Harvesting report

Abstract

A crop detection system (20) with at least one processing unit (630) which, connected to a display (24), is configured to receive (1002) a detected grain yield from a sensor (36) for at least one forage plant harvested from one of several sections of a harvest width involved in the harvest, and to cause the display (1006) of information for the at least one forage plant harvested from one of the several sections, based on the detected grain yield, on the display (24), characterized in that several sensors (36, 36A-36H) are assigned to different sections of the harvest width and are configured to detect the grain yield of the forage plants introduced in the respective section independently of an adjacent section by means of an interaction with a forage plant, by each of the sensors (36,36A-36H) detects an interaction or impact force of a grain on a row unit of a picker (34) assigned to the respective section of the harvest width and a grain mass is derived from the detected impact force and other detected or known values, or the sensors (36) detect a stem thickness or stem diameter of an individual plant and the grain mass is derived from the detected stem thickness or stem diameter.

Description

[0001] The invention relates to a crop detection system. State of the art

[0002] Harvesting machines such as combine harvesters sometimes contain crop throughput sensors. Such sensors measure the current crop yield of the harvester's mowed swath.

[0003] For example, DE 697 23 874 T2 shows a combine harvester equipped with sensors for grain yield and crop moisture. The sensor readings can be georeferenced and displayed on a map.

[0004] The information generated by such sensors may not be sufficient for the increasingly complex management of crops, as they relate to the entire cutting width of the header. invention

[0005] The present invention is defined by the claims.

[0006] A crop detection system comprises at least one processing unit connected to a display configured to receive a detected grain yield from a sensor for at least one forage crop harvested from one of a plurality of sections of a harvesting width involved in the harvest, and to cause information for the at least one forage crop harvested from the one of the plurality of sections to be displayed on the display based on the detected grain yield.A plurality of sensors are assigned to different sections of the harvesting width and are configured to record the grain yield of the forage plants planted in the respective section based on an interaction with a forage plant, independently of a neighboring section, by each of the sensors recording an interaction or impact force of a grain on a row unit of a picker assigned to the respective section of the harvesting width and a grain mass is derived from the recorded impact force and other recorded or known values, or the sensors detect a stalk thickness or a stalk diameter of an individual plant and the grain mass is derived from the recorded stalk thickness or the stalk diameter. Short description of the drawings Fig. Figure 1 is a schematic representation of an exemplary crop detection system. Fig. 2 is a flowchart of an exemplary method used by the crop detection system of Fig. 1 can be executed. Fig. 3 is a flowchart of another exemplary method used by the crop detection system of Fig. 1 can be executed. Fig. Figure 4 is an illustration of an example field map generated by the crop tracking system of Fig. 1 by carrying out the procedure of Fig. 3 can be created. Fig. Figure 5 is an illustration of another example field map generated by the crop tracking system of Fig. 1 by carrying out the procedure of Fig. 3 can be created. Fig. Figure 6 is an illustration of an exemplary configuration display screen used by the crop sensing system of Fig. 1 can be presented. Fig. Figure 7 is an illustration of an exemplary output display screen used by the crop sensing system of Fig. 1 can be presented. Fig. Figure 8 is a schematic diagram of an example of the crop detection system of Fig. 1. Fig. 9 is a side elevational view of an exemplary crop detection system incorporating the crop detection system of Fig. 8. Fig. 10 is a schematic diagram illustrating detection of one or more crop attributes by the system of Fig. 9 shows. Fig. 11 is a flowchart showing an exemplary method used by the crop detection system of Fig. 9 can be executed. Fig. 12 is a flowchart showing another exemplary method used by the crop detection system of Fig. 9 can be executed. Fig. 13 is a front view of an exemplary harvesting platform for the crop collection system of Fig. 9. Fig. 14 is a top perspective view of an exemplary row unit of the harvesting platform of Fig. 13. Fig. 15 is a perspective view from below of the row unit of Fig. 14. Fig. 16 is a top perspective view of an exemplary frame of the row unit of Fig. 14 and Fig. 15. Detailed description of the embodiments

[0007] Fig. 1 schematically shows an exemplary crop detection system 20. The crop detection system 20 outputs crop data and field maps with an enhanced resolution. In an exemplary embodiment, the term "resolution" refers to the level of detail related to crop data and / or field maps. A resolution for crop data or field maps is determined by the smallest unit for which an attribute is captured or for which an attribute is derived. Generally, the smaller the detail, the greater the resolution. The crop detection system 20 outputs crop data and maps of a field using captured or derived attributes and / or identified conditions for individual units or sections of the field with a width that is less than a used crop harvesting width of a harvesting vehicle.For example, even though a harvester may have a 12-row harvest swath, the crop tracking system 20 may output crop data or field maps that provide crop attributes, such as yield, for fewer than 12 rows, such as on a row-by-row basis or even on a plant-by-plant basis. The crop tracking system 20 may also be implemented with respect to a non-row crop and non-row harvester. The greater crop data resolution provided by the crop tracking system 20 facilitates advanced and sophisticated crop management.

[0008] The crop detection system 20 includes an agricultural machine, of which the illustrated harvesting vehicle 22 is an example. The crop detection system 20 further includes a display 24, an input 26, a processor 30, and a memory 28. The harvesting vehicle 22 includes a mobile machine configured to move across a field or property while harvesting a crop. The harvesting vehicle 22 includes a picker 34 and sensors 36A-36H (collectively referred to as sensors 36). In other implementations, the crop detection system 20 may include other types of agricultural machines.

[0009] The picker 34 includes a mechanism configured to collect and harvest a crop along a mowed swath. The mowed swath of picker 34 has a usable width, Wu, when harvesting crop. In an exemplary embodiment, the usable width Wu represents the portion of the length or mowed swath width used to harvest crop at a given time. Although in most cases, the usable width Wu is equal to the physical length of the mowed swath of picker 34, under certain circumstances, the usable width Wu may represent only a portion of the mowed swath of picker 34, such as along an end row, a waterway, and / or the like. The picker 34 includes various harvesting mechanisms, such as mechanisms for cutting or separating the crop from the rest of a plant. Such mechanisms may include knives or blades, stripper plates, rollers, picker rollers, augers, gathering chains or belts, and / or the like.In one embodiment, the header 34 may include a corn header for a combine harvester, wherein the corn header separates corn cobs from the remaining stalk. In another embodiment, the header 34 may include a grain header for a combine harvester, wherein the grain is separated along with the stalk and subsequently threshed by the combine harvester. In other embodiments, the header 34 may have other configurations. For example, although the header 34 is shown at a front end of the harvesting vehicle 22 and may be replaced with other headers (facilitating the interchange of corn and grain headers), in other embodiments, the header 34 may be mounted at other locations on the harvesting vehicle 22 and / or may be a permanent, non-replaceable component of the harvesting vehicle 22.

[0010] The sensors 36 include mechanisms for sensing or detecting one or more crop attribute values ​​for a crop of forage plants. In an exemplary embodiment, a forage plant includes a plant from the Poacea family or grass plant, a plant from the Fabaceae family or vegetable plant, and / or a perennial plant, but excludes trees such as conifers and deciduous trees. Examples of Poaceae plants or grass plants include corn, rice, wheat, barley, millet, oats, sugarcane, sorghum, rye, and bamboo. Examples of Fabacea plants or vegetable plants include beans such as soybeans. An example perennial plant includes a sunflower plant. The sensors 36 detect one or more crop attribute values ​​for the forage plants along the entire cutting swath of the header 34 or a portion of the cutting swath or the harvesting width of the header 34.In one exemplary embodiment, the sensors 36 are arranged on or supported by the picker 34. In one exemplary embodiment, the sensors 36 are arranged in each row harvesting section of the picker 34. In other embodiments, the sensor 36 may be provided at other locations.

[0011] Each of the sensors 36 detects one or more crop attribute values ​​for a crop being harvested from a corresponding separate portion of the harvesting width Wu. The sensors 36 collectively detect multiple non-zero crop attribute values ​​for multiple separate portions of the harvesting width Wu. In other words, each of the sensors 36 detects only a portion of the total crop being harvested by the picker 34 at a given moment, with each of the sensors 36 providing crop attribute values ​​for that exact portion. For example, in one embodiment, each of the sensors 36 may detect a crop attribute for plants along a single row, thereby providing "per-row" crop attributes.

[0012] For example in Fig. 1, in one case, the entire picker 34 may pick up and harvest crop such that the usable width Wu of the picker 34 is substantially equal to the physical width or swath of the picker 34. The sensors 36 each detect less than an entire section or a fraction of the crop harvested by the usable width Wu. In one embodiment, as illustrated by the partition 40, the usable width Wu may be separated or divided into two equal sections P1 and P2, with sensors 36A-36D providing a first crop attribute value for crop picked up by section P1, while sensors 36E-36H provide a second crop attribute value for crop picked up by section P2.In another embodiment, as represented by partition 42, the harvesting width Wu may be separated or divided into four equal sections P1, P2, P3, and P4, wherein sensors 36A-36B, sensors 36C-36D, sensors 36E-36F, and sensors 36G-36H provide independent and discrete crop attribute values ​​for crop received by sections P1-P4, respectively. In another embodiment, as represented by partition 44, the harvesting width Wu may be separated or divided into eight equal sections P1-P8, wherein sensors 36A-36H each provide a discrete crop attribute value for crop received by sections P1-P8, respectively.

[0013] Although the individual sections of partitions 40 and 42 are each shown as being associated with multiple sensors, in other embodiments, each of the sections of partitions 40 and 42 may be associated with a single sensor or any number of sensors. Although the picker 34 is shown as having eight sensors, in other embodiments, the picker 34 may include a greater or lesser number of such sensors along the physical width or swath of the picker 34. For example, a row-type harvester may have more or fewer than eight rows, and the picker of the harvester may also be divided into sensors sensing more or fewer than eight rows. Although the picker 34 is shown as being divided into equal sections, in other exemplary embodiments, the picker 34 is divided into unequal sections, with sensors sensing crop attributes for the unequal sections.For example, in another embodiment, one of the sensors 36 senses or detects crop attributes for a single row, while another center 36 senses or detects crop attributes for multiple rows.

[0014] As in Fig. 1, in some implementations, each of the sensors 36 may provide a higher degree of crop detection resolution by being configured to detect crop attribute values ​​for the individual plants 46 per se. In some implementations, the detected crop attribute values ​​for individual plants 46 may be aggregated into sets or assemblies 48 of plants based on time, distance, number of plants, and / or the like to reduce the amount of data that is processed or stored. Aggregating individual plant data may also improve the usability of the data by eliminating noise in the data. The detected crop attribute values ​​for the individual plants 46 include values ​​that are independent of, or do not solely encompass, the presence or location of the plant.Such crop attribute values ​​for the individual plants 46 include not only data regarding the population of plants or the spacing of plants. Rather, each of the sensors 36 can be configured to specifically sense other attributes of the individual plant, so that crop attribute values ​​can be derived that relate to an estimated mass of the individual plant's grain or product, the estimated mass other than grain (MOG) of the plant, and / or the like.

[0015] For example, in one embodiment, each of the sensors 36 detects an interaction or impact force of a grain on a portion of the picker 34, such as a stripper plate of the picker 34, wherein a grain mass can be derived from the detected impact force and other detected or known values. In another embodiment, the sensors 36 detect a stalk thickness / diameter of an individual plant. The stalk thickness / diameter of the individual plant can be detected either through physical contact with the individual plant or through laser or optical and camera-based sensors. The grain mass, or MOG, can be derived from the detected stalk thickness / diameter.Other examples of sensors 36 include, but are not limited to, light detection and ranging (LIDAR or LADAR), structured light or stereo vision camera, strain gauges and / or accelerometers (where crop impact is detected), and / or the like.

[0016] The display 24 includes a device for presenting information to an operator of the harvesting vehicle 22 or to a remotely located monitor / manager / operator of the harvesting vehicle 22. The display 24 may include a monitor or screen that is inherently stationary or inherently mobile. In one embodiment, the display 24 is carried by the harvesting vehicle 22 along with the operator. In another embodiment, the display 24 includes a stationary monitor remote from the harvesting vehicle 22. In further embodiments, the display 24 may be inherently mobile, provided as part of a computer tablet, smartphone, personal data assistant (PDA), and / or the like.

[0017] Input 26 includes one or more devices through which controls and input are provided to processor 28. Examples of input 26 include, but are not limited to, a keyboard, a touchpad, a touchscreen, a steering wheel or controller, a joystick, a microphone with associated voice recognition software, and / or the like. Input 26 facilitates the input of selections, commands, and controls. In embodiments where harvesting vehicle 22 is remotely controlled or steered, input 26 may facilitate such remote steering.

[0018] The memory 28 includes a non-transitory, computer-readable medium or a persistent storage device for storing data used by the processor 30 or created by the processor 30. In one embodiment, the memory 28 may additionally store instructions in the form of code or software for the processor 30. The instructions may be loaded from a read-only memory (ROM), a mass storage device, or other persistent storage into a random access memory (RAM) for execution by the processor 30. In other embodiments, hard-wired circuitry may be used instead of, or in combination with, software instructions to perform the described functions. For example, at least portions of the memory 28 and processor 30 may be embodied as part of one or more application-specific integrated circuits (ASICs). In one embodiment, the memory 28 is carried by the harvesting vehicle 22.In other embodiments, the storage 28 may be provided remotely from the harvesting vehicle 22.

[0019] In the illustrated example, the memory 28 includes a data storage section 52, a correlation module 54, a condition detection module 56, a display module 58, and an operational settings module 60. The data storage section 52 includes historical data, such as lookup tables, that facilitate analysis of data and information sensed by the sensors 36. The data storage section 52 is further configured to store the crop attribute values ​​sensed directly by the sensors 36, crop attribute values ​​derived from the directly sensed crop attribute values ​​using the correlation module 54, and crop or field conditions identified from the directly sensed crop attribute values ​​and / or the derived crop attribute values. Such stored information may be in various formats, such as tables, field maps, and / or the like.The data storage section 52 can additionally store various settings and operator preferences.

[0020] The correlation module 54, the condition detection module 56, the display module 58, and the operation settings module 60 contain programming, software, or code for directing the operation of the processor 30. The correlation module 54 directs the processor 30 in correlating one or more directly sensed crop attribute values ​​sensed by the sensors 36 with derived crop attribute values. In other words, the correlation module 54 directs the processor 30 in deriving crop attribute values, such as yield and / or the like, from directly sensed crop attribute values. In one embodiment, the correlation module 54 directs the processor 30 to consult a lookup table in the data storage section 52 for a correlation of a stalk thickness / diameter sensed by the sensors 36 with a grain mass or grain yield value, the derived crop attribute value.In another embodiment, the correlation module 54 directs the processor 30 to execute one or more algorithms / mathematical equations using a detected impact of a plant or grain, and possibly using other additional factors, to derive a grain mass or yield of the plant. In other embodiments, the correlation module 54 directs the processor 30 to derive crop attribute values ​​from directly detected crop attribute values ​​in another manner.

[0021] The condition detection module 56 guides the processor 30 in identifying field and / or crop conditions based on the directly sensed crop attribute values ​​or the derived crop attribute values. Examples of such field / crop conditions include, but are not limited to, the absence of plants, a field washout condition, an area of ​​the field suffering yields from wheel marks above a predetermined threshold, the presence of a weed patch, the presence of a yield loss due to an inappropriate chemical application, and / or the like.In one embodiment, the condition detection module 56 directs the processor 30 to use a lookup table in the data storage section 52 to correlate a stalk thickness / diameter as sensed by the sensors 36 and / or a derived grain mass or grain yield value, the derived crop attribute value, with one of various predefined conditions, examples of which are provided above. In another embodiment, the condition detection module 56 directs the processor 30 to execute one or more algorithms and / or one or more mathematical equations using a directly sensed crop attribute value and / or a derived crop attribute value, and to further compare the resulting calculation to one or more predefined thresholds to identify a field and / or crop condition.In other embodiments, the condition detection module 56 may direct the processor 30 to identify or detect crop and / or field conditions in other ways.

[0022] The display module 58 instructs the processor 30 to generate control signals that cause a display 24 to display various information and / or prompts to an operator. For example, a display module 58 may cause a processor 30 to prompt an operator to select which enclosure 40, 42, 44 or individual plants to use, whether to collect individual plant data, how to display data (graph, chart, field map), which conditions to identify, how to notify or warn the operator of such conditions, whether to save such data, and / or the like. The display module 58 further instructs the processor 30 in displaying data per operator preferences.

[0023] The operational settings module 60 includes code or programming that directs the processor 30 to automatically generate control signals that adjust operating parameters of a harvesting vehicle 22 based on directly sensed or derived crop attribute values. In one implementation, the operational settings module 60 generates control signals that independently adjust operating parameters of discrete portions of the header 34 along its usable width Wu. For example, the operational settings module 60 may adjust operating parameters of only one row unit of the header 34 independently of, or differently than, another row unit of the header 34 based on directly sensed or derived crop attribute values ​​for the crop currently being harvested by the other row units.For example, the operational adjustment module 60 may automatically adjust control signals for an actuator coupled to stripper plates of the row unit to adjust the spacing of the stripper plates in response to sensed or derived crop attribute values ​​for a crop being harvested by a particular row unit. This adjustment of stripper plates for the particular row unit may be independent of and different from the adjustment of other stripper plates for other row units. As a result, the enhanced crop sensing resolution provides finer control of the operation of the harvesting vehicle 22 to better harvest a crop.

[0024] The processor 30 includes one or more processing units configured to execute instructions, either hard-wired as part of an application-specific integrated circuit or provided as code or software stored in the memory 28. In the illustrated example, the display 24, the input 26, the memory 28, and the processor 30 are each shown as part of, and carried by, a harvesting vehicle 22. In other implementations, one or more such components may be located remotely from the harvesting vehicle 22 and in wireless communication with the harvesting vehicle 22. In some implementations, some of the above-noted functions of the processor 30 in the memory 28 may be shared by multiple processors or processing units and multiple memories / databases, where at least some of the processors and memories / databases may be located remotely with respect to the harvesting vehicle 22.

[0025] Fig. 2 is a flowchart illustrating an exemplary method 100 that may be performed by the system 20 for detecting crops. As illustrated in block 110, the processor 30 receives detected crop attribute values ​​for each of the plurality of sections of the usable width Wu of the picker 34 of the harvesting vehicle 22. For example, in an implementation using a partition 44, the sensor 36A provides the processor 30 with a first detected crop attribute value for section P1. Sensor 36B provides the processor 30 with a second detected crop attribute value for section P2. The sensors 36C-36H, similar to the processor 30, provide discrete crop attribute values ​​for their associated sections P3-P8. In some implementations, the detected crop attribute values ​​may include a thickness or diameter of a plant stem.In some implementations, the detected crop attribute values ​​may include an impact of a grain, such as a corn cob, on a portion of the picker, such as a stripper plate.

[0026] As illustrated in block 112, following instructions provided by correlation module 54, processor 30 uses the received crop attribute values ​​(EAW1) for each of the sections to derive a secondary crop attribute value (EAW2) for each of the sections. In one embodiment, secondary crop attribute value EAW2 may include an estimated yield. In such an embodiment, processor 30 derives an estimated yield for sections that produce a crop. For example, in an embodiment using partition 44, processor 30 derives a first yield value for section P1, a second yield value for section P2, a third yield value for section P3, and so on. In other embodiments, other secondary crop attribute values ​​(EAW2), such as MOG, may be derived from the directly acquired crop attribute values ​​EAW1.

[0027] As illustrated in block 114, the processor 30 generates control signals based on the instructions contained in the display module 58 to store or display the derived crop attribute values. In one embodiment, the processor 30 stores the derived crop attribute values ​​in the data storage portion 52 of the memory 28. In one embodiment, the processor 30 sends the derived secondary crop attribute values ​​to a remote database or storage location over a wide area network, such as a wired or wireless connection. In some embodiments, the root or base data, EAW1, is also stored and / or sent. In some embodiments, the derived secondary crop attribute values ​​are further displayed on the display 24.In some implementations, a visual or audible alarm or notification may be issued by the display 24 in response to the derived secondary crop attribute value for a particular section P meeting a predefined threshold. For example, if a derived crop yield for a particular section P, such as a particular row unit of the picker 34, falls below a certain threshold, an alarm or notification may be provided to the operator indicating problems with the operation of the particular row unit.

[0028] Because the system 20, as noted above, establishes crop attributes for individual sections of the harvesting width, such as individual rows or individual plants (or collections of plants along a row), the system 20 provides an operator with more detailed, higher-resolution information so that the operator (or the harvester automatically) can make row-by-row adjustments to the harvesting vehicle's settings to accommodate various conditions that may be present row by row. The operator can further use such information to correlate the yield results for individual rows during harvest with individual row settings of other operations, such as planting, tilling, fertilizer, insecticide, or crop protection product application, and / or the like.As a result, for other equipment operations such as planting, tilling, fertilizer, insecticide, or pesticide application, row-by-row adjustments can subsequently be made based on the row-by-row harvest information. For example, a roller mill, planters, fertilizer, insecticide, or pesticide application equipment, and / or the like may have resulted in irregular crop occurrence or development rates. The row-by-row information allows an operator to determine that a problem exists, identify the causes, and identify solutions before the next harvest season.

[0029] Such information can also be used to better calibrate crop-input yield estimation devices. For example, per-row yield estimates can be combined with yield data collected elsewhere in the machine, such as from a grain yield sensor mounted on a clean-grain auger or off-machine, such as on a scale in a grain storage facility. Combining this data can be used for purposes such as sensor calibration and post-harvest data processing.

[0030] Fig. 3 is a flowchart illustrating an exemplary method 200 that may be performed by the system 20. As in Fig. 3, the method 200 includes blocks 110 and 112, which are described above with respect to the method 100. As indicated in block 213, the processor 30, according to instructions included in the condition detection module 56, uses the derived secondary crop attribute values ​​and / or the directly sensed primary crop attribute values ​​EAW1 to identify crop and / or field conditions. For example, the processor 30 may determine a field condition such as yield-reducing soil compaction, a wet patch, a weed patch, leaching, a yield-reducing chemical application, and / or the like using the directly sensed primary crop attribute values ​​and / or the derived secondary crop attribute values.

[0031] Other factors may also be used by processor 30 in determining a crop or field condition. For example, planting history data may be used by processor 30 in determining such a condition. In some embodiments, processor 30 may additionally generate control signals that cause a display 24 to prompt an operator for input based on a visual inspection of the crop or field during harvest or planting, and such input information may be incorporated into processor 30's determination of the condition.

[0032] As indicated in block 214, the processor 30 generates control signals based on the instructions contained in the display module 58 to store or display the determined field / crop condition. In one implementation, the processor 30 stores the determined conditions for various regions of a field or plot in the data storage portion 52 of the memory 28. In one implementation, the processor 30 sends the identified conditions to a remote database or storage location over a wide area network, such as a wired or wireless connection. In some implementations, the root or base data, EAW1, and the derived secondary crop attribute values ​​are also stored and / or sent. In some implementations, the determined conditions are further displayed on the display 24.In some implementations, the display 24 may issue a visual or audible alarm or notification in response to the detection of a particular condition. In some implementations, the processor 30 may determine and retrieve solutions from the memory 28 and generate control signals that cause the display 24 to display the recommended corrective actions for the detected condition.

[0033] Although the system 20 and methods 100, 200 have been described with respect to the harvesting vehicle 22, such individual row-by-row sensing may also be incorporated into other vehicles or mobile machines. For example, such row-by-row sensing may be used with corn headers used in seed grain production to achieve high-throughput phenotyping, to characterize different growth patterns / yields for different varieties, and / or the like. In one embodiment, individual row sensors may be mounted on each vehicle, providing information related to different development rates (stalk size at different times of a season). In further embodiments, individual plant or row-by-row characterization may alternatively be used in other vehicles such as crop sprayers, scout vehicles, autonomous vehicles, wheelbarrows, and / or the like.

[0034] Fig. 4 is an illustration showing an exemplary field map 300 that the system 20 may store in the memory section 52 and / or present on the display 24. The field map 300 represents one embodiment of methods 100 and 200 performed by the system 20, in which both the derived secondary crop attribute values ​​and the identified conditions are plotted across a field. The field map 300 has an enhanced resolution. In the illustrated example, the field map 300 has a row-by-row resolution. The field map 300 is the product of the compartmentalization of the harvesting width Wu of the picker 34 on a row-by-row basis, with a metric or crop attribute detected for each row unit of the picker 34.The different recorded metric values ​​for the different rows of crop harvested by the different row units of the picker 34 are used to derive the secondary crop attribute values, such as yield, for each row on a row-by-row basis. In the example shown in . Fig. 4, the field map 300 graphically displays the derived secondary crop attribute values ​​for 14 rows. As the harvester traverses the field, the collected primary crop attribute values ​​and the derived secondary crop attribute values ​​(EAW2) vary along the row. Based on the derived secondary crop attribute values, the processor 30 further identifies field conditions using the method 200. The identified conditions are further graphically displayed as part of the field map 300.

[0035] Fig. 5 shows a field map 400 that the system 20 may store in the memory section 52 and / or display on the display 24. The field map 400 represents an implementation of the methods 100 and 200 performed by the system 20, in which both the derived secondary crop attribute values ​​and the identified conditions are plotted across a field. The field map 400 has an enhanced resolution. In the illustrated example, the field map 400 has a plant-by-plant resolution. The field map 400 is the product of compartmentalizing the harvesting width Wu of the picker 34 on a row-by-row basis and distinguishing each individual plant from neighboring individual plants, detecting a harvested crop metric for each plant. In other implementations, the field map 400 may be the product of distinguishing aggregate sets of individual plants based on time, distance, or plant count.For example, instead of processing and storing a sensed crop attribute value on a plant-by-plant basis, crop attributes may be processed and / or stored for all plants harvested by a particular row unit during a particular time period, for all plants harvested while a harvesting vehicle travels a predetermined distance, or for a predetermined number of plants. The different sensed metric or crop attribute values ​​for the individual plants or collections of individual plants harvested by the different row units of the picker 34 are used to derive the secondary crop attribute values, such as yield, for each plant or collection of plants. In the example illustrated in FIG. Fig. 5, the field map 400 graphically displays the derived secondary crop attribute values ​​for 15 plants. As the harvester traverses the field, the detected primary crop attribute values ​​and the derived secondary crop attribute values ​​(EAW2) vary from plant to plant. Based on the derived secondary crop attribute values, the processor 30 further detects or identifies field conditions according to method 200. The identified conditions are further displayed as part of the field map 400.

[0036] Fig. 6 and Fig. 7 show example screen displays on the display 24 during operation of System 20. Fig. 6 shows an exemplary configuration of a screen display 500 that may be presented on the display 24 by the processor 30 following instructions in the display module 58. The screen display 500 presents various prompts or choices for options or modes for configuring and operating the system 20 from which an operator may select. As indicated by the prompts 502, the display 24 allows the operator to enter and select the interval for which the collected crop attributes for individual plants 46 are to be aggregated into a single data value for processing and / or storage. In the illustrated example, the operator may select a specific time, a specific distance, or a specific number of individual plants.

[0037] As indicated by prompts 504, the operator may specify how crop attribute values ​​should be derived for the particular interval or assemblage of individual plants: determining an average derived crop attribute value for the assemblage of plants, determining a median derived crop attribute value, or a range of derived crop attribute values.

[0038] As indicated by prompts 506, the operator can select how the derived secondary crop attribute values ​​are displayed: whether on a continuous basis or only in response to a predefined condition being met. As indicated by prompts 508, the operator can specify how the identified conditions are presented on the display 24: whether they are displayed continuously or only when certain conditions are identified.

[0039] As indicated by prompts 510, the operator can select which conditions are identified and then presented on the display 24 when they are detected. Examples of such conditions include: no plants, washout, wheel marks, chemicals, and weed patches. In other implementations, the operator may be presented with other options and choices for the compilation interval, processing, display, and conditions.

[0040] Fig. Figure 7 shows an exemplary output display screen 550 that may be presented on the display 24 by the processor 30 according to instructions in the display module 58. The display screen 550 presents the output of the system 20 based on the configuration selection made with respect to the screen shown in Fig. 6. As represented by data series 552 and 554, processor 30 outputs on display 24 the derived instantaneous secondary crop attribute of yield for each of the eight combine rows. In other words, data series 552 and 554 identify the instantaneous yield (bushels per acre) for a crop harvested for each of the eight row units of header 34.

[0041] As indicated by data row 556, processor 30 further retrieves data from data storage section 52 and correlates the respective combine rows with previously stored planter rows (the row units of the planter that planted the particular rows now being harvested by the harvester / combine). In some implementations, additional planting information for each of the specified planting rows may be further retrieved by processor 30 from data storage section 52 and presented on screen display 550. For example, different planted rows may have different values ​​for the type or amount of applied crop protection product, insect repellent, or seed used in the particular row. In another example, containers containing seeds and agrochemicals may have different weights in different sections of the field.As a result, the operator can be presented with information useful in subsequent planting by correlating different planting conditions with various yield outcomes on a row-by-row basis. In the present example, data from planting is correlated with a per-row yield. Without limitation, data could also be obtained from prior row-by-row data collection, such as during tillage, spraying, scouting, land-based reconnaissance, and aerial reconnaissance. The data can be collected or aggregated at resolutions such as greater than a field, field level, subfield level, row level, and plant level. In some embodiments, the data is georeferenced and timestamped to facilitate later analysis.

[0042] In some implementations, in addition to correlating positions relative to the machine during various operations (row 3 on an 8-row combine with row 11 on a 16-row planter), the system 20 may further provide an indication 550 regarding the direction of travel of the particular mobile machine for the particular rows. For example, the direction of travel may be very favorable when comparing processing data with tillage data, where the direction of travel may be 45° to directions of travel during planting and harvesting.

[0043] As indicated by prompts 558, in addition to presenting such information in the form of a chart, the system 20 further allows the operator to select other formats for presenting such information. In the illustrated example, the operator may request that such information be additionally presented as a bar graph. In other implementations, other derived crop attribute values, such as MOG, may also be displayed in the same or different formats.

[0044] As indicated by data line 560, using the results of condition detection module 56 and instructions from display module 58, processor 30 presents the detected condition present for a single row or a group of rows. In the illustrated example, processor 30 has determined with a 73% confidence level that the weight of the feedstock tank during planting was a problem that may have caused soil compaction, which could have resulted in a lower yield for the particular rows. As indicated by section 562, processor 30 additionally queries data storage section 52 (or additional local or remote databases) to analyze possible causes for the detected conditions and present such possible causes as part of screen display 550.In the illustrated example, the processor 30 presents on the display 24 the various conditions that occurred for the particular set of rows, for example, that the material weight in the feedstock tank was high during planting of the particular rows, the landform of the rows is a depression, and that heavy rainfall occurred prior to planting.

[0045] Fig. 8 schematically shows the crop detection system 620, an exemplary implementation of the crop detection system 20. The crop detection system 620 includes a crop characterizer 623, an on-board operator output 624, an on-board operator input 626, a localization input 627, a memory 628, an on-board processor 630, a static database 700, a trained database 702, an online database 704, connections 706, company back office 708, third-party service providers 710, other on-site machines 712, and remote operators / observers 714.

[0046] The crop characterizer 623 includes a device configured to capture or detect multiple non-zero crop attribute values ​​for multiple different portions of a harvesting machine's working width. In the described example, the crop characterizer 623 detects crop attributes or crop properties at least on a row-by-row basis. Individual rows of crop 720 are captured independently, and different attribute values ​​may be identified and stored for the individual rows. In the described example, the crop characterizer 623 detects crop attributes on a plant-by-plant basis.Individual plants 722 are independently detected, and various attribute values ​​may be identified and stored for the individual plants or for a predefined compilation of individual plants along a row 720 (for example, a compilation based on time, distance, or plant count as described above). As a result, the crop characterizer 623 facilitates data collection and field maps with increased resolution for more sophisticated analysis and better crop management. In one example, crop attributes are defined by a crop characterizer 623 on both a per-plant and per-row basis. In another example, crop attributes are defined based on a selected per-plant or per-row basis.

[0047] The crop characterizer 623 includes sensors 636 and one or more cameras 637. The sensors 636 are similar to the sensors 36 described above. The sensors 636 include mechanisms to simultaneously sense or detect one or more crop attribute values ​​for multiple portions of a utilized crop harvesting width of the harvesting vehicle. In other words, each of the sensors 636 senses only a portion of the total crop harvested by the harvesting vehicle 622 at any one time, with each of the sensors 636 providing crop attribute values ​​for only that portion. As noted above, in one embodiment, the sensors 636 provide crop attribute values ​​on a row-by-row basis. In another embodiment, the sensors 636 provide crop attribute values ​​on a plant-by-plant basis. Such crop attribute values ​​for the individual plants 722 include not only data regarding the population of plants or the spacing of plants.Each of the sensors 636 may be configured to specifically sense other attributes of the individual plant so that crop attribute values ​​related to the individual plant's estimated grain mass or product, the estimated non-grain plant mass (MOG), and / or the like may be derived.

[0048] For example, in one embodiment, each of the sensors 636 detects an interaction or impact force of grain on a portion of the harvesting vehicle, such as a stripper plate. A grain mass can be inferred from the detected impact force. In another embodiment, sensors 636 detect a stalk thickness / diameter of an individual plant (either through physical contact with the individual plant or through non-physical contact mechanisms such as laser or optical and camera-based sensors). The grain mass or MOG can be inferred from the detected stalk thickness / diameter. Examples of sensors 636 include, but are not limited to, light detection and ranging (LIDAR or LADAR), structured light or stereo vision cameras, strain gauges, and / or accelerometers (where crop impact is detected).

[0049] In one embodiment, camera 637 includes an image capture device carried by harvesting vehicle 622 to capture one or more rows 720 immediately prior to harvesting such rows 720. In one embodiment, camera 637 captures images used to detect or determine one or more crop attributes or crop characteristics on a row-by-row or plant-by-plant basis. In one embodiment, camera 637 uses stereo vision or LIDAR for such detection. In one embodiment, camera 637 captures images of the crop prior to harvest, with each image or video segment linked to the crop attribute values ​​detected by sensors 636. These values ​​may be stored.The captured images or video are linked and indexed on a time basis or a location basis to specific regions, individual rows, or individual plants for which data is collected by the sensors 636. Therefore, when reviewing directly sensed crop attribute values ​​(as detected by the sensors 636) or derived crop attribute values ​​for a particular region of a field, a particular set of rows of the field, or a particular grouping of plants in the field, the operator also obtains and views images or videos of the actual region of the field, the particular rows of the field, or the particular plants of the field corresponding to the data seen in a graph or map.Thus, system 620 allows an operator / monitor to visually inspect the actual crop to either verify one or more conditions that may have affected a crop attribute such as yield, or allows the operator / monitor to visually confirm the crop / field condition identified by processor 630 as the cause of a particular crop yield or other attribute. For example, based on data from sensors 636, processor 630 may output a conclusion that a reduction in yield was caused by a wet patch in the field. Camera 637 allows the operator to load (from memory) actual stored video images of the particular section of the field to confirm whether the particular rows were indeed located in a wet patch.

[0050] In the illustrated example, system 620 provides multiple operating modes for characterizer 623. In one mode, sensors 636 can be used for crop characterization. In another mode, camera 637 can be used for crop characterization. In yet another mode, both sensors 636 and camera 637 can be used for crop characterization. In some implementations, system 620 can omit one of sensors 636 or camera 637.

[0051] In some implementations, crop characterizer 623 may additionally include a local processor 639. Processor 639 receives signals from sensors 636 and conditions such signals before sending them over data link 730 to on-board processor 630. For example, in some implementations, processor 639 derives other crop attribute values ​​from the signals before sending them to processor 630. Processor 639 may filter such signals to reduce noise prior to transmission over link 730. In some implementations, processor 639 may clip or compress data prior to sending such data over link 730 to processor 630 to reduce transmission and / or processing loads. In another implementation, processor 639 may be omitted.

[0052] The onboard operator output 624 includes one or more devices carried by the harvesting vehicle 622 through which information and data can be presented to an operator onboard the harvesting vehicle 622. The output 624 may include a display including a monitor or screen with or without a speaker. The onboard operator input 626 includes one or more devices carried by the harvesting vehicle 622 through which selections and / or data can be entered, entered, and provided by a local operator 32 driving or operating the harvesting vehicle 622. Examples of an input 626 include, but are not limited to, a keyboard, a touchpad, a touchscreen, a steering wheel or controller, a joystick, a microphone with associated voice recognition software, and / or the like.In one embodiment, input 626 may be provided as part of output 624 in the form of a touch screen.

[0053] Localization input 627 includes an input to a processor 630 that provides geospatial data to the processor 630. In other words, input 627 provides location or position information to the processor 630. For example, in one embodiment, localization input 627 may include a global positioning system (GPS) receiver. In other examples, other sources of geospatial data may be used.

[0054] Memory 628 includes a non-transitory, computer-readable medium or a persistent storage device for storing data for use by processor 630 or generated by processor 630. In one implementation, memory 628 may additionally store instructions in the form of code or software for processor 630. The instructions may be loaded from read-only memory (ROM), a mass storage device, or other persistent storage into random access memory (RAM) for execution by processor 630. In other embodiments, hard-wired circuitry may be used instead of, or in combination with, software instructions to perform the described functions. For example, at least regions of memory 628 and processor 630 may be implemented as part of one or more application-specific integrated circuits (ASICs).In the illustrated example, the storage unit 628 is carried by the harvesting vehicle 622. In other embodiments, the storage unit 628 may be provided remotely from the harvesting vehicle 622.

[0055] In the illustrated example, the memory 628 includes a configuration module 650, a correlation module 654, and a condition detection module 656. The configuration module 650 includes software code and associated stored data relating to the configuration of the system 620. In the illustrated example, the configuration module 650 includes sub-modules that direct the processor 630 to request a selection from an operator, store such a selection, and perform operation in accordance with such different selections. The stored selection controls how the processor 630 handles and analyzes data from the characterizer 623 or presents information on an output 624. In the illustrated example, the configuration module 650 includes an interval sub-module 670, a processing sub-module 672, and a notification sub-module 674 that cooperate to present a display screen 500, as described above with respect to Fig. 6. The interval submodule 670 requests and stores operator input regarding the manner in which individual plants are to be grouped, as the various grouping technique prompts 502 in Fig. 6. The processing submodule 672 requests and stores operator input regarding how such data should be processed, for example, using statistical values ​​such as average, median, or range. The notification submodule 674 requests and stores display settings, such as with prompts 506 and 508, as well as prompts 510.

[0056] The correlation module 654 and condition detection module 656 contain programming, software, or code for directing the operation of the processor 630. The correlation module 654 instructs the processor 630 in correlating one or more directly sensed crop attribute values ​​detected by the sensors 36 with derived crop attribute values. In other words, the correlation module 654 instructs the processor 630 in deriving crop attribute values, such as yield and / or the like, from directly sensed crop attribute values ​​or possibly together with other factors or inputs. In one implementation, the correlation module 654 directs the processor 630 to consult a lookup table in a database to correlate a stalk thickness / diameter, as detected by sensors 636, with a grain mass or grain yield value, the derived crop attribute value.In another implementation, the correlation module 654 directs the processor 630 to execute one or more algorithms / mathematical equations based on a detected impact of a plant or grain to derive a grain mass or yield of the plant. In other implementations, the correlation module 654 may direct the processor 630 to derive crop attribute values ​​in other ways from directly detected crop attribute values.

[0057] The condition detection module 656 guides the processor 630 in identifying field and / or crop conditions based on the directly sensed crop attribute values ​​or the derived crop attribute values. Examples of such field and crop conditions include, but are not limited to, the absence of plants, a field washout condition, an area of ​​the field with yields suffering from wheel marks above a predetermined threshold, the presence of a weed patch, and the presence of yield loss due to an inappropriate chemical application.In one embodiment, the condition detection module 656 directs the processor 630 to consult a lookup table in the database to correlate a stalk thickness / diameter as detected by the sensors 636 and / or a derived grain mass or grain yield value (the derived crop attribute value) with one of several predefined conditions, examples of which are given above. In another embodiment, the condition detection module 656 directs the processor 630 to execute one or more algorithms / mathematical equations using a directly sensed crop attribute value and / or a derived crop attribute value and compare the resulting calculation to one or more predefined thresholds to derive a field and / or crop condition.In other implementations, the condition detection module 656 may direct the processor 630 to identify or detect crop and / or field conditions in other ways.

[0058] The static database 700 includes a data store containing data regarding historical or predefined data, such as planting history data, yield history information, field or soil history data (e.g., topography, soil type). The static database 700 may additionally include tables and other information for correlating sensed crop attribute values ​​with derived crop attribute values. The learned database 702 includes a data store containing data that changes as the harvesting vehicle 622 traverses a field. The database 702 stores the raw, directly sensed crop attribute values ​​from the sensors 636 and / or the camera 637, video or images captured by the camera, derived crop attribute values, and varying or adjustable harvesting vehicle operating parameters, e.g., harvesting vehicle speed, picker height, and other harvesting vehicle settings.In one example, database 702 further stores GPS data.

[0059] In the illustrated example, static database 700 and learned database 702 include databases that are part of a memory 628 onboard harvesting vehicle 622. In other implementations, such databases 700, 702 may be remote from harvesting vehicle 622 and accessible through connection 706. Online database 704 includes a database accessed through a wide area network or a local area network via connection 706. Online database 704 may include additional information for use by processor 630 and harvesting vehicle 622. Connection 706 includes an interconnection network that facilitates a connection between harvesting vehicle 622 and remote facilities, such as online database 704, an office 708, a service provider 710, other on-site machines 712, and a remote operator / observer 714.

[0060] The company office 708 includes a location remote from the harvesting vehicle 622, such as the main farm. The company office 708 may include computing devices and a database, with the processor 630 sending data stored in a trained database 702 to the office 708 through the connection 706 for data backup and / or remote analysis. The third-party service provider 710 includes a server connected to the harvesting vehicle 622 through the connections 706 and associated with a third party, such as an agronomist, a seed dealer, a seed company, a chemical, insecticide, or fertilizer supplier, or a third-party data storage host.

[0061] As through Fig. 8, other harvesting vehicles or other machines at a particular worksite or field may also be connected to harvesting vehicle 622 through connections 706. Crop data collected thereby may be shared by such multiple machines at a particular field or worksite. In some implementations, harvesting vehicle 622 may communicate with remote operator / observer 714 through connections 706. This allows for remote control of harvesting vehicle 622 (steering harvesting vehicle 622 and / or adjusting the settings for crop sensing operation by harvesting vehicle 622).

[0062] Fig. 9 and Fig. 10 show the crop detection system 820, an example of the crop detection system 20, or an example of the crop detection system 620. In the illustrated example, the crop detection system 820 includes a harvesting vehicle 822 (in the form of a combine harvester). The crop detection system 820 includes each of the Fig. 8 shown and described components, some of which are shown in Fig. 9 and are numbered alike, except that the crop sensing system 820 specifically includes sensors 836, certain examples of the sensors 636.

[0063] The harvesting vehicle 822 includes a chassis 912 supported and driven by traction wheels 914. Although the harvesting vehicle 822 is shown supported and driven by traction wheels 914, it may also be supported and driven by full tracks or half tracks. A harvesting device 916 (shown as a corn head) is used to receive and convey crop material to an intake housing 918. The crop is directed from the intake housing 918 to a beater drum 920. The beater drum 920 guides the crop upward through a receiving transition area 922 to a rotating threshing and separating device 924.Although the harvesting vehicle 822 is described as a rotary combine, in other embodiments, the harvesting vehicle 822 may include other types of combines (e.g., combines with a transverse threshing cylinder and straw walkers or combines with a transverse threshing cylinder and rotating separation rotors) or other agricultural harvesting machines, including, without limitation, self-propelled forage harvesters, sugar cane harvesters, and windrowers.

[0064] The rotating threshing and separating device 924 includes a rotor housing 926 and a rotor 928 disposed within the rotor housing 926. The incoming crop enters the rotor housing 926 through the receiving transition area 922. The rotating threshing and separating device 924 threshes and separates the incoming crop. Grain and chaff fall through grates at the bottom of the rotor housing onto a cleaning device 934. The cleaning device 934 removes chaff and directs the clean grain to a grain elevator 936, which leads upward to a distribution auger 938. The distribution auger 938 discharges the clean grain into a grain tank 940. The clean grain in the grain tank 940 can be unloaded into a trailer or truck via an unloading auger 942. Threshed straw separated from the grain is passed through an outlet from the rotating threshing and separating device 924 to a discharge turning drum 946.The discharge turning drum 946 ejects the straw from the rear of the harvesting vehicle 822.

[0065] The operation of the harvesting vehicle 822 is controlled from an operator's cab 948. In the illustrated embodiment, a location input 627 (a geographic position sensor in the form of a receiver) for receiving GPS (Global Positioning System) signals is mounted above the operator's cab 948. A speed sensor that measures the speed of the wheels 914 may be provided. On the side of the clean grain elevator 936 is a condenser moisture sensor 952 for measuring the moisture content of the clean grain. Such a sensor is disclosed in DE 199 34 881 A, the complete disclosure of which is incorporated herein by reference. A mass flow sensor 954 is located at the outlet of the clean grain elevator 936. The mass flow sensor 954 includes an impeller plate that rotates about a horizontal axis. Its deflection depends on the mass flow rate of the clean grain.The deflection of the impeller plate is measured, thus providing data regarding the mass flow rate of the harvested grain. Such a sensor is described in EP 0 853 234 A (the entire disclosure of which is incorporated herein by reference) and the documents cited therein.

[0066] Sensors 836 are similar to sensors 636 in that sensors 836 include mechanisms to simultaneously sense or detect one or more crop attribute values ​​for multiple portions of a utilized crop harvesting width of the harvesting vehicle. In other words, each of sensors 836 senses only a portion of the total crop being harvested by harvesting vehicle 822 at any one time, with each of sensors 836 providing crop attribute values ​​for only that portion. In one embodiment, sensors 836 provide crop attribute values ​​on a row-by-row basis. In another embodiment, sensors 836 provide crop attribute values ​​on a plant-by-plant basis or on a group-by-plant basis. Such crop attribute values ​​for the individual plants do not only include data regarding the population of plants or the spacing of plants.Rather, each of the sensors 836 is configured to specifically sense other attributes of the individual plant so that crop attribute values ​​related to the individual plant's estimated grain mass or product, the estimated mass of the plant other than grain (MOG), and / or the like can be derived.

[0067] As further shown by Fig. 9, a crop detection control unit 956 is located in the operator's cab 948 or elsewhere on the harvesting vehicle 822. The crop detection control unit 956 includes the memory 628, the processor 630 and the databases 700, 702 described above with respect to Fig. 8. The crop detection control unit 956 communicates with the localization input 627, the moisture sensor 952, the mass flow sensor 954, the speed sensor, if present, and the sensors 836. The crop detection control unit 956 is provided with an internal clock or receives external time signals, for example, from the input 627. The crop detection control unit 956 records the amount of harvested grain measured by the mass flow sensor 954 and its moisture content measured by the moisture sensor 952, depending on the geographical position of the harvesting vehicle 822 (measured by the localization input 627, e.g., a GPS receiver). The crop detection control unit 956 additionally receives signals and / or data from the sensors 836 and derives one or more crop attribute values ​​for each of a plurality of different sections of the harvesting platform 916.In one embodiment, the crop detection controller 956 derives one or more crop attributes for individual rows or road units of the harvesting platform 916, with the data being processed and stored on a row-by-row basis. In another embodiment, the crop detection controller 956 derives and stores one or more crop attributes for individual plants or assemblies of individual plants. The crop detection controller 956 writes the data to the trained database 702 and generates a field total, which may also be stored in the trained database 702, and presents an output 624. In one embodiment, the crop detection controller 956 creates a yield map, similar to one of the maps 300 or 400 shown in FIG. Fig. 4 and 5 respectively.

[0068] Fig. 10 schematically shows an exemplary operation of the sensors 836 and the crop detection control unit 956. As in Fig. 10, in one embodiment, the sensors 836 are mounted on or in the harvesting platform 916 (shown as a corn head). In one embodiment, the sensors 836 include strain gauge sensors and / or the like mounted or coupled to at least one stripper plate 980 along a plurality of row units of the harvesting platform 916. In one embodiment, the sensors 836 are mounted or coupled to at least one stripper plate 980 along each row unit of the harvesting platform 916. The sensors 836 are connected to the processor 630 of the crop sensing control unit 956 (in Fig. 9). In one embodiment, one sensor is associated with a row unit. In other embodiments, more than one sensor may be associated with a row unit. In such a case, the sensors may be of the same type, sensing the same or different attributes, or of different types, sensing the same or different attributes. In further embodiments, one sensor may be associated with multiple row units.

[0069] Fig. 11 is a flow diagram of an exemplary method 1000 by which the crop detection control unit 956 may determine or derive one or more crop attribute values ​​using signals from the sensors 836. As illustrated in block 1002, the processor 630 receives signals from the sensors 836 that detect the interaction, such as contact or movement, of the crop with or relative to the header or harvesting platform 916. In the illustrated example, where the harvesting platform 916 includes a corn header, the processor 630 receives signals from the sensors 836 coupled to at least one stripper plate 980 of each row unit, where the sensors 836 detect an impact of a corn ear 984 on the one or more stripper plates 980 along a row unit. As illustrated in block 1004, the processor 630, based on at least this detected interaction, i.e., the impact of the corn ear 984 on the one or more stripper plates 980, a secondary crop attribute value, such as yield. As shown in block 1006, the processor 630 stores and / or displays the secondary crop attribute value. Although the processor 630 is described as receiving signals from the sensors 836, which are shown coupled to stripper plates, to detect the interaction of an ear 984 with the stripper plates 980, in other implementations, the processor 630 may receive crop interaction signals from the sensors 836 mounted at other locations to detect other interactions of the plant or its grain product with the harvesting platform 916.

[0070] Fig. 12 is a flow diagram of a method 1050, a particular embodiment of a method 1050 by which the crop detection controller 956 may determine and / or derive one or more crop attribute values ​​using signals from the sensors 836. As indicated in block 1052, the processor 630 receives signals from the sensors 836 that detect an impulse from a piston impact on the stripper plate 980. As indicated in block 1054, the processor 630 further determines the velocity component of the piston 984. Such velocity may be determined based at least in part on the velocity of the harvesting vehicle 822 while traveling in the direction indicated by arrow 988. The velocity may be obtained from the aforementioned velocity sensor or from the location input 627.As indicated in block 1056, the processor 630 divides the sensed pulse by the determined velocity to estimate a mass of the single piston 984.

[0071] As indicated in block 1058, the processor 630 may then determine the crop attribute, such as yield, for the cob 984 based on the determined mass of the cob 984. In one implementation, the processor 630 may consult a lookup table contained in the database 700 to derive a grain yield for the cob 984. The processor 630 may also determine a yield for the individual plant using such information. Based on the time interval between consecutive pulses provided by the sensor 836, the processor 630 may determine whether consecutive pulses are the product of two cobs on a single plant or two cobs on separate plants. This allows the processor 630 to determine the yield for the individual plant.Results for individual plants may be aggregated along a row (as described above) or may be indistinguishable from one another to output yield on a row-by-row basis. As illustrated in block 1068, the derived crop attributes, such as yield, may be stored in the learned database 702 and / or may be presented at output 624.

[0072] Fig. 13-16 show the harvesting platform 1116 (shown as a corn picker) and sensors 1136, which are Fig. 14, examples of a harvesting platform 916 and sensors 836 as described above. As shown in Fig. 13, the harvesting platform 1116 includes a frame 1212, row units 1214, an auger 1215, outer dividers 1216, 1218, and center dividers 1220. The frame 1212 extends the physical width of the harvesting platform 1116 and supports the row units 1214. The row units 1214 harvest corn from individual rows of the crop and convey the harvested corn to the auger, which further conveys it into the harvesting vehicle 1212. The row units 1214 are spaced apart in a side-by-side relationship, with the spacing consistent with the spacing between adjacent harvested corn rows. In some implementations, the row units 1214 may be adjustable to accommodate other corn row spacings. The outer dividers 1216, 1218 and the central divider 1220 separate intertwined stalks of adjacent rows. The central dividers 1220 extend between consecutive row units 1214.The dividers 1216, 1218 and 1220 cooperate to define longitudinal passages 1222 centered relative to the rows to be harvested, as well as a fore-and-aft extending, relatively narrow throat 1224 defined by each row unit 1214.

[0073] Fig. 14-16 show an example of a series unit 1214 in more detail. As Fig. 14-16, each row unit 1214 includes, in addition to the sensor 1136, a frame 1226, right and left stripper plates, also known as cover plates, 1228, 1230, right and left collecting units 1232, 1234, and picking rollers 1236, 1238 (shown in Fig. 15). As in Fig. As shown in Figure 16, the frame 1226 includes a U-shaped member having right and left forward and rearward extending legs 1240, 1242 connected by a transversely extending hoop or loop 1244. The legs 1240, 1242 support the stripping plates 1228, 1230 as well as the right and left collecting units 1232, 1234 and picking rollers 1236, 1238.

[0074] The stripper plates 1228, 1230 include plates with inner edges that are spaced apart from each other to define a narrow throat 1224. The throat 1224 receives corn stalks from an aligned row as the row unit 1214 moves along a row of crop. As the row unit 1214 moves along the row, the stalks are pulled through the throat 1224 by means of the picking rollers 1236, 1238 (shown in Fig. 15) so that the corn ears carried by the stalk impact the stripper plates and are separated from the stalk. Such stripper plates 1228, 1230 may include elongated openings for receiving fasteners so that the stripper plates 1228, 1230 may be adjusted laterally to adjust the width or size of the throat 24. As noted above, in some embodiments, an actuator may be coupled to the stripper plates to automatically adjust the spacing of the stripper plates 1228, 1230 in response to control signals from the processor 630 based on derived crop attribute values ​​from the sensor for the particular row unit 1214.

[0075] In the illustrated example, at least one sensor 1136 (shown schematically), such as an accelerometer or a strain gauge, is mounted on a bottom surface of at least one of the stripper plates 1228, 1230 to detect the impact of the ear of corn on the stripper plates 1228, 1230. As discussed above with respect to sensors 836 and method 1050, signals generated by sensor 836 are used by processor 630 to ultimately derive a mass of the particular ear of corn that impacted the stripper plates 1228, 1230, as well as the yield from the particular ear of corn.

[0076] Right and left collecting units 1232, 1234 collect the corn cobs and transport such cobs backward to the auger 1215 (shown in Fig. 13). In the illustrated example, each of the gathering units 1232, 1234 includes a drive shaft 1240, a drive pinion 1242, a idler shaft 1244, an idler pulley 1246, a gathering chain 1248, and a chain tensioning assembly 1250. Each of the drive shafts 1240 extends from and is driven by a gear 1252 to rotate the pinion 1242. Each of the drive shafts 1240 extends through a corresponding opening 1254 in the loop 1244 of the frame 1226 (shown in Fig. 16). The drive pinions 1242 cooperate with the idler pulleys 1246 to support and drive the gathering chain 1248.

[0077] The idler shafts 1244 are rotatably supported by chain tensioning assemblies 1250. The idler shafts 1244 rotatably support the idler pulleys 1246. The chain tensioning assemblies 1250 adjustably support the idler pulleys 1246 for movement between various forward and rearward positions to adjust the tension of the gathering chains 1248. The picking rollers 1236, 1238 are mounted on a pair of drive shafts 1260 projecting forward from the gearbox 1252. As noted above, the picking rollers 1236, 1238 pull corn stalks downward in the throat 1224 between the stripper plates 1228, 1230. Since the corn cobs are too large to pass downward through the throat 1224, such cobs impact the stripping plates 1228, 1230 and are detached and separated from the stalks so that they are collected by the collecting chains 1248.

[0078] Although the present disclosure has been described with reference to exemplary embodiments, those skilled in the art will recognize that changes in form and detail may be made without departing from the spirit and scope of the claimed subject matter. For example, not every feature illustrated in the drawings is required, and one or more features may be omitted. Although various exemplary embodiments may be described that include one or more features that provide one or more advantages, it is understood that the described features may be interchanged or combined with one another in the described exemplary embodiments or in other alternative embodiments. Because the technology of the present disclosure is relatively complex, not all changes in the technology are foreseeable.The present disclosure, described with reference to the exemplary embodiments and set forth in the following claims, is clearly intended to be as broad as possible. For example, unless otherwise stated, claims that specify a single specific element also encompass a plurality of such specific elements.

Claims

[1] Crop detection system (20) with at least one processing unit (630) which, connected to a display (24), is configured to receive (1002) a detected grain yield from a sensor (36) for at least one forage plant harvested from one of a plurality of sections of a harvesting width involved in the harvest, and to cause the display (1006) of information for the at least one forage plant harvested from the one of the plurality of sections on the basis of the detected grain yield on the display (24), characterized byin that a plurality of sensors (36, 36A-36H) are assigned to different sections of the harvesting width and are set up to detect the grain yield of the forage plants brought into the respective section independently of a neighboring section based on an interaction with a forage plant, in that each of the sensors (36, 36A-36H) detects an interaction or impact force of a grain on a row unit of a picker (34) assigned to the respective section of the harvesting width and a grain mass is derived from the detected impact force and other detected or known values, or the sensors (36) detect a stalk thickness or a stalk diameter of an individual plant and the grain mass is derived from the detected stalk thickness or the stalk diameter. [2] Crop detection system (20) according to claim 1, wherein the section associated with a sensor (36, 36A-36H) contains a single crop row of the harvesting width. [3] The crop detection system (20) of claim 1, further comprising an input (26), wherein the processing unit (630) is configured to generate control signals that cause the display (24) to present a plurality of selections for the portion of the harvesting width for which information is to be displayed, and wherein the processing unit (630) generates control signals that display information for plants harvested in a selected portion of the harvesting width based on an input selection. [4] Crop detection system (20) Apparatus according to claim 1, further comprising an input (26), wherein the processing unit (630) is configured to generate control signals that cause the display (24) to present a plurality of selections for a compilation of data in the portion of the harvesting width, and wherein the processing unit (630) generates control signals that cause the display (24) to display information for the portion of the harvesting width based on the selected compilation of data. [5] The crop detection system (20) of claim 4, wherein the plurality of selections include: a time interval, a distance interval, and a number of plants. [6] The crop detection system (20) of claim 1, wherein the processing unit (630) is configured to generate the control signals in response to a predetermined trigger that cause the display (24) to present information based on the detected crop attribute for forage crops harvested in the one of the plurality of portions of the harvesting width. [7] The crop detection system (20) of claim 6, further comprising an input (26), wherein the processing unit (630) is configured to generate control signals that cause the display (24) to display a plurality of selections for a predetermined trigger, and wherein the processing unit (630) generates control signals that cause the display (24) to display information for the one of the plurality of portions of the harvest width based on the selected predetermined trigger. [8] The crop detection system (20) of claim 1, further comprising an input (26), wherein the processing unit (630) is configured to receive observation data for the one of the plurality of portions of the crop width through the input (26); and linking and storing the observation data with the information. [9] The crop detection system (20) of claim 8, wherein the processing unit (630) is configured to generate control signals that cause the display (24) to present types of selections for observation data, the types of selections being selected from a group of types consisting of: a no-plant condition, a washout condition, a wheel track condition, a chemical load condition, and a weed condition. [10] The crop detection system (20) of claim 8, wherein the processing unit (630) is configured to analyze the information and generate control signals that cause the display (24) to present reasons for the information presented on the display (24). [11] The crop detection system (20) of claim 1, further comprising a camera (637), wherein the processing unit (630) is configured to receive observation data for the one of the plurality of portions of the crop width from the camera (637); and linking and storing the observation data with the information. [12] The crop detection system (20) of claim 1, wherein the at least one processing unit (630) is configured to generate control signals that cause the display (24) to present planting information for plants harvested from the one of the plurality of portions of the harvesting width concurrently with the information for plants harvested from the one of the plurality of portions of the harvesting width based on the detected crop attribute.

Images