JPH01211410A - Crop row detection apparatus of farm working machine - Google Patents

Abstract

PURPOSE:To prevent stamping of transplanted seedlings with a working machine, by switching a virtual line calculation means to the mode to calculate a quadratic or cubic curve when the deviation of the machine from a row exceeds a prescribed permissible limit. CONSTITUTION:The operation for detecting a crop with an image pickup means 40 is started in the step S3 and the image data is inputted in the step S4. In the step S5, the data are digitized to discriminate the transplanted area from the other farm area. The digitized coordinates of the positions of the transplanted plant are determined in the step S6 and a virtual straight line is calculated in the step S7 from the data of the center or gravitational center of the target area A. When the deviation i between the machine and the virtual line is larger than a prescribed level, the virtual line is judged to be a curve in the step S8. The virtual line calculation means is switched to a curve function generation circuit in the step S11.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention is directed to a system that enables agricultural machinery such as a rice transplanter to run substantially parallel to so-called rows of crops that have already been planted in a field and lined up in rows. This invention relates to the structure of a crop row detection device for automatic steering control.

[Conventional technology]

Conventionally, when planting seedlings in a field using a rice transplanter, the rice transplanter is equipped with a planting mechanism at appropriate intervals on the left and right sides of the rice transplanter, and the planting mechanism that moves up and down as the rice transplanter advances moves the seedling mat on the seedling stand. Since the seedlings are divided into appropriate numbers of plants and planted in the field, the seedlings are planted at appropriate intervals along the direction of movement of the rice transplanter. It is well known that rice is planted in multiple rows at appropriate intervals in the left and right direction: Then, the rice transplanter is made to run approximately parallel to the rows of planted seedlings (hereinafter referred to as crop rows) that have already been planted in the field. As a prior art of automatic steering system, Japanese Patent Application Laid-Open No. 62-61509
In the publication, a color video camera mounted on a rice transplanter that moves forward images an appropriate range of the crop rows in the adjacent parts, and this imaged screen information is binarized to determine the location of each crop. After extracting the region corresponding to
gh) Approximately calculate a straight line from the row made up of the plurality of regions by processing such as conversion, and calculate the lateral and inclination deviations between this calculated virtual straight line and arbitrary reference lines and reference points such as the vertical and horizontal center lines of the imaging screen. It is proposed to perform aircraft steering control to keep the gap within a certain tolerance range.

[Problem to be solved by the invention]

By the way, some fields are rectangular in plan view, others are deformed fields where the ridges are partially curved, and crop rows can be linear, curved, or straight depending on the shape of the field. There are various combinations with curves.

However, in the prior art, the crop row is imagined to be a straight line, and the rice transplanter is automatically steered so as to run substantially parallel to the side portions of the row along this virtual straight line.
When the actual crop row is a straight line, if you imagine the actual crop row to be a straight line and run the rice transplanter in a straight line even though the actual crop row is curved, it will become a row of crops that have already been planted. The specified seedling planting row spacing (the spacing between seedlings planted on the left and right sides perpendicular to the traveling direction of the traveling machine) may be too wide or too narrow, and in severe cases, the running wheels may already be planted. There are problems such as trampling over mature seedlings.

Furthermore, since a management machine that applies fertilizer or sprays chemicals at an appropriate time after planting seedlings performs the work while moving along the rows of crops that have already been planted, such a farm machine is equipped with an automatic steering device. In this case, the same problem as above occurs.

The present invention aims to solve this problem.

[Means to solve the problem]

Therefore, the present invention provides a crop row detection device used for automatic steering control of an agricultural machine such as a rice transplanter so that the crop row detecting device runs substantially parallel to the rows of crops already planted in a field. Planting in a crop row consists of an imaging means for taking an image of a crop location, and a virtual line calculation means for calculating a virtual line along the crop row from the image information of the imaging means. The calculation means is configured to once calculate a straight virtual line, and if the deviation from the crop row is greater than a predetermined value, the calculation is switched to a calculation to obtain a curved virtual line such as a quadratic curve.

[Action/effect of the invention]

According to this configuration, by imaging the rows of crops that have already been planted by the imaging means, it is possible to identify the position of the crop in the field scene.

Based on this specified position data, the arrangement of the crop rows is assumed to be a predetermined straight line or curved line, and the agricultural machine is run parallel to the side along the imaginary line. When calculating a virtual line using a line calculation means, −
First, let's calculate by assuming that the virtual line is a straight line.

The virtual straight line obtained in this way is compared with the data of the position, and if the deviation is within a predetermined tolerance range,
Automatic steering is executed based on the virtual straight line, and when the deviation is outside a predetermined allowable range, the virtual line calculation means is switched to calculate a quadratic or cubic virtual line, and the virtual line is converted into a quadratic curve or a cubic curve. Automatic steering is performed based on this.

This makes it possible to reliably and quickly perform automatic steering to move straight ahead at an appropriate distance to the side of a straight row of crops. In addition, when the crop row is curved, such as when there is a row of crops along a curved ridge, when the virtual line is forced to be a straight line and the automatic steering is performed along the virtual straight line, it is possible to This eliminates inconveniences such as trampling on crop areas with the wheels of the traveling machine.

〔Example〕

An example applied to a Honda rice transplanter will be described below. In the figure, 1 indicates front wheels 3.
A traveling machine body supported by rear wheels 4.4 on both left and right rear sides, and a multi-row seedling planting device consisting of a seedling platform 5 and a plurality of planting mechanisms 6 is installed at the rear of the traveling machine body 1. 7 is attached via a link mechanism 8 so as to be able to move up and down.

The power of the engine 9 mounted on the upper surface of the frame 2 of the traveling body 1 is transmitted to both the front and rear axles 3.4 via the clutch lO and the transmission case 11, and via the PTO shaft 12 protruding from the transmission case 11. power is transmitted to the seedling planting device 7.

In addition, reference numeral 13 is an ON-OFF actuator for the clutch 10, 14 is an actuator for traveling speed change, and 15 is a PTO.
Actuator for variable shaft peripheral speed.

A steering gear box 17 is provided on the upper surface of the traveling aircraft 1 in front of the pilot seat 16, and a steering shaft 19 inserted into the steering column 18 is connected to the upper end of the steering column 1B that stands up from the steering gear box 17. The control handle 20 is attached.

Reference numeral 21 denotes a left and right long transmission case in which front wheels 3.3 are attached to both left and right ends via knuckles 22.22, and a power transmission mechanism from the transmission case 11 is housed inside, and the transmission case 21 is attached to it. The bracket 21a, which is U-shaped in plan view, is connected to the swing shaft 21c, which is rotatably supported by a support member 21b at the center of the lower surface of the frame 2, so that it can swing horizontally and vertically. has been done.

The steering device includes a steering arm 24 which is horizontally rotatably mounted on a rotational fulcrum shaft 23 erected from one side of the transmission case 21, and a pair of left and right tie rods 25 connected to the steering arm 24. 25, hydraulic cylinder 2G, steering IIJ control valve 27, and the steering control valve 27
It consists of a pitman arm 28 that can freely swing back and forth of a steering gear box 17 that operates the steering gear box 17.

One ends of the pair of left and right tie rods 25, 25 are connected to the arm portion 24a of the steering arm 24 extending in the front-rear direction of the frame 2 via a ball joint, respectively.
Both tie rods 25, 25 are extended along the transmission case 21 to the left and right of the movement of the traveling body 1, and the other ends of the tie rods 25, 25 are extended forward from the knuckles 22, 22, respectively.
9. Connect to 29 so that it can swing freely.

A control valve 27 is connected rearward via a ball joint to a support shaft 30 of an arm extending inwardly from the steering arm 24 toward the side surface of the frame 2, and a spool at the rear end of the control valve 27 It is connected to the pitman arm 28 via a connecting rod 31.

Further, the rear end of a hydraulic cylinder 26 disposed substantially parallel to the outer surface of the frame 2 is connected to the support shaft 30 via a ball joint, while the front end of the piston loft 26a is connected to the frame via a ball joint. 2 is connected to a bracket horizontal shaft 32 protruding from the outer surface.

A hydraulic pump 33 is connected to the control valve 27 and the hydraulic cylinder 26 through hydraulic hoses, and is driven by the engine 5.
The hydraulic pressure is sent from the solenoid control valve 27 to the electromagnetic solenoid control valve 27.

Then, the pitman arm 28, which swings in accordance with the rotation angle of the steering handle 10, moves the spool of the control valve 27 forward and backward, causing the piston rod 26a in the hydraulic cylinder 26 to move in and out, thereby rotating the steering arm 24. The direction of the left and right front wheels 3, 3 is changed accordingly.

This hydraulic cylinder 26 is connected to a crop row detection device W137, which will be described later.
It is also driven by an electromagnetic solenoid type steering control valve 34 operated by a central control device 35 for automatic steering and driving that outputs an output signal in response to a signal from Potentiometer 36 attached to 23
This is executed by detecting the rotation angle of the steering arm 24 at.

Note that the ON-OFF actuator 13 of the clutch 10, the traveling speed change actuator 14, the PTo shaft circumferential speed change actuator 15 are operated by the central control device 35.

The crop row detection device 37 includes an imaging means 40 for imaging an object, and an image processing device 41 for processing the captured image and exchanging necessary information (data) with the central control device 35.
It consists of.

The imaging means 40 is a so-called area sensor which has an imaging screen having a two-dimensional plane extending vertically and horizontally like an xy plane, like a so-called video camera, when detecting an object.

In the imaging means 40, when the optical image of the object to be detected is resolved in time series of pixels on the photoconductive surface of the photoelectric sensor, the repetition of the scanning line scanned along the horizontal axis (X-axis) of the imaging screen is repeated vertically. By sequentially shifting the images along the axis (Y-axis), − images are formed, and according to this two-dimensional imaging means 40, multiple plantings on − images are performed at different crop locations. can be simultaneously detected along with their geometric relationships and obtained as image information.

As an example of this imaging means 40, for example, a two-dimensional MO
In devices with built-in 3-image sensors or two-dimensional CCD image sensors, the image formed through the lens is sensed by each image sensor (photoelectric device) arranged in a two-dimensional array on the image plane, and the image is captured. Information on the screen 42 can be output as an electrical signal.

In order to configure one image capturing screen 42, the image capturing means 40, which is composed of the two-dimensional image sensor, samples the image using minute pixels of 256×256.

The image processing device 41 and the central control device 35 execute processing according to the schematic flowchart shown in FIG. 7, and finally the central control device 35 outputs a signal to follow the virtual straight line or virtual curve to start rice planting. It controls the automatic steering of the aircraft.

To explain according to the flowchart, in step S1 following the start, initial values are set, and then in step S2, the operator of the agricultural machine moves the traveling machine 1 along with it to the side of the crop rows that have already been planted in the field. Start driving along.

Next, in step S3, the detection operation by the imaging means 40 is started, and in step S4, image data is captured (
FIG. 5 shows a state in which the planted crop location (NAE) is imaged on the imaging screen 42).

Next, in step S5, binarization processing is performed to distinguish the planting crop area (NAE) from other field scenes.

In this embodiment, when configuring a captured image on a color screen, the RGB color system [red (R), green (
G), blue (B) color light is used as primary color light, and white is obtained by adding light] The characteristics of the field scene are extracted from the signals of each color component: red component, green component, and blue component. The green color (G
) When the signal output ratio of the component is equal to or higher than a predetermined value, it is determined that the area (A) is a seedling (crop), and the area (A) is segmented from other parts of the imaging screen 42 (Segmentation). Execute.

In addition, binarization is performed using color difference processing, which determines as seedlings (crops) where the color difference image data (GB) obtained by subtracting the blue component from the green component of the color signal in the image is output above a certain level. Also good.

In addition, crop areas and other mud surfaces (like black and white television)
It is also possible to detect the difference in brightness between the target area (A ) shows the binarized state).

Furthermore, by utilizing the phenomenon that the reflectance of infrared rays from plants such as seedlings is higher than the reflectance of infrared rays from mud and water in the field,
In the color or black and white imaging means 40, an image sensor that is highly sensitive to visible light in the infrared and/or near-infrared region is used, or a filter that highly transmits visible light in the infrared and/or near-infrared region is used. If images are taken using an infrared filter (such as an infrared filter), the location of the planted crop can be reliably and easily identified.

In step S6, the binarized planting performs a calculation to determine the coordinates of the position of the crop site.

That is, each binarized target area (A) is specified as a set of a plurality of pixels on the imaging screen 42 so as to have an appropriate area in a plan view (see FIG. 7).

From this specified target area (A), using a predetermined method using software installed in the image processing device 41,
The coordinates of the center position or center of gravity of each specific area (A) are calculated.

One method for calculating these coordinates is to calculate the number of pixels corresponding to the area of the target area (A) in a set of pixels arranged in matrix on the vertical axis (Y axis) and horizontal axis (X axis) of the imaging screen 42. Finally, by replacing the level V = 1 part (high level) with level v-0 (low level) in a spiral manner from the outer periphery of the target area (A), etc., using a method similar to so-called area contraction. The coordinates are determined by determining the position of the remaining high level portion (1 to 2 pixels) as the center of gravity.

Step S7 is a calculation step in which the virtual line is assumed to be a straight line and the virtual line is calculated from the center or center of gravity position data of the plurality of target areas (A) identified. A virtual line calculation means (including a straight line or curved function generation circuit and an arithmetic circuit) built into the image processing device 41 or the central control device 35 executes calculation of the virtual line.

As one of the virtual line calculation means for specifying the straight virtual line Kl, there is a generally well-known method for determining the virtual straight line Kl by estimating the least squares error.

That is, this method uses a set of multiple regions (coordinates (χi, Yi) (i = L2+3+"...
, n) ) is given, and the linear function F (x)-aO+alx to be sought is given, then the function F (x ).

Note that here, the Y axis is taken in the direction in which the traveling aircraft moves forward, and the
The axis is taken in the left and right direction of the traveling aircraft.

Next, in step S8, the plurality of target areas Al, A2, A3 identified above with respect to this virtual straight line KN are
, ...Coordinates (χi, Yi) at A n (
i=1.2,3. ...+n) and the deviation of the lateral slip (
Δi) (see Figure 8).

As can be understood from FIG. 8, the deviation (A
1) , A5 (X5.Y5 )0) Deviation (A5) ,
It is found that the deviation (A8) of A8 (X8.Y8'') is larger than the deviations of other coordinates, and in step s9, this large deviation is compared with a preset allowable deviation,
If it is within the allowable range, proceed to ■ and proceed to step SI.
In O, the inclination angle θ and lateral deviation δ between the calculated virtual straight line and the reference line KO (for example, the Y-axis at the left-right center of the imaging screen 42) are calculated, and then in step Sll, this inclination angle θ and lateral deviation are calculated. The automatic steering control is executed so that δ falls within the allowable range and the reference line KO and the virtual straight line 1 substantially coincide with each other. That is, an output signal is output to the central controller 35 according to the tilt angle θ and the lateral deviation δ, and the steering control valve 3
The electromagnetic solenoid No. 4 is operated to drive the hydraulic cylinder 26 that changes the rotation angle of the steering arm 24 in the steering mechanism, thereby performing corrective steering and keeping lateral deviation, etc. within an allowable error range.

On the other hand, if the deviation (Δi) is greater than or equal to a predetermined value in the determination in step S8, it is determined that the virtual line is not a straight line but a curved line.

When it is determined that the vehicle is curved, automatic steering control is executed by image processing from the area sensor 39 in steps 8-12 to S14.

That is, in step Sll, virtual line calculation means (
(including a linear or curved function generation circuit and an arithmetic circuit) is switched to a curved function generation circuit, and the virtual line Kc of the planted seedling row is again approximated as a curved line.

At this time, using the above-mentioned method of determining the virtual line by estimating the least squares error can contribute to the simplification of the software. For example, the desired function F (x) = aO+alx
Assuming that it is a quadratic curve like +a2x, we create a set of multiple regions (locus ai (Xi, Yi) (i = 1.2.3.
・th・, n) ) has already been obtained as data in step S6, so the error E−Σ1YiF(Xi)
What is necessary is to find a function F (x) that minimizes zl.

The virtual quadratic curve Kc at this time is shown as a solid line in FIG.
The virtual straight line KI! Compared to target areas Al, A2.
A3. ""Coordinates (Xi, Yi) (i
=1.2.3. ”, n) is small.

Next, in step 312, the slope (θ) and lateral deviation (δ) of the virtual curve Kc obtained as described above with respect to the reference point, etc., and the curvature R at appropriate intervals on the virtual curve Kc are calculated. It is something.

In this case, as shown in FIG.
The inclination angle (θ) of the virtual line Kc is calculated using the Y-axis (vertical axis) as the reference line in the X-Y orthogonal coordinate system passing through the reference point 0, while the The lateral shift (δ) may be calculated as the distance from the intersection with 1 to the reference point 0, or another location may be used as the reference.

Then, in step S13, automatic steering control is executed to follow the virtual curve Kc. At this time, output signals are sent to the central controller 35 so that the inclination angle (θ), lateral deviation (δ), and curvature R of the virtual curve Kc of the traveling aircraft 1 by actual steering are within the allowable error range, The electromagnetic solenoid of the steering control valve 34 is actuated to drive the hydraulic cylinder 26 that changes the rotation angle of the steering arm 24 in the steering mechanism, thereby performing corrective steering.

In this case, the potentiometer 36 that detects the rotation angle of the steering arm 24 can detect whether or not the front wheel 3 has a steering angle that matches the inclination angle (θ) of the virtual curve Kc. , the results can be used as feedback for automatic steering control.

[Brief explanation of the drawing]

The drawings show an embodiment of the present invention, and Fig. 1 is a plan view of a riding rice transplanter, Fig. 2 is a side view, Fig. 3 is a plan view of main parts of the steering device, and Fig. 4 is a steering/travelling diagram. A block diagram of the automatic control device and an action explanatory diagram including a hydraulic circuit; Figure 5 is a diagram of the imaging screen; Figure 6 is a diagram of the imaging screen;
The figure is an explanatory diagram of a binarized imaging screen, and (
a), (b). (C) is a flowchart, FIG. 8 is a comparative explanatory diagram of the case where the virtual line of the crop row is approximated by a straight line and the case where it is approximated by a curve, and FIG.
The figure is an explanatory diagram of a virtual curve on an imaging screen. 1... Traveling body, 2... Frame, 3.4...
... Wheels, 5 ... Seedling stand, 6 ... Planting mechanism, 7
...Seedling planting device, 8...Link mechanism, 9...
Engine, 11...Mission case, 17...
- Steering gear box, 20... Control handle, NAE... Planting at crop location, KA... Virtual straight line, Kc... Virtual curve, 23... Rotation fulcrum axis, 24... Steering arm, 26... Hydraulic cylinder, 34... Steering control valve, 35... Central control device, 36... Potentiometer, 40...
- Imaging means, 41... image processing device, 42...
Imaging screen. Figure 5 Figure 6 (b) (c]

Claims (1)

[Claims] (1) A crop row detection device used for automatic steering control of an agricultural machine such as a rice transplanter so that it runs approximately parallel to and along the rows of crops already planted in the field. imaging means for imaging the planted crop location in the row;
and a virtual line calculation means for calculating a virtual line along the crop row from the image information of the imaging means, and the virtual line calculation means is configured to calculate a straight virtual line by the virtual line calculation means, and then calculate a virtual line along the crop row. 1. A crop row detection device for an agricultural working machine, characterized in that, if the deviation of the curve is equal to or greater than a predetermined value, the calculation is switched to obtain a virtual line of a curve such as a quadratic curve.