Frequently Asked Questions

What can I do if I don't have any image data available?

Our partner Skyability is specialized in capturing georeferenced mobile mapping data (images and point clouds) with drones or cars. Together we are able to provide an end-to-end solution for your own needs.

Which image data does Detekt work with?

We are able to work with basically any image data, including videos. This includes data obtained via mobile phone, planar images, stereoscopic images, or 360° captions. Any camera setup should be calibrated to increase detection accuracy.

What data is needed for basic georeferencing?

To determine the location where an image was taken and to display it properly in the Viewer, GNSS coordinates (e.g. GPS, GLONASS, Galileo or BEIDOU) and image orientation are needed as minimum requirement.

How can the exact position and size of a detection be determined?

Detekt works with different methods to determine the exact location and size of any detected object or surface from any provided image depth information:

  • In case camera pose and orientation is provided with each image, distance to detected objects can be estimated to provide an approximate location of each detection.
  • Stereoscopic images allow us to calculate the distance from the camera(s) to an object within the image using photogrammetric methods (image matching) with interior and exterior orientation as input parameters.
  • 3D point clouds are most commonly generated using 3D laser scanners and LiDAR (light detection and ranging) technology and allow precise and detailed measurements. Compared to 3D information calculated from image data, laser scanning delivers more accuarate positioning information.
How can Detekt minimize the number of incorrect detections?

Detekt uses an in-house developed method to merge separate detections in all images and other data sources, called object fusion. A custom-developed algorithm combines the classification and locations, weighs them logically and thus maximizes accuracy. Furthermore, same objects captured at different times can be tracked and compared over time to assess changes in condition.

How do you make sure that GDPR and anonymization requirements are met?

Our partner Celantur provides a high-quality and scalable image anonymization solution to blur faces, bodies and license plates on panoramas, planar images and videos which we can fully integrate in our pipeline.