Abstract: Systems and methods are disclosed herein for detecting impurities of harvested plants in a receptacle of a harvester. In an embodiment, a harvester controller receives, from a camera facing the contents of the receptacle, an image of the contents. The harvester controller applies the image as input to a machine learning model. The harvester controller receives, as output from the machine learning model, an identification of an impurity of the harvested plants. The harvester controller transmits a control signal based on the impurity.

Abstract: A process and a system for creating a visual guide for developing training data for a classification of image, where the training data includes images tagged with labels for the classification of the images. A processor may prompt a user to define a framework for the classification. For an initial set of images within the training data, qualified human classifiers are prompted to locate the images within the framework and to tag the images with labels. The processor determines whether the tagged images have consistent labels, and, if so, the processor adds images to the training data. The processor may add the images by providing a visual guide, the visual guide including tagged images arranged according to their locations within the framework their labels, and prompting human classifiers to tag the additional images with labels for the classification, according to the visual guide.

Abstract: Systems and methods are disclosed herein for creating a visual guide for developing training data for a classification of image, where the training data includes images tagged with labels for the classification of the images. A processor may prompt a user to define a framework for the classification. For an initial set of images within the training data, qualified human classifiers are prompted to locate the images within the framework and to tag the images with labels. The processor determines whether the tagged images have consistent labels, and, if so, the processor adds images to the training data. The processor may add the images by providing a visual guide, the visual guide including tagged images arranged according to their locations within the framework their labels, and prompting human classifiers to tag the additional images with labels for the classification, according to the visual guide.

Abstract: Systems and methods are disclosed herein for optimizing harvester yield. In an embodiment, a controller receives a pre-harvest image from a front-facing camera of a harvester. The controller inputs the pre-harvest image into a model, and receives as output from the model a predicted harvest yield. The controller receives, from an interior camera of the harvester, a post-harvest image including the plants as harvested. The controller inputs the post-harvest image into a second model and receives, as output, an actual harvest yield of the plants as-harvested. The controller determines that the predicted harvest yield does not match the actual harvest yield, and outputs a control signal.

Abstract: A mounting substrate has a patterned metal layer defining a plurality of top metal bond pads for bonding to bottom metal bond pads of LED dies. A solder mask layer is formed over the mounting substrate, where the mask has openings that expose the top metal bond pads and protects metal traces on the substrate. The mask layer is a highly reflective white paint. The exposed top metal bond pads are then wetted with solder. The LED dies' bottom metal bond pads are then soldered to the exposed top metal bond pads, such that the mask layer surrounds each LED die to reflect light. A reflective ring is affixed to the substrate to surround the LED dies. A viscous phosphor material then partially fills the ring and is cured. All downward light by the LED dies and phosphor is reflected upward by the ring and solder mask layer.

Abstract: A process and a system for creating a visual guide for developing training data for a classification of image, where the training data includes images tagged with labels for the classification of the images. A processor may prompt a user to define a framework for the classification. For an initial set of images within the training data, qualified human classifiers are prompted to locate the images within the framework and to tag the images with labels. The processor determines whether the tagged images have consistent labels, and, if so, the processor adds images to the training data. The processor may add the images by providing a visual guide, the visual guide including tagged images arranged according to their locations within the framework their labels, and prompting human classifiers to tag the additional images with labels for the classification, according to the visual guide.

Abstract: Systems and methods are disclosed herein for optimizing harvester yield. In an embodiment, a controller receives a pre-harvest image from a front-facing camera of a harvester. The controller inputs the pre-harvest image into a model, and receives as output from the model a predicted harvest yield. The controller receives, from an interior camera of the harvester, a post-harvest image including the plants as harvested. The controller inputs the post-harvest image into a second model and receives, as output, an actual harvest yield of the plants as-harvested. The controller determines that the predicted harvest yield does not match the actual harvest yield, and outputs a control signal.

Abstract: Systems and methods are disclosed herein for detecting impurities of harvested plants in a receptacle of a harvester. In an embodiment, a harvester controller receives, from a camera facing the contents of the receptacle, an image of the contents. The harvester controller applies the image as input to a machine learning model. The harvester controller receives, as output from the machine learning model, an identification of an impurity of the harvested plants. The harvester controller transmits a control signal based on the impurity.

Abstract: Systems and methods are disclosed herein for creating a visual guide for developing training data for a classification of image, where the training data includes images tagged with labels for the classification of the images. A processor may prompt a user to define a framework for the classification. For an initial set of images within the training data, qualified human classifiers are prompted to locate the images within the framework and to tag the images with labels. The processor determines whether the tagged images have consistent labels, and, if so, the processor adds images to the training data. The processor may add the images by providing a visual guide, the visual guide including tagged images arranged according to their locations within the framework their labels, and prompting human classifiers to tag the additional images with labels for the classification, according to the visual guide.

Abstract: A method for hand gesture based human-machine interaction with an automobile may comprise: automatically starting a first mode of control of the automobile, wherein the first mode is associated with a first set of hand gestures, each hand gesture corresponding to a command for controlling the automobile; determining whether a trigger event has been detected; and in response to determining that the trigger event has been detected, performing control of the automobile in a second mode, wherein the second mode is associated with a second set of hand gestures, each hand gesture corresponding to a command for controlling the automobile, and wherein the first set of hand gestures and the corresponding commands are a subset of the second set of hand gestures and the corresponding commands.

Abstract: A mounting substrate has a patterned metal layer defining a plurality of top metal bond pads for bonding to bottom metal bond pads of LED dies. A solder mask layer is formed over the mounting substrate, where the mask has openings that expose the top metal bond pads and protects metal traces on the substrate. The mask layer is a highly reflective white paint. The exposed top metal bond pads are then wetted with solder. The LED dies' bottom metal bond pads are then soldered to the exposed top metal bond pads, such that the mask layer surrounds each LED die to reflect light. A reflective ring is affixed to the substrate to surround the LED dies. A viscous phosphor material then partially fills the ring and is cured. All downward light by the LED dies and phosphor is reflected upward by the ring and solder mask layer.

Abstract: A mounting substrate (40) has a patterned metal layer defining a plurality of top metal bond pads for bonding to bottom metal bond pads of LED dies. A solder mask layer (52) is formed over the mounting substrate, where the mask has openings that expose the top metal bond pads and protects metal traces on the substrate. The mask layer is a highly reflective white paint. The exposed top metal bond pads are then wetted with solder. The LED dies' bottom metal bond pads are then soldered to the exposed top metal bond pads, such that the mask layer surrounds each LED die to reflect light. A reflective ring (60) is affixed to the substrate to surround the LED dies. A viscous phosphor material (62) then partially fills the ring and is cured. All downward light by the LED dies and phosphor is reflected upward by the ring and solder mask layer.

Abstract: A semiconductor light-emitting device includes a semiconductor structure having a light-emitting region. A surface of the semiconductor structure has flattened peaks.

Abstract: A semiconductor light-emitting device includes a semiconductor structure having a light-emitting region. A surface of the semiconductor structure has flattened peaks.

Abstract: A semiconductor light-emitting device includes a semiconductor structure having a light-emitting region. A surface of the semiconductor structure has flattened peaks.

Abstract: A mounting substrate (40) has a patterned metal layer defining a plurality of top metal bond pads for bonding to bottom metal bond pads of LED dies. A solder mask layer (52) is formed over the mounting substrate, where the mask has openings that expose the top metal bond pads and protects metal traces on the substrate. The mask layer is a highly reflective white paint. The exposed top metal bond pads are then wetted with solder. The LED dies' bottom metal bond pads are then soldered to the exposed top metal bond pads, such that the mask layer surrounds each LED die to reflect light. A reflective ring (60) is affixed to the substrate to surround the LED dies. A viscous phosphor material (62) then partially fills the ring and is cured. All downward light by the LED dies and phosphor is reflected upward by the ring and solder mask layer.

Abstract: A semiconductor light-emitting device includes a semiconductor structure having a light-emitting region. A surface of the semiconductor structure has flattened peaks.

Abstract: A method according to embodiments of the invention includes roughening (FIG. 6) a surface (58) of a semiconductor structure (46-48, FIG. 5). The semiconductor structure includes a light emitting layer (47). The surface (58) is a surface from which light is extracted from the semiconductor structure. After roughening, the roughened surface is treated (FIG. 7) to increase total internal reflection, or absorption at the surface, or to reduce an amount of light extracted from the semiconductor structure through the surface (58).

Abstract: A method according to embodiments of the invention includes roughening (FIG. 6) a surface (58) of a semiconductor structure (46-48, FIG. 5). The semiconductor structure includes a light emitting layer (47). The surface (58) is a surface from which light is extracted from the semiconductor structure. After roughening, the roughened surface is treated (FIG. 7) to increase total internal reflection, or absorption at the surface, or to reduce an amount of light extracted from the semiconductor structure through the surface (58).