Methods and systems for auto-leveling of point clouds and 3D models
A method includes creating a point cloud model of an environment, applying at least one filter to the point cloud model to produce a filtered model of the environment and defining a plane in the filtered model corresponding to a horizontal expanse associated with a floor of the environment.
1. A method comprising:
creating a point cloud model of an environment;
applying at least one filter to the point cloud model to produce a filtered model of the environment, wherein:
the at least one filter removes at least one point from the point cloud model,
the at least one filter is a height filter,
applying the height filter comprises dropping one or more points from the point cloud model each of which located outside of a predetermined distance range from a scanning device when producing the point cloud model, and
the predetermined distance range corresponds to a range of distance encompassing an average distance from the scanning device to a floor surface; and
defining a plane in the filtered model corresponding to a horizontal expanse associated with a floor of the environment.
2. The method of claim 1 , further comprising applying a rotation to the point cloud model to align at least one data point of the point cloud model with the defined plane.
3. The method of claim 1 , wherein the applying comprises applying a sub-sampling filter.
4. The method of claim 3 , wherein the sub-sampling comprises dropping at least one point forming a part of the point cloud model based, at least in part, on a minimum distance of the at least one point form another point forming a part of the point cloud model.
5. The method of claim 1 , wherein the applying comprises applying a curvature filter.
6. The method of claim 1 , wherein the applying comprises applying a normal vector filter.
7. The method of claim 1 , wherein the defining comprises applying a Random Sample Consensus (RANSAC) method to the filtered model.
8. The method of claim 7 , wherein the RANSAC identifies the plane having a determined pitch and a determined roll.
9. The method of claim 8 , further comprising applying a rotation to the point cloud model to align at least one data point of the point cloud model with the defined plane using, at least, the determined pitch and the determined roll.
10. The method of claim 8 , wherein steps of applying and defining are repeated to identify a plurality of planes each corresponding to a single floor of a building.
11. The method of claim 10 , wherein each of the plurality of planes is adjusted to a previous plane in sequence.
12. The method of claim 10 , wherein a transition between a first floor and a second floor of the building is identified based on, at least, a stabilized z-value over a predetermined period of time of one or more points of the point cloud model.
13. A system comprising:
a camera unit;
a laser scanning unit; and
a computing system in communication with the camera unit and the laser scanning unit, wherein the computing system comprises at least one processor adapted execute to software that when executed causes the system to:
create a point cloud model of an environment;
apply at least one filter to the point cloud model to produce a filtered model of the environment, wherein:
the at least one filter removes at least one point from the point cloud model,
the at least one filter is a height filter,
applying the height filter comprises dropping one or more points from the point cloud model each of which located outside of a predetermined distance range from a scanning device when producing the point cloud model, and
the predetermined distance range corresponds to a range of distance encompassing an average distance from the scanning device to a floor surface; and
define a plane in the filtered model corresponding to a horizontal expanse associated with a floor of the environment.
14. The system of claim 13 , wherein the processor is further adapted to apply a rotation to the point cloud model to align at least one data point of the point cloud model with the defined plane.
15. The system of claim 13 , wherein the applying comprises applying a sub-sampling filter.
16. The system of claim 15 , wherein applying the sub-sampling filter comprises down-sampling the point cloud model.
17. The system of claim 16 , wherein the down-sampling comprises dropping at least one point forming a part of the point cloud model based, at least in part, on a minimum distance of the at least one point form another point forming a part of the point cloud model.
18. The system of claim 13 , wherein the applying comprises applying a curvature filter.
19. The system of claim 13 , wherein the applying comprises applying a normal vector filter.