System and method for detecting crop rows in an agricultural field

• US 20040264761A1
• Filed: 04/06/2004
• Published: 12/30/2004
• Est. Priority Date: 04/30/2003
• Status: Active Grant

• Current Assignee: Deere & Company, University of Illinois
• Original Assignee: Deere & Company
• Inventors: Reid, John Franklin, Zhang, Qin, Mas, Francisco Rovira
• Granted Patent: US 8,712,144 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• 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 79/005 Precision agriculture
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• 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

Abstract

A system and method for creating 3-dimensional agricultural field scene maps are disclosed comprising producing a pair of images using a stereo camera and creating a disparity images based on the pair of images, the disparity image being a 3-dimensional representation of the stereo images. Coordinate arrays can be produced from the disparity image and the coordinate arrays can be used to render a 3-dimensional local map of the agricultural field scene. Global maps can also be made by using geographic location information associated with various local maps to fuse together multiple local maps into a 3-dimensional global representation of the field scene.

Claims

1. An apparatus for creating a 3-dimensional field scene map, comprising:

at least one camera for producing a pair of images of the field scene; and

means for creating a disparity image from the pair of images;

wherein the disparity image comprises a 3-dimensional image encoded with x, y, and z coordinates relative to the at least one camera.

2. The apparatus of claim 1, wherein the at least one camera comprises a stereo camera.

3. The apparatus of claim 1, wherein each of the pair of images comprises ditigal images.

4. The apparatus of claim 3, wherein the pair of digital images overlap and include common features, and wherein the means for creating a disparity image is configured to match the common features from the pair of digital images.

5. The apparatus of claim 4, wherein the means for creating a disparity image comprises a computer running a software program.

6. The apparatus of claim 1, further comprising means for transforming the disparity image into a 3-dimensional local map of the field scene.

7. The apparatus of claim 6, wherein multiple 3-dimensional local maps of the field scene from generated disparity images, and further comprising means for fusing the multiple 3-dimensional local maps into a 3-dimensional global image.

8. The apparatus of claim 7, wherein the means for transforming the disparity image is configured to use image parameters to transform the disparity image.

9. The apparatus of claim 8, wherein the image parameters include camera focal length and camera center.

10. The apparatus of claim 1, further comprising a location tracking device configured for providing geographic location information.

11. The apparatus of claim 10, wherein the location tracking device comprises a global positioning system.

12. The apparatus of claim 1 further comprising a filter for filtering errors from the disparity image.

13. The apparatus of claim 1, wherein the field scene is an agricultural field scene.

14. The apparatus of claim 1, wherein the at least one camera comprises two distinct cameras.

15. A method for making a 3-dimensional map of a field scene, the method comprising the steps of:

acquiring at least one set of images of the field scene;

creating a disparity image based on the at least one set of images, the disparity image including depth information for objects captured in the at least one set of images; and

creating a coordinate array of 3-dimensional coordinates for the objects captured in the at least one set of images.

16. The method of claim 15, wherein the at least one set of images comprise stereo images.

17. The method of claim 15, wherein the 3-dimensional coordinates are 3-dimensional camera coordinates;

, and wherein the method further comprises the step of converting the 3-dimensional camera coordinates into 3-dimensional ground coordinates.

18. The method of claim 15, further comprising the step of filtering the 3-dimensional coordinates to remove noise.

19. The method of claim 18, wherein the step of filtering the 3-dimensional coordinates comprises ignoring 3-dimensional coordinates above a predetermined threshold.

20. The method of claim 18 wherein the step of filtering the 3-dimensional coordinates comprises ignoring 3-dimensional coordinates below a predetermined threshold.

21. The method of claim 18, wherein the at least one set of images is acquired by a stereo camera, and wherein the step of filtering the 3-dimensional coordinates comprises ignoring 3-dimensional coordinates a predetermined distance away from stereo camera.

22. The method of claim 15, further comprising the step of rendering the coordinate array as a 3-dimensional map.

23. The method of claim 15 further comprising the step of filtering the 3-dimensional ground coordinates by ignoring ground coordinates having a Z value above a predetermined threshold.

24. The method of claim 15, wherein the at least one set of images comprise stereo images, the at least one set of stereo images being acquired by a stereo camera, and wherein a corrected camera tilt angle is applied such that the method produces a resulting 3-dimensional map of a field scene having a plane parallel to a Z=O plane.

25. A method for making a 3-dimensional map of a field scene, comprising the steps of:

acquiring a plurality of sets of images of the field scene;

creating a disparity image based on each set of images, each disparity image including depth information for objects captured in the corresponding set of images;

creating a coordinate array of 3-dimensional coordinates for the objects captured in each set of stereo images;

acquiring a geographic location origin for each set of stereo images;

performing a coordinate transformation on the 3-dimensional coordinates for the objects captured in each set of images so that the coordinates relate to a common origin; and

merging the transformed 3-dimensional coordinates into a global map comprising a 3-dimensional representation of the field scene.

26. The method of claim 25, further comprising the step of rendering the transformed 3-dimensional coordinates of the global map into a 3-dimensional map of the field scene.

27. The method of claim 26, wherein the field scene is an agricultural field scene.

28. The method of claim 27, wherein each of the plurality of sets of images are stereo images generated from a stereo camera.