Image and point cloud data represent the environment in the form of 2- and 3-dimensional data, respectively. For example, color cameras produce 2D visual (visible to humans) color images, thermal imaging cameras capture thermal signatures in the environment, and 3D LiDAR sensors use laser beams to scan their surroundings in the form of 3D point clouds.
It is often very easy for a human to extract higher-level information from this rich imagery and point cloud data to generate added value. However, this is very time consuming, costly and requires expert knowledge. We support the automation of this task to save costs and valuable staff time in the medium term, as well as to enable innovative applications. For example, we use 2D color images to automatically assess the quality of a workpiece in production, reveal Energy potential in plants using thermal images, and detect DSGVO-compliant pedestrians in 3D point clouds for optimized traffic light control in our cities of tomorrow.