Crop row segmentation by K-means clustering for a vision guidance system

• US 6,686,951 B1
• Filed: 02/28/2000
• Issued: 02/03/2004
• Est. Priority Date: 02/28/2000
• Status: Expired due to Term

• Current Assignee: Blue Leaf IP Incorporated (CNH Industrial N.V.), CNH Industrial America LLC (CNH Industrial N.V.)
• Original Assignee: Case, LLC (Chenega Corporation)
• Inventors: Han, Shufeng, Ni, Bingcheng, Dickson, Monte Andre
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): SENFI, BEHROOZ M
• Application Number:
  US09/514,433
• Time in Patent Office: 1,436 Days
• Field of Search: 701/28, 701/50, 701/120, 701/200, 701/208, 701/223, 348/116, 348/119, 348/162, 348/148, 348/113, 348/118, 348/120, 340/854.6, 340/957, 702/5, 702/7, 702/38, 702/115
• US Class Current: 348/120
• CPC Class Codes: A01B 69/008 automatic
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/188 Vegetation
• CPC Class Codes: G06V 20/38 Outdoor scenes

Abstract

An automatic vision guidance system for an agricultural vehicle is disclosed and described. The vision guidance system uses a K-means clustering algorithm in image processing to distinguish between crop and non-crop features. The vision guidance system utilizes moment algorithms to determine the location and orientation of crop rows, from which desired wheel angles are determined and steering is commanded. The vision guidance system may adjust the location and orientation of visually determined crop rows according to a predetermined distance between crop rows. Further, the vision guidance system may utilize a redundant number of regions of interest in determining crop row locations and orientations.

Claims

1. An automatic guidance system for an agricultural vehicle, the guidance system comprising:

an electromagnetic sensor for gathering information about field characteristics, the electromagnetic sensor configured to provide a signal representative of the field characteristics, the signal representative of pixels of an image;

an information processor having a memory and a central processing unit, and the information processor coupled to the electromagnetic sensor; and

a program in the memory of the information processor configured to be executed by the central processing unit, the program configured to perform a clustering algorithm that categorizes the pixels into categories of field characteristics.

2. The guidance system of claim 1, wherein the program categorizes by using a clustering operation.

3. The guidance system of claim 2, wherein the electromagnetic sensor includes a video camera.

4. The guidance system of claim 3, wherein the video camera includes a charge coupled device (CCD).

5. The guidance system of claim 2, wherein the electromagnetic sensor is configured to substantially sense electromagnetic radiation in the near infrared (NIR) spectrum.

6. The guidance system of claim 2, wherein the clustering algorithm includes a partitioning method clustering operation.

7. The guidance system of claim 2, wherein the clustering algorithm includes a K-means clustering operation.

8. The guidance system of claim 2, wherein the clustering algorithm includes a self-organizing map.

9. The guidance system of claim 7, wherein the K-means clustering algorithm is terminated according to a predetermined tolerance.

10. The guidance system of claim 2, wherein the electromagnetic sensor includes a digital camera.

11. The guidance system of claim 3, wherein the video camera includes a complementary metal-oxide semiconductor (CMOS) array.

12. A method of sensing field characteristics, comprising:

sensing electromagnetic radiation with an electromagnetic sensor;

communicating a signal representative of the sensed electromagnetic radiation, and representative of pixels of an image, to a processing device; and

categorizing the pixels into field characteristic categories by using a clustering operation.

13. The method of claim 12, wherein the clustering operation includes a K-means clustering operation.

14. The method of claim 12, wherein the clustering operation comprises:

producing a histogram of pixel gray levels;

dividing the histogram into a predetermined number of classes; and

assigning a center to each class.

15. The method of claim 14, wherein the clustering operation further comprises:

assigning each pixel to its closest center; and

moving each center to the mean of the points assigned to it.

16. The method of claim 15, wherein the clustering operation further comprises:

repeating, assigning each pixel to its closest center and moving each center to the mean of the points assigned to it; and

terminating the operation if a movement threshold is reached.

17. The method of claim 12, further comprising:

assigning a crop designation to at least one field characteristic category.

18. The method of claim 17, further comprising:

controlling an agricultural vehicle based on a control signal generated from the crop field characteristic category.

19. An agricultural vehicle configured to be guided through a field by an automatic guidance system, the agricultural vehicle comprising:

a visual means for gathering visual input about field characteristics in the format of a digitized image, including pixel information; and

a clustering means configured to cluster pixel information into groups.

20. The agricultural vehicle of claim 19, wherein the groups can be distinguished as crop and non-crop.

21. The agricultural vehicle of claim 19, wherein the clustering means includes a program utilizing a K-means clustering operation.

22. The agricultural vehicle of claim 19, wherein the visual means includes a charge coupled device (CCD) camera.

23. The agricultural vehicle of claim 19, wherein the visual means includes a complementary metal-oxide semiconductor (CMOS) camera.

24. The agricultural vehicle of claim 19, further comprising:

a control means for controlling the direction of movement of the agricultural vehicle based upon the visual input.

25. The agricultural vehicle of claim 19, wherein the clustering means includes a partitioning operation.

26. The agricultural vehicle of claim 19, wherein the clustering means includes a self-organizing map.