SYSTEMS AND METHODS FOR PROCESSING 2D/3D DATA FOR STRUCTURES OF INTEREST IN A SCENE AND WIREFRAMES GENERATED THEREFROM
The inventions herein relate generally to improvements in the generation of wireframe renderings derived from 2D and/or 3D data that includes at least one structure of interest in a scene. Such wireframe renderings and similar formats can be used in, among other things, 2D/3D CAD drawings, designs, drafts, models, building information models, augmented reality or virtual reality, and the like. Measurements, dimensions, geometric information, and semantic information generated according to the inventive methods can be accurate in relation to the actual structures. The wireframe renderings can be generated from a combination of a plurality of 2D images and point clouds, processing of point clouds to generate virtual/synthetic views to be used with the point clouds, or from 2D image data that has been processed in a machine learning process to generate 3D data. In some aspects, the wireframe renderings are accurate in relation to the actual structure of interest, automatically generated, or both.
1 ) A library of information for use in generating wireframe renderings of one or more structures in a scene, comprising:
a. providing, automatically by a computer, 2D and 3D data for at least one structure of interest in a scene;
b. processing, automatically by the computer, the 2D and 3D data to generate 3D information comprising an edge or skeletal representation associated with the structure, wherein the 2D and 3D data comprising the at least one structure of interest in the scene is generated by:
i. providing a plurality of 2D images including the at least one structure of interest and at least one point cloud including the at least one structure of interest, wherein the plurality of 2D images is associated with the at least one point cloud;
ii. processing a plurality of point clouds to extract at least some 2D data associated with the at least one structure of interest, thereby providing point cloud data associated with 2D data derived from the plurality of point clouds; and
iii. extracting, automatically by a computer, at least one geometric primitive from the 3D information comprising the edge or skeletal representation each of the at least one geometric primitive being an object surface of the at least one structure of interest; and
c. incorporating, automatically by the computer, information associated with the at least one geometric primitive in a machine learning library for use in subsequent processes for generating wireframe renderings of one or more structures from images of scenes including each of the one or more structures.