Alessandro Cefalu

Photogrammetric point cloud collection with multi-camera systems

We present an efficient method for the recording of 3D point clouds using a compact handheld camera rig and an automated software pipeline for an accurate surface reconstruction. Multiple industrial cameras are mounted on a rectangular shaped frame with a size of 15cm by 15cm in order to collect images from multiple views at once. By using the presented software pipeline, one dense 3D point cloud can be computed efficiently for each shot. The system is particularly designed for close range cultural heritage applications, where the requirements regarding accuracy, density but also acquisition efficiency are high. For each shot up to 3.5 Mio. 3D points can be derived. An area of 60cm by 50cm is covered at a distance of 70cm. Depending on distance and surface texture the points reach a precision of up to 0.2mm. Within this paper, we will present the system design, the data acquisition process, the automatic orientation/registration approach and the dense surface reconstruction method. Finally, we will demonstrate results for an example covering a large scale cultural heritage project, where 2 billion 3D points were acquired efficiently with sub-mm accuracy.