Abstract: A sorting device for sorting agricultural products coming from a bulk flow and a corresponding method are described. A sorting device includes an image acquisition unit; an image processing unit configured to identify and analyze each product in the bulk flow; a decision unit configured to determine the products to be separated; a separation unit arranged to separate at least some of the products coming from the bulk flow; and a unit for conveying the agricultural products in the form of bulk flow. The sorting device may further include means for turning over the agricultural products on themselves, mounted in the conveying unit facing the image acquisition unit, and configured to allow an exposure to the image acquisition unit, of the different parts of the conveyed agricultural products.

Abstract: A weeding system for an agricultural weeding vehicle including at least one camera for mounting on an agricultural vehicle to acquire an image of a portion of a field while the agricultural vehicle is moving. The system also includes a spraying unit to be mounted on the agricultural vehicle, a control unit to receive images from the camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent by the spraying unit on the basis of the weed species detection signal. The control unit executes a training-based algorithm based on a set of reference images labeled to indicate the presence or not of at least one weed species in the images.

Abstract: A plant treatment system comprises a spray boom capable of moving over an area to be treated, the boom being provided with a plurality of spray nozzles distributed over the boom and supplied by a spray control device, a set of cameras capable of taking images of an area to be treated, and a digital processing device capable of analyzing the images taken by the camera, identifying plants to be treated, and applying instructions to the spray control device in view of spraying locally, and at times determined depending on the displacement of the boom, a nominal product dose on the plants to be treated. According to the invention, the system further comprises an error detection device capable of providing an error signal to the spray control device in case of an error, the spray control device being configured to apply by means of a plurality of nozzles, in downgraded mode, a generally uniform dose of a product to at least part of the area to be treated. For use in cultivated or non-cultivated spaces.

Abstract: A system for treating plants includes a spray boom provided with a plurality of spray nozzles distributed over the boom and fed by a spray control device, a set of cameras capable of taking images of an area to be treated, and a digital processing device capable of analyzing the images taken by the camera, identifying plants to be treated, and applying instructions to the spray control device in view of spraying at least one product onto plants to be treated, According to the invention, the spray nozzles and the spray control device are configured to apply a generally uniform dose of a product to the area to be treated, independently of the identification of the plants to be treated in the images, and to apply locally a complementary dose of a product to plants to be treated identified by the digital processing device. To be used in particular in agriculture or in the treatment of non-cultivated spaces.

Abstract: A system for treating plants, in particular in agriculture, comprising a spray boom (RP) provided with a plurality of spray nozzles (BPi) supplied by a spray control device, and comprising a set of cameras (CAk) capable of capturing images of an area to be treated, a digital processing device capable of analyzing the images captured by the camera, identifying plants to be treated and applying commands to the spray control device with a view to selectively spraying a product on plants to be treated, each camera (CAk) being capable of capturing images of the crop area.

Abstract: A sorting device for sorting agricultural products coming from a bulk flow and a corresponding method are described. A sorting device includes an image acquisition unit; an image processing unit configured to identify and analyze each product in the bulk flow; a decision unit configured to determine the products to be separated; a separation unit arranged to separate at least some of the products coming from the bulk flow; and a unit for conveying the agricultural products in the form of bulk flow. The sorting device may further include means for turning over the agricultural products on themselves, mounted in the conveying unit facing the image acquisition unit, and configured to allow an exposure to the image acquisition unit, of the different parts of the conveyed agricultural products.

Abstract: A system for treating plants for use in agriculture, comprising a spray boom provided with a plurality of spray nozzles supplied by a spray control device, the apparatus comprising a set of cameras capable of capturing images of a crop area, a digital processing device capable of analyzing the images captured by the camera, identifying plants to be treated and sending commands to the spray control device with a view to selectively spraying a product on plants to be treated, the apparatus also comprising an arrangement for lighting the crop area captured by the cameras. According to the invention, the lighting arrangement comprises a plurality of projectors distributed along the boom and having fields of illumination such that each point of a scene captured by a camera receives light from at least two projectors in at least two different orientations in a plane passing through the point and the projectors in question.

Abstract: A weeding system for a railway weeding vehicle including at least one camera for mounting on a railway vehicle to acquire an image of a portion of a railway track while the railway vehicle is moving. The system also includes a spraying unit to be mounted on the railway vehicle, a control unit to receive images from the camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent on the basis of the weed species detection signal. The control unit executes a training-based algorithm based on a set of reference images labeled to indicate the presence or not of at least one weed species in the images.

Abstract: A weeding system for an agricultural weeding vehicle including at least one camera for mounting on an agricultural vehicle to acquire an image of a portion of a field while the agricultural vehicle is moving. The system also includes a spraying unit to be mounted on the agricultural vehicle, a control unit to receive images from the camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent by the spraying unit on the basis of the weed species detection signal. The control unit executes a training-based algorithm based on a set of reference images labeled to indicate the presence or not of at least one weed species in the images.

Abstract: A control system for agricultural spraying is especially intended to be connected to an agricultural machine comprising a spraying ramp and having at least one spraying nozzle selectively activatable to spray an agricultural product. The system includes a set of cameras (42) suitable for being secured to the spraying ramp to acquire images (51) of the ground (12) on which the agricultural machine moves (10), a measuring system (59) for determining, in real time, distance information between a camera (42) and the ground (12), and a processing unit (44) communicating with the cameras (42) and said measurement system (59), the processing unit (44) being suitable for selectively controlling the spraying nozzles (34).

Abstract: A weeding system for a railway weeding vehicle comprising a camera and a spraying unit with several supply modules, a nozzle and a controller module to receive a weed species detection signal and to command the spraying of chemical agent. The weeding system also comprises a weed species identification unit with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.

Abstract: A weed control system (2) for an agricultural sprayer (1) comprising a camera (3) and a spraying unit (4) with several supply modules, a nozzle (9) and a controller module to receive a weed species detection signal and to control the spraying of chemical agent. The weed control system (2) also comprises a weed species identification unit (5) with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.

Abstract: A weed control system (2) for an agricultural sprayer (1) comprising a camera (3) and a spraying unit (4) with several supply modules, a nozzle (9) and a controller module to receive a weed species detection signal and to control the spraying of chemical agent. The weed control system (2) also comprises a weed species identification unit (5) with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.

Abstract: A control system for agricultural spraying is especially intended to be connected to an agricultural machine comprising a spraying ramp and having at least one spraying nozzle selectively activatable to spray an agricultural product. The system includes a set of cameras (42) suitable for being secured to the spraying ramp to acquire images (51) of the ground (12) on which the agricultural machine moves (10), a measuring system (59) for determining, in real time, distance information between a camera (42) and the ground (12), and a processing unit (44) communicating with the cameras (42) and said measurement system (59), the processing unit (44) being suitable for selectively controlling the spraying nozzles (34).

Abstract: A weeding system for a railway weeding vehicle comprising a camera and a spraying unit with several supply modules, a nozzle and a controller module to receive a weed species detection signal and to command the spraying of chemical agent. The weeding system also comprises a weed species identification unit with a communication module, a memory module and a processing module having several parallel processing cores. Each parallel processing core performs a convolution operation between a sub-matrix constructed from nearby pixels of the image and a predefined kernel stored in the memory module to obtain a feature representation sub-matrix of the pixel values of the image. The processing module computes a probability of presence of a weed species from the feature representation matrix and generates a weed species detection signal.