Systems and methods for generating three dimensional geometry
Systems and methods are described for creating three dimensional models of building objects by creating a point cloud from a plurality of input images, defining edges of the building object's surfaces represented by the point cloud, creating simplified geometries of the building object's surfaces and constructing a building model based on the simplified geometries. Input images may include ground, orthographic, or oblique images. The resultant model may be scaled according to correlation with select image types and textured.
1. A method of generating a building model, the method comprising:
receiving a plurality of initial two-dimensional (2D) images of a building object;
creating, from the plurality of initial 2D images, a point cloud representing the building object in a three-dimensional (3D) coordinate system;
identifying, within at least one image of the plurality of initial 2D images, at least one surface of the building object and a plurality of vertices of the at least one identified surface;
for each vertex of the identified plurality of vertices of the at least one identified surface:
defining a region in the at least one image based on a location of the identified vertex; and
identifying data points in the point cloud corresponding to the defined region;
correlating the identified plurality of vertices of the at least one identified surface to the corresponding identified data points in the point cloud;
creating a simplified geometry for the at least one surface within the at least one image based on an average planar fit of the correlated identified data points in the point cloud;
constructing a 3D building model of the building object based on the simplified geometry; and
scaling the 3D building model based on the correlation of plurality of vertices of the at least one identified surface to the corresponding identified data points in the point cloud.
2. The method of claim 1 , wherein the plurality of initial 2D images comprise aerial images.
3. The method of claim 2 , wherein the aerial images comprise oblique images.
4. The method of claim 1 , wherein identifying the plurality of vertices of the at least one identified surface comprises defining a plurality of edges of the at least one identified surface based on the identified plurality of vertices.
5. The method of claim 1 , further comprising:
correlating at least two vertices of the 3D building model with an orthogonal image of the building object; and
scaling the 3D building model based on the correlated orthogonal image.
6. The method of claim 1 , further comprising:
correlating at least two vertices of the 3D building model with an oblique image of the building object; and
scaling the 3D building model based on the correlated oblique image.
7. The method of claim 1 , wherein identifying the datapoints in the point cloud corresponding to the defined region comprises identifying data points in the point cloud that are in proximity to the defined region.
8. One or more non-transitory computer readable medium storing instructions that, upon execution, cause a computing device to perform operations including:
receiving a plurality of initial two-dimensional (2D) images;
creating, from the plurality of initial 2D images, a point cloud representing the building object in a three-dimensional (3D) coordinate system;
identifying, within at least one image of the plurality of initial 2D images, at least one surface of the building object and a plurality of vertices of the at least one identified surface;
for each vertex of the identified plurality of vertices of the at least one identified surface:
defining a region in the at least one image based on a location of the identified vertex; and
identifying data points in the point cloud corresponding to the defined region;
correlating the identified plurality of vertices of the at least one identified surface to the corresponding identified data points in the point cloud;
creating a simplified geometry for the at least one surface within the at least one image based on an average planar fit of the correlated identified data points in the point cloud;
constructing a 3D building model of the building object based on the simplified geometry; and
scaling the 3D building model based on the correlation of plurality of vertices of the at least one identified surface to the corresponding identified data points in the point cloud.
9. The one or more non-transitory computer readable medium of claim 8 , wherein the plurality of initial 2D images comprise aerial images.
10. The one or more non-transitory computer readable medium of claim 9 , wherein the aerial images comprise oblique images.
11. The one or more non-transitory computer readable medium of claim 8 , wherein identifying the plurality of vertices of the at least one identified surface comprises defining a plurality of edges of the at least one identified surface based on the identified plurality of vertices.
12. The one or more non-transitory computer readable medium of claim 8 , further storing instructions that, upon execution, cause a computing device to perform operations including:
correlating at least two vertices of the 3D building model with an orthogonal image of the building object; and
scaling the 3D building model based on the correlated orthogonal image.
13. The one or more non-transitory computer readable medium of claim 8 , further storing instructions that, upon execution, cause a computing device to perform operations including:
correlating at least two vertices of the 3D building model with an oblique image of the building object; and
scaling the 3D building model based on the correlated oblique image.
14. The one or more non-transitory computer readable medium of claim 8 , wherein identifying the datapoints in the point cloud corresponding to the defined region comprises identifying data points in the point cloud that are in proximity to the defined region.