Reduction of temporal and spatial jitter in high-precision motion quantification systems

• US 10,594,940 B1
• Filed: 01/12/2018
• Issued: 03/17/2020
• Est. Priority Date: 01/12/2018
• Status: Active Grant

• Current Assignee: Vulcan SA (Ampco-Pittsburgh Corporation)
• Original Assignee: Vulcan SA (Ampco-Pittsburgh Corporation)
• Inventors: Persiantsev, Michael
• Primary Examiner(s): Yenke, Brian P
• Application Number:
  US15/870,678
• Time in Patent Office: 795 Days
• CPC Class Codes: G01B 11/26 for measuring angles or tapers; for testing the alignment of axes
• CPC Class Codes: H04N 23/683 performed by a processor, e.g. controlling the readout of an image memory

Abstract

A first image and a second image recorded during a video capture event is obtained. A correction factor is computed based at least in part on a target interval and an interval of time between recording the first image and recording the second image. A motion value is computed based at least in part on a difference between the first region and the second region, with the first region and the second region both containing a reference object present in the first image and the second image. A normalized motion value is provided based at least in part on normalizing the motion value according to the correction factor.

Claims

1. A computer-implemented method, comprising:

determining a target frame interval corresponding to a model duration of time between capture of a first image frame and a second image frame, the second image frame being adjacent to the first image frame in a sequence of image frames;

determining an actual interval of time between capture of the first image frame and capture of the second image frame, the actual interval of time being different from the target frame interval;

registering a static feature common to both the first image frame and the second image frame;

identifying an occurrence of the static feature in the first image frame and another occurrence of the static feature in the second image frame;

computing, at least in part by aligning the occurrence of the static feature in the first image frame with the other occurrence of the static feature in the second image frame, a spatial distance between a first set of pixels in the first image frame and second set of pixels in the second image frame;

computing a normalized motion value based at least in part on the spatial distance, the actual interval of time, and the target frame interval; and

performing an operation based at least in part on the normalized motion value reaching a value relative to a threshold.

2. The computer-implemented method of claim 1, wherein the spatial distance is a difference between one or more color space components in the first image frame and one or more color space components in the second image frame.

3. The computer-implemented method of claim 1, wherein aligning the occurrence with the other occurrence includes:

determining an amount of displacement of the static feature in the first image frame from the static feature in the second image frame; and

for each pixel of the first image frame, determining a corresponding pixel in the second image frame based at least in part on the amount of displacement.

4. The computer-implemented method of claim 3, wherein:

the static feature is a first static feature;

registering the static feature includes registering a second static feature common to both the first image frame and the second image frame; and

the computer-implemented method further comprises;

determining, based at least in part on the first static feature and the second static feature, an amount of rotation between the first image frame and the second image frame; and

rotating the pixels of the second set of pixels in accordance with the amount of rotation.

5. The computer-implemented method of claim 3, wherein registering the static feature includes storing characteristics of a region in the sequence of image frames into memory of a computing device.

6. A system, comprising:

one or more processors; and

memory including executable instructions that, if executed by the one or more processors, cause the system to;

obtain a first image and a second image;

compute a correction factor based at least in part on;

an actual interval of time between recording the first image and recording the second image; and

a target interval of time that is different from said actual interval of time;

identify, based at least in part on a displacement of a reference object present in both the first image and the second image, a first region in the first image common to a second region in the second image;

compute a difference value between the first region and the second region;

normalize, based at least in part on the correction factor, the difference value to produce a normalized difference; and

store the normalized difference to a data store.

7. The system of claim 6, wherein the first image and the second image are contiguous image frames in a sequence of image frames.

8. The system of claim 6, wherein executable instruction that compute the difference value further include instructions that cause the system to compute the difference value based at least in part on a displacement of the reference object between the first image and the second image.

9. The system of claim 8, wherein the executable instructions that cause the system to compute the difference value based at least in part on the displacement further include instructions that cause the system to:

not detect an occurrence of a first reference object in the first image or the second image;

identify occurrences of a second reference object in both the first image and the second image; and

compute the displacement between the occurrences of the second reference object.

10. The system of claim 6, wherein:

the first image and the second image are recorded during a video capture event; and

the first region and the second region correspond to a region of a scene of the video capture event that is common to both the first image and the second image.

11. The system of claim 6, wherein the executable instructions that cause the system to compute the difference value include instructions that cause the system to, for each pixel in the first region, compute a difference between a value of the pixel and a value of a corresponding pixel in the second region.

12. The system of claim 11, wherein the value of the pixel and the value of the corresponding pixel are values in a color space.

13. The system of claim 12, wherein the values in the color space are luminance values.

14. A non-transitory computer-readable storage medium having stored thereon executable instructions that, if executed by one or more processors of a computer system, cause the computer system to at least:

determine a target interval of time between recording of a first image and recording a second image;

determine an actual interval of time between recording the first image and recording the second image, the actual interval of time being different from the target interval of time;

identify, based at least in part on a displacement of a static feature common to both the first image and the second image, a first region in the first image common to a second region in the second image;

compute a difference between the first region and the second region;

normalize, based at least in part on the target interval and the actual interval, the difference to produce a normalized difference; and

store the normalized difference to a data store.

15. The non-transitory computer-readable storage medium of claim 14, wherein the executable instructions further include instructions that cause the computer system to perform an operation based at least in part on a determination that the normalized difference has reached a value relative to a threshold.

16. The non-transitory computer-readable storage medium of claim 14, wherein the executable instructions that identify the first region common to a second region include instructions that cause the computer system to identify, in the first image and the second image, regions of pixels that represent a same portion of a scene in common between both the first image and the second image.

17. The non-transitory computer-readable storage medium of claim 14, wherein the second image is adjacent in time of capture to the first image in a set of images.

18. The non-transitory computer-readable storage medium of claim 14, wherein the target interval in time is based at least in part on a specified frame rate of an image capture device that recorded the first image and the second image.

19. The non-transitory computer-readable storage medium of claim 14, wherein the executable instructions further include instructions that cause the computer system to:

receive a selection of the static feature in a baseline image; and

identify, based at least in part on finding a match in the first image and the second image to characteristics of the static feature in the baseline image, occurrences of the static feature in the first image and the second image.

20. The non-transitory computer-readable storage medium of claim 14, wherein:

the static feature is a member of a plurality of static features; and

the executable instructions that cause the computer system to identify the first region common to the second region include instructions that cause the computer system to compute the displacement based at least in part on a perspective transform using the plurality of static features.