Automated 360-degree dense point object inspection

Patent metadata

Field	Value
Publication number	US-11042146-B2
Application number	US-201916401890-A
Country	US
Kind code	B2
Filing date	May 2, 2019
Priority date	Nov 17, 2017
Publication date	Jun 22, 2021
Grant date	Jun 22, 2021

Abstract

A system and method for performing real-time quality inspection of objects is disclosed. The system and method include a transport to move objects being inspected, allowing the inspection to be performed in-line. At least one optical acquisition unit is provided that captured optical images of the objects being inspected. The captured optical images are matched to CAD models of objects, and the matched CAD model is extracted. A laser with an illumination light beam has a wavelength in the violet or ultraviolet range then conducts scans of the objects, which are formed into three-dimensional point clouds. The point clouds are compared to the extracted CAD models for each object, where CTF are compared to user input or CAD model information and the object is determined to be acceptable or defective based on the extent of deviation between the point cloud and the CAD model.

First claim

The invention claimed is:

1. A method for determining the recommended scan set-up parameters for an object inspection system, comprising:
loading a CAD Model of the object to be scanned;
estimating the initial capture parameters from the size and extent of the CAD model;
computing a simulated scan of the object using ray casting to develop an estimated point cloud;
evaluating and scoring the estimated point cloud using a weighting function;
determining whether the scoring of the estimated point cloud is adequate by comparing to a pre-defined threshold; and
computing new estimated capture parameters for estimated point clouds with inadequate scores to determine if additional rest positions need to be considered.

2. The method of claim 1 , further comprising representing two laser profilometers in the simulated scan, with the ray casting including estimates of transmissions and receptions of the two laser profilometers.

3. The method of claim 1 , wherein the user is notified when no additional rest positions are available for consideration.

4. The method of claim 1 , further comprising estimating capture parameters associated with at least one simulated scan whose score was determined to be adequate.

5. A method for calibrating an object inspection system comprising:
scanning a calibration target to obtain a point cloud representing the target;
tessellating the point cloud into one or more tiles containing a plurality of points of the point cloud;
for each of the one or more tiles, fitting a plane model to the points contained in the tile, wherein the plane model includes value of a three-dimensional vector normal to the surface of the plane and the distance of the plane from a coordinate system reference point;
adding the normal vectors from each of the one or more tiles and calculating the average of the collection of normal vectors;
using average normal vector orientation to define a reference plane outside the point cloud and calculating each cloud point to reference plane; and
using a histogram to find local maximums, and creating a group of points each with a distance to the defined reference plane that falls within a tolerance threshold to the local maximum.

6. The method of claim 5 , wherein the calibration target includes fiducial holes at known locations and positions, and further comprising analyzing the one or more plane models to detect the location and position of representations of these fiducial holes in the one or more plane models.

7. The method of claim 6 , further comprising determining a transformation matrix, based on the detected locations and positions of the representations of fiducial holes, that determines the orientation of the calibration target in three-dimensional space.

8. A method for calibrating the object inspection system comprising:
scanning the calibration target to obtain a point cloud;
creating a reference plane and measuring the distance of each point to the reference plane;
following a gradient descent approach to refine the orientation of the defined reference plane; and
creating a group of points each with a distance to the defined reference plane that falls within a tolerance threshold to the local maximum of a histogram of distances from the points to the defined reference plane.

9. The method of claim 8 , wherein the calibration target includes fiducial holes at known locations and positions, and further comprising analyzing the one or more plane models to detect the location and position of representations of these fiducial holes in the one or more plane models.

10. The method of claim 9 , further comprising determining a transformation matrix, based on the detected locations and positions of the representations of fiducial holes, that determines the orientation of the calibration target in three-dimensional space.

11. A method for maintaining performance of the scanning system, comprising:
obtaining two or more traversals of an object by one or more non-contact profilometers;
detecting regions of overlap between the obtained traversals and classifying and recording the amount of spatial displacement;
determining whether the classified degree of recorded spatial displacement in the overlap regions exceeds a predetermined threshold; and
comparing recorded spatial displacement data to a last recorded set.

12. The method of claim 11 , wherein the degree of spatial displacement is estimated from the regions of overlap between the two or more traversals, and is classified by changes in velocity.

13. The method of claim 11 , wherein a transformation matrix is created to correct the displacement and register the full traversal scans to each other thus creating a complete scan of the object when the recorded spatial displacement exceeds a predetermined threshold.

14. The method of claim 11 , wherein a projection will be calculated of when the spatial displacement in the overlap regions will exceed a pre-determined threshold when there is a change in the recorded spatial displacement from the last record.

15. A method for aligning and merging point clouds, comprising:
receiving a target three dimensional point cloud representing a rigid object;
calculating a 2D projection of the target point cloud to generate its characteristic vector;
generating a corresponding geometric transformation between the target point cloud and a reference model mesh;
performing a fine 3D registration of the transformed target point cloud with the reference model mesh;
determining a final geometric transformation between target point cloud and reference model mesh to the 3D registration; and
applying the final geometric transformation to the target point cloud; and
measuring the difference between the transformed target point cloud and the reference model mesh.

16. The method of claim 15 , wherein the corresponding geometric transformation includes a translated and rotated target point cloud coarsely aligned with the reference mesh model.

17. The method of claim 15 , wherein the 3D registration is performed using an iterative closest point algorithm or an iterative closest face algorithm to generate a refined geometric transformation matrix.

18. The method of claim 17 , wherein the target point cloud is a movable point cloud, and wherein using the iterative closest point algorithm includes:
finding the closest point in a reference point cloud with each iterative pass;
computing an error vector for each point in the movable cloud; and
forming a corrective translation and rotation of the movable point cloud that is compounded into the transformation matrix.

19. The method of claim 17 , wherein iterative closest face algorithm locates the nearest point on the face of the CAD model mesh during each iterative pass.

20. A method for automated set-up, maintenance, and scan processing of an object inspection system, the method comprising:
determining a system calibration transform;
determining a recommended scan set-up parameters for an object to be scanned;
performing at least one scan of the object, wherein the at least one scan includes capturing two or more point clouds representing the same view of the scanned object and two or more point clouds representing different views of the scanned object;
determining a three-dimensional registration between the two or more point clouds representing the same view of the object;
determining a three-dimensional registration between the two or more point clouds representing different views of the object; and
monitoring the pe

Assignees

• Kodak Alaris Inc

Inventors

• Link Bruce A
• Johnson Robert W
• Zegarra Jose Zvietcovich
• Stubler Peter O
• Barton Mark
• Brockler Frank R
• Axman Michael S
• Das Madirakshi
• Ferencz Jr Gabor J
• Garcell Erik

Classifications

• G05B2219/35134

  3-D cad-cam · CPC title

• G06T2207/20221

  Image fusion; Image merging · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T7/33

  using feature-based methods · CPC title

• G06T2219/2004

  Aligning objects, relative positioning of parts · CPC title