METHOD FOR IMAGE-BASED ALTERATION RECOGNITION

摘要

The invention relates to a method for image-based alteration recognition for three-dimensional objects and/or surface sections. In this case, a three-dimensional model for an object is generated (2) from a plurality of photographs for a particular time, and a reference model or comparison model for the object is also provided. A visual focus on the three-dimensional model of the object is then defined and a 2.5D view of the object is derived (3) for this visual focus - in the form of a Cartesian data record. In this data record, at least besides two-dimensional coordinate values, a colour value derived from the three-dimensional model and a depth value derived from the three-dimensional model are also recorded (4) as data attributes for the respective data point. The respective data attributes of the respective data point are then compared (5) with the corresponding data from the reference model in order to establish discrepancies and/or changes. In this way, the method according to the invention very easily reduces complexity for recognition or ascertainment of alterations and/or differences between three-dimensional object photographs that are available in the form of what are known as point clouds. The data records, which comprise both geometric and colour information for the respective data points, allow very easy recognition of alterations in a three-dimensional object.