A computer-implemented method, computer program product and computer system (100) for identifying weeds in a crop field using a dual task convolutional neural network (120) having a topology with an intermediate module (121) to execute a classification task being associated with a first loss function (LF1), and with a semantic segmentation module (122) to execute a segmentation task with a second different loss function (LF2). The intermediate module and the segmentation module are being trained together, taking into account the first and second loss functions (LF1, LF2). The system executes a method including receiving a test input (91) comprising an image showing crop plants of a crop species in an agricultural field and showing weed plants of one or more weed species among said crop plants; predicting the presence of one or more weed species (11, 12, 13) which are present in the respective tile; outputting a corresponding intermediate feature map to the segmentation module as output of the classification task; generating a mask for each weed species class as segmentation output of the second task by extracting multiscale features and context information from the intermediate feature map and concatenating the extracted information to perform semantic segmentation; and generating a final image (92) indicating for each pixel if it belongs to a particular weed species, and if so, to which weed species it belongs.

A method includes receiving, by the treatment system, during operation in an agricultural environment, one or more images comprising one or more agricultural objects in the agricultural environment, identifying, in real-time, one or more objects of interest from the one or more agricultural objects by analyzing the one or more images, wherein the analyzing results in a first object being identified as belonging to one or more target objects and a second object being identified as not belonging to the one or more target objects, logging one or more results of the identification of each of the one or more objects of interest and a corresponding treatment decision; and activating the treatment mechanism to treat the one or more target objects.

A multi-spectral optical plant treatment device (10) employs a vegetation scanner (20), an electromagnetic radiator (30) and a plant treatment controller (40) for multi-spectral plant treatment applications. In operation, the plant treatment controller (40) executes a discriminating recognition between unwanted plants and wanted plants, and further executes a systematic herbicide EM radiation emission for damaging a recognized unwanted plant in accordance with a photosynthesis termination and/or a photomorphogenesis termination and/or a systematic fertilizer EM radiation emission enhancing a recognized wanted plant in accordance with a plant protection enhancement and/or a plant flavor enhancement.

The present invention provides a method which exerts excellent control effect in controlling weeds. The method for controlling weeds, which comprises a step of performing a spot treatment of clethodim in a cultivation area of soybean, cotton, sugar beet, rapeseed or sunflower.

The present invention relates to a method (10) to control weeds comprising the steps of: a) acquiring geopositional information of planted crop seeds on an agricultural field and generating a crop seed map, b) acquiring soil elevation data and the corresponding geopositional information of the soil elevation on the agricultural field where the crop seeds have been planted or are being planted at at least two different time points and generating soil surface profile maps of the agricultural field, the soil surface profile maps showing the soil surface profiles at the at least two different time points, c) comparing the soil surface profile maps and the crop seed map to identify differences in the soil elevation profile that are not associated with seed growth of the planted seeds on the agricultural field, d) generating a weed control agent spray map on the basis of the differences in the identified soil elevations on the agricultural field that are not associated with seed growth of the planted crop seeds on the agricultural field.

Systems and methods of restoring a lake including dredging, island creation, water treatment, real estate development, computer modeling of environmental conditions, wave height reduction, sediment removal and encapsulation, bathymetry contouring, littoral zone restoration, plant restoration, and/or fish restoration.

Systems and methods of restoring a lake including dredging, island creation, water treatment, real estate development, computer modeling of environmental conditions, wave height reduction, sediment removal and encapsulation, bathymetry contouring, littoral zone restoration, plant restoration, and/or fish restoration.

A method of real-time plant selection and removal from a plant field including capturing a first image of a first section of the plant field, segmenting the first image into regions indicative of individual plants within the first section, selecting the optimal plants for retention from the first image based on the first image and the previously thinned plant field sections, sending instructions to the plant removal mechanism for removal of the plants corresponding to the unselected regions of the first image from the second section before the machine passes the unselected regions, and repeating the aforementioned steps for a second section of the plant field adjacent the first section in the direction of machine travel.

A method of real-time plant selection and removal from a plant field including capturing a first image of a first section of the plant field, segmenting the first image into regions indicative of individual plants within the first section, selecting the optimal plants for retention from the first image based on the first image and the previously thinned plant field sections, sending instructions to the plant removal mechanism for removal of the plants corresponding to the unselected regions of the first image from the second section before the machine passes the unselected regions, and repeating the aforementioned steps for a second section of the plant field adjacent the first section in the direction of machine travel.

Historical information is accessed that describes a previous state of a field, previous environmental conditions for the field, and previous farming machine actions performed in the field. A tank management model is applied to the historical information to determine expected weed densities within field portions and an amount of treatment fluid required to treat plants within the field. While the farming machine is treating plants in the field, current information describing a current state of the field is accessed. The tank management model is applied to the current information to determine updated weed densities within field portions not yet treated. The farming machine performs a modified plant treatment action based on the updated weed densities and a comparison of a remaining amount of treatment fluid within a tank of the farming machine and an updated amount of treatment fluid for treating plants within field portions not yet treated.