METHOD FOR CONTROLLING THE OPERATION OF A MACHINE FOR HARVESTING ROOT CROP

Abstract

A method is provided for controlling the operation of a machine for harvesting root crop. At least one optical image-capturing unit captures at least one test image of harvested material comprising root crop which is moved along relative to a machine frame by means of at least one conveyor element. A conveying speed of the conveyor element is set on the basis of a test data set which is generated using the test image or formed by means of the latter. An evaluation device generates, on the basis of the test data set, a conveying speed signal, independent of a speed of the harvested material, for setting the conveying speed.

Claims

1. A method for controlling the operation of a machine for harvesting root crop, the method comprising the steps of: Capturing, via at least one optical image-capturing unit, at least one test image of harvested material comprising root crop which is moved along relative to a machine frame by at least one conveyor element; generating a test data set formed using the test image or by the test image; generating, via an evaluation device, a conveying speed signal based on the test data set, independent of a speed of the harvested material, for setting the conveying speed; and setting a conveying speed of the conveyor element based on the conveying speed signal.

2. The method as claimed in claim 1, wherein the conveying speed signal is also determined independently of the speed of the conveyor element.

3. The method as claimed in claim 1, wherein the evaluation device compares the test data set with an initial data set which is generated on the basis of an initial image or formed from the initial image.

4. The method as claimed in claim 3, wherein the test data set from a first execution of the method serves as an initial data set for a further execution of the method.

5. The method as claimed in claim 3, wherein the evaluation device determines the conveying speed signal on the basis of an evaluation of the optical flow of the harvested material which is obtained from the test data set and the initial data set.

6. The method as claimed in claim 3, wherein the evaluation device calculates at least one movement characteristic data set which characterizes a movement of at least one object which is at least partially represented by the test image, wherein the conveying speed signal is generated on the basis of the movement characteristic data set.

7. The method as claimed in claim 6, wherein the evaluation device generates in each case a movement characteristic data set for different objects which are represented with the test image or different, first partial image areas.

8. The method as claimed in claim 7, wherein the evaluation device calculates, in a first calculation step for a multiplicity of partial image areas comprising at least a first number of pixels, in each case a movement characteristic data set, and calculates in a later calculation step, taking into account the movement characteristic data sets calculated in the first calculation step, in each case a further movement characteristic data set for a relatively high number of different partial image areas, which comprise a relatively low number of pixels.

9. The method as claimed in claim 6, wherein the evaluation device calculates a capacity utilization characteristic value (LS) on the basis of at least one movement characteristic value, characterizing a direction of movement, of the at least one movement characteristic data set.

10. The method as claimed in claim 9, wherein the evaluation device statistically evaluates a plurality of movement characteristic values, which are included in different movement characteristic data sets, in order to calculate the capacity utilization characteristic value (LS).

11. The method as claimed in claim 9, wherein the capacity utilization characteristic value (LS) is determined by a deviation, calculated by the evaluation device, of the first portion (A1) from a threshold value (R).

12. The method as claimed in claim 9, wherein the conveying speed signal is calculated using a multiplicity of capacity utilization characteristic values (LS), or at least one previously calculated capacity utilization characteristic value (LS) is input into the calculation of the capacity utilization characteristic value (LS).

13. The method as claimed in claim 1, wherein the evaluation device calculates at least one first portion (A1), formed by at least one image area, of the test image, wherein the at least one image area represents at least partially a defined component of the harvested material or of the machine.

14. The method as claimed in claim 13, wherein the at least one image area, which forms the first portion (A1), is identified, on the basis of a test data subset which is generated using the image area, as the defined component of the harvested material or the machine.

15. The method as claimed in claim 13, wherein the test data subset is classified by an statistical classification method, and an image area is classified as being associated with the first portion (A1).

16. The method as claimed in claim 13, wherein the at least one test value of the test data subset is compared with at least one reference value, and an image area is classified as being associated with the first portion (A1).

17. The method as claimed in claim 15, wherein when exemplary image areas, which can be classified as being associated with the first portion (A1), of a reference image are input, the evaluation device automatically further develops a model on which the classification method is based and/or automatically calculates or changes the at least one reference value range.

18. The method as claimed in claim 13, wherein different image areas are weighted differently during the calculation of the first portion (A1).

19. The method as claimed in claim 13, wherein the entire test image or a coherent test image part is divided into partial image areas.

20. The method as claimed in claim 13, wherein the test image comprises a plurality of test image parts for which the evaluation device respectively calculates a first portion (A1).

21. The method as claimed in claim 13, wherein the image areas which form the first portion (A1) show root crop or parts thereof and image areas which form a second portion show extraneous materials or parts thereof.

22. The method as claimed in claim 1, wherein at least one sensor transmits sensor data to the evaluation device, which data is input into the calculation of the conveying speed signal.

23. The method as claimed in claim 1, wherein the evaluation device triggers either an increase or a reduction in the conveying speed of at least individual conveyor elements by different conveying speed signals.

24. The method as claimed in claim 23, wherein a conveying speed gradient which is triggered by the conveying speed signal and/or the difference between the conveying speeds upstream and downstream of an acceleration or deceleration is dependent on the capacity utilization characteristic value (LS).

25. The method as claimed in claim 23, wherein after the triggering of a change in the conveying speed no further change in the conveying speed is triggered for a defined time period or a defined conveying distance.

26. The method as claimed in claim 1, wherein the conveying speed signal is transmitted in a wired fashion or in a wireless fashion, to a conveying speed control unit.

27. The method as claimed in claim 1, wherein the evaluation device evaluates the test data sets locally on the machine or on a directly connected tractor vehicle.

28. A machine for harvesting root crop, the machine comprising: at least one machine frame, at least one conveyor element, at least one optical image-capturing unit and one evaluation device; wherein the machine is operable to perform the method recited in claim 1.

29. The machine as claimed in claim 28, wherein the evaluation device comprises a graphic processor unit.

30. The machine as claimed in claim 28, further including at least one sensor which is coupled to the evaluation device.

31. The machine as claimed in claim 28, further including a plurality of image-capturing units which during operation each capture at least one test image of the same conveyor element or of different conveyor elements.

32. The machine as claimed in claim 28, wherein the conveyor element is embodied as a screening belt or hedgehog web, or a screening star (10P, 10Q, 10S) or conveyor roller.

33. The machine as claimed in claim 28, wherein the image-capturing unit is arranged in such a way that the test image shows at least two alternative conveying paths for different components of harvested material.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Reference is now made more particularly to the drawings, which illustrate the best presently known mode of carrying out the invention and wherein similar reference characters indicate the same parts throughout the views.

[0081] FIG. 1 shows a program sequence diagram of a method according to the invention.

[0082] FIG. 2 shows a view of a detail relating to the determination of components of harvested material at a monitored conveying line area.

[0083] FIG. 3 shows a program sequence diagram of the calculation of the conveying speed signal.

[0084] FIG. 4 shows a program sequence diagram of the evaluation of the conveying speed signal.

[0085] FIG. 5 shows a view of a test image and its partial evaluation.

[0086] FIG. 6 shows the test image according to FIG. 5 and its further possible partial evaluation.

[0087] FIG. 7 shows a subject matter according to the invention.

[0088] FIGS. 8 and 9 show the subject matter according to FIG. 7 in different side views.

[0089] FIG. 10 shows a partial view of the subject matter according to FIG. 7 with a conveyor element.

[0090] FIG. 11 shows a view of a detail of an area of the device according to FIG. 7 which is partially illustrated in FIG. 10.

[0091] FIG. 12 shows the subject matter according to FIG. 11 from a different perspective.

[0092] FIG. 13 shows an illustration of the test image of the image-capturing unit according to FIG. 11.

[0093] FIG. 14 shows a separating device of the machine according to FIG. 7 with an image-capturing unit.

[0094] FIG. 15 shows a schematic test image captured from the perspective of the image-capturing unit shown in FIG. 14.

[0095] FIG. 16 shows a further separating device of the machine according to FIG. 7 with an image-capturing unit.

[0096] FIG. 17 shows a schematically illustrated test image captured from the perspective of the image-capturing unit shown in FIG. 16.

[0097] FIG. 18 shows a further view of a detail of a machine according to FIG. 7 with a further image-capturing unit.

[0098] FIG. 19 shows a schematic illustration of a test image considered from the perspective of the image-capturing unit according to FIG. 18.

[0099] FIG. 20 shows a view of a detail of a further device according to the invention.

DETAILED DESCRIPTION OF THE DRAWINGS

[0100] Identically or similarly acting parts are, where expedient, provided with identical reference symbols. Individual technical features of the exemplary embodiments described below can also be combined with the features of the exemplary embodiments described above to form developments according to the invention, but always at least in combination with the features in one of the independent claims. The subject matters specified in the list of the figures are in some cases only illustrated partially in individual figures.

[0101] The method according to the invention serves to control the operation of a machine 2 for harvesting root crop 4 (cf. FIGS. 6 to 8). In the method, at least one optical image-capturing unit 6 captures at least one test image 8 which shows harvested material comprising root crop 4 which is moved along relative to a machine frame 12 of the machine 2 by means of at least one conveyor element which is designated initially generally by 10.

[0102] The test image 8 is transmitted to an evaluation device which generates, on the basis of a test data set which is generated on the basis of the test image 8 or formed thereby, a separating device setting signal for setting at least one operating parameter of a separating device of the machine 2. The representations which are illustrated as test images or initial images merely show schematically the parts which are relevant for the invention without any borders or limitations. Images, in particular digital images, which are captured by a camera, comprise, under certain circumstances, further information which is not illustrated in the representations. This information can, for example, already be masked or filtered at the camera or when a test data set is produced or processed.

[0103] In one exemplary embodiment according to the invention, a crop flow 1.1 of a separating device is captured by means of a first image-capturing unit 6 (block 1.2, FIG. 1). Moreover, the crop flow of two further optical image-capturing units is additionally monitored (blocks 1.3 and 1.4), for example downstream of the outlet of the separating device and in the region of a discharge belt for extraneous materials 5, which are separated off by means of the separating device. Capacity utilization characteristic values LS_1 to LS_3 are determined (blocks 1.5, 1.6, 1.7) for the respective measuring points or areas captured by the image-capturing units 6 by means of the method according to the invention. These values are combined arithmetically in block 1.8, which gives rise to a conveying speed signal for at least one conveyor element 10 of the separating device. In this way, the conveying speed of the conveyor element is set (block 1.9), which optimizes the crop flow 1.1 in the separating device.

[0104] The determination of the conveying speed signal is illustrated in FIG. 2 with a higher level of detail. Accordingly, a test image 8 comprising harvested material on a conveyor element 10 (block 3, corresponds to block 1.1) is firstly captured by the image-capturing unit. After the capturing of the test image 8, according to a first method sequence according to the invention a relevant image section or part of the test image 8 is extracted by means of corresponding filtering or masking. For this purpose, a mask or region of interest (ROI) is predefined on the basis of the position of the image-capturing unit and is used to differentiate sections of the test image 8 which are to be taken into account and ones which are not to be taken into account (block 13.1). A movement characteristic value for a multiplicity of image areas, in particular for each pixel of the image section, is calculated on the basis of the relevant image section of the test image 8 and of the associated test data set (block 13.2). The movement characteristic value comprises in particular a direction of movement. Subsequently, the multiplicity of movement characteristic values is evaluated statistically (block 13.3). For this purpose, the movement characteristic values are each compared with assigned reference characteristic values which are provided from a preferably machine-specific database which can, in particular, be updated (block 13.4), and a difference between said values is calculated, or the movement characteristic values are each compared with a uniform reference characteristic value and a deviation therefrom is calculated. The movement characteristic values or the calculated deviations are evaluated statistically by the evaluation device, in particular a standard deviation of the movement characteristic values from the reference characteristic values is calculated.

[0105] A low-pass filter for smoothing the acquired values subsequently passes via the continuously evaluated statistic (block 13.5). A predefined and in particular predefinable filter time constant is used for this (block 13.6), which specifies the degree of smoothing.

[0106] A capacity utilization characteristic value, generally denoted by LS, of the conveying line area which is represented in the test image is acquired on the basis of the filtered or smoothed statistic of the deviations described above (block 13.7). Said value represents the movement situation of the harvested material or of the crop flow in the region of the separating device, in particular on the conveyor element or in the transition region between two conveyor elements.

[0107] Referring to the second supplementary or alternative path, the relevant test image parts are also firstly extracted (block 2.1). For this purpose, a mask or region of interest (ROI) can be predefined on the basis of the position of the image-capturing unit 6 (block 2.2) and is used to differentiate distances in the test image 8 which are to be taken into account and ones which are not to be taken into account. The calculation of portions of the individual image areas showing components of the harvested material is now performed on the basis of the relevant image section of the test image 8 and of the test data set which is provided for processing (block 2.3). In particular the color information can be evaluated for this purpose. These values can be obtained from a reference table or else specified by an operator (block 2.4).

[0108] The deviations of the calculated portions from the threshold value are calculated (block 2.6) on the basis of a threshold value definition (block 2.5). The threshold value is, for example, an ideal value for the respectively considered portion (e.g. root crop, amount of extraneous material 1, amount of extraneous material 2). Subsequently, low-pass filtering is carried out for the purpose of smoothing the acquired deviations (block 2.7). In this context, a filter time constant which is defined according to block 2.8 is used. Subsequently, a further capacity utilization characteristic value LS or the capacity utilization characteristic value LS is calculated on the basis of the smoothed values of the deviations for the individual positions along the conveying line and the respective portions (block 2.9).

[0109] Subsequently, the conveying speed signal will be generated on the basis of the capacity utilization characteristic value or values LS, for example by means of a three-point controller, described below (block 2.10).

[0110] FIG. 3 shows a program sequence diagram of the calculation of the capacity utilization characteristic value LS to form the conveying speed signal. In this embodiment, the capacity utilization characteristic value LS has a value of −1, 0 or 1, and has been generated as described above. After the start of the method, the device listens or waits for a new capacity utilization characteristic value LS (block 14.1). Of course, the respective capacity utilization characteristic values which are also all simply denoted here by “LS”, have to be differentiated for the purpose of the programming, and are therefore denoted by LS_x in FIG. 3. After the transfer of the capacity utilization characteristic value, the procedure is continued as a function of the magnitude thereof. A capacity utilization characteristic value LS_x of 0 represents a desired capacity utilization of the separating device, a capacity utilization characteristic value of −1 represents an underload, i.e. excessively low capacity utilization of the separating device, and a capacity utilization characteristic value of 1 represents an overload, i.e. an excessively high capacity utilization with a risk of blockage. If the capacity utilization characteristic value is 0, this is input into the memory 14.2 of the last capacity utilization characteristic values (block 14.3) without a conveying speed signal for changing the conveying speed being output. If the capacity utilization characteristic value is 1, a previous capacity utilization characteristic value which is stored in the memory 14.2 is interrogated (block 14.4) and it is subsequently determined whether an overload has already been detected after the last stored capacity utilization characteristic value of 0 (block 14.5). If this is not the case, the evaluation device outputs a conveying speed signal for reducing the speed (deceleration signal, block 14.6). If this is the case, the new capacity utilization characteristic value is input into the memory 14.2 and no conveying speed signal (a further one which reduces the conveying speed) is output. The speed control according to the invention (block 14.7), i.e. the adaptation of the conveying speed to the capacity utilization of the individual monitored areas of the conveying line or of the separating device, occurs on the basis of the conveying speed signal according to block 14.6.

[0111] If the capacity utilization characteristic value has a value of −1, a capacity utilization characteristic value which is input into the memory 14.2 is in turn interrogated (block 14.8), and in accordance with the differentiation described above it is decided whether a conveying speed signal for accelerating the conveying speed is output or has been already output. The program sequence can optionally be optimized by virtue of the fact that an acceleration is triggered only a specific sequence of a number of capacity utilization characteristic values which indicate an underload or insufficient loading. Therefore, for example for the respective areas of the conveying line it is monitored whether an underload is present (block 14.9), and only then is an acceleration pulse emitted (block 14.10).

[0112] FIG. 4 shows a program sequence diagram of the evaluation of the conveying speed signal. In the method sequence shown, a conveying speed increment or decrement for changing the conveying speed is calculated (block 17.2) on the basis of the conveying speed signal 17.1. Values such as the degree of the capacity utilization characteristic value can be input into the calculation on the basis of a rule base which is present and can in particular be predefined and varied (block 17.3). Likewise, for the calculation of the increment or decrement it can be taken into account whether the machine is in a fine control range of the speed, e.g. near to the capacity utilization limit (e.g. a difference of less than 10%), or is still in a rough control range further away (e.g. more than 50%) from the capacity utilization limit. The capacity utilization limit can preferably be defined in the evaluation device as that value starting from which an excessively large deviation, which signals blockage of material, occurs.

[0113] The conveying speed increment or decrement is converted by the evaluation device into a speed specification for a separating device drive (block 17.5). The resulting conveying speed signal is transmitted to the separating device drive (block 17.6). This results in a conveying speed of the separating device (17.4).

[0114] FIGS. 5 and 6 show, by way of example, the evaluation of individual test images. FIG. 5 is a schematic illustration of an initial image 9 and of a test image 8, each with root crop 4 on a conveying line comprising two conveyor elements 10A and 10B. In the text which follows, conveyor elements are generally also denoted by “10” for the purpose of simplification. A conveyor element 10 is then one or more conveyor elements from the set of conveyor elements (10A, 10B, 10C, 10D, . . . ).

[0115] In one preferred embodiment of the method according to the invention, the evaluation device compares the initial image 9 with the test image 8 insofar as directions of movement of objects illustrated in the images are determined. An object does not necessarily characterize a coherent body but rather in the test image 8 merely constitutes an area which can be identified in respect of its movement and which is in particular of the size of an area which is represented by means of one pixel of the test image 8. In particular, in this way the evaluation device therefore calculates a direction of movement for each pixel of the test image 8, assesses its deviation from a reference direction which is known for each area—in particular for each pixel—and evaluates these deviations statistically. FIG. 5 shows, by way of example, a respective calculated direction of movement, in the form of a simultaneously displayed vector for each type of root crop 4, independently of the consideration of the movement at the pixel level. Each arrow represents a movement characteristic value 20.

[0116] The movement characteristic values 20 are evaluated statistically for the calculation of the capacity utilization characteristic value LS. In this context, the movement characteristic values 20 merely comprise a direction of movement, and not a movement distance, indicated for example by the length of the arrow. FIG. 5 also shows a histogram with one column per movement characteristic value 20. Each column characterizes here an absolute-value deviation of the corresponding movement characteristic value 20 from a uniform reference characteristic value 22.

[0117] In order to calculate a capacity utilization characteristic value LS, indicated by the line 14, in particular a standard deviation of these movement characteristic value deviations from the reference characteristic value 22 is formed. For this purpose, in particular the deviations can in particular be respectively squared and then summed. This sum is then divided by the number of movement characteristic values 20, and the square root of the quotient resulting therefrom is formed. The value which is obtained in this way is the capacity utilization characteristic value LS, which is indicated by way of example in the illustrated histogram.

[0118] In order to calculate the movement characteristic values 20, first image areas 16 of the test image 8 are advantageously compared with further image areas 18 of the initial image 9, wherein each image area 16, 18 comprises the same number of pixels and is in particular rectangular. For the purpose of simplified illustration, only a few exemplary image areas 16, 18 are illustrated in FIG. 9. Therefore, a movement characteristic value 20 is obtained for each image area 16, in particular for each pixel of the test image 8.

[0119] Depending on the conveying line area, it is possible to determine in the evaluation device which capacity utilization brings about a reduction or an increase in the conveying speed. It is therefore possible for example to increase the speed when there is a standard deviation of less than 10°, to maintain the speed when there is a standard deviation of 10° to 20°, and to reduce the conveying speed when there is a larger standard deviation. Accordingly, for the conveyor elements 10A and 10B, embodying a drop step between two screening belts, it is possible to determine, on the basis of the evaluation solely of the detected directions and their standard deviation, whether a blockage of harvested material occurs on the conveyor element 10B which is located below. If a corresponding state, owing for example to a threshold value R indicating a blockage being exceeded, is detected, a conveying speed signal for accelerating the conveyor element 10B is output by the evaluation device, as an alternative to or in addition to a reduction in the conveying speed of the inwardly conveying conveyor element 10A.

[0120] FIG. 6 shows by way of example a test image 8 in the upper part of the figure, which image also again shows the transition from the conveyor element 10A to the conveyor element 10B. Root crop 4 and extraneous materials 5 which can comprise stones and weeds are located in this conveying line area. According to the classifiers which are defined in the training of the algorithm or specified by means of a database, for example a table with color values in the HSV format, individual partial image areas 16 are checked for the presence of identical components. Therefore, the assignment of the respective image areas to the individual portions, illustrated by way of example bottom left in FIG. 5, results in a portion distribution of individual portions of root crop 4 and extraneous materials 5 in the test image 8. A1 therefore shows the portion of the root crop 4 in the test image 8 or the corresponding test data set, A2 shows the portion of weeds and A3 shows the portion of stones. This assignment is preferably made on the basis of the color information, preferably also comprising black-and-white and/or gray values of the individual pixels, i.e. an image area 19 which is assigned to a portion corresponds in particular to an area of a pixel. The capacity utilization characteristic value which is denoted generally by LS is based by way of example, and also preferably, on a deviation of the first portion A1 from a threshold value which is again denoted generally by R and indicates an optimum portion distribution of root crop at the observed location on the conveying line. For example, the capacity utilization characteristic value LS is set to 1 when there is a deviation ≥50% from the cleaning threshold value, and to 0 when there is a deviation of <50% from the cleaning threshold value. These values are then correspondingly stored and processed in the further program sequence according to FIGS. 1 to 4.

[0121] An arrangement of the optical image-capturing units 6 is disclosed in FIG. 8. The machine 2 according to the invention is embodied as a towed potato harvester, wherein a multiplicity of conveyor elements 10 and their associated separating devices are secured by means of a machine frame 12, which is only partially designated. Along the conveying line there are a multiplicity of image-capturing units 6 which capture images of the harvested material which is transported on the conveyor elements 10 and comprises root crop 4. The optical image-capturing units 6 form individual measuring points for monitoring the respective separating devices.

[0122] The positions of image-capturing units 6 which are indicated in FIG. 7 are an area directly after a grubbing device 29 (measuring point MS1), a transition from a first conveyor element 10A in the form of a screening belt to a second conveyor element 10B in the form of a screening belt which is additionally surrounded by a coarse weed belt (measuring point MS2), the transition from this second screening belt 10B to a further conveyor element 10C comprising a further separating device (measuring point MS3). Moreover, on the output side of this separating device a conveyor element 10E which leads to the sorting table and has a further image-capturing unit 6 (measuring point MS4) is monitored, wherein at the same time images of a further conveyor element 10F which is provided for residues of extraneous materials 5, in particular stones, are captured. Finally, a further optical image-capturing unit 6 (measuring point MS5) is present at the sorting table 45.

[0123] An evaluation device can be positioned at any desired centrally accessible location, but preferably in the vicinity of the sorting table. Information relating to the setting of the separating devices can be sent to an operator on a tractor vehicle from the evaluation device, for example via a cable 12.1 which can be seen in FIG. 7.

[0124] The machine 2 which is illustrated in the side view in FIGS. 8 and 9 clarifies the positions of the optical image-capturing units 6. In particular, the image-capturing unit 6 which is located at the sorting table 45 can be arranged directly at a drop step leading to a bunker 33.

[0125] FIGS. 10 and 11 show the arrangement of an optical image-capturing unit 6 which is arranged on the frame above a first drop step between a conveyor element 10A and a conveyor element 10B and whose field of vision is directed downward (measuring point 2). A light source 7 ensures that the field of vision is illuminated in order to capture a sufficiently lit test image 8. The conveyor element 10A is a screening belt which already screens out some of the extraneous materials 5, in particular earth, coming from a grubbing device 29 and transfers them to a further conveyor element 10B, embodied as a screening belt, via a drop step. This conveyor element 10B additionally has a coarse weed belt which is provided for separating off the weeds present with the potatoes or in the harvested material. Stripping devices 32 are correspondingly arranged over the width of the conveyor element 10B.

[0126] A height H of the stripping device 32 above the conveying plane of the conveyor element 10B can also be set. The conveying speeds of the conveyor elements 10A and 10B can be set by means of the method according to the invention. FIG. 11 illustrates only one coarse weed belt 43, and not the actual conveyor element 10B (cf. FIG. 13), embodied in the form of a screening belt, for purposes of clarity.

[0127] A test image 8 which is obtained from the field of vision of the optical image-capturing unit 6, which is shown by means of dashes in FIG. 12, is illustrated in detail (without harvested material) in FIG. 13. The evaluations described above are made using a test data set provided from this test image 8 on the basis of the detected directions of movement of the harvested material and/or on the basis of the respective portions of the components of harvested material, and when necessary the conveying speeds of the conveyor elements are adjusted.

[0128] The harvested material which is still present is transferred from the conveyor element 10B to a further conveyor element 10C with a conveying direction 1C. A separating device in the form of a plurality of rotating deflection rollers 24 which are positioned one above the other is assigned to said further conveyor element 10C. The harvested material is transported in the direction of the conveyor element 10D (FIG. 14) by means of a pulse which is applied by said separating device.

[0129] A distance H between a conveyor element 10C and the lower deflection roller 24 can be set by the operating personnel for the purpose of varying a separating performance. The speeds of at least the inward conveying conveyor element 10C and outward conveying conveyor element 10D, which are embodied as screening belts, can be varied by means of the method according to the invention. In addition, according to one advantageous development the separating performance or deflection can be varied by virtue of the adjustability of the circulation speeds of the deflection rollers 24.

[0130] The image-capturing unit 6 illustrated in FIG. 14 generates the test image which is illustrated in FIG. 15 and in which a test image part 8A is defined by means of filtering or masking. In addition, a test image part 8B, which is located behind the deflection rollers 24 when viewed from a conveying direction 1C, is also defined by filtering. Therefore, the areas of the conveyor element 10C which are located upstream and downstream of the separating element formed by the deflection rollers 24 are monitored for the setting of the conveying speed. Respective test data sets can be produced for the two image areas 8A and 8B, and the respective evaluations for the two image areas 8A and 8B can result from the corresponding partial areas of a test data set.

[0131] Insofar as an associated setpoint value for the test image part 8A reveals accumulation of material upstream of the deflection rollers 24, the conveying speed of the conveyor element 10C is increased.

[0132] Alternatively, the evaluation can be based only on the areas 8A and 8C which are located upstream of the deflection rollers 24, are surrounded by dashed lines and are adjacent to another. Permissible densities of portions can be defined for these two areas, for example by means of the respective threshold values R. Starting from the upward transgression of e.g. a portion of, for example, root crop 4 which is associated with excessive accumulation directly upstream of the deflection rollers, the inward conveying belt 10C can be made to run more quickly, and alternatively or additionally an outward conveying belt can be made to run more quickly.

[0133] A height H of the lower ends of fingers 26 of a separating device which is embodied as a finger web 26.1 can also be settable as one of a plurality of operating parameters by the operating personnel. The height H describes the distance between the fingers 26 and the upper edge of the conveyor element which is embodied as a hedgehog web. Moreover, an attitude angle of the finger web 26.1 can be configured in such a way that it can be set with respect to a vertical to the conveying plane of the conveyor element. The same applies to the circulation speed of the finger web 26.1.

[0134] A further optical image-capturing unit 6, which is arranged in the area of the conveyor belts 10C and 10D is illustrated in FIG. 16. This image-capturing unit 6 can be used, in addition to the image-capturing unit according to FIG. 14, to monitor the transportation of harvested material in the test image area 8D. In particular, the image-capturing unit 6 therefore serves to monitor the effect of the separating and deflection device which is embodied by the deflection rollers 24. In particular, the conveying speed of the conveyor element 10D can be adapted as a function of the results of the evaluation of the test images 8 of the optical monitoring unit 6 according to FIG. 14. The monitoring unit 6 according to FIG. 16 is also assigned a light source 7 for better illuminating the monitored area 8D.

[0135] A further optical image-capturing unit 6 is arranged with an associated light source 7 above a sorting table with a view of a conveyor element 10E and a conveyor element 10F (FIG. 18). In this context, as described above, perspective correction is performed on the basis of the “fisheye” representation of the image-capturing unit 6. By means of masking, the test image parts 8A and 8B which are represented in the test image 8 according to FIG. 19 are selected, and, on the one hand, monitor the conveyor element 10E, as a conveying path, with a conveying direction 1E for transporting away root crop and, on the other hand, monitor the conveyor element 10F, as a further conveying path, with a conveying direction 1F for transporting away extraneous materials 5 in the form of stones. By means of the evaluation described above it is checked whether the portions of root crop 4 on the conveyor element 10F are too large. If this is the case, the conveyor element 10D connected upstream is given a slower setting by means of the method according to the invention, by means of the evaluation device. In addition, in one development of the invention the finger web 26.1, which is illustrated above the conveyor element 10D embodied as a hedgehog web, can be adapted with respect to its separating effect as a function of corresponding control specifications, said finger web 26.1 having fingers 26 (illustrated by dashed lines by way of example) behind the cover 40 located in front of them. For example, the distance between the fingers 26 and the conveyor element 10D is reduced in order to convey away a greater amount of harvested material, in the form of root crop 4, onto the conveyor element 10E via an associated chute 41.

[0136] FIG. 20 illustrates the arrangement of measuring points MS1 to MS5 having optical image-capturing units 6 on a schematically illustrated conveying line of a machine 2 embodied as a beet lifter. The image-capturing units 6 are arranged downstream of a grubbing device 29 above a roller table 10M and at the end of a conveyor element 10N which is embodied as a screening belt (measuring points MS1 and MS2). A further optical image-capturing unit 6 monitors in particular a conveyor element 10P which is embodied as a screening star (measuring point MS3). The subsequent conveyor element 10Q which is embodied as a screening star is also monitored in precisely the same way as a conveyor element 10R which is embodied as a ring elevator (measuring points MS4 and MS5). If e.g. a blockage at one of the conveyor elements 10M, 10N, 10P, 10Q, 10S is detected, this conveyor element can be made to run more quickly at the instigation of the evaluation device. This can be done according to one of a plurality of possible control scenarios, initially only for a specific time up to subsequent checking, or can take place until monitoring reveals that the critical state has been eliminated.