18 results about "Crop mapping" patented technology

This invention discloses a multi-sensor fusion adaptive control method and system for a micro-agricultural box. The method simultaneously collects three types of data: environmental, cultivation medium, and crop images. It utilizes an improved unscented Kalman filter algorithm for multi-source data fusion and multi-parameter coupling calculation, combined with a BP neural network-optimized adaptive PID controller to achieve closed-loop control. The system also includes an image recognition dynamic correction unit and a fault diagnosis and tolerance unit. This invention addresses the pain points of existing micro-planting equipment, such as low control precision, large parameter coupling interference, inability to adapt to the entire growth cycle, and poor reliability for unattended operation. This invention improves temperature and humidity control precision to ±0.5℃ / ±3%RH, reduces pest and disease incidence by more than 95%, and achieves pesticide-free, unmanned adaptive planting, suitable for home and commercial micro-agricultural scenarios.

The present application relates to water and fertilizer management technical field, specifically to a kind of agricultural water and fertilizer management method and system based on cloud platform, including the following steps, utilize sensor to collect crop image and extract chlorophyll and leaf area characteristics, analyze variation rate to determine crop growth process and time sensitivity, construct index type dynamic weight mapping relationship, task resource coupling index is calculated in combination with cloud node load and fertilization data fluctuation, based on index task sequencing and execution time delay deviation compensation, generate water and fertilizer management instruction.In the present application, by fusing multi-dimensional morphological features and environmental load data to construct a dynamic control model, a nonlinear correlation between crop demand and execution weight is established using an exponential function mapping mechanism, precise perception of crop growth demand and adaptive optimization of task execution timing are achieved, the task queue is flexibly adjusted according to the resource coupling state, resource competition conflicts are effectively avoided, and the efficiency of water and fertilizer collaborative management is improved.

This application provides a method and related equipment for greenhouse control command decision-making, belonging to the field of greenhouse automatic control technology. The method includes: performing environmental deviation analysis based on various environmental indicator data within the greenhouse to determine environmental deviation results; the environmental deviation results include the deviation degree of each environmental indicator data; detecting control conflicts based on the environmental deviation results, and, in the presence of control conflicts, identifying the crop growth stage based on greenhouse crop images to obtain the current crop growth stage; querying indicator weights based on the crop growth stage to obtain the control weights of each conflicting indicator; determining the priority indicator score of the conflicting indicator based on the control weight and deviation degree of the conflicting indicator; and making a priority adjustment decision for each conflicting indicator based on the priority indicator score to determine the greenhouse control command. This application can improve the efficiency and effectiveness of greenhouse environmental control.

The present application relates to the field of artificial intelligence technology, which can be applied to the field of financial technology, and discloses a processing method, device and equipment for multi-source data of agricultural insurance underwriting and a medium, comprising: in response to multi-media materials submitted by a user for agricultural insurance underwriting, using multi-modal analysis technology to analyze the multi-media materials to obtain structured text information and crop image visual feature information with unique correlation mapping relationship; taking the correlation mapping relationship as a trigger condition, extracting multi-dimensional feature information through an agricultural insurance scene rule engine; generating a multi-modal prompt field suitable for an agricultural insurance underwriting model according to the multi-dimensional feature information; and through the attention mechanism of the agricultural insurance underwriting model, performing risk correlation reasoning on the multi-dimensional feature information according to the multi-modal prompt field to obtain a risk assessment report for agricultural insurance underwriting. Through the precise adaptation of multi-dimensional feature information and the model, this process realizes multi-dimensional feature cross-linking reasoning, which can effectively mine potential risk correlations behind the data.

This invention discloses a deep learning-based method for generating wide-field crop images, belonging to the field of smart agriculture technology. The method utilizes a mobile platform equipped with multiple high-resolution RGB cameras to simultaneously acquire top-view images of crops after calibration and distortion correction. A dataset is constructed and enhanced based on the acquired images, and a cascaded network of SuperPoint and SuperGlue is built. The former detects key points and generates descriptors, while the latter achieves feature matching through a graph neural network. Intrinsic points are selected using the RANSAC algorithm, the homography matrix is ​​calculated, the images are aligned through perspective transformation, and multi-band fusion is used to eliminate seams, gradually stitching together to generate a wide-field image. This invention solves the problems of limited field of view, severe distortion, and insufficient generalization ability of traditional techniques, providing high-resolution and accurate crop images and reliable data support for crop phenotypic analysis.

We provide the system. [Solution] A means for receiving crop image information, soil information, and weather information, and for preprocessing the information, A means for performing a method to analyze the growth status of agricultural products and environmental assessment based on the aforementioned information, A means for generating harvest dates and work schedules based on the analyzed information, A means of giving work instructions to labor machines and automating agricultural work, A means of matching people from urban areas who wish to start farming with agricultural institutions through collaboration with human resource supply organizations, A means by which users can check agricultural information and receive notifications about agricultural schedules and farming opportunities, A system that includes this.

We provide highly convenient work vehicles. [Solution] The system comprises a machine body, running wheels 2 that support the machine body and steer the machine body's direction of travel along a row of crops, a growth status sensor 39 that captures images of crops located perpendicular to the direction of travel of the machine body to detect the growth status of the crops, and a support device 30 that supports the growth status sensor 39 and is supported by the machine body to move the growth status sensor 39. The movement of the growth status sensor 39 by the support device 30 includes movement in the direction of approaching and moving away from the row of crops, movement along the row of crops, and vertical movement.

This invention relates to the field of smart agriculture technology, providing a granular fertilizer and pesticide application drone system and control method. The granular fertilizer and pesticide application drone system includes: a drone flight platform for providing power and flight support; a positioning module for acquiring the drone's spatial position information; a visual detection module for acquiring crop image information of the target area; a control system for processing the spatial position information and crop image information, generating operational flight paths and application control commands, controlling the drone to fly according to the operational flight path while carrying the granular fertilizer and pesticide application mechanism, and sending control commands to the granular fertilizer and pesticide application mechanism when it approaches the target area; and a granular fertilizer and pesticide application mechanism for releasing the granular fertilizer and pesticide. The granular fertilizer and pesticide application drone system and control method provided by this invention can improve the efficiency and accuracy of granular fertilizer and pesticide application, meeting the needs of refined management.

This application discloses a method for measuring the path spacing between rows of closed-row crops. The method includes the following steps: acquiring crop image information from different perspectives using a first depth camera mounted on the top of the agricultural equipment and two second depth cameras mounted at the two front wheels, wherein the fields of view of the two second depth cameras overlap with those of the first depth camera; extracting the boundary lines between the soil and crops from the two second images from the second depth cameras, thereby determining the corresponding travel path of the front wheels; mapping the starting points of the travel paths in the two second images onto the first image of the first depth camera based on the positional relationship between the second depth cameras and the first depth camera; and calculating the distance between the two starting points mapped to the first depth camera. This method has high measurement accuracy and strong stability, and can be used for path calculation and navigation guidance in inter-row operations during the middle and late stages of crop growth, facilitating timely adjustment of wheel spacing by agricultural equipment based on the measured distance, and enabling flexible and efficient autonomous operation.

This invention discloses a smart agricultural crop growth monitoring method based on image processing, comprising the following steps: S1, acquiring and preprocessing target crop images at a preset frequency to construct a crop image sequence; S2, extracting crop regions to construct a crop region sequence; S3, extracting leaf morphology, color distribution, and texture structure features to generate a crop feature sequence; S4, extracting the spatial coordinates of the crop regions and performing spatial calculations to obtain a growth parameter sequence; S5, constructing a growth state sequence based on the crop feature sequence and the growth parameter sequence; S6, performing two-dimensional empirical mode decomposition and statistical analysis on the growth state sequence to construct a growth trend sequence; S7, classifying the growth trend sequence using a support vector machine to generate crop growth monitoring results. This invention comprehensively utilizes DeepLabV3+ models and other technologies, possessing advantages such as high monitoring accuracy, high automation, and strong environmental adaptability.

A method for analyzing the time-series growth of a crop based on flower cluster analysis and tracking is provided. The method comprises the steps of: acquiring an image of a crop (hereinafter, crop image) captured by a camera; recognizing a predetermined unit object included in the crop from the crop image; clustering the unit object to form a plurality of clusters; reconstructing the plurality of clusters into flower cluster units; and generating linkage information between the unit object and clusters or between the plurality of clusters in each image having different time information.

The invention discloses a crop seedling growth center positioning method and system based on a leaf skeleton. The method comprises the following steps: performing leaf segmentation on a crop image and generating a binary image of a leaf mask; a mask skeleton is extracted, an undirected graph is constructed, a blade main path is determined, and a blade center fitting curve is obtained through parameterization and B spline fitting; extending the curve outwards based on the minimum circumcircle to form an extension line section; obtaining a single plant area through closed operation, and calculating a geometric centroid as a centroid clue; and extracting a convergent point of the extension line section as a convergent clue, performing adaptive selection between the two clues in combination with a stability index, and finally outputting a crop center point coordinate. The system comprises an image acquisition device, a positioning processing device and a visualization device. The method can still realize robust positioning in a complex field environment, and is suitable for precise agricultural operations such as weeding, thinning and the like.

This application provides a method, apparatus, and terminal device for crop yield prediction, applicable to the field of data processing technology. The method includes: generating first-modality crop growth feature information and second-modality crop growth feature information based on first-modality and second-modality crop image information; aligning and classifying the first-modality and second-modality crop growth feature information to obtain crop growth area information; and calculating crop yield prediction information based on crop yield prediction weight information, crop yield prediction offset information, crop yield prediction weight correction step distance information, crop yield prediction offset correction step distance information, and crop growth area information. This application comprehensively captures the spatiotemporal dynamics of crop growth from different observation modalities, eliminates the interference of spatiotemporal differences on prediction, dynamically adjusts prediction parameters to improve crop yield prediction accuracy, and effectively enhances the precision of farmland management and the rationality of resource allocation.

The application discloses a kind of multi-agent collaborative agricultural pest diagnosis method, system, equipment and medium, method includes inputting the picture of crop to be diagnosed, and the initial state of crop picture is initialized;According to the initial state of crop picture to be diagnosed, decision action is output to feature recognition agent, to identify the feature of crop image, and update the history text in initial state according to the feature identified;According to the state of updated crop picture, think again, and output decision action, decision action is feature recognition action or classification action;If output is feature recognition action, then feature recognition agent receives feature recognition action, and further identifies the feature of crop image, and updates the history text in state according to the feature identified;If output is classification action, final category determination is generated by classification agent according to the state of current crop picture.This application can improve the accuracy of image classification.

This application relates to a method, system, device, and medium for cross-domain detection of crop diseases based on contrastive learning. The method enhances crop images in the target domain through style transfer and extracts features. After obtaining object-level features using a student detection network, clustering is performed in the feature space, and sample quality weights are assigned based on distance. Weighted positive and negative sample pairs are constructed based on these weights to calculate the contrastive loss. Simultaneously, high-quality enhanced images are selected, and weighted pseudo-labels are generated using a teacher detection network. Finally, the network parameters are iteratively updated by combining the contrastive loss and the pseudo-label supervision loss, enabling the model to adapt online to the target domain distribution. This significantly improves the robustness and accuracy of disease detection in variable farmland environments and effectively overcomes the domain bias problem.

The application discloses a kind of farmland dynamic monitoring method and system based on unmanned aerial vehicle, it is related to image processing technical field;Crop image is carried out artifact denoising processing and crop overexposure repair processing to obtain original crop image;Original crop image is substituted into preset weed crop segmentation model to obtain target crop image;Target crop image is substituted into focus recognition model to obtain focus type and focus position;Based on preset monitoring period, crop image is collected again to analyze, the focus data obtained by twice monitoring is associated and matched, and the growth state of crop is determined;After artifact denoising and overexposure repair of unmanned aerial vehicle collected image, the preset weed crop segmentation model can accurately distinguish crops and weeds, improve the purity of target crop extraction, and then the focus recognition model is used to accurately determine the type and position of the focus.Combined with the associated matching of multi-cycle monitoring data, the growth state of crops can be dynamically and comprehensively mastered, and the accuracy and efficiency of farmland monitoring are improved.

The application relates to the technical field of agricultural pest identification, and provides an agricultural pest pattern recognition method and system based on computer vision, which comprises the following steps: receiving a crop image of a crop to be diagnosed in a field, performing preliminary diagnosis on the crop image, obtaining a preliminary diagnosis result and identifying key visual features supporting the preliminary diagnosis; generating a candidate set of similar diseases according to the preliminary diagnosis result; performing counterexample comparison analysis on each disease in the candidate set of similar diseases, obtaining excluded similar diseases and generating exclusion reasons of the excluded similar diseases; providing and displaying a typical case reference picture of the preliminary diagnosis result and the excluded similar diseases for an agronomist; integrating the preliminary diagnosis result, the key visual features, the exclusion reasons and the typical case reference picture, generating a structured diagnosis report and outputting the same, so as to realize agricultural pest pattern recognition. The application has the effects of improving the accuracy and practicability of agricultural pest pattern recognition.