Kinematic Data Extraction from Technical Videography

• US 20170109894A1
• Filed: 10/19/2015
• Published: 04/20/2017
• Est. Priority Date: 10/19/2015
• Status: Abandoned Application

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Uphoff, Daniel Waite
• Application Number:
  US14/886,692
• Publication Number:
  US 20170109894A1
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments

Abstract

This disclosure describes a system and a method of extracting kinematic data, the method of extracting kinematic data, the method includes the steps of positioning a camera so that a test component is in a video frame; recording the test component using the camera while the test component is operating to generate video data; measuring kinematic values of a reference component; defining a search region in the video data encompassing an area of the test component; analyzing the measured kinematic values of the reference component; calculating, based on the analyzed kinematic values of the reference component, kinematic values of the test component; and generating an output file containing the calculated kinematic values of the test component.

Claims

1. A method of extracting kinematic data, the method comprising the steps of:

positioning a camera so that a test component is in a video frame;

recording the test component using the camera while the test component is operating to generate video data;

measuring kinematic values of a reference component;

defining a search region in the video data encompassing an area of the test component;

analyzing the measured kinematic values of the reference component;

calculating, based on the analyzed kinematic values of the reference component, kinematic values of the test component; and

generating an output file containing the calculated kinematic values of the test component.

2. The method of claim 1, wherein:

the calculating step includes the step of comparing a change in position of the search region from one video frame to a next video frame.

3. The method of claim 1, further comprising:

defining a plurality of signature regions within the search region on the test component.

4. The method of claim 3, wherein:

the test component has a plurality of color contrast locations; and

each signature region encompasses a color contrast location.

5. The method of claim 1, further comprising:

illuminating the test component.

6. The method of claim 1, wherein

the reference component is the camera.

7. The method of claim 1, further comprising the steps of:

inserting a measuring device into the video frame, thereby determining a length of a pixel of the camera.

8. The method of claim 1, wherein:

the positioning step includes the step of positioning the camera orthogonally to the test component.

9. The method of claim 1, further comprising:

determining a noise signature of the camera; and

removing noise from video data generated by the camera by subtracting the noise signature from movement of the test component.

10. The method of claim 1, wherein:

positioning the camera so that the reference component is in the video frame.

11. A system for extracting kinematic data, the system comprising:

a machine including a test component;

a camera configured to record the test component in a video frame;

a computer processor configured to execute computer-executable instructions, the computer-executable instructions comprising;

defining a search region in the video data encompassing an area of the test component;

analyzing measured kinematic values of a reference component;

calculating, based on the analyzed kinematic values of the reference component, kinematic values of the test component; and

generating an output file containing the calculated kinematic values of the test component.

12. The system of claim 11, wherein:

the calculating is performed by comparing a change in position of the search region from one video frame to a next video frame.

13. The system of claim 11, wherein the computer-executable instructions further comprise:

defining a plurality of signature regions within the search region on the test component.

14. The system of claim 13, wherein:

the test component has a plurality of color contrast locations; and

each signature region encompasses a color contrast location.

15. The system of claim 11, further comprising:

a light source positioned to illuminate the test component.

16. The system of claim 11, wherein:

the reference component is the camera.

17. The system of claim 11, further comprising:

a measuring device positioned so that it is within the video frame; and

the computer-executable instructions further comprise;

determining a length of a pixel of the camera represents based on the measuring device.

18. The system of claim 11, wherein:

the camera is positioned orthogonally to the test component.

19. The system of claim 11, wherein the computer-executable instructions further comprise:

determining a noise signature of the camera; and

removing noise from video data generated by the camera by subtracting the noise signature from movement of the test component.

20. The system of claim 11, wherein:

the camera is positioned so that the reference component is in the video frame.