Abstract: A method and non-transitory computer-readable medium capture an image of bulk grain and apply a feature extractor to the image to determine a feature of the bulk grain in the image. For each of a plurality of different sampling locations in the image, based upon the feature of the bulk grain at the sampling location, a determination is made regarding a classification score for the presence of a classification of material at the sampling location. A quality of the bulk grain of the image is determined based upon an aggregation of the classification scores for the presence of the classification of material at the sampling locations.

Abstract: A computer vision camera unit comprising first and second pairs, of image capture assemblies, both of which have an approximately same orientation to a first axis. The first and second pairs are optically focused to capture first and second fields of view that, at least, overlap each other. Providing the first and second pairs with imager chips of differing light sensitivity permits high dynamic range to be realized. Having the second field of view within the first field of view permits specialization, between the first and second pairs, similar to the roles of peripheral and foveal vision, found in biological stereo vision systems. The image capture assemblies can be organized in a rectangular configuration that implies third and fourth pairs, orthogonal to the first and second pairs. The orthogonal but interlocking nature, of the first and second pairs in relation to the third and fourth pairs, enables an autocalibration technique.

Abstract: A method and system for controlling the quality of harvested grains include capturing, by one or more image sensors, one or more images of material at a sampling location within a grain elevator of the combine harvester. The captured images are defined by a set of image pixels represented by image data and having a classification feature indicative of grain or non-grain material. One or more controllers receive the image data associated with the one or more images captured by the image sensor(s) and select a sample image defined by a subset of image pixels of the set of image pixels. The controller(s) apply a convolutional neural network (CNN) algorithm to the image data of the subset of image pixels of the selected sample image to determine the classification feature. The controller(s) analyze the determined classification feature to adjust an operational parameter of the combine harvester.

Abstract: A grain tailings elevator for a combine harvester includes a an elevator housing having an interior containing a conveyor arrangement configured to transport grain tailings through the elevator housing to a discharge outlet. The elevator housing has a side wall with a window to the interior of the elevator housing. A camera having a camera housing containing an image sensor is mounted to the side wall of the elevator housing over the window with the image sensor in registration with the window. The image sensor is trained on the conveyor arrangement and configured to image the grain tailings transported by the conveyor arrangement through the elevator housing.

Abstract: A computer vision camera unit comprising first and second pairs, of image capture assemblies, both of which have an approximately same orientation to a first axis. The first and second pairs are optically focused to capture first and second fields of view that, at least, overlap each other. Providing the first and second pairs with imager chips of differing light sensitivity permits high dynamic range to be realized. Having the second field of view within the first field of view permits specialization, between the first and second pairs, similar to the roles of peripheral and foveal vision, found in biological stereo vision systems. The image capture assemblies can be organized in a rectangular configuration that implies third and fourth pairs, orthogonal to the first and second pairs. The orthogonal but interlocking nature, of the first and second pairs in relation to the third and fourth pairs, enables an autocalibration technique.

Abstract: The present disclosure relates to a material handling system for manipulating items. The material handling system includes a repositioning system comprising a robotic tool which includes a robotic arm portion and an end effector. The robotic tool is configured to manipulate an item in a first orientation and reorient the item to a second orientation. The material handling system further includes a vision system having one or more sensors positioned within the material handling system. The vision system is configured to generate inputs corresponding to the characteristics of the items. The material handling system may further include a controller executing instructions to cause the material handling system to identify the item in the first orientation, based on the one or more characteristics of the item, initiate, by the repositioning system, picking of the item in the first orientation, and re-orient the item in the second orientation.

Abstract: A system is provided that can include a 3D sensor. The 3D sensor can be configured to detect an area of an elevator on a harvester. The 3D sensor can further be configured to transmit a first signal associated with the area. The system can also include a processing device in communication with the 3D sensor. The system can further include a memory device in which instructions executable by the processing device are stored for causing the processing device to receive the first signal and determine a volume of a material on the elevator based on the first signal.

Abstract: A volume of contents in a container of a work vehicle can be estimates. For example, a system can include a 3D sensor on a work vehicle. The 3D sensor can capture multiple images of contents in a container of the work vehicle. The system can also include a sensor for detecting an angle of the 3D sensor with respect to a position of the container for at least some of the images. A processor device can be in communication with the 3D sensor and the sensor. A memory device can include instructions executable by the processor device for causing the processor device to determine a volume of the contents in the container using the images and the angle.

Abstract: Disclosed herein is a system for evaluating agricultural material which comprises, in one embodiment, a housing having a passage in or through an interior of the housing with an inlet for receiving agricultural material and an outlet for outputting the agricultural material. The system further comprises a wall opening in a wall of the passage. An imaging device having a lens is located inward from a border of the imaging device. The imaging device is pivotally mounted for rotation with respect to a housing such that in a closed state the border of the imaging device rests on, engages or interlocks the wall opening of the housing, and in an open state the border exposes the wall opening and an interior of the housing.

Abstract: A system for creating a near-spherical point cloud of RGBD data includes one or more sensing units for providing depth data, each sensing unit having a stereo pair of sensors fitted with the wide-angle lens from which a one-dimensional line of pixels is read, and one or more lasers for illuminating the single line of pixels, the sensing units mounted on a spinning platform. The spinning platform is mounted on the base having a plurality of cameras mounted therein for providing 360-degree RGB data.

Abstract: An adjustable transfer device for unloading processed crop onto a container of a transport vehicle including a control arrangement with an electronic control unit, among other integrated components. Electronic control unit calculates position of expected point of incidence of crop flow on the container. Further provided is a system that identifies and tracks a target object in image data, which is then used to determine the trajectory of the target. With the trajectory known, the control arrangement can accurately direct the crop flow into the container.

Abstract: Disclosed is a self-guided blossom picker that uses a vision system to identify and locate blossoms or inflorescence growing on a plant. The device is intended to be used on a farm and towed by a tractor, for example, or it can be self-propelled. As the device is moved over the blossom the image data captured by the vision system is sent to a machine vision module, which interprets the data and identifies a location of blossom. A controller uses the location data to command a picker to the proper location. A cutter on the picker is actuated to remove the blossom.

Abstract: First imaging device collects first image data, whereas second imaging device collects second image data of a storage portion. An image processing module identifies a rim of a container in either the first image data or the second image data. The image processing module then overlays an outline of the rim in an image presented on a display to an operator of a transferring vehicle. The image processing module further identifies the fill level of material in a receiving vehicle container and overlays this information in the image presented on the display.

Abstract: An adjustable transfer device for unloading processed crop onto a container of a transport vehicle including a control arrangement with an electronic control unit, among other integrated components. Electronic control unit calculates position of expected point of incidence of crop flow on the container. Further provided is a system that identifies and tracks a target object in image data, which is then used to determine the trajectory of the target. With the trajectory known, the control arrangement can accurately direct the crop flow into the container.

Abstract: An adjustable transfer device for unloading processed crop onto a container of a transport vehicle including a control arrangement with an electronic control unit, among other integrated components. Electronic control unit calculates position of expected point of incidence of crop flow on the container. Further provided is a system that identifies and tracks a target object in image data, which is then used to determine the trajectory of the target. With the trajectory known, the control arrangement can accurately direct the crop flow into the container.

Abstract: An imaging system comprising a panoramic visual image display, an associated directional sound playback device, and an associated motion reproduction device is disclosed. The imaging system conveys visual, sound and motion information related to a particular viewing direction to provide a realistic experience for the viewer. The imaging system can also comprise a panoramic visual image recording device capable of recording panoramic images, an associated directional sound capturing device capable of recording sound, and an associated directional motion capturing device capable of recording motion. Recorded panoramic images, sound and motion can be synchronously recorded to a common time code for simultaneous playback.

Abstract: A method and non-transitory computer-readable medium capture an image of bulk grain and apply a feature extractor to the image to determine a feature of the bulk grain in the image. For each of a plurality of different sampling locations in the image, based upon the feature of the bulk grain at the sampling location, a determination is made regarding a classification score for the presence of a classification of material at the sampling location. A quality of the bulk grain of the image is determined based upon an aggregation of the classification scores for the presence of the classification of material at the sampling locations.

Abstract: The invention disclosed herein describes a supervised autonomy system designed to precisely model, inspect and process the surfaces of complex three-dimensional objects. The current application context for this system is laser coating removal of aircraft, but this invention is suitable for use in a wide variety of applications that require close, precise positioning and maneuvering of an inspection or processing tool over the entire surface of a physical object. For example, this system, in addition to laser coating removal, could also apply new coatings, perform fine-grained or gross inspection tasks, deliver and/or use manufacturing process tools or instruments, and/or verify the results of other manufacturing processes such as but not limited to welding, riveting, or the placement of various surface markings or fixtures.

Abstract: The invention disclosed herein describes a supervised autonomy system designed to precisely model, inspect and process the surfaces of complex three-dimensional objects. The current application context for this system is laser coating removal of aircraft, but this invention is suitable for use in a wide variety of applications that require close, precise positioning and maneuvering of an inspection or processing tool over the entire surface of a physical object. For example, this system, in addition to laser coating removal, could also apply new coatings, perform fine-grained or gross inspection tasks, deliver and/or use manufacturing process tools or instruments, and/or verify the results of other manufacturing processes such as but not limited to welding, riveting, or the placement of various surface markings or fixtures.

Abstract: A method and non-transitory computer-readable medium capture an image of bulk grain and apply a feature extractor to the image to determine a feature of the bulk grain in the image. For each of a plurality of different sampling locations in the image, based upon the feature of the bulk grain at the sampling location, a determination is made regarding a classification score for the presence of a classification of material at the sampling location. A quality of the bulk grain of the image is determined based upon an aggregation of the classification scores for the presence of the classification of material at the sampling locations.