Crop row detection system, agricultural machine having a crop row detection system, and method of crop row detection

Patent metadata

Field	Value
Publication number	US-12469169-B2
Application number	US-202318392251-A
Country	US
Kind code	B2
Filing date	Dec 21, 2023
Priority date	Jun 29, 2021
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

A crop row detection system includes a camera mounted to an agricultural machine to image a ground surface traveled by the agricultural machine to acquire time-series color images including at least a portion of the ground surface, and a processor configured or programmed to (i) perform image processing for the time-series color images, (ii) generate, from the time-series color images, an enhanced image in which a color of a crop row for detection is enhanced to provide an enhanced image, (iii) generate from the enhanced image a plan view image as viewed from above the ground surface, the plan view image being classified into first pixels having a color index value for the crop row equal to or greater than a threshold and second pixels having the color index value below the threshold, and (iv) determine positions of edge lines of the crop row based on the color index values of the first pixels.

First claim

What is claimed is:

1 . A crop row detection system comprising:
a camera mounted to an agricultural machine to image a ground surface traveled by the agricultural machine to acquire time-series color images including at least a portion of the ground surface; and a processor configured or programmed to:
perform image processing for the time-series color images;
generate from the time-series color images an enhanced image in which a color of a crop row for detection is enhanced to provide an enhanced image;
generate from the enhanced image a plan view image as viewed from above the ground surface, the plan view image being classified into first pixels having a color index value for the crop row equal to or greater than a threshold and second pixels having the color index value below the threshold;
split an entirety or a portion of the plan view image into a plurality of blocks;
determine positions of edge lines of the crop row for each of the plurality of blocks based on the color index values of the first pixels; and
determine a direction in which the crop row extends by connecting the positions of the edge lines in each of the plurality of blocks.

2 . The crop row detection system of claim 1 , wherein the processor is configured or programmed to:
total the color index values of the first pixels along a plurality of scanning lines in the plan view image to determine total values, and generate a histogram in which positions of the scanning lines and the total values are associated; and determine the positions of the edge lines of the crop row based on the histogram.

3 . The crop row detection system of claim 2 , wherein the processor is configured or programmed to refer to the histogram, and determine the positions of the edge lines of the crop row from predetermined positions on opposite sides of a peak of the total values.

4 . The crop row detection system of claim 1 , wherein
in the plan view image, the plurality of blocks have belt shapes that are continuous along a horizontal direction in the image or a vertical direction in the image; and the processor is configured or programmed to determine the edge lines of the crop row based on a belt shape in a direction that is different from a traveling direction of the agricultural machine.

5 . The crop row detection system of claim 1 , wherein
the plan view image is an overhead view image in which a reference plane extending along the ground surface is viewed directly from above along a normal direction of the reference plane; and the processor is configured or programmed to generate the overhead view image through homography transformation from the time-series color images or preprocessed images of the time-series color images.

6 . The crop row detection system of claim 5 , wherein the reference plane is offset upward by a predetermined distance that is set in accordance with bumps and dents on the ground surface having the crops being planted thereon, from bottoms of the bumps and dents of the ground surface.

7 . The crop row detection system of claim 1 , wherein the processor is configured or programmed to generate and output a target path based on the positions of the edge lines of the crop row.

8 . An agricultural machine comprising:
the crop row detection system of claim 1 ; a wheel; and an automatic steering controller configured or programmed to control a steering angle of the wheel based on the positions of the edge lines of the crop row as determined by the crop row detection system.

9 . The agricultural machine of claim 8 , wherein, based on the time-series color images, the processor is configured or programmed to monitor a positional relationship between the edge lines of the crop row and the wheel, and supply a positional error signal to the automatic steering controller.

10 . A computer-implemented method of crop row detection, the method comprising:
acquiring from a camera mounted to an agricultural machine, time-series color images by imaging a ground surface that is traveled by the agricultural machine, the time-series color images including at least a portion of the ground surface; generating from the time-series color images an enhanced image in which a color of a crop row for detection is enhanced; generating from the enhanced image a plan view image as viewed from above the ground surface, the plan view image being classified into first pixels having a color index value for the crop row equal to or greater than a threshold and second pixels of having the color index value below the threshold; splitting an entirety or a portion of the plan view image into a plurality of blocks; determining positions of edge lines of the crop row for each of the plurality of blocks based on the color index values of the first pixels; and determining a direction in which the crop row extends by connecting the positions of the edge lines in each of the plurality of blocks.

Assignees

• Kubota Kk

Inventors

• Miyashita Shunsuke
• TAMBO Toru
• Nagao Mitsuaki

Classifications

• A01B69/001 Primary

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

• G06V10/56

  relating to colour · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/30188

  Vegetation; Agriculture · CPC title