| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a method which enables prompt and automated object classification of a measured three-dimensional (3D) object scene. <P>SOLUTION: The method can be implemented during 3D measuring procedures such as data capturing or measuring procedures using captured data. An object scene is irradiated with a light beam and an image is captured or an object scene is irradiated with configured light beams and a sequence of images of the object scene irradiated with patterns of different spatial phases is captured. Coordinates of a plurality of points in one or more images are determined and a value of translucency is determined for each point. On the basis of the value of translucency for each point, an object class is determined for each point. Optionally, in order to support the determination of the object class, additional information such as a gray scale or color image data may be used for each point. <P>COPYRIGHT: (C)2012,JPO&INPIT |
