Determining image feature height disparity

Patent metadata

Field	Value
Publication number	US-11615543-B2
Application number	US-202016926449-A
Country	US
Kind code	B2
Filing date	Jul 10, 2020
Priority date	Jul 11, 2019
Publication date	Mar 28, 2023
Grant date	Mar 28, 2023

Abstract

A device to determine a height disparity between features of an image includes a memory including instructions and processing circuitry. The processing circuitry is configured by the instructions to obtain an image including a first repetitive feature and a second repetitive feature. The processing circuitry is further configured by the instructions to determine a distribution of pixels in a first area of the image, where the first area includes an occurrence of the repetitive features, and to determine a distribution of pixels in a second area of the image, where the second area includes another occurrence of the repetitive features. The processing circuitry is further configured by the instructions to evaluate the distribution of pixels in the first area and the distribution of pixels in the second area to determine a height difference between the first repetitive feature and the second repetitive feature.

First claim

The invention claimed is:

1. A device to determine a height disparity between features of an image, the device comprising:
a camera system to obtain an image, the image comprising a first repetitive feature and a second repetitive feature; and
a machine controller comprising:
a first distribution element configured to determine a distribution of pixels in a first area of the image, the first area comprising an occurrence of the first repetitive feature and an occurrence of the second repetitive feature;
a second distribution element that is configured to determine a distribution of pixels in a second area of the image, the second area comprising another occurrence of the first repetitive feature and another occurrence of the second repetitive feature, and
a comparator element configured to evaluate the distribution of pixels in the first area and the distribution of pixels in the second area to determine a height difference between the first repetitive feature and the second repetitive feature.

2. The device of claim 1 , wherein the camera system comprises a mono camera system.

3. The device of claim 1 , wherein the second area has a different observation angle than the first area.

4. The device of claim 1 , wherein the first repeated feature is a crop row and the second repeated feature is a furrow.

5. The device of claim 1 , wherein the machine controller comprises a transformation element configured to transform, prior to determining the distribution of pixels in the first area or the distribution of pixels in the second area, the first area and the second area to an image frame.

6. The device of claim 1 , wherein to obtain a distribution of pixels in the first area, the first distribution element is configured to determine a centroid of a distribution of pixels in the first area in a color space.

7. The device of claim 1 , wherein the first distribution element is configured to obtain a distribution of pixels in the first area using an intensity level of pixels in the first area.

8. The device of claim 7 , wherein the intensity level of pixels in the first area comprises a mean intensity level of pixels in the first area.

9. The device of claim 1 , wherein the first distribution element is configured to obtain a distribution of pixels in the first area based on an area of the first repeated feature that is occluded by the second feature.

10. The device of claim 1 , wherein to determine the difference in height between the first repetitive feature and the second repetitive feature, the comparator element is configured to calculate the difference in height using an observation angle of the first area and an observation angle of the second area.

11. The device of claim 1 , wherein to determine the difference in height between the first repetitive feature and the second repetitive feature, the comparator element is configured to calculate the difference in height using a difference between the first distribution and the second distribution.

12. The device of claim 1 , wherein:
the first repeated feature comprises a first color,
the second repeated feature comprises a second color, and
to determine the difference in height between the first repetitive feature and the second repetitive feature, is the comparator element is configured to identify, a color space, a shift in the distribution of pixels in the first area, relative to the distribution of pixels in the second area, towards the first color in a color space.

13. The device of claim 1 , wherein the machine controller comprises an element that is configured to identify, using the difference in height, a feature that is closet to a camera that captured the image.

14. Method for determining a height disparity between features of an image, the method comprising:
obtaining an image, the image comprising a first repetitive feature and a second repetitive feature;
determining a distribution of pixels in a first area of the image, the first area comprising an occurrence of the first repetitive feature and an occurrence of the second repetitive feature;
determining a distribution of pixels in a second area of the image, the second area comprising another occurrence of the first repetitive feature another occurrence of the second repetitive feature, and
evaluating the distribution of pixels in the first area and the distribution of pixels in the second area to determine a height difference between the first repetitive feature and the second repetitive feature.

15. The method of claim 14 , further comprising capturing the first image using a mono camera system.

16. The method of claim 14 , wherein the second area is at a different observation angle than the first area.

17. The method of claim 14 , wherein the first repeated feature is a crop row and the second repeated feature is a furrow.

18. The method of claim 14 , further comprising transforming, prior to determining the distribution of pixels in the first area or the distribution of pixels in the second area, the first area and the second area to an image frame.

19. The method of claim 14 , wherein to obtain a distribution of pixels in the first area comprises calculating a centroid of a distribution of pixels in the first area in a color space.

20. The method of claim 14 , wherein obtaining a distribution of pixels in the first area comprises using an intensity level of pixels in the first area.

21. The method of claim 20 , wherein the intensity level of pixels in the first area comprises a mean intensity level of pixels in the first area.

22. The method of claim 14 , wherein further comprising obtaining the distribution of pixels in the first area based on an area of the first repeated feature that is occluded by the second feature.

23. The method of claim 14 , wherein determining the difference in height between the first repetitive feature and the second repetitive feature comprises calculating the difference in height using an observation angle of the first area and an observation angle of the second area.

24. The method of claim 14 , wherein determining the difference in height between the first repetitive feature and the second repetitive feature comprises calculating the difference in height using a difference between the first distribution and the second distribution.

25. The method of claim 14 , wherein:
the first repeated feature comprises a first color,
the second repeated feature comprises a second color, and
determining the difference in height between the first repetitive feature and the second repetitive feature comprises identifying, a color space, a shift in the distribution of pixels in the first area, relative to the distribution of pixels in the second area, towards the first color in a color space.

26. The method of claim 14 , further comprising identifying, using the difference in height, a feature that is closet to a camera that captured the image.

27. A non-transitory machine-readable medium including instructions for determining a height disparity between features of an image, the instructions, when executed by processing circuitry, cause the processing circuitry to perform operations comprising:
obtaining an image, the image comprising a first repetitive feature and a second repetitive feature;
determining a distribution of pixels in a first area of the image, the first area comprising an occurrence of the first repetitive feature and an

Assignees

• Raven Ind Inc

Inventors

• Sneyders Yuri
• Preheim John D

Classifications

• A01B69/001

  Steering by means of optical assistance, e.g. television cameras (steering devices for road marking vehicles E01C23/163) · CPC title

• A01C14/00

  Methods or apparatus for planting not provided for in other groups of this subclass · CPC title

• A01D75/00

  Accessories for harvesters or mowers · CPC title

• G06T7/536 Primary

  from perspective effects, e.g. by using vanishing points · CPC title

• G06T7/90

  Determination of colour characteristics · CPC title