EP4387432A1 - Procédé d'évaluation d'image d'un paramètre de fonctionnement d'un outil frontal de récolte agricole - Google Patents
Procédé d'évaluation d'image d'un paramètre de fonctionnement d'un outil frontal de récolte agricoleInfo
- Publication number
- EP4387432A1 EP4387432A1 EP22765095.9A EP22765095A EP4387432A1 EP 4387432 A1 EP4387432 A1 EP 4387432A1 EP 22765095 A EP22765095 A EP 22765095A EP 4387432 A1 EP4387432 A1 EP 4387432A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- evaluation
- image
- value
- image data
- grains
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003306 harvesting Methods 0.000 title claims abstract description 128
- 238000011156 evaluation Methods 0.000 title claims abstract description 126
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000003287 optical effect Effects 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims abstract description 4
- 230000008859 change Effects 0.000 claims description 31
- 238000005457 optimization Methods 0.000 claims description 11
- 239000002689 soil Substances 0.000 claims description 9
- 230000002829 reductive effect Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 5
- 238000011109 contamination Methods 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims description 2
- CDBYLPFSWZWCQE-UHFFFAOYSA-L Sodium Carbonate Chemical compound [Na+].[Na+].[O-]C([O-])=O CDBYLPFSWZWCQE-UHFFFAOYSA-L 0.000 claims 1
- 235000013339 cereals Nutrition 0.000 description 84
- 240000008042 Zea mays Species 0.000 description 14
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 13
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 11
- 235000005822 corn Nutrition 0.000 description 11
- 235000013399 edible fruits Nutrition 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 241000196324 Embryophyta Species 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000036961 partial effect Effects 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 240000002791 Brassica napus Species 0.000 description 2
- 235000004977 Brassica sinapistrum Nutrition 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 2
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 210000005069 ears Anatomy 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 235000009973 maize Nutrition 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 240000005979 Hordeum vulgare Species 0.000 description 1
- 235000007340 Hordeum vulgare Nutrition 0.000 description 1
- 206010061217 Infestation Diseases 0.000 description 1
- 241000209056 Secale Species 0.000 description 1
- 235000007238 Secale cereale Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000009331 sowing Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000036561 sun exposure Effects 0.000 description 1
- 238000003971 tillage Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D41/00—Combines, i.e. harvesters or mowers combined with threshing devices
- A01D41/12—Details of combines
- A01D41/14—Mowing tables
- A01D41/141—Automatic header control
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D41/00—Combines, i.e. harvesters or mowers combined with threshing devices
- A01D41/12—Details of combines
- A01D41/127—Control or measuring arrangements specially adapted for combines
Definitions
- the present invention relates to a method for image evaluation of an operating parameter of an agricultural header by means of software-aided image evaluation of image data records of an optical sensor in evaluation electronics, which is aimed at an area processed by the header.
- the invention also relates to a harvesting machine with a data processing device and to a computer program product.
- a generic method is known from document EP 2 545 761 A1.
- it is proposed to optically record the worked area directly behind the harvesting attachment and to evaluate the data recorded in order to draw conclusions about the condition of the worked area .
- Information on setting up the harvesting machine and on subsequent work steps should also be derived.
- crop losses on the header should also be reduced by matching the individual components of the header to one another and as a function of the soil conditions.
- Assessing the quality of the stubble is stated as a means of reducing crop losses through improved adjustment of the components of the header. It has been found that assessing the quality of the stubble using an image evaluation does not represent a reliable assessment basis for determining the working quality of the agricultural header and optimizing the settings of its components.
- the object is achieved for a generic method in that the image evaluation of the image datasets generated by the optical sensor is aimed at determining, as an operating parameter, a value for the number of lost grains recognizable in the image dataset, at least approximately.
- the object is achieved for a harvesting machine with a data processing device in that it includes a means for carrying out this method.
- the object is achieved for a computer program product in that it comprises instructions which, when the method is executed by a computer, cause the computer to execute this method.
- a certain value for the number of lost grains is better suited to assess the working quality of an agricultural header.
- the number of lost grains determined shows directly how efficiently the harvesting attachment is working, while the stubble quality has no clearly assignable functional connection with the number of lost grains that are at the current settings of the individual components when operating the agricultural harvesting machine.
- the value for the number of lost grains can be very high with a perfect stubble image due to an incorrect setting of the harvesting attachment, while with an unsatisfactory stubble image there can still be only a small number of lost grains because the grain kernels with the selected setting of the components of the header are not lost.
- the stubble pattern is only suitable for evaluating the working quality of the header in extreme processing situations, such as with laid grain, damage to the header or in swampy soil conditions, but not in normal operating situations, which largely determine the day-to-day operation of agricultural machinery.
- the term "lost kernels” does not only mean individual kernels in the narrower sense, but also ears of corn, pods, corn on the cob and the like, in which the lost kernels still cling to the infructescence, but the infructescence then contains the Loss grains adhering to it have been lost, whereby damaged infructescences with loss grains still adhering can also be the subject of the image evaluation.
- the image evaluation of the number of lost grains recognizable in the image data set to determine the working quality of a header device is also advantageous because the current loss level of a harvesting machine assumed by the driver is often used to regulate the speed of the harvesting machine.
- the ability to accurately estimate the loss level of the harvesting attachment results in a completely new assessment basis for setting the speed of the harvesting machine. If the capacity of the harvesting attachment represents the performance limit for the entire system of the harvesting machine with the harvesting attachment, it is now possible to set the forward speed only or at least mainly on the basis of the loss level of the harvesting attachment, while the other loss sensors installed in the harvesting machine are used only or to a lesser extent to optimize the settings of the working components of the harvester.
- the possibility of determining the loss level of the harvesting attachment is now available for the first time via an optical sensor with a software-supported image evaluation connected to it, with which the image data sets generated by the optical sensor are evaluated for the number of lost grains recognizable in the image data set as operating parameters.
- the software-supported image evaluation offers various possibilities and mathematical methods, including artificial intelligence, to extract the information from the respective image data sets that indicate the presence of a loss grain.
- the gray or color space values that indicate a loss grain can be recognized from one or more pixels of an image data set.
- the evaluation electronics can calculate image values for each individual pixel or also for pixel fields in which the image values of a number of pixels are viewed together. By considering pixel fields, the complexity of the calculations can be reduced without a loss of quality in the determination of the number of loss grains necessarily having to occur.
- Colored RGB images can be converted into grayscale images and vice versa in order to increase the recognition accuracy by converting color values into brightness values and vice versa. In colored images, the color channels of the individual pixels can be evaluated differently or further calculated without the color values.
- the geometries and/or areas of connected pixels with a comparable gray or color space value can be compared with a geometry and/or an area value to be expected for a lost grain. From such processing of the image datasets determined by the optical sensor, the number of loss grains recognizable in the image dataset can then be determined at least approximately.
- optical sensor can be aimed at the partial area of the area processed by the front harvesting device that corresponds to a partial working width of the front harvesting device.
- a single optical sensor which only observes a partial area corresponding to a partial working width, enables a statement to be made about the number of lost grains detected on the harvested area.
- a numeric value for the number of detected Loss grains is also understood to be a relative value, for example a percentage that the detected loss grains occupy in the number of evaluated pixels, or a simple indicator value indicating a low/medium/high level of loss in any gradation, or a trend value that only indicates whether the number of lost grains is increasing or decreasing in relation to a previously determined value for the number of lost grains.
- Such a trend value is of particular interest when it is observed whether a desired change in the loss level occurs as a result of a change in the setting of components of the crop header. From the number of lost grains detected in the image data set or the relative values derived from this, the image evaluation determines the value for the number of lost grains recognizable in the image data set, which as a signal then forms the basis for optimizing the harvesting attachment and/or the harvesting machine.
- a camera is designed as an optical sensor on the harvesting attachment in such a way that it still supplies usable sensor values under the difficult operating conditions of agricultural technology.
- a digital or electronic camera comes into consideration as a camera, which calculates images directed at an image sensor into an image data set, as is done, for example, by CCD image sensors as light-sensitive electronic components.
- a camera must be adequately sealed against dirt, it must be able to be cleaned with a high-pressure cleaner, it must be protected against vibrations and impacts, any electrostatic charges must not impair the quality of the image files, no condensation must be left on the lenses sat, and additional headlights may have to be attached to the harvesting attachment in order to improve the quality of the image files in difficult light conditions.
- the area processed by the header, on which the optical sensor is directed can be the area that is directly behind the header in the space between the rear wall of the header and the chassis parts of the harvesting machine, such as the wheels, at the time an image data record is created or caterpillar tracks. This area is still unaffected by tracks left by the harvester. However, the area that is located below the harvesting attachment at the time an image data record is created can also be viewed. This area in particular is well shielded by the harvesting attachment from dust generated by the harvesting machine or other vehicles in the field.
- the area can also be under a conveying unit of the harvesting machine, such as a feederhouse of a combine harvester, or between the axles of the harvesting machine, because these areas are also well covered by the harvesting machine against dust.
- the optical sensor is installed at a suitable point. This can be on the rear wall of the header, above the rear wall of the header, under the header, in front of or behind the cutter bar, on the side of the header or at a mounting position on the harvesting machine, such as in the area inside or outside the driver's cab, under or next to the inclined conveyor, in the area of the axle or above or behind the wheels or the crawler tracks.
- the crop attachments that are equipped with the optical sensor can be all types of crop attachments that pick up crops from the field and deliver them to an associated harvesting machine.
- cereal cutters with screw or belt conveyor systems, corn pickers, corn headers that convey away rotating or in a linear movement, pick-up devices and the like come into consideration here.
- the value for the number of detected lost grains is evaluated in a control loop by evaluation electronics, in which it is evaluated in a first stage whether the value for the detected lost grains is acceptable or not, with an acceptable value of the evaluation electronics output a signal to increase the driving speed of the agricultural machine, and if the value is evaluated as unacceptable, a decision is made in a second stage as to whether the evaluation electronics send a signal to reduce the driving speed of the agricultural machine and/or a signal to change settings of the header components. If no lost grains are detected, this indicates that nothing needs to be changed in the settings of the components of the header harvesting device initially and that the current settings of the components of the header harvesting device for the selected driving speed of the agricultural machinery seem optimal. Based on this knowledge, it would be possible to increase the driving speed of the agricultural machine in order to check whether the settings of the components of the header can also be maintained at a higher driving speed or whether an increased number of lost grains can be determined at the higher driving speed.
- a contamination detection of the sensor is integrated into the image evaluation. If the values of the image data sets for one or more pixels do not change when the machine drives up, the corresponding pixels can be evaluated as "dirty" because without dirt covering the lens, the individual pixel values would have to change continuously when the harvesting machine drives up. Since these pixels can no longer contribute to the detection of lost grains, the detection accuracy of the image evaluation deteriorates the more pixels are dirty. Up to a certain degree of contamination, the determined value of the lost grain detection can be corrected and/or the pixels identified as "dirty" are no longer taken into account in the image evaluation. Above a certain degree of contamination, however, the image evaluation can no longer provide reliable data on the detected grain losses. In this case, the image evaluation should be aborted and an error signal sent to a control device, which indicates that the camera sensor is too dirty.
- the image evaluation takes place according to parameters that are differentiated specifically for the harvested crop.
- the harvested crop can be differentiated between those fruits in which the header harvests the entire Plants absorbs and forwards unprocessed to the harvester, so that the processes of separating, sifting and cleaning are carried out there, and those fruits in which the harvesting attachment already takes over part of the work of one or more of these processes.
- the first fruits are wheat, rye, barley, soybeans, rapeseed and grain maize for the second fruits.
- the maize plants While with the first crops only the mowed stubble remains on the field, between which the lost grains can be clearly identified, the maize plants are separated between the cobs and the remaining plant parts in the grain maize harvest in the harvesting attachment. Only the cobs are transported to the harvester for further processing, the other plant parts are thrown from the harvesting attachment onto the field and form a mat of material that covers the entire surface of the ground, between which it is more difficult to identify corn cobs or individual corn kernels. Lost corncobs should also be included in the loss detection with a loss number, as they contain a larger number of corn kernels. In order to obtain usable values for the number of lost grains and/or ears and/or cobs recognizable in the image data record, differentiated parameters specific to the harvested crop must be programmed in the image evaluation software, according to which the image evaluation is carried out.
- the image evaluation software can have differentiated evaluation logarithms that are specific to the harvested crop and which compare the material mat to a normal one field soil take into account the different image of the material mat, such as the different color and structure of the leaf and stem parts lying on the field.
- the image evaluation for the former fruits can also be more precisely differentiated, because, for example, different color values, different geometric shapes and different degrees of ripeness have to be taken into account for the detection of black rapeseed grains and yellow wheat grains in order to calculate the number of lost grains recognizable in the image data set with a to recognize as accurately as possible with sufficient accuracy for evaluation purposes.
- the type of fruit to be harvested can be entered manually into the evaluation electronics before the start of the harvest, or the electronic evaluation system runs through an operating loop of the automated fruit type recognition, in which it first recognizes the respective fruit type by means of the image evaluation, and then the programming required for the respective fruit type-specific image evaluation activated.
- several consecutive image data sets of the optical sensor are calculated to form a new image data set for averaging and limiting values of the pixel values, for which a value for the number of lost grains is determined. Since the loss grains in the image data set of a single camera image from the optical sensor statistically do not have exactly the same texture and color as in another camera image and local gray value or color fluctuations in particular can occur, there is a risk that such fluctuations will lead to evaluation errors.
- the fluctuations in the averaging balance out and take in the new image data record a gray or color value averaged from the individual camera images that have been calculated with one another.
- the pixels representing a lost grain generally have a lighter or darker gray or color level value than the rest of the material represented in the camera image, and they may also have a lower standard deviation or variance, respectively. Therefore, instead of the arithmetic mean, the standard deviation or the lower variance can also be determined.
- Other methods can also be used as a metric for forming an average value for combining multiple images, such as forming a geometric or harmonic mean, forming average values in different color spaces, determining weighted average values, determining spatial or temporal gradients of brightness and/or color, the use of high-pass, low-pass or other filters, without this list of examples being limited to the methods mentioned.
- the evaluation electronics calculate the values determined with the image evaluation for the number of lost grains recognizable in the image data set over a time interval in a trend line, register any changes made in the settings of one or more operating parameters of the harvesting attachment and assign them chronologically to the trend line, if there is a coincidence in time between the beginning of a change in the trend line and the change in the settings of one or more operating parameters, makes an assessment as to whether the trend line has increased or decreased since the change in the settings of one or more operating parameters, and generates a from the result of the assessment Signal indicating whether the change made in the settings of one or more operating parameters increases, leaves unchanged or decreases the observed grain losses.
- the evaluation of changes in the settings of one or more operating parameters of the header is an aid to adjust the components of the header so that the loss level is kept as low as possible.
- a grain header as a header
- corn pickers several different operating parameters can also be adjusted.
- a value determined by the image evaluation for the number of lost grains recognizable in the image data set is used as input in an automated software-controlled control loop, in which at least a first operating parameter of at least one adjustable first component of the harvesting attachment is changed by control electronics, in order to use a new value with the evaluation electronics after the change has been made to evaluate whether the loss level of the harvesting attachment has decreased as a result of the adjustment of the first operating parameter and is evaluated as satisfactory, the first operating parameter of the first component is changed further until a Adjusts loss level of the header until it is rated as satisfactory by the control electronics using a new value, then at least a second operating parameter of the adjustable first or a second component of the harvesting attachment is changed by the control electronics, in order to evaluate after the change has been made by means of a new value with the evaluation electronics whether the loss level of the harvesting attachment has been reduced by the adjustment of the second operating parameter and is evaluated as satisfactory, and also the second Operating parameters of first or second component is changed further until a loss level of the harvesting
- the reel of a grain cutter can serve as an example of an adjustable first component.
- adjustable operating parameters of the reel for example, its speed, its height, its horizontal distance to the cutter bar and the angular position of the reel tines can be specified.
- the value determined by the evaluation electronics can now be used by the evaluation electronics to change the setting of the individual operating parameters of the reel in such a way that the lowest possible loss level of the harvesting attachment is set. It is proposed to start with a first operating parameter, such as the reel height, adjust it in an upward or downward direction, and then use a new value to check whether the loss level has improved. If no improvement or a deterioration was found, an adjustment in the opposite direction can be attempted in order to first identify the correct optimization direction of the adjustment.
- the adjustment can be continued in the same direction.
- the adjustment can be made in small Steps are continued in the direction recognized as correct until no further optimization of the operating parameter in this direction appears possible, which in turn can be determined on the basis of the values generated by the evaluation electronics.
- a second operating parameter of the reel can then be optimized, such as the horizontal position of the reel in relation to the cutter bar.
- the adjustment strategy here is the same as that described above for the reel height. First the direction of optimization is determined and then adjusted until an optimal setting of the changed parameter is identified. In this way, all variable operating parameters of a first component can be successively adjusted towards an optimal loss level.
- a second, then the third and so on component can be optimized accordingly in their adjustable operating parameter settings, or after the first operating parameter of the first component the first operating parameter of the second component is optimized, then the second operating parameter of the second component and then the first operating parameter the third component, i.e. in a sequence with which a loss-optimized setting of the components of the harvesting attachment can be achieved as quickly as possible.
- Functional dependencies must be taken into account when determining the order.
- the value for the number of loss grains that can be identified in the image data set, determined by the image evaluation can be used as input in an automated, software-controlled control loop.
- the value determined by the image evaluation for the number of lost grains recognizable in the image data set form a good basis for assessment in order to automatically set the adjustable operating parameters of the harvesting attachment in such a way that the lowest possible Set loss level by the header.
- the adjustment can be made in particular in a control loop that is programmed in the associated software.
- the evaluation electronics can be the electronics that evaluate the image data sets of the optical sensor, but they can also be other evaluation electronics that are arranged on the harvesting attachment or the harvesting machine.
- the evaluation electronics consists of hardware and corresponding software.
- the control electronics can be physical act the same hardware computer chips on which the software of the evaluation electronics runs, but it can also be separate electronics.
- the control electronics is the controller that controls the actuators that change the operating parameters of the components of the header.
- the control electronics receive control signals from the evaluation electronics, which transmit them as control commands to the actuators of the respective components.
- the sequence of the optimization of the individual operating parameters is variable depending on the respective crop to be harvested, detected soil conditions, stored grain occurring, yield map data from previous harvests, growth height of the crop stand, degree of moisture and/or degree of ripeness of the crop.
- the soil conditions to change in a field or for laid grain to appear in certain areas.
- the harvested crop can differ in its growth height, degree of humidity and/or degree of humidity depending on the water supply, fertilization, weed and disease infestation, sun exposure, slope and other influencing factors.
- it can also be advantageous to adapt the sequence of the optimization of operating parameters to the respective prevailing harvesting conditions. It is just as advantageous to use data from yield maps that have been created for previous harvests in order to derive an optimized sequence of the operating parameters to be adjusted.
- the value determined by the image evaluation for the number of lost grains recognizable in the image data set, the trend line and/or an indicator value derived therefrom are transmitted by the evaluation electronics to a display unit and displayed by the latter.
- the display unit can be attached to the harvesting attachment, but it can also be a display unit arranged remotely from the harvesting attachment.
- the display can be an operating screen of the harvesting machine, but it can also be a display that is present on the harvesting machine for separate operation of the harvesting attachment. However, the display can also be made on a control station that is operated remotely from the harvesting machine.
- the value, the trend line and/or an indicator value derived therefrom can be observed by an operator of the harvesting machine via the display unit and made the basis of control commands for the operation of the harvesting machine.
- the values displayed, the trend line and/or indicator values derived therefrom can be stored via the display unit and used for evaluation or documentation purposes.
- the evaluation electronics emit an alarm signal if a preset or optionally adjustable threshold value for the value determined by the image evaluation for the number of loss grains recognizable in the image data set, the trend line and/or an indicator value derived therefrom is exceeded.
- the output of an alarm signal simplifies operation because the driver of the harvesting machine does not have to develop the value determined by the image evaluation for the number of lost grains recognizable in the image data set no longer has to be constantly observed, but it is only automatically alarmed when reaching the threshold value makes a control intervention in the current settings of the harvesting attachment and/or the harvesting machine appear necessary.
- the evaluation electronics store the determined values for the number of loss grains recognizable in the image data record, the trend line and/or indicator values derived therefrom, georeferenced in a loss map. So that the evaluation electronics can store the corresponding data in a georeferenced manner, the evaluation electronics preferably have a module with which the data of a satellite navigation system can be received.
- a loss map is created, which enables a later evaluation of the harvesting work and a more precise planning of the subsequent tillage, sowing and care of the following crops.
- the loss map can be linked to other georeferenced data in order to be able to make optimized decisions in the management of the corresponding arable land in the context of this other georeferenced data.
- the evaluation electronics have interfaces to external systems.
- the interfaces can reduce the complexity of the software and/or hardware of the evaluation electronics by relocating subfunctions of the image evaluation to other electronics via the interface.
- the sub-functions can be data acquisition, data Data storage and the execution of software programs that cover sub-functions of the evaluation electronics.
- the other electronics can be connected to the evaluation electronics in particular via mobile radio and the Internet.
- the other electronics can be, for example, expert systems that run on a central server.
- the interfaces can also serve the purpose of networking the harvesting attachment with the harvesting machine. The function of the harvesting attachment can then be better matched to the functions of the harvesting machine, in particular operational optimizations are possible as a result.
- the interface can in particular be an interface for controlling the forward speed of the harvesting machine.
- the evaluation electronics can further process the determined values for the number of lost grains recognizable in the image data set, the trend line and/or indicator values derived therefrom to form a signal with which the forward speed of the harvesting machine is reduced or increased. So that this signal can be transmitted to the control electronics of the harvesting machine, a corresponding interface is required in the evaluation electronics.
- the interface can in particular also be an interface for the automated adjustment of the threshing, separating and/or cleaning elements of the harvesting machine.
- the evaluation electronics can further process the determined values for the number of lost grains recognizable in the image data record, the trend line and/or indicator values derived therefrom into a signal with which the threshing, Separating and / or cleaning organs of the harvester can be adjusted. So that this signal can be transmitted to the control electronics of the harvesting machine, a corresponding interface is required in the evaluation electronics.
- the interface can in particular also be an interface to the cloud.
- the cloud is a computer network that provides shared computer resources as a service, e.g. in the form of servers, data storage or applications, promptly and with little effort if required - mostly via the Internet and device-independent. User access to application programs or to function inputs can be provided via the cloud. Programming or runtime environments with flexible, dynamically adaptable computing and data capacities are also possible.
- the surface onto which the optical sensor is directed is brightened by a light source attached to the harvesting attachment when an image data set is created.
- the illuminant can generate normal white light, but it is also possible that the illuminant only generates light waves from a specific range of wavelengths, with which the loss grains can be better recognized by the image evaluation. UV, black light or infrared light or other light colors from the spectrum of visible wavelengths can also be used here, or the respective light color and/or wavelengths are selected depending on the fruit and light conditions.
- image data sets of loss grains can be accessed in the image evaluation of the evaluation electronics, which are associated with the optical Sensor transmitted image data sets are compared.
- the recognition quality of loss grains in the image evaluation is improved on the basis of the accessible image data sets.
- the accessible image datasets can also be stored remotely in the cloud.
- the algorithms can continuously improve their recognition quality and reliability by integrating the information obtained from the various image data sets for identifying loss grains into an ongoing image evaluation and storing them for later evaluation of new image data sets.
- different mathematical analysis algorithms but also different color filters, contrasts, geometric shapes and the like can be used.
- algorithms for self-learning systems are integrated in the software of the evaluation electronics.
- the self-learning systems use algorithms that enable machine learning. These algorithms can be programmed for supervised learning, in which data sets are tagged in such a way that patterns are recognized and then used to tag new data sets. However, the algorithms can also be programmed to process data sets that are not marked, they sort the data sets according to similarities or differences and derive recognition patterns from them, which can be used to improve the recognition quality and recognition reliability. Finally, the algorithms can also be programmed for reinforcement learning in which data sets are not labeled. which, but after one or more actions, the AI system is given feedback.
- the algorithms for self-learning systems work particularly well when the evaluation electronics communicate with external computers and exchange data in a neural network.
- Fig. 2 a schematic data flow diagram
- Fig. 3 a diagram of a possible course of a trend line
- 4 a schematic program flow chart
- FIG. 1 shows a side view of a harvesting machine 2 with a front-mounted harvesting attachment 4 .
- Behind the rear wall of the soil attachment 4 is an optical sensor 6 which is directed towards the surface 12 of the soil.
- the optical sensor 6 is connected to evaluation electronics 8 which have a device 10 for image evaluation.
- the images created by the optical sensor 6, in particular in the form of image data records 100, can be examined by the image evaluation 10 for the number of loss grains 22 recognizable in the image data record 100.
- the harvesting attachment 4 shown in FIG. 1 is a grain cutter.
- the grain cutter has a cutter bar 14 , a reel 16 and an auger 18 .
- the crop 20 located on the field is cut with the grain cutter, drawn into the grain cutter and delivered to the harvesting machine 2 .
- lost grains 22 fall onto the farmland, so that they can no longer be harvested by the harvesting machine 2 .
- the number of grains 22 that are lost can depend on the settings of the operating parameters of components of the harvesting attachment 4 and on the forward speed of the harvesting machine 2 .
- the optical sensor 6 examines the surface 12 , the lost grains 22 lying on the farmland are visible and can be recognized by the image evaluation 10 .
- a display unit 24 with a display 24a, which is connected to the evaluation electronics 8, is located in the driver's cab of the harvesting machine 2.
- the connection can be wired or wireless.
- the evaluation electronics 8 has a corresponding interface 28a.
- Another interface 28b is connected to the harvesting machine electronics 30 .
- Information and control commands about the driving speed 36, the setting of the threshing, separating and cleaning devices and the like can be exchanged via this interface 28b.
- the evaluation electronics 8 receive position data from a satellite navigation system 26 via the interface 28c.
- the evaluation electronics 8 can communicate with the cloud 34 via the interface 28d.
- a light source 32 is attached to the rear wall of the harvesting attachment 4 .
- the illuminant 32 illuminates the surface 12 so that lost grains 22 lying there on the soil can be better recognized by the image evaluation 10 .
- FIG. 2 shows a schematic data flow diagram.
- the optical sensor 6 When the harvesting machine 2 travels over a field, the optical sensor 6 generates a number of image data sets 100, an example of which is shown as an image in FIG.
- the stubble 104 of the cut crop 20 can be seen in the picture.
- the respective image data record 100 is transmitted to the image evaluation 10 located in the evaluation electronics 8 .
- the image data set 100 is digitized in this case.
- the image evaluation 10 analyzes the number of loss grains 22 in the image data record 100 that it recognizes.
- a value 102 for the number of lost grains 22 recognizable in the image data set 100 is generated from the number of lost grains 22 identified.
- a possible course of a trend line 152 over a time interval 150 is shown in FIG.
- the trend line 152 of the value 102 for the number of loss grains 22 recognizable in the image data record 100 runs at a value >4, while the dividing line 152 falls in a second section and settles at a value of approximately 2.6.
- the drop in the trend line 152 is explained by a change 154 made to an operating parameter of a component of the header device 4.
- the value 102 has therefore decreased as a result of the change 154 made.
- the evaluation electronics 8 can now decide whether the change 154 made previously to an operating parameter of a component is to be continued in the same direction, or whether the loss level achieved is satisfactory in order to then change another operating parameter of the same component or another component. If the trend line 152 had risen after the change 154 made, the evaluation electronics 8 could take back the change 154 made and adjust the corresponding operating parameter in the opposite direction or adjust another operating parameter of the same component or another component.
- FIG. 4 shows a schematic program flow chart that can run when deciding whether the driving speed 36 of the harvesting machine 2 should be reduced or increased. Based on the determined value 102, in a first step it is to be evaluated whether the determined loss level is acceptable or not. If the loss level is acceptable, the ground speed 36 can be increased. Is If the loss level determined is not acceptable, a further step must be to select whether the driving speed 36 of the harvesting machine 2 should be reduced, or whether an operating parameter of a component of the harvesting attachment 4 should be adjusted with a change 154 .
- the exemplary program flow chart can be stored in software for evaluation electronics 8 .
- the invention is not limited to the above exemplary embodiments. It is not difficult for a person skilled in the art to modify the exemplary embodiments in a manner that he deems suitable in order to adapt them to a specific application.
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
L' invention concerne un procédé pour déterminer des paramètres de fonctionnement d'un outil frontal de récolte agricole (4) au moyen d'une évaluation d'image (10), assistée par logiciel, d'ensembles de données d'image (100) provenant d'un capteur optique (6) dans un système électronique d'évaluation (8), lequel capteur est dirigé vers une surface (12) traitée par l'outil frontal de récolte (4). L'invention concerne également une moissonneuse dotée d'un dispositif de traitement de données ainsi qu'un produit-programme informatique. L'objectif de l'invention est de développer un procédé au cours duquel un paramètre de fonctionnement est acquis et évalué, qui soit mieux adapté pour évaluer la qualité de travail de l'outil frontal de récolte agricole et optimiser les réglages de ses composants. À cet effet, l'évaluation d'image (10) des ensembles de données d'image (100) générés par le capteur optique (6) vise à déterminer au moins approximativement, en tant que paramètre de fonctionnement, une valeur (102) pour le nombre de grains perdus (22) identifiables dans l'ensemble de données d'image (100).
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021121366.5A DE102021121366A1 (de) | 2021-08-17 | 2021-08-17 | Verfahren zur Bildauswertung eines Betriebsparameters eines landwirtschaftlichen Erntevorsatzgerätes |
PCT/EP2022/072788 WO2023021005A1 (fr) | 2021-08-17 | 2022-08-15 | Procédé d'évaluation d'image d'un paramètre de fonctionnement d'un outil frontal de récolte agricole |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4387432A1 true EP4387432A1 (fr) | 2024-06-26 |
Family
ID=83193329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP22765095.9A Pending EP4387432A1 (fr) | 2021-08-17 | 2022-08-15 | Procédé d'évaluation d'image d'un paramètre de fonctionnement d'un outil frontal de récolte agricole |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4387432A1 (fr) |
CA (1) | CA3228885A1 (fr) |
DE (1) | DE102021121366A1 (fr) |
WO (1) | WO2023021005A1 (fr) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102011017621A1 (de) * | 2011-04-27 | 2012-10-31 | Deere & Company | Anordnung und Verfahren zur Erfassung der Menge von Pflanzen auf einem Feld |
DE102011051784A1 (de) | 2011-07-12 | 2013-01-17 | Claas Selbstfahrende Erntemaschinen Gmbh | Verfahren zum Betreiben einer selbstfahrenden Erntemaschine |
US10757859B2 (en) * | 2017-07-20 | 2020-09-01 | Deere & Company | System for optimizing platform settings based on crop state classification |
DE102017129193A1 (de) * | 2017-12-07 | 2019-06-13 | Claas Selbstfahrende Erntemaschinen Gmbh | Verfahren zum Betreiben einer selbstfahrenden Erntemaschine |
-
2021
- 2021-08-17 DE DE102021121366.5A patent/DE102021121366A1/de active Pending
-
2022
- 2022-08-15 EP EP22765095.9A patent/EP4387432A1/fr active Pending
- 2022-08-15 WO PCT/EP2022/072788 patent/WO2023021005A1/fr active Application Filing
- 2022-08-15 CA CA3228885A patent/CA3228885A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
WO2023021005A1 (fr) | 2023-02-23 |
CA3228885A1 (en) | 2023-02-23 |
DE102021121366A1 (de) | 2023-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3358932B2 (fr) | Procede de fonctionnement d'une moissonneuse a l'aide d'un modele de croissance de plante | |
US11140807B2 (en) | System for optimizing agricultural machine settings | |
DE102020118160A1 (de) | Anpassung der Feldoperation basierend auf Erntegutrückständen | |
EP3085221B1 (fr) | Système de récolte comprenant une moissonneuse automobile | |
EP2042019B1 (fr) | Véhicule de travail agricole | |
EP2057882B2 (fr) | Procédé de contrôle de la qualité de récoltes | |
DE69814847T2 (de) | Agrar-erntemaschine mit roboter-kontrolle | |
EP3494771B1 (fr) | Dispositif de hauteur de coupe automatique | |
EP3075223A1 (fr) | Moissonneuse-batteuse | |
DE102015122269A1 (de) | Verfahren für den Betrieb eines Mähdreschers | |
DE112014000906T5 (de) | Pflanzenweise Ernteguterfassungsauflösung | |
DE112014000918T5 (de) | Ernteguterfassungsanzeige | |
DE102015213037A1 (de) | Erfassen von Biomasse | |
DE102011082908A1 (de) | Verfahren und Anordnung zur optischen Beurteilung von Erntegut in einer Erntemaschine | |
EP2918159A1 (fr) | Agencement et procédé de reconnaissance et documentation de qualité de paille | |
DE102021200028A1 (de) | Landwirtschaftliche erntemaschine mit vorauflauf-unkrauterkennungs- und -eindämmungssystem | |
DE102011051784A1 (de) | Verfahren zum Betreiben einer selbstfahrenden Erntemaschine | |
DE102017122645A1 (de) | Landwirtschaftliche Arbeitsmaschine | |
DE102019214486B4 (de) | Erntevorsatzüberwachung anhand von Erntemengenabweichungen | |
EP1900272B1 (fr) | Machine de travail agricole | |
EP1321024B1 (fr) | Procédé et dispositif d'optimisation du fonctionnement d'un véhicule agricole | |
EP4387432A1 (fr) | Procédé d'évaluation d'image d'un paramètre de fonctionnement d'un outil frontal de récolte agricole | |
EP3242257A1 (fr) | Procédé et agencement d'optimisation de paramètres de travail d'une machine de récolte | |
DE102020203220A1 (de) | Vorwärts gerichtete Wahrnehmungsschnittstelle und -Steuerung | |
DE102019209526A1 (de) | Überwachen einer Anbaufläche |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20240227 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |