IMAGE FILTER BASED ON ROW IDENTIFICATION

• US 20150324648A1
• Filed: 05/07/2015
• Published: 11/12/2015
• Est. Priority Date: 05/09/2014
• Status: Active Grant

• Current Assignee: Raven Industries Incorporated (CNH Industrial N.V.)
• Original Assignee: Raven Industries Incorporated (CNH Industrial N.V.)
• Inventors: Nelson, Robert Leonard Jr., Fowler, David Anthony, Wilson, Edwin Ernest
• Granted Patent: US 9,576,215 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A01B 69/001 Steering by means of optical assistance, e.g. television cameras steering devices for road marking vehicles E01C23/163
• CPC Class Codes: A01B 69/007 Steering or guiding of agricultural vehicles, e.g. steering of the tractor to keep the plough in the furrow
• CPC Class Codes: A01D 34/008 for automated or remotely controlled operation
• CPC Class Codes: G06K 2207/1016 Motor control or optical moving unit control
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20092 Interactive image processing based on input by user
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/536 from perspective effects, e.g. by using vanishing points
• CPC Class Codes: G06V 10/48 by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
• CPC Class Codes: G06V 20/188 Vegetation
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/38 Outdoor scenes
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/68 Food, e.g. fruit or vegetables

Abstract

System and techniques for an image filter based on row identification are described herein. A crop row center represented in an image of a crop row can be calculated. A filter corresponding to a set of expected crop characteristics of the crop row can be obtained. Elements in the image can then be categorized based on applying the filter to the image when the filter anchored on the crop row.

Claims

1. A system to filter an image, the system comprising:

an image capture controller to;

interface with a camera mounted on agricultural equipment; and

obtain an image of a crop row, from the camera, during operation of the agricultural equipment corresponding to a field with the crop row;

a crop row characteristic circuit set to;

calculate a crop row center from the image of the crop row; and

obtain a set of expected crop characteristics of the crop row; and

a filter circuit set to;

obtain a filter corresponding to the set of expected crop characteristics of the crop row; and

categorize elements in the image into categories based on applying the filter to the image, the filter anchored on the crop row center.

2. The system of claim 1, wherein to determine the crop row center includes the crop row characteristic circuit set to:

apply a feature threshold to identify elements of interest in the image; and

perform a Hough transform on the elements of interest to generate a crop row center line.

3. The system of claim 1, wherein the a set of expected crop characteristics are determined from an average of previously determined crop characteristics corresponding to a plurality of previous images of crops of a same type as the crop row.

4. The system of claim 1, wherein the filter is transformed based on a perspective of a sensor that captured the image.

5. The system of claim 1, wherein to categorize elements in the image based on the crop row center and the filter includes the filter circuit set to:

create a mask for the image, the mask anchored to the crop row center with edges defined by the filter;

apply the mask to the image; and

assign a category of crop element or non-crop element to elements of the image based on application of the mask to the image.

6. The system of claim 5 comprising a discriminator to:

compare non-crop elements, as determined by the against a desired non-crop element model to determine a deviation in the non-crop elements; and

flag the deviation.

7. The system of claim 6 comprising an applicator to control crop product application based on the flagged deviation.

8. The system of claim 7, wherein the crop product application is contemporaneous to capturing the image.

9. A method to filter an image, the method comprising:

calculating a crop row center represented in an image of the crop row;

obtaining a filter corresponding to a set of expected crop characteristics of the crop row; and

categorizing elements in the image into categories based on applying the filter to the image, the filter anchored on the crop row.

10. The method of claim 9, wherein determining the crop row center includes:

applying a feature threshold to identify elements of interest in the image; and

performing a Hough transform on the elements of interest to generate a crop row center line.

11. The method of claim 9, wherein the a set of expected crop characteristics are determined from an average of previously determined crop characteristics corresponding to a plurality of previous images of crops of a same type as the crop row.

12. The method of claim 9, wherein the filter is transformed based on a perspective of a sensor that captured the image.

13. The method of claim 9, wherein categorizing elements in the image based on the crop row center and the filter includes:

creating a mask for the image, the mask anchored to the crop row center with edges defined by the filter;

applying the mask to the image; and

assigning a category of crop element or non-crop element to elements of the image based on application of the mask to the image.

14. The method of claim 13 comprising:

comparing non-crop elements against a desired non-crop element model to determine a deviation in the non-crop elements; and

flagging the deviation.

15. The method of claim 14 comprising controlling crop product application based on the flagged deviation.

16. The method of claim 15, wherein the crop product application is contemporaneous to capturing the image.

17. A set of non-transitory machine readable media including instructions that, when executed by a machine, cause the machine to perform operations comprising:

calculating a crop row center represented in an image of the crop row;

obtaining a filter corresponding to a set of expected crop characteristics of the crop row; and

categorizing elements in the image into categories based on applying the filter to the image, the filter anchored on the crop row.

18. The set of machine readable media of claim 17, wherein determining the crop row center includes:

applying a feature threshold to identify elements of interest in the image; and

performing a Hough transform on the elements of interest to generate a crop row center line.

19. The set of machine readable media of claim 17, wherein the a set of expected crop characteristics are determined from an average of previously determined crop characteristics corresponding to a plurality of previous images of crops of a same type as the crop row.

20. The set of machine readable media of claim 17, wherein the filter is transformed based on a perspective of a sensor that captured the image.

21. The set of machine readable media of claim 17, wherein categorizing elements in the image based on the crop row center and the filter includes:

creating a mask for the image, the mask anchored to the crop row center with edges defined by the filter;

applying the mask to the image; and

assigning a category of crop element or non-crop element to elements of the image based on application of the mask to the image.

22. The set of machine readable media of claim 21, wherein the operations further comprise:

comparing non-crop elements against a desired non-crop element model to determine a deviation in the non-crop elements; and

flagging the deviation.

23. The set of machine readable media of claim 22, wherein the operations further comprise controlling crop product application based on the flagged deviation.

24. The set of machine readable media of claim 23, wherein the crop product application is contemporaneous to capturing the image.