Abstract: Systems and methods are provided for guiding an agricultural machine utilising image data received from one or more imaging sensors associated with the agricultural machine. The image data is analysed utilising a detection model to classify at least one object within the environment of the agricultural machine and the classification is used to identify a cooperative machine for performing a cooperative operational task with the agricultural machine. The systems extend to controlling operation of the guidance system in dependence on the identified cooperative machine.

Abstract: Systems and methods are provided for mapping one or more agricultural operations within a working environment. Image data is received from one or more imaging sensors mounted or otherwise associated with one or more agricultural machines within the working environment and configured to obtain image data indicative of the working environment and/or one or more objects located therein. The data is analysed utilising a detection model to classify one or more objects within the working environment to identify, from the one or more classified objects, one or more working machines within the working environment. Operational information for the working machine(s) is logged and/or updated in an operational map of the working environment in dependence on the identification of the classified object(s).

Abstract: An object detection system for an agricultural machine which utilises image data from one or more imaging sensors associated with the agricultural machine. The image data is analysed utilising first and second detection models to classify, for one or both models, an object within the environment of the agricultural machine. A classification metric for the object indicative of an overlap associated with the classification obtained for each of the models for the object is used in determining an identity for the object. One or more operable components associated with the agricultural machine may then be controlled in dependence on the determined identity.

Abstract: A system includes an agricultural crop receiving vehicle with a bin for receiving and holding agricultural crop material and a camera positioned to capture images of an area proximate the receiving vehicle. One or more computing devices receive the image data from the camera, identify one or more features of a harvester in the image data, determine a location of the agricultural harvester relative to the crop receiving vehicle, and use the location of the agricultural harvester to generate control signals for controlling movement of the agricultural crop receiving vehicle to coordinate receiving crop material in the bin from the harvester or for controlling a graphical user interface to present a visual indicator of the relative locations of the agricultural crop receiving vehicle and the agricultural harvester.

Abstract: Methods and systems are provided for monitoring operation of an agricultural machine. Image data indicative of an input image of a working environment of the agricultural machine is receive and encoded utilizing an encoder network to map the image data to a lower-dimensional feature space. The encoded data is then decoded form a reconstructed image of the working environment which is compared with the input image to identify anomalies within the working environment. One or more operable components associated with the machine may be controlled based on the identification of one or more anomalies.

Abstract: An agricultural harvester includes a crop processor for reducing crop material to processed crop and an unload conveyor for transferring processed crop out of the agricultural harvester. One or more sensors generate data indicating a fill level of processed crop within a receiving vehicle. A camera generates image data including at least a portion of the receiving vehicle. A controller receives the data from the one or more sensors, determines the fill level of the processed crop in the grain bin of the receiving vehicle, receives the image data from the camera and generates a graphical indicator of the fill level. The graphical indicator includes a graphical depiction of the receiving vehicle from the image data and a graphical marker superimposed over at least a portion of the graphical depiction of the receiving vehicle. A graphical user interface presents the graphical indicator of the fill level to a user.

Abstract: Described herein are technologies that use LIDAR and computer vision to detect a location of a receiving vehicle relative to a forage harvester, fill levels of crop material within the receiving vehicle, and path and landing position of material expelled from the forage harvester and received by a bin of the receiving vehicle. The technologies use such information as feedback for operating the harvester or the receiving vehicle. Some embodiments detect ground level in front of the harvester or the receiving vehicle, and such information is used as feedback too. Some embodiments include a link to communicate the feedback to a GUI for user visualization of the feedback and semi-automated operations of the harvester or the receiving vehicle. For example, readings from LIDAR and a camera of the harvester detect a topography of the material deposited in the bin of the receiving vehicle, and a GUI outputs the topography.

Abstract: Described herein are technologies that use LIDAR and computer vision to detect locations of receiving vehicles grouped together relative to a forage harvester and detect fill levels of crop material within each receiving vehicle and path and landing position of material expelled from the harvester into a bin of a receiving vehicle of the group. Such information is used as feedback for operating the harvester or one or more self-propelled vehicles moving the receiving vehicles. Some embodiments detect ground level in front of the harvester or the receiving vehicles and use such information as feedback. Some embodiments include a link to communicate the feedback to a GUI for user visualization of the feedback and semi-automated operations. For example, readings from LIDAR and a camera of the harvester detect a position and a crop material fill level for each receiving vehicle in the group, and the GUI outputs the information.

Abstract: Systems and methods for mapping the distribution of residue material in an environment in which one or more agricultural machines are operable. A sensing arrangement having one or more sensors mounted or otherwise coupled to an agricultural machine operating within the environment is used to obtain sensor data indicative of residue material spread by a spreader tool of the agricultural machine. From this a local distribution of residue material associated with the spreader tool is determined which is used to update a map of a global distribution of the residue material across the environment. The map comprises a grid-based map having a plurality of cells corresponding to sub-regions within the environment, wherein a value associated with each cell is representative of a measure of the residue material present within the corresponding sub-region.

Abstract: Methods and systems for mapping the distribution of residue material in an environment in which one or more agricultural machines are operable. A sensing arrangement including one or more sensors mounted or otherwise coupled to an agricultural machine operating within the environment is used to obtain sensor data indicative of residue material spread by a spreader tool of the machine. A local distribution of material associated with the spreader tool is determined and used to update a map of a global distribution of the material across the environment. The map of the global distribution comprises one or more sub-regions categorized based on the local distribution dependent on material characteristics at those sub-regions.