2D map showing what is grass and what is the street.

Data

We received the camera images from BeeXact's "mobile mapping cars. These 360-degree images were already taken, but the processing was not automatic. We calibrated the images and related them to the position in the real world.

Services

Datacadabra has developed a tool based on computer vision. With this, the algorithm is able to process camera images and the tool indicates what type of ground cover is present where. This is then displayed on a 2D image (GIS maps).

The result

Video images from the mobile mapping cars no longer need to be analyzed and entered by hand, saving BeeXact considerable time. In addition, functionalities have been added, such as the "blurring" of faces and license plates. This was previously not performed automatically, so we have also taken a hit in shielding privacy-sensitive information.