Method and apparatus of automatically identifying faults in a machine vision measuring system
First Claim
1. An apparatus for detecting a fault of a machine vision measuring system comprising:
- a memory that stores an image formed by a camera of a target having a plurality of fiducials;
a data processor coupled to the memory and having stored instructions which, when executed by the data processor, cause the data processor to carry out the steps of;
creating and storing a list of values representing detected fiducials of the target based on the image;
comparing the values representing the detected fiducials to a plurality of second values representing true fiducials of the target in a stored model of the target;
based on the comparing step, selectively removing one or more of the detected fiducials from the list that fail to satisfy pre-determined criteria;
generating a warning message using the machine vision measuring system when fewer than a first pre-determined number of detected fiducials remain in the list.
1 Assignment
0 Petitions
Accused Products
Abstract
An apparatus and method for automatically identifying faults in the operation of a machine vision measuring systems provides an improved self-diagnostic capability for machine vision based metrology and tracking systems. The method and apparatus validate performance of tracking operations, and detect deterioration that may be caused by electronic noise, environmental contamination, etc. A mathematical model of the target visualized by the system is created and stored. A target is imaged in the field and fiducials of the target are identified. Centroid positions of detected fiducials of the imaged target are compared to the centroid positions of fiducials in the mathematical model. When a fiducial is obscured or dirty, its geometric characteristics (such as centroid, brightness, edge smoothness, area, or shape) differ from the true or idealized values of the characteristics. Values representing detected fiducials are discarded when the offset exceeds predetermined criteria, or when its properties vary from ideal. If the remaining number of detected fiducials is below a predetermined threshold, a warning message is displayed or an error is generated. Thus, when a fault is detected that degrades performance beyond a preset tolerance, the fault is flagged for attention and a suggested corrective action is displayed.
64 Citations
18 Claims
-
1. An apparatus for detecting a fault of a machine vision measuring system comprising:
-
a memory that stores an image formed by a camera of a target having a plurality of fiducials;
a data processor coupled to the memory and having stored instructions which, when executed by the data processor, cause the data processor to carry out the steps of;
creating and storing a list of values representing detected fiducials of the target based on the image;
comparing the values representing the detected fiducials to a plurality of second values representing true fiducials of the target in a stored model of the target;
based on the comparing step, selectively removing one or more of the detected fiducials from the list that fail to satisfy pre-determined criteria;
generating a warning message using the machine vision measuring system when fewer than a first pre-determined number of detected fiducials remain in the list. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference in position of a centroid value of a detected fiducial as compared to a centroid value of the stored model.
-
-
3. An apparatus as recited in claim 1, wherein the instructions further cause the data processor to carry out the steps of:
generating an error message using the machine vision measuring system when the list contains fewer than a second predetermined number of detected fiducials.
-
4. An apparatus as recited in claim 1, wherein the instructions further cause the data processor to carry out the steps of:
generating an error message using the machine vision measuring system and terminating operation of the machine vision measuring system when the list contains fewer than a second predetermined number of detected fiducials.
-
5. An apparatus as recited in claim 1, wherein the instructions for carrying out the step of generating a warning message further comprise instructions for carrying out the steps of:
-
generating a message that prompts the user to clean the target;
receiving user input;
in response to user input, repeating the steps of forming, determining, and selectively removing.
-
-
6. An apparatus as recited in claim 1, wherein the instructions for carrying out the step of generating a warning message further comprise instructions for carrying, out the steps of:
-
generating a message that prompts the user to clean the target;
repeating the steps of forming, determining, and selectively removing;
determining that the target has been cleaned when the list contains a number of detected fiducials or equal to or greater than a second predetermined number.
-
-
7. An apparatus as recited in claim 1, wherein the instructions further cause the data processor to carry out the steps of:
-
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference of a centroid value of a detected fiducial as compared to a centroid value of the stored model corresponding to an actual fiducial of the target;
selectively removing from the list, values representing each detected fiducial having a difference value that is greater than a predetermined threshold value and more than a pre-determined multiple of the average deviation value.
-
-
8. An apparatus as recited in claim 1, wherein the instructions further cause the data processor to carry out the steps of:
-
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference of a centroid value of a detected fiducial as compared to a centroid value of the stored model corresponding to an actual fiducial of the target;
identifying one of the detected fiducials that has a greatest difference value;
selectively removing from the list, values representing the detected fiducial having the greatest difference value, when the difference value is greater than a predetermined threshold value and more than a predetermined multiple of the average deviation value.
-
-
9. A method of detecting a fault of a machine vision measuring system that includes a target having a plurality of fiducials and stored image of the target and the fiducials, the method comprising the steps of:
-
creating and storing a list of values representing detected fiducials of the target based on the image;
comparing the detected fiducials to a plurality of values representing true fiducials of the target in a stored model of the target;
selectively removing one or more of the detected fiducials from the list that fail to satisfy pre-determined criteria;
generating a warning message using the machine vision measuring system when fewer than a first pre-determined number of detected fiducials remain in the list. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference of a centroid value of a detected fiducial as compared to a centroid value of the stored model corresponding to an actual fiducial of the target.
-
-
11. A method as recited in claim 9, further comprising the steps of:
generating an error message using the machine vision measuring system when the list contains fewer than a second predetermined number of detected fiducials.
-
12. A method as recited in claim 9, further comprising the steps of:
generating an error message using the machine vision measuring system and terminating operation of the machine vision measuring system when the list contains fewer than a second predetermined number of detected fiducials.
-
13. A method as recited in claim 9, wherein generating a warning message further comprises the steps of:
-
generating a message that prompts the user to clean the target;
receiving user input;
in response to user input, repeating the steps of forming, determining, and selectively removing.
-
-
14. A method as recited in claim 9, further comprising the steps of:
-
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference of the centroid of a detected fiducial as compared to a centroid value of the stored model corresponding to an actual fiducial of the target;
selectively removing from the list, values representing each detected fiducial having a difference value that is greater than a predetermined threshold value and more than a pre-determined multiple of the average deviation value.
-
-
15. A method as recited in claim 9, further comprising the steps of:
-
generating a message that prompts the user to clean the target;
repeating the steps of forming, determining, and selectively removing;
determining that the target has been cleaned when the list contains a number of detected fiducials or equal to or greater than a second predetermined number.
-
-
16. A method as recited in claim 9, further comprising the steps of:
-
determining a centroid of each of the detected fiducials;
determining an average difference value that represents an average of a plurality of difference values associated with the detected fiducials, wherein each difference value represents a difference of a centroid value of a detected fiducial as compared to a centroid value of the stored model corresponding to an actual fiducial of the target;
identifying one of the detected fiducials that has a greatest difference value;
selectively removing from the list, values representing the detected fiducial having the greatest difference value, when the difference value is greater than a predetermined threshold value and more than a pre-determined multiple of the average deviation value.
-
-
17. A computer-readable medium carrying one or more sequences of instructions for detecting a fault of a machine vision measuring system that includes a target having a plurality of fiducials and stored image of the target and the fiducials, wherein execution of the one or more sequences of instructions by one or more processors causes the one or more processors to perform the steps of:
-
creating and storing a list of values representing detected fiducials of the target based on the image;
comparing the detected fiducials to a plurality of values representing true fiducials of the target in a stored model of the target;
selectively removing one or more of the detected fiducials from the list that fail to satisfy pre-determined criteria;
generating a warning message using the machine vision measuring system when fewer than a first pre-determined number of detected fiducials remain in the list.
-
-
18. A computer-aided machine vision motor vehicle wheel alignment apparatus comprising:
-
a camera that forms an image of a target and a plurality of fiducials on the target;
a memory that stores the image formed by the camera;
a data processor coupled to the memory and having stored instructions which, when executed by the data processor, cause the data processor to carry out the steps of;
creating and storing a list of values representing detected fiducials of the target based on the image;
comparing the detected fiducials to a plurality of values representing true fiducials of the target in a stored model of the target;
selectively removing one or more of the detected fiducials from the list that fail to satisfy pre-determined criteria;
generating a warning message using the machine vision measuring system when fewer than a first pre-determined number of detected fiducials remain in the list.
-
Specification