Parametric model generation based on constrained geometric parameters

A computer-implemented method for generating a parametric model of a physical structure based on point cloud data, the point cloud data describing a point cloud comprising points acquired in an environment in which the physical structure is located, wherein the physical structure comprises a plurality of parts, wherein the plurality of parts are arranged as an interconnected chain of parts that are physically connected, the method comprising:

• acquiring the point cloud data, the point cloud data comprising geometry information of the environment;
• acquiring geometry information of a set of predefined geometric shapes related to the plurality of parts;
• performing a classification on the point cloud data to:
• detect parts of the plurality of parts in the point cloud data based on the geometry information;
• assign to each detected part of the plurality of parts a set of points of the point cloud;
• and
• detect physical connections of two or more detected parts of the plurality of parts;
• and
• generating a parametric model of the physical structure based on the detected physical connections of the two or more detected parts of the plurality of parts and the geometry information of the set of predefined geometric shapes,
• deriving geometric parameters for each detected part of the plurality of parts from the geometry information of the set of predefined geometric shapes, wherein generating the parametric model of the physical structure is further based on the derived geometric parameters for each detected part of the plurality of parts, wherein at least one of the derived geometric parameters of a preceding part is used as a constraint for at least one of the geometric parameters of a subsequent part physically connected to the preceding part.