Software development for detecting the real volume and convex hulls of objects using 3D scanners. Sensor technology and 2D/3D graphics for measurement, object recognition and calibration of the laser. Development of algorithms for the above areas. In detail: Rotating Calipers, Minimal Bounding Box, RANSAC, eigenvalue calculation and others. Pre-calculation and testing of the algorithms with Matlab.
Customer: International sensor manufacturer
Technologies: C++, Visual Studio, Matlab, OpenCV, PCL, Halcon, Eigen, UML, SVN, Blender, AutoCAD
- read more
For an international sensor manufacturer, we developed mathematical models and software algorithms for evaluating 3D scan data. Numerous filters were applied upstream of the evaluation to improve the calculations and optimise the source data.
The task was to recognise and classify objects from the 3D scan data (point cloud), i.e. to recognise the geometric shape (cylinder, cuboid, sphere, etc.). A subsequent calculation of the volume delivered the desired results with fast performance.
In the test phase, we installed the scanners at various positions in the laboratory, connected them to the embedded system and configured them. Data from a production plant fitted with the newly developed 3D scanners was also used. To produce a wealth of variants for the tests, we modelled a set-up in 3D for a scan data simulation.
kununu