Gauging using sub-model poses

• US 6,459,820 B1
• Filed: 08/25/1998
• Issued: 10/01/2002
• Est. Priority Date: 08/25/1998
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Sarachik, Karen B.
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US09/140,124
• Time in Patent Office: 1,498 Days
• Field of Search: 382/286, 382/293, 382/298, 382/143, 382/145, 382/141, 382/86, 382/95, 702/158, 702/155
• US Class Current: 382/286
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80

Abstract

A method is provided for measuring distances between locations in an image. The method includes finding a position of a full model using sub-models to find a plurality of locations in an image, then labeling the locations and determining distances using the labels. The method improves upon conventional gauging techniques by exploiting information typically provided by a sub-model based shape finder so as to eliminate one or more computationally intensive applications of one or more vision tools. More specifically, the features of the found instance of the model that are used as a basis for performing measurements are those features that have already been accurately located by the sub-model based shape finder.

Claims

1. A method for measuring distances between locations in an image, the method comprising:

using a machine vision sub-model shape finder to find a plurality of locations in an image;

labeling the locations with respective labels; and

determining distance between locations in the image using the labels.

2. The method of claim 1, further comprising:

performing a projection of a distance using an angle so as to provide a projected distance.

3. The method of claim 2, wherein using sub-models includes finding a position of a full model in the image using sub-models, and

wherein the projected distance is one of a length, a width, a depth, a height, a thickness, and a size.

4. The method of claim 1, wherein using sub-models includes:

providing a pose of a full model in the image using sub-models.

5. The method of claim 1, further comprising:

evaluating the distances.

6. The method of claim 5, wherein evaluating the distances includes:

using a tolerance.

7. The method of claim 6, wherein the tolerance is scaled.

8. The method of claim 7, wherein using sub-models includes providing a pose of a full model in the image using sub-models, and

wherein the tolerance is scaled using a scale of the full model pose.

9. The method of claim 1, wherein determining distances using the labels includes:

identifying pairs of locations.

10. The method of claim 9, further including:

identifying groups of pairs of locations.

11. The method of claim 10, further including:

computing an average distance using an identified group of pairs of locations.