DE102022212161A1 - Method for determining a width index of plants in a row of plants in an agricultural area - Google Patents

Abstract

The invention relates to a method for determining a width index of plants (12) of at least one row of plants (14) of an agricultural area, wherein width values for identified plants (12) of identified rows of plants (14) are determined in received image information (10), wherein the image information (10) is divided into transverse regions (18) and a width value represents a maximum width (22) of the respective plant (12) in the respective transverse region (18), and a width index of the plants (12) is determined using the determined width values.

Description

State of the art

The invention is based on a method for determining a width index of plants of at least one row of plants in an agricultural area and a corresponding computing unit, a plant identification unit and an agricultural working machine according to the class of the independent claims. The present invention also relates to a computer program and a machine-readable storage medium

In agriculture, crop size is often an important characteristic. In addition, this information is also important for the parameterization of algorithms for plant classification. The BBCH scale is usually used for this. This scale describes the growth stage of a plant and is a standard procedure in agriculture. Describing a plant size using this scale leaves a lot of room for interpretation, especially for non-agronomists. In addition, the BBCH scale describes plant size less directly, but rather properties of the plant such as germination status or number of leaves. For example, two sugar beet plants, each with 4 leaves, are in the same BBCH stage, but can differ significantly in size.

The plant width across the plant row is an important feature, especially for plant classification. A variety of parameters for a variety of algorithms can be derived from this information. A field of several hectares rarely grows at the same rate everywhere. Depending on the amount of water and nutrients in the soil, there can be significant local differences in different regions of the field.

• - Reihenkulturen wie Mais oder Soja wachsen schnell zusammen und bilden eine zusammenhängende Reihe.
• - Innerhalb eines Bildes kann die Größe der Pflanzen stark variieren.

There are two major challenges in visually determining plant size, especially in row crops:

• - Row crops such as corn or soy grow together quickly and form a continuous row.
• - Within one picture the size of the plants can vary greatly.

The still unpublished EN 10 2021 213 280 discloses a method for identifying weeds in a row of plants in an agricultural area, wherein a length value is determined for each identified plant in a defined crop area, wherein the length value is the number of transverse areas over which an identified plant in the defined crop area extends.

Other algorithms use networks (deep learning) or classification methods to recognize plants. This requires a lot of training data, a lot of label data and offline training beforehand. In addition, these methods are very computationally intensive.

Disclosure of the invention

• - Empfangen einer Bildinformation von einem mittels einer optischen Erfassungseinheit erfassten Feldabschnitt einer landwirtschaftlichen Fläche mit Pflanzen;
• - Identifizieren von Pflanzen in der Bildinformation mittels einer Recheneinheit;
• - Identifizieren von Pflanzenreihen in der Bildinformation unter Verwendung der identifizierten Pflanzen mittels der Recheneinheit;
• - Ermitteln von Breitenwerten für identifizierte Pflanzen identifizierter Pflanzenreihen in der Bildinformation mittels der Recheneinheit, wobei die Bildinformation in Querbereiche unterteilt ist und ein Breitenwert jeweils eine maximale Breite der jeweiligen Pflanze in dem jeweiligen Querbereich repräsentiert; und
• - Ermitteln einer Breitenkennzahl der Pflanzen zumindest einer der Pflanzenreihen unter Verwendung der ermittelten Breitenwerte mittels der Recheneinheit.

The present invention relates to a method for determining a width index of plants of at least one row of plants in an agricultural area, comprising the steps:

• - Receiving image information from a field section of an agricultural area with plants captured by means of an optical detection unit;
• - Identifying plants in the image information using a computing unit;
• - Identifying rows of plants in the image information using the identified plants by means of the computing unit;
• - determining width values for identified plants of identified plant rows in the image information by means of the computing unit, wherein the image information is divided into transverse areas and a width value represents a maximum width of the respective plant in the respective transverse area; and
• - Determining a width index of the plants of at least one of the plant rows using the determined width values by means of the computing unit.

The method described above can in particular be a computer-implemented method for determining a width index of plants of at least one row of plants in an agricultural area using the above-mentioned steps.

The present invention further relates to a computing unit which is configured to execute and/or control the steps of a previously described method.

The present invention also relates to a plant identification unit with an optical detection unit for detecting a field section of an agricultural area with plants in order to obtain image information from the detected field section, and a previously described computing unit.

The present invention further relates to an agricultural working machine, in particular an agricultural field sprayer, with an agricultural working tool, in particular a spraying device, and a plant identification unit as described above, wherein the working tool, in particular the spraying device, can be controlled depending on the determined width index, in particular the plants classified on the basis thereof.

The present invention also relates to a computer program which is designed to carry out and/or control the steps of a method described above when the computer program is executed on a computer, as well as to a machine-readable storage medium on which the computer program is stored.

Since plants usually grow rotationally symmetrically, the plant width across the row of plants is sufficient information to determine a plant size. Therefore, according to the invention, the image is divided into defined transverse areas in order to then determine width values for identified plants in identified rows of plants, with a width value representing a maximum width of the respective plant in the respective transverse area. This makes it possible to determine a corresponding width index for plants in a row of plants, in particular a row of cultivated plants, in a very simple and resource-saving manner, for example to set parameters for further algorithms or to control an agricultural work machine.

The method according to the invention works much more precisely and error-free than manually entering a static and inaccurate value such as the BBCH value, so that the parameters of the algorithms can now be set more precisely and automatically by the system dynamically. In this way, they each improve their own performance in order to achieve the most accurate classification of plants and weeds possible in the overall system. This method is also a relief for the software developer who has to parameterize his algorithms.

An agricultural area can be understood as an area used for agriculture, a cultivation area for plants or even a plot of such an area or cultivation area. The agricultural area can therefore be arable land, grassland or pasture. The plants include cultivated plants or useful plants whose fruit is used agriculturally, for example as food, animal feed or as an energy crop, as well as weeds or weeds.

The method can comprise a step of detecting a field section of an agricultural area with plants using the optical detection unit. The detection step can be carried out during a crossing or a flight of the plant identification unit or the agricultural work machine. At least one further step of the method, in particular all steps of the method, can be carried out during a crossing or a flight of the plant identification unit or the agricultural work machine.

The plant identification unit can comprise a mobile unit or be arranged on a mobile unit, wherein the mobile unit can be designed in particular as a land vehicle and/or aircraft and/or trailer. The mobile unit can also be a self-propelled or autonomous robot. The plant identification unit is preferably part of an agricultural work machine. The agricultural work machine is preferably a weed control machine, in particular an agricultural field sprayer. The agricultural work tool is preferably a spraying device, but can also be a mechanical tool for weed control.

The field section can be a detection section or a detected image section of an optical detection unit. The image information can be, for example, an image of the detected field section. An optical detection unit can be understood to be, for example, a camera or a 3D camera or an infrared detection unit. The optical detection unit can be calibrated, for example, to calculate the height assignment from detected images.

The method comprises a step of identifying plants in the image information or the image by means of a computing unit. The plants in the image information are understandably pixels, in particular connected pixels with corresponding pixel values in the image information or the image, which characterize or represent a plant object from the real world in the image. The plant object can be selected from the group consisting of: a single plant, a single plant part, several overlapping plants and/or plant parts, plant mass, biomass and combinations thereof. The step of identifying plants can involve identifying a color component, in particular a red color component and/or an infrared component in the image information. tion or the image. Plants can be detected using the optical detection unit, e.g. by evaluating light spectra or using a predetermined NDVI value (Normalized Differenced Vegetation Index, which is formed from reflection values in the near infrared and visible red wavelength range of the light spectrum), by distinguishing plant mass or biomass from the (earth) soil. Identifying plants here also includes determining the presence of plants or parts of plants or plant mass or biomass in the field section, in particular without (initially) classifying the individual plants.

The method further comprises a step of identifying rows of plants in the image information using the identified plants by means of the computing unit. The rows of plants are plants, in particular cultivated plants, sown in rows, i.e. essentially linearly. Accordingly, the rows of plants are preferably rows of cultivated plants. Therefore, by definition, it can be assumed (initially) that plants in the row of cultivated plants are cultivated plants and plants between the cultivated plants are weeds.

The rows of plants or rows of cultivated plants extend essentially in a straight line across the agricultural area and thus also in the image information or the image. The identification of the rows of plants or rows of cultivated plants is preferably carried out using at least one of the following pieces of information: color component, in particular red color component of plants in the recorded field section, infrared component of plants in the recorded field section, plant spacing, plant row spacing, growth stage of the plants, geocoordinates of a sowing of the plants. Using this information, the rows of plants can be easily identified since, for example, cultivated plants are usually planted equidistantly along rows or the cultivated plants are further along in terms of growth stage than the weeds. In the step of identifying the rows of plants, all rows of plants in the image information or the image are preferably identified.

Since the plant rows extend essentially in a straight line, the identification of a plant row can be done, for example, by fitting a straight line or a straight plant row center line into an image trajectory with a calculated NDVI index or the highest NDVI value (normalized distance or difference between red and infrared/NIR). The plant row center lines can thus be considered part of the plant rows.

Preferably, in the step of identifying the plant rows, a plant row center line is generated or created in each of the plant rows. The plant row center line can either have been generated to identify the plant rows or be generated afterwards. In this case, the transverse areas preferably extend transversely, in particular orthogonally to the generated plant row center lines in the image information.

The method also includes a step of determining width values for identified plants of identified plant rows in the image information using the computing unit, wherein the image information is divided into transverse areas and a width value represents a maximum width of the respective plant in the respective transverse area, i.e. within the respective transverse area. The width is determined transversely, in particular perpendicularly to the plant rows or generated plant row center lines.

The transverse areas preferably extend transversely, in particular orthogonally, to the rows of plants or generated plant row center lines in the image information. The transverse areas can, for example, run at an angle of greater than or equal to 45° to less than or equal to 90°, more preferably at an angle of greater than or equal to 85° to less than or equal to 90° to the rows of plants or generated plant row center lines. However, the transverse areas can also run horizontally in the image information or the image, independently of the rows of plants or generated plant row center lines. The transverse areas preferably extend over the entire image width of the image information or the image.

The transverse regions have a substantially equal length along a defined longitudinal direction, in particular along a direction of the plant rows or one of the plant row center lines. The length of the transverse regions can be predetermined or can be predetermined. The transverse regions preferably have a substantially equal length in the defined longitudinal direction. The length of the transverse regions is greater than 1 pixel. The length of the transverse regions is preferably in a range from greater than or equal to 5 pixels to less than or equal to 50 pixels.

Consequently, the transverse areas are defined strip-shaped pixel areas which divide the image information or the image into “stripes”, in particular of equal size.

The width value is preferably a number of pixels of the respective plant in the respective transverse area of the image information. Accordingly, the width value represents or characterizes the number of pixels along which the respective plant extends in the respective transverse area transversely, in particular perpendicularly to the plant rows or generated plant row center lines. In the step of determining, each transverse area is advantageously assigned a width value per plant row.

Consequently, for x transverse areas and y identified plant rows, x * y = z width values are determined.

The method further comprises a step of determining the width index of the plants in at least one of the plant rows using the determined width values by means of the computing unit. Advantageously, in the step of determining the width index, width values with the value zero are deleted or ignored. The width index is preferably selected from the group consisting of: minimum width value, maximum width value, mean value of the width values, median of the width values, outlier value of the width values. Advantageously, in the step of determining, the width index is determined for one identified plant row and/or one received image information item and/or for several received image information items, in particular a defined number of previously received image information items. In other words, depending on the desired resolution level or data transmission capacity, it can be selected whether the width index is to be determined for one plant row or several plant rows from one image or several images, in the latter case an even more stable width index is obtained.

In this case, the width index is advantageously dynamically adjusted with an increasing number of previously identified plants or a defined number of immediately previously identified plants during the process, in particular during a movement of the optical detection unit over the agricultural area. In other words, the width index changes dynamically during the field crossing, since (new) width values of newly identified plants are always included. Furthermore, (old) width values of old identified plants can preferably be excluded, e.g. if only a defined constant number of currently identified plants or image information is taken into account, so that the width index adapts to the latest conditions on the agricultural area. This measure makes the process very flexible, since the width index is constantly updated automatically during the crossing, so that the algorithm can constantly learn the current field situation and widths of the plants and is also dynamic enough that it can adapt its decision regarding the control of the agricultural work tool even if plant growth changes across the agricultural field.

Preferably, in the step of determining, in addition to the width values, length values for identified plants of identified plant rows in the image information are determined by means of the computing unit. In this case, a length value represents a number of transverse areas over which the respective plant extends, in particular along a/the direction of the plant rows or one of the plant row center lines. In other words, the length of the plants is determined in the unit “transverse areas”. The determination can be carried out in particular according to the above-mentioned EN 10 2021 213 280 Subsequently, in the determining step, a length index of the plants of at least one of the plant rows is determined using the determined length values by means of the computing unit.

This makes it possible to show the farmer in a very simple and precise way, for example, when (in terms of time based on the crossings / date the images were taken) or where (georeferenced information from the system) his crops have grown from being isolated to forming a closed row.

Preferably, the width index and, if applicable, the length index are used as input variables for calculation methods and control methods of an agricultural working machine in order to adapt them dynamically, in particular during a movement of the optical detection unit over the agricultural area.

The method can comprise a step of classifying the identified plants depending on the determined width index using the computing unit. In this case, the identified plants can be classified in particular into a first plant class or class of cultivated plants and/or into a second plant class or class of weeds. Accordingly, no usual classification method is used that performs clustering from plant-specific properties and then determines which class (cultivated plant or weed) an object most likely belongs to. A classifier is a method, which ultimately calculates a probability of how well an object belongs to a class.

• - Es resultierte eine verbesserte Klassifizierung der Pflanzen, insbesondere Kulturpflanzen und/oder Beikräuter.
• - Es ist keine Sammlung von vielen Bilddaten und kein Anfertigen von Labels notwendig, um ein Netz oder Klassifikation zu trainieren, wodurch der Gesamtaufwand stark reduziert wird.
• - Es ist kein Offline-Training anhand von Bilddaten im Vorfeld notwendig.
• - Die erforderliche Rechenzeit für die Klassifizierung ist sehr gering.
• - Die Information über die klassifizierten Pflanzen, insbesondere Kulturpflanzen und Beikräuter in dem Kulturpflanzenbereich kann für darauffolgende Schritte genutzt werden, um Pflanzenreihen besser bzw. genauer zu identifizieren, da die identifizierten bzw. erkannten Beikräuter hierfür unberücksichtigt bleiben bzw. „ignoriert“ werden können.

This offers a number of advantages:

• - This resulted in an improved classification of plants, especially cultivated plants and/or weeds.
• - There is no need to collect a lot of image data or create labels to train a network or classifier, which greatly reduces the overall effort.
• - No offline training using image data is necessary beforehand.
• - The computing time required for classification is very low.
• - The information on the classified plants, in particular cultivated plants and weeds in the cultivated plant area can be used for subsequent steps to better or more accurately identify plant rows, since the identified or recognized weeds can be disregarded or "ignored" for this purpose.

Preferably, before the step of classification, a pre-classification of the identified plants can be carried out independently of the width index, whereby in the step of classification the pre-classified plants retain their pre-classification or are reclassified. In other words, the plants can first be (pre)classified according to another classification method and then a validation or reclassification can be carried out depending on the width index. For example, the identified plants or plant objects could be classified according to a EN 10 2017 210 804 A1 known methods in order to then be reclassified by means of the method according to the invention if a “misclassification” occurs.

Furthermore, it is advantageous if the method comprises a step of controlling an agricultural working machine, in particular an agricultural working tool of an agricultural working machine, in particular a spraying device of a field sprayer, depending on the determined width index, in particular the plants classified on the basis thereof. The method thus makes it possible to specifically combat or regulate weeds in and/or between the rows of plants.

It is also advantageous if a step of storing the width index in a storage unit of an agricultural work machine or an external storage unit, in particular the cloud, is provided. Alternatively or additionally, it is advantageous if a step of outputting the width index to a display unit of an agricultural work machine or an external display unit is provided. The display unit can be, for example, an external display or operating terminal or HMI device, which is designed, for example, as a smartphone or tablet.

The computing unit is or the computing units are designed or set up for image processing so that it can carry out calculation steps or image processing steps for carrying out the method according to the invention. Accordingly, each computing unit has corresponding image processing software. The computing unit can be, for example, a signal processor, a microcontroller or the like, wherein the storage unit can be a flash memory, an EPROM or a magnetic storage unit. The communication interface can be designed to read in or output data wirelessly and/or via a wired connection, wherein a communication interface that can read in or output wired data can read this data, for example, electrically or optically from a corresponding data transmission line or output it to a corresponding data transmission line.

Accordingly, the method according to the invention can be implemented, for example, in software or hardware or in a hybrid form of software and hardware in the computing unit or a control unit. The computing unit can be arranged completely or partially on the agricultural work machine or integrated into it. However, the computing unit can also be completely or partially integrated externally, e.g. in a cloud. The computing unit can therefore also be divided into different units, e.g. mobile and stationary units.

Also advantageous is a computer program product or computer program with program code that can be stored on a machine-readable carrier or storage medium such as a semiconductor memory, a hard disk memory or an optical memory and is used to carry out, implement and/or control the steps of the method according to one of the embodiments described above, in particular when the program product or program is executed on a computer or device.

• 1 eine schematische Darstellung eines Bildes mit identifizierten Pflanzen, welches in Querbereiche unterteilt ist;
• 2 einen Ausschnitt einer Tabelle mit Breitenwerten zu dem Bild aus 1; und
• 3 ein Ablaufdiagramm eines Verfahrens gemäß einem Ausführungsbeispiel.

Embodiments of the invention are shown in the drawings and explained in more detail in the following description. It shows:

• 1 a schematic representation of an image with identified plants, divided into transverse regions;
• 2 an excerpt from a table with width values for the image from 1 ; and
• 3 a flow chart of a method according to an embodiment.

1 schematically shows image information 10 or an image 10 of a field section of an agricultural area with plants 12 captured by means of an optical detection unit or camera (not shown).

As from 1 As can be seen, in image 10 the plants 12 and plant rows 14 were first identified using the identified plants 12 by means of a computing unit (not shown). The identification of the plant rows 14 was carried out by generating defined straight plant row center lines 16 in image trajectories with the highest NDVI value of the plants 12.

How to continue 1 As can be seen, the image 10 is divided into thirteen (13) transverse regions 18. The transverse regions 18 extend transversely or orthogonally to the plant rows 14 or the plant row center lines 16. The transverse regions 18 are of the same design. The transverse regions 18 extend over the entire width of the image 10 and have the same length along a defined longitudinal direction 2, which corresponds to the direction of the plant rows 14 or the plant row center lines 16.

According to the invention, width values are determined for identified plants 12 of identified plant rows 14 in the image 10, wherein a width value represents or characterizes a maximum width 22 of the respective plant 12 in the respective transverse area 18. The width value is a number of pixels of the respective plant 12 in the respective transverse area 18 of the image 10.

2 shows an excerpt from a table with the width values for image 10 from 1 , whereby each transverse area 18 was assigned a width value per plant row 14.

Using the determined width values, a width index of the plants 12 can then be determined according to the invention. When determining the width index, width values with the value zero can advantageously be deleted or ignored. The width index can be selected from the group consisting of: minimum width value, maximum width value, mean value of the width values, median of the width values, outlier value of the width values. Furthermore, the width index can be determined for each identified row of plants 14 and/or each received image 10 and/or for several received images 10, in particular a defined number of previously received images 10.

3 shows a flow chart of an embodiment of the approach presented here as a method 100 for determining a width index of plants 12 of at least one row of plants 14 of an agricultural area. The method 100 comprises a step of receiving 102 image information 10 from a field section of an agricultural area with plants 12, detected by means of an optical detection unit. The method further comprises a step of identifying 104 plants 12 in the image information 10 by means of a computing unit. The method 100 also comprises a step of identifying 106 rows of plants 14 in the image information 10 using the identified plants 12 by means of the computing unit. The method 100 further comprises a step of determining 108 width values for identified plants 12 of identified plant rows 14 in the image information 10 by means of the computing unit, wherein the image information 10 is divided into transverse regions (18) and a width value represents a maximum width 22 of the respective plant 12 in the respective transverse region 18. The method further comprises a step of determining 110 a width index of the plants 12 of at least one of the plant rows 14 using the determined width values by means of the computing unit.

The method also includes an optional step of classifying 112 the identified plants 12 depending on the determined width index by means of the computing unit, in particular into a first plant class or class of cultivated plants 12 and/or into a second plant class or class of weeds. Alternatively or additionally, the method 100 includes an optional step of controlling 114 an agricultural work machine, in particular an agricultural work tool of an agricultural work machine, in particular a spraying device of a field sprayer, depending on the determined width index, in particular the plants 12 classified based thereon.

QUOTES INCLUDED IN THE DESCRIPTION

This list of documents listed by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions.

Cited patent literature

• EN 102021213280 [0005, 0032]
• DE 102017210804 A1 [0037]

Claims (20)

Method (100) for determining a width index of plants (12) of at least one row of plants (14) of an agricultural area, comprising the steps: - receiving (102) image information (10) from a field section of an agricultural area with plants (12) detected by an optical detection unit; - identifying (104) plants (12) in the image information (10) by means of a computing unit; - identifying (106) rows of plants (14) in the image information (10) using the identified plants (12) by means of the computing unit; - determining (108) width values for identified plants (12) of identified rows of plants (14) in the image information (10) by means of the computing unit, wherein the image information (10) is divided into transverse regions (18) and a width value represents a maximum width (22) of the respective plant (12) in the respective transverse region (18); and - determining (110) a width index of the plants (12) of at least one of the rows of plants (14) using the determined width values by means of the computing unit. Procedure (100) according to Claim 1 , characterized in that the width value is a number of pixels of the respective plant (12) in the respective transverse area (18) of the image information (10). Procedure (100) according to Claim 1 or 2 , characterized in that the width index is selected from the group consisting of: minimum width value, maximum width value, mean value of the width values, median of the width values, outlier value of the width values. Method (100) according to one of the preceding claims, characterized in that in the step of determining (110) the width index is determined for each identified row of plants (14) and/or each received image information (10) and/or for several received image information items (10), in particular a defined number of previously received image information items (10). Method (100) according to one of the preceding claims, characterized in that in the step of determining (108) each transverse region (18) is assigned a width value per row of plants (14). Procedure (100) according to Claim 5 , characterized in that in the step of determining (110) the width index, width values with the value zero are deleted or disregarded. Method (100) according to one of the preceding claims, characterized in that the transverse regions (18) extend transversely, in particular orthogonally, to the rows of plants (14) in the image information (10). Procedure (100) according to Claim 7 , characterized in that in the step of identifying (106) the plant rows (14) a plant row center line (16) is generated in each of the plant rows (14), wherein the transverse regions (18) extend transversely, in particular orthogonally, to the generated plant row center lines (16) in the image information (10). Method (100) according to one of the preceding claims, characterized in that the transverse regions (18) have substantially the same length along a defined longitudinal direction (20), in particular along a direction (20) of the plant rows (14) or one of the plant row center lines (16). Method (100) according to one of the preceding claims, characterized in that in the step of determining (108) further length values for identified plants (12) of identified plant rows (14) in the image information (10) are determined by means of the computing unit, wherein a length value represents a number of transverse regions (18) over which the respective plant (12) extends, in particular along a/the direction (20) of the plant rows (14) or one of the plant row center lines (16), wherein in the step of determining (110) further a length index of the plants (12) of at least one of the plant rows (14) is determined using the determined length values by means of the computing unit. Method (100) according to one of the preceding claims, characterized in that the width index is used as an input variable for calculation methods and control methods of an agricultural working machine in order to dynamically adapt them, in particular during a movement of the optical detection unit over the agricultural area. Method (100) according to one of the preceding claims, characterized by a step of classifying (112) the identified plants (12) depending on the determined width index by means of the computing unit, in particular into a first plant class or class of cultivated plants (12) and/or into a second plant class or class of weeds. Procedure (100) according to Claim 12 , characterized in that before the step of classifying izing (112) a pre-classification of the identified plants is carried out independently of the width index, wherein in the classifying step (112) the pre-classified plants retain their pre-classification or are reclassified. Method (100) according to one of the preceding claims, characterized by a step of controlling (114) an agricultural working machine, in particular an agricultural working tool of an agricultural working machine, in particular a spraying device of a field sprayer, depending on the determined width index, in particular the plants (12) classified based thereon. Method (100) according to one of the preceding claims, characterized by a step of storing the width index in a storage unit of an agricultural working machine or an external storage unit, in particular cloud, and/or outputting the width index to a display unit of an agricultural working machine or an external display unit, in particular a smartphone or tablet. Computing unit which is configured to execute and/or control the steps of a method (100) according to one of the preceding claims. Plant identification unit with an optical detection unit for detecting a field section of an agricultural area with plants (12) in order to obtain image information (10) from the detected field section, and a computing unit according to Claim 14 . Agricultural working machine, in particular an agricultural field sprayer, with an agricultural working tool, in particular a spraying device, and a plant identification unit according to Claim 17 , wherein the working tool, in particular the spraying device, can be controlled depending on the determined width index, in particular the plants (12) classified based thereon. Computer program which is designed to carry out the steps of a method (100) according to one of the Claims 1 until 15 to execute and/or control when the computer program is executed on a computer. Machine-readable storage medium on which the computer program is Claim 19 is stored.

Images