Crop row segmentation by K-means clustering for a vision guidance system
First Claim
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.
3 Assignments
0 Petitions
Accused Products
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.
88 Citations
26 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
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. - View Dependent Claims (13, 14, 15, 16, 17, 18)
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. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26)
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.
Specification