IP Library › Granted Patent US 11,270,046
Granted Patent B2
US 11,270,046 · App. 16/451,298 · Granted Mar 8, 2022

Conversion of point cloud data points into computer-aided design (CAD) objects

Inventors: Heiko Bauer (Korntal-Münchingen, DE); Denis Wohlfeld (Ludwigsburg, DE)
Assignee: FARO TECHNOLOGIES, INC.
G06F30/23G06N3/08G06T7/33G06T7/73
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,270,046
App. No.
16/451,298
Granted
Mar 8, 2022
Kind
B2
Abstract

Aspects include a system and method for converting from point cloud data to computer-aided design (CAD) objects. A method includes providing a point cloud and a catalog of CAD objects. One of a plurality of points in the point cloud representing an item is selected. A CAD object in the catalog that corresponds to the item is selected. The CAD object is aligned to the item in the point cloud. A position and orientation of the aligned CAD object is output. The position and orientation are expressed in a coordinate system of the point cloud.

Claims (34)

1. A method for converting from point cloud data to computer-aided design (CAD) objects, the method comprising:

providing a first point cloud;

providing a catalog of CAD objects;

selecting an item in the first point cloud;

providing a suggested CAD object from the catalog of CAD objects based on a determination that the suggested CAD object corresponds to the item;

selecting a CAD object in the catalog that corresponds to the item;

aligning, by a processor, the CAD object to the item in the first point cloud, the aligning comprising executing a virtual scanner to convert the CAD object into a second point cloud and aligning the second point cloud with the item in the first point cloud;

outputting a position and orientation of the aligned CAD object, the position and orientation expressed in a coordinate system of the point cloud.

2. The method of claim 1 , wherein the selecting an item, the selecting a CAD object, the aligning, and the outputting are repeated for at least one additional item in the first point cloud.

3. The method of claim 1 , wherein the outputting is to a CAD model.

4. The method of claim 1 , wherein the first point cloud comprises a plurality of items including the item and the CAD object is visualized on the first point cloud.

5. The method of claim 1 , wherein a pair that includes the item in the first point cloud and the CAD object are used as labeled training data for an artificial intelligence (AI) system that identifies CAD objects in point clouds.

6. The method of claim 1 , wherein an AI system provides the suggested CAD object to a user, wherein the selecting a CAD object comprises the user selecting the suggested CAD object as the CAD object or selecting another CAD object as the CAD object.

7. The method of claim 1 , wherein the selecting an item in the first point cloud is performed by an AI system.

8. The method of claim 1 , wherein the CAD object has an identifier identifying a type of the object.

9. The method of claim 1 , further comprising generating the first point cloud using a three-dimensional (3D) scanner.

10. The method of claim 9 , wherein the scanner is a laser scanner.

11. A system for converting from point cloud data to computer-aided design (CAD) objects, the system comprising:

a memory having computer readable instructions; and

one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:

providing a first point cloud;

providing a catalog of CAD objects;

selecting an item in the first point cloud-;

providing a suggested CAD object from the catalog of CAD objects based on a determination that the suggested CAD object corresponds to the item;

selecting a CAD object in the catalog that corresponds to the item;

aligning, by a processor, the CAD object to the item in the first point cloud, the aligning comprising executing a virtual scanner to convert the CAD object into a second point cloud and aligning the second point cloud with the item in the first point cloud;

outputting a position and orientation of the aligned CAD object, the position and orientation expressed in a coordinate system of the point cloud.

12. The system of claim 11 , wherein the selecting an item, the selecting a CAD object, the aligning, and the outputting are repeated for at least one additional item in the first point cloud.

13. The system of claim 11 , wherein the outputting is to a CAD model.

14. The system of claim 11 , wherein the first point cloud comprises a plurality of items including the item and the CAD object is visualized on the first point cloud.

15. The system of claim 11 , wherein a pair that includes the item in the first point cloud and the CAD object are used as labeled training data for an artificial intelligence (AI) system that identifies CAD objects in point clouds.

16. The system of claim 11 , wherein an AI system provides the suggested CAD object to a user, wherein the selecting a CAD object comprises the user selecting the suggested CAD object as the CAD object or selecting another CAD object as the CAD object.

17. The system of claim 11 , wherein the selecting an item in the first point cloud is performed by an AI system.

18. The system of claim 11 , wherein the operations further comprise generating the first point cloud using a scanner.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 8, 2019
From: BAUER, HEIKO; WOHLFELD, DENIS
To: FARO TECHNOLOGIES, INC.
Reel/Frame 049683/0740 →
Continuity (1)
Related Publication 20200410064A1 · Dec 31, 2020