A combine harvester includes a threshing unit for threshing picked-up crop to obtain grain, a driver assistance system, with a memory for storing data, for controlling the threshing unit, and a computing unit for processing at least the data stored in the memory. A sensor system ascertains at least a portion of the current harvesting-process state. A sensor configuration assigned to the sensor system is defined by the type and scope of operational sensors is stored or can be stored in the memory. A functional system model for at least a portion of the combine harvester is stored in the memory. The computing unit is designed to carry out an autonomous determination of a threshing-unit parameter based on the system model, and defines the system model forming a basis of the control of the threshing unit depending on the sensor configuration stored in the memory.

A residue deflection assembly for a crop loss monitoring system includes a residue deflector configured to be positioned rearward of a row unit of a header of an agricultural harvester relative to a direction of travel of the agricultural harvester. The residue deflector is configured to direct residue away from a field of view of a camera of the crop loss monitoring system and to enable crop material to be present within the field of view of the camera.

A grain loss sensing system for a combine harvester. The grain loss sensing system employs at least one emitter and receiver on the combine harvester and uses what is received by the receiver to calculate grain loss. The system can be configured to use, for example, microwave, ultraviolet, x-ray and/or photographic technology. The results are used to differentiate between grain and MOG. The results are relayed to the operator so that the operator can make adjustments and/or the combine harvester host controller receives this information and responds by making adjustments automatically.

Disclosed are various embodiments for using artificial intelligence to monitor harvest losses of combine harvesters. Images can be periodically captured from a ground-facing camera mounted to a combine harvester. An amount of gleanings can be counted in the image. An estimated amount of harvest loss is then calculated based at least in part on the amount of gleanings. The estimated amount of the harvest loss can then be displayed to a user or can be used as the basis for automatically adjusting the operation of the combine harvester.

In an embodiment, a method of real-time disease recognition in a crop field is disclosed. The method comprises causing a camera to continuously capture surroundings to generate multiple images. The method further comprises causing a display device to continuously display the multiple images as the multiple images are generated. In addition, the method comprises processing each of one or more of the multiple images. The processing comprises identifying at least one of a plurality of diseases and calculating at least one disease score associated with the at least one disease for a particular image; causing the display device to display information regarding the at least one disease and the at least one disease score in association with a currently displayed image; receiving input specifying one or more of the at least one disease; and causing the display device to show additional data regarding the one or more diseases, including a remedial measure for the one or more diseases.

A user interface element includes a plurality of moveable outer points on a circular line and a fixed inner point inside the circular line, the fixed inner point being connected to each of the outer points by a straight line such that each pair of adjacent straight lines and a portion of the circular line between the adjacent straight lines defines a section of the graphical user interface element. The user interface is configured to, in response to interaction from the user, move any of the outer points along the circular line and independently of the other outer points to thereby change the size of two or more of the sections. Each section corresponds to one of a plurality of crop processing parameters, such that changing the amount of area within any section results in an adjustment to an operation of a crop processing system.

A crop loss level generator receives a crop loss sensor signal from a crop loss sensor and generates a crop loss metric indicative of a sensed crop loss level based on the crop loss sensor signal. A first crop loss display generator generates a first crop loss display element based on the crop loss metric and controls a display device to display the first crop loss display element relative to a target loss range indicator indicative of a target loss range. A historic crop loss display generator generates a historic crop loss display element, based on previously generated crop loss metrics, and controls the display device to display the historic crop loss display element relative to the target loss indicator and relative to the first crop loss display element.

A harvesting vehicle including a cleaning section including a blower and at least one sieve. The sieve is configured to transport a layer comprising a mixture of grain kernels and residue material towards an exit edge of the sieve so that kernels fall through openings of the sieve and the residue remains on the sieve until it is ejected from the sieve by crossing the exit edge. The sieve may be subject to a grain loss, including a sieve-off loss and a blowout loss. The cleaning section further includes a sensor configured to determine whether the blowout loss or the sieve-off loss is a highest contributor to the grain loss. The cleaning section may also include a grain loss detector configured to measure the sieve-off loss and at least a portion of the blowout loss and a blowout sensor mounted above the sieve for measuring the blowout loss.

A method and apparatus estimate yield. A first signal is received that an aggregate yield measured by an aggregate yield sensor during a measurement interval. A second signal is received that indicates a plurality of geo-referenced regions across which a harvester has traveled prior to the measurement interval. The method and apparatus allocate, to each of at least two geo-referenced regions, an aggregate yield portion allocation based upon different travel times for crops to the aggregate yield sensor Visual-Infrared Vegetative Index data derived from sensing of plants in selected portions of the electromagnetic spectrum at a time other than harvest. The aggregate yield portion allocations are output.

A method of estimating the mass of crop entering into a grain tank on a harvesting machine, comprising the steps of mounting a load sensor on the upper bearing of a conveyor belt moving crop through the clean grain elevator into the grain tank, connecting the load sensor to a processor, using the load sensor to measure a load on the conveyor belt when no crop is present in the clean grain elevator, and also when crop is moving through the clean grain elevator, and comparing the load with no crop present to the load when crop is present to estimate the mass of crop moving through the clean grain elevator.