52 results about "Soil map" patented technology

The invention relates to the technical field of remote sensing monitoring equipment, and discloses tropical agricultural ecology remote sensing monitoring equipment which comprises an unmanned aerial vehicle platform, a remote sensing unmanned aerial vehicle is arranged on the unmanned aerial vehicle platform, and a monitoring sensor assembly is loaded on the remote sensing unmanned aerial vehicle. The monitoring sensor assembly comprises a high-resolution camera device, a hyperspectral sensor, a thermal infrared sensor and a laser radar, a data receiving module, a data processing module and a display module are arranged in the unmanned aerial vehicle platform, and the monitoring sensor assembly is mainly used for obtaining soil images and data information. The data processing module can judge soil ecological information according to images and data, and the monitoring sensor assembly and the data processing module are matched to obtain the erosion degree and fertility condition of soil in the planting area, the moisture content, the soil type, the moisture evaporation condition and the slope and direction information of the soil. The growth state of plants in a planting area and the ecological environment of soil are monitored, and producers are better assisted in formulating targeted agricultural management measures.

According to the agriculture-like cultivated land and land humidity monitoring robot and the monitoring method, structurally, a soil turning device, a soil extraction device and a driving wheel device are connected with a driving motor, the driving motor, a camera device and the soil extraction device are in signal connection with a remote control terminal, and the soil turning device is arranged in a front-back telescopic and up-down movable mode relative to a machine body; the soil extraction device is movably arranged up and down relative to the machine body, the camera device is rotationally arranged relative to the machine body and used for monitoring the movement of the robot in real time, and by optimizing robot hardware configuration and sensor layout and integrating multiple sensors and a core control unit, comprehensive and accurate collection of farmland soil key parameters is achieved. And a wireless data transmission and cloud storage system is deployed to ensure real-time and accurate transmission and analysis of data. Artificial intelligence and computer vision technologies are integrated, soil images are processed, features are extracted and classified, and accurate evaluation and prediction of soil quality are achieved.

The invention relates to the technical field of soil image processing, in particular to a vegetation detection method and system for soil environment restoration. According to the method, color features and position distribution features of pixel points are analyzed, a vegetation coverage factor of each superpixel block is obtained, and vegetation coverage blocks are screened out; according to the position distribution of the pixel points in each vegetation coverage block and the chromaticity fluctuation characteristics, the artificial cultivation characteristic degree of each vegetation coverage block is obtained; according to the centroid position and the vegetation coverage factor of each superpixel block, obtaining a vegetation coverage class cluster and a non-vegetation coverage class cluster; and in combination with the relative position between each vegetation coverage block in each non-vegetation coverage class cluster and each vegetation coverage block in the adjacent vegetation coverage class cluster, obtaining the soil remediation vegetation significance of each super-pixel block, and further obtaining the soil remediation weighted significance of each super-pixel block. According to the method, the vegetation characteristics in the soil environment restoration process are accurately analyzed, so that the accuracy of soil environment restoration assessment is improved.

The invention provides a soil image soil type identification method based on multi-scale feature fusion, and the method comprises the steps: S1, obtaining a sample soil image, and carrying out the preprocessing of the sample soil image; s2, constructing an MAFL-SoilMobileNet model based on multi-scale feature fusion and a multi-scale dilatation attention mechanism, and inputting the sample image into the MAFL-SoilMobileNet model for training; s3, acquiring a soil image to be identified, preprocessing the soil image to be identified, and inputting the soil image to be identified into the trained MAFL-SoilMobileNet model to obtain a soil type identification result; according to the method, the key features of soil type identification in the soil image can be extracted, the distinction degree of the soil type identification features is enhanced, dynamic attention to a small number of soil type samples can be improved, and the discriminative feature information learning ability of an identification model can be improved.

Methods and systems provided for generating a soil data map. One example method includes instructing, by a computing device, a user to draw a field boundary in a map of a geographic area and receiving an input, from the user, at the map of the geographic area, where the input includes multiple vertices of the field boundary. The method also includes appending, by the computing device, a shape of the field boundary to the map, based on the multiple vertices, and overlaying at least one management zone within the field boundary on the map. The at least one management zone is associated with specific soil data for the geographic area corresponding to the at least one management zone within the field boundary.

The invention discloses a soil moisture content calculation method and device and a medium, and relates to the technical field of air-shrinkage cracked soil moisture content detection.The method comprises the steps that an air-shrinkage cracked soil image is obtained; the air shrinkage cracked soil image is input into a preset crack segmentation model, a crack area of the air shrinkage cracked soil image is obtained, and the preset crack segmentation model is a trained deep learning network; based on the crack region of the air-shrinkage cracked soil image, calculating the crack area density in the air-shrinkage cracked soil image; and based on a preset area density-water content correlation model, calculating the water content corresponding to the air shrinkage cracked soil image according to the crack area density. According to the method, the moisture content of the surface soil can be efficiently and accurately obtained on the premise that the original state of the soil is prevented from being damaged.

An intelligent irrigation control system that includes: • a plurality of soil moisture sensors (101) configured to monitor the volumetric water content of the soil in real time; • a camera module (102) configured to capture periodic images of the ground surface; • a microcontroller (103) operatively connected to the soil moisture sensors and the camera module, the microcontroller being programmed to: (i) receive and analyze sensor data; (ii) apply image processing algorithms to detect visual indicators of soil dryness; (iii) compare the sensor data with the results of the image analysis; and (iv) activate a relay module (104) to control a water pump for irrigation only when both the sensor data and the image analysis confirm soil dryness; and • a wireless communications module (105) configured to transmit data to a remote interface (106) for user access and control; wherein the system performs automated, image-guided irrigation to optimize water use and crop health.

The invention provides a rotary cultivator crushed soil quality detection system and method based on an image technology, and the method comprises the steps: obtaining and preprocessing a soil image in the working process of a rotary cultivator, the soil image being a multi-channel color image; extracting a soil feature region from the preprocessed soil image through an image segmentation technology; constructing a regularization model of soil quality evaluation based on the texture information of the soil feature region, and constructing a minimization problem of the soil quality evaluation according to the regularization model; calculating parameters of soil quality evaluation based on a minimization problem, wherein the parameters comprise indexes such as soil particle size distribution and soil humidity; and according to the calculated soil quality evaluation parameters, evaluating the crushed soil quality of the rotary cultivator to obtain a final crushed soil quality evaluation result. According to the method, key indexes such as soil particle size distribution and humidity can be rapidly and accurately evaluated, and the efficiency of agricultural mechanized operation and the quality of soil cultivation are improved.

The invention discloses a soil data rapid extraction, integration and cartographic updating method and system based on a knowledge-enhanced large language model, and the method comprises the steps: carrying out the textualization processing of soil survey data and the construction of a knowledge base, obtaining background knowledge assisting the large language model in soil data extraction through RAG retrieval, and fusing the background knowledge with an input literature text; constructing an optimized soil data extraction prompt by utilizing a thinking chain prompt method, and accurately and quickly extracting soil data in literatures; cleaning and treating the extracted heterogeneous soil data to form standard and unified structured soil data, and integrating the structured soil data with historical soil data; and coupling environmental factor data influencing the soil, and drawing and updating the region by using an empirical Bayesian Criging regression method. The method can replace manual work to extract the soil data in the literature, and complete the cleaning and integration of the extracted data and the updating of the regional soil map, thereby greatly improving the efficiency of public source soil data acquisition and map updating.

Methods and systems provided for generating an irrigation map. In one computer-implemented method, a user is instructed, by a computing device, to draw an irrigation boundary in a map of an agricultural field. In response, the computing device receives a first input, from the user, at the map of the agricultural field displayed to the user, where the input includes a point of the irrigation boundary. A second input is solicited from the user and, in turn, the computing device receives the second input, which defines a dimension of the irrigation boundary. The computing device then appends a shape of the irrigation boundary to the map, based on the point and the dimension, wherein the irrigation boundary is positioned based on the point indicated by the user.

The invention relates to the technical field of intelligent irrigation, and discloses an intelligent irrigation system for a fruit tree planting greenhouse. The system comprises a multi-dimensional data acquisition module, a data fusion processing module, an irrigation decision module and an irrigation control execution module which are connected in sequence. The system obtains a root soil image, a leaf surface temperature distribution map and stem micro-deformation data, and performs multi-dimensional fusion calculation to generate a spatial water potential distribution map capable of representing the overall moisture condition of crops. And calculating specific regional water demand and preferential irrigation sites based on the map, and further driving an execution terminal to realize precise irrigation. According to the method, the physiological water demand signal of the crop can be responded, the spatial difference of water stress can be identified, the limitation that the traditional technology depends on single soil information is overcome, the crossing from environment monitoring to crop body sensing is realized, and the irrigation accuracy and the water resource utilization efficiency are improved.

The invention relates to the technical field of machine vision, and discloses a road defect evaluation system and method based on machine vision, and the method comprises the steps: collecting road surface pictures and road surface gradient data, analyzing road surface defects based on the road surface pictures and the road surface gradient data, collecting slope soil data and vegetation pictures, and evaluating the road surface defects. The method comprises the steps of analyzing soil loosening based on a soil picture, analyzing a vegetation disease risk based on a vegetation picture, analyzing a slope risk based on the soil loosening and the vegetation disease risk, collecting future weather data, predicting the influence of weather on a landslide based on the weather data and the slope risk, and collecting historical traffic flow data in the same period. The influence of traffic flow on landslide is predicted based on the traffic flow data and the slope risk, the safety of the road under the influence of the landslide is predicted by integrating the influence of weather on the landslide, the influence of the traffic flow on the landslide and pavement defects, and whether the road needs traffic restriction is analyzed based on the safety of the road, so that the accuracy of road risk prediction is improved, and the traffic safety is guaranteed.

The invention belongs to the technical field of soil prediction mapping. The invention provides a soil type map updating method fusing a soil voluntary and soil map data. According to the embodiment of the invention, by constructing the soil-environment text information model, the unstructured soil voluntary and the soil map vector polygon are uniformly converted into the sample point data set. Obtaining a partition clustering number based on a soil-environment text information model, and obtaining a class cluster corresponding to an environment factor combination in each parent material partition by adopting partition clustering analysis; based on the environment factor information of the environment factor combination class clusters and the quantified environment factor information in the soil-environment text information model, calculating the similarity between the environment factor combination and the text information framework, and further determining the soil type semantic information of each environment factor combination class cluster; and a representative point set corresponding to each soil type is screened out from each environment combination class cluster, and a quantitative soil-environment relationship is obtained by adopting a kernel density estimation method.

The invention discloses a soil remediation monitoring method and system, and the method comprises the steps: inputting a historical soil image and a real-time soil image into a pre-constructed image recognition model, and judging whether at least one pixel point in the real-time soil image is the same as a pixel point at a corresponding position in the historical soil image or not according to the image recognition model, if at least one pixel point in the real-time soil image is the same as a pixel point at a corresponding position in the historical soil image, marking the at least one pixel point in the real-time soil image as an abnormal pixel point, and clustering at least two adjacent abnormal pixel points to obtain at least one abnormal region, and correcting at least one risk area in the real-time soil image based on a preset correction strategy to obtain a real-time pollution area map at the current acquisition moment. The precision of determining the soil remediation range can be improved while the soil data acquisition amount is reduced.

The invention discloses a farming agricultural machine operation quality detection method and system based on an unmanned aerial vehicle, and the method comprises the steps: obtaining a first farmland soil image before operation and a second farmland soil image after operation, recognizing the displacement deviation of a farmland calibration region through the comparison of the images, and determining the displacement deviation as an operation fluctuation deviation, and determining a to-be-detected area in the tillage area, outputting a soil attribute based on a soil density difference value between the to-be-detected area and the reference area, and performing comprehensive scoring by combining a fluctuation stability index output based on the operation fluctuation deviation and a land parcel analysis index output based on the soil attribute of the to-be-detected area so as to output an operation quality grade. According to the method, the two-dimensional evaluation system of the operation fluctuation stability and the cultivated soil form is established, so that the dynamic monitoring of the operation process and the quantitative analysis of the cultivation effect are realized, the one-sidedness of single-dimensional evaluation is overcome, and the output operation quality grade is more comprehensive, objective and accurate.

The present invention discloses a method for segmenting biological pores in soil CT images, including: performing CT scanning on soil samples and performing image preprocessing; using the "Purify" plug-in in the Fiji software to obtain the maximum pore network and isolated pores of each preprocessed image, respectively, and segmenting the coarse biological pores from the maximum pore network and the isolated pores respectively; using Tubeness to detect fine biological pores in isolated pores; separating fine biological pores; superimposing coarse biological pores and fine biological pores together, and naming them as biological pores; calculating biological pore-related characteristic parameters. The present invention combines the Fiji software, the distance transform watershed algorithm and the Tubeness filter, and combines the advantages of multiple image processing algorithms to accurately segment coarse biological pores and fine biological pores, solving the problem in the prior art that biological pores are difficult to accurately segment because they are connected to non-biological pores such as cracks with complex and diverse morphologies.

The invention discloses a soil micro-plastic recognition and detection method and system based on image recognition, and belongs to the technical field of micro-plastic detection.The method specifically comprises the steps that micro-plastic and water are mixed to prepare a pure soil sample, the soil image, the pH value and the soil ventilation capacity of the soil sample are sequentially collected, and then the volume weight of the soil sample is obtained; converting the soil image into an HSV image, extracting soil image features, inputting the soil image features and corresponding volume weight data into an SVR model for training, and constructing a prediction model; constructing a micro-plastic identification model based on the soil bulk density, the soil throughput, the pH value and the corresponding micro-plastic quantity; a contaminated soil sample is collected and shot, the corresponding soil bulk density is output based on the SVR model, the corresponding soil bulk density, the contaminated soil ventilation capacity and the pH value are input into the micro-plastic recognition model together, and the corresponding micro-plastic quantity is output; the microplastic in the soil can be quickly and accurately identified and detected, and powerful technical support is provided for environmental protection.

The present invention discloses a spinach sowing positioning method and system based on image data analysis, which relates to the technical field of spinach sowing positioning. The method comprises the following steps: obtaining a soil image, determining a screenshot size according to an actual area, and intercepting a plurality of image blocks for analysis; analyzing the soil color and texture characteristics of each block, and calculating an average value to construct a soil comprehensive characteristic expression model; adjusting model parameters to obtain a soil comprehensive characteristic expression model for comparison and a corresponding sowing interval; classifying the models, establishing a reference expression model set, analyzing and determining marker factor parameters of characteristic factors, and constructing a reference expression model library; analyzing a currently captured soil image, constructing a current soil comprehensive characteristic expression model, and determining a comparison model with the highest degree of fit by comparing it with models in the reference expression model library, thereby accurately determining the position of spinach sowing. The technical solution of the present invention improves the accuracy and efficiency of sowing, and provides strong support for intelligent agriculture.

To promote the automation of paddy rice cultivation.SOLUTION: An information processing device includes first acquisition means for acquiring a soil image obtained by imaging soil of a paddy field, second acquisition means for acquiring an inference result indicating a degree of partial drying of the soil of the paddy field by causing inference means to perform inference based on the soil image, and execution means for executing control processing related to management of the paddy field based on the inference result.SELECTED DRAWING: Figure 6

The invention belongs to the technical field of intelligent control, and provides a bionic subsoiler control method based on intelligent driving, a terminal and a storage medium, and the method comprises the steps: firstly obtaining a soil image of a target area, motion parameters of a subsoiler, positioning information and a target path; determining a first parameter according to the soil image and the motion parameter; the first parameter represents a jitter parameter caused by soil stress when the subsoiler works; performing offset correction on the soil image according to the first parameter; determining motion control information of the subsoiler according to the corrected target image and the positioning information; and finally, according to the motion control information, controlling the subsoiler to work along the target path. According to the invention, the shot soil image is corrected by considering the shake of the subsoiler in the operation process, real-time monitoring and intelligent adjustment can be carried out in the operation process of the subsoiler, and the operation efficiency is improved.

The invention provides a surface soil type identification method based on MCP-ShuffleNet V2, and the method comprises the following steps: S1, obtaining a sample soil image, and carrying out the preprocessing of the sample soil image, and then forming a training data set; s2, constructing an MCP-ShuffleNet V2 prediction model, and inputting the training data set into the MCP-ShuffleNet V2 prediction model to carry out training; and S3, obtaining a to-be-detected soil image, preprocessing the to-be-detected soil image, and inputting the preprocessed to-be-detected soil image into the trained MCP-ShuffleNet V2 prediction model to obtain a soil classification result of the to-be-detected soil image, so that interference of non-soil elements in the soil image can be effectively inhibited, a neural network is guided to focus on a key soil area, a continuous and derivable MELU activation function is provided, and the accuracy of the soil classification result is improved. And the gradient disappearance problem is effectively avoided, so that the final soil type identification precision is effectively ensured.

Present disclosure discloses determining soiling maps based on soiling loss of photovoltaic panels (PV). Receive sensor data associated with accumulation of plurality of particles on PV panels and environmental data. Sensor data is received for each time interval of a plurality of predefined time intervals. Sensor data includes particle data associated with plurality of particles, tilt angle data, and orientation data. Determine deposition rate data associated with the accumulation of plurality of particles on PV panel based on sensor data and the environmental data. Determine soiling loss data associated with PV panel based on deposition rate data. Determine correlation coefficient data based on deposition rate data and soiling loss data. Correlation coefficient data indicates one or more correlation coefficients between corresponding soiling loss and observational data. Generate one or more soiling maps associated with PV panel based on correlation coefficient data. Output one or more for PV panels.

The application provides a soil species identification method based on residual graph convolution, which comprises the following steps: mapping a sample soil image from an RGB color space to a Lab color space, removing a brightness component L in the Lab color space, and forming first input information by combining components of three color channels of the RGB color space of the sample soil image with a component a and a component b of the Lab color space; converting the sample soil image into a gray-scale image and forming second input information from the gray-scale image; constructing a soil species identification model, wherein the soil species identification model comprises a PH color channel correlation enhancement module, a multi-scale edge space self-adaptive enhancement module, an average pooling layer, a soil layer graph convolution module and a priori layer level guiding module; inputting first input information and second input information of a soil sample to be tested, soil genus-soil species layer level label word embedding features and a soil genus-soil species layer level relationship adjacency matrix into the soil species identification model which has been trained to obtain a soil species of the soil sample to be tested.

The invention is related to a system that can analyze the condition of the soil using image processing and artificial intelligence algorithms and displays the mineral values that trees take from the soil and its characterized by; at least one infrared camera (3) that takes soil images, database (2) where the collected data is recorded, a analysis application (5), which analyzes data collected from infrared cameras (3) and compares it with previous data stored in the database (2), at least one processor (1) containing the artificial intelligence algorithm (6) and an artificial intelligence algorithm (6) to report the soil condition with the help of the collected data.

The invention provides a soil image recognition method based on a multi-color channel and PH channel attention mechanism, and the method comprises the steps: S1, obtaining a sample soil image, and determining the PH value of the sample soil; s2, respectively mapping the sample soil image to an LAB color space, an HSL color space, an HSV color space and a YUV color space from an RGB color space, and removing brightness components in the LAB color space, the HSL color space, the HSV color space and the YUV color space to form first input information; s3, determining a correlation coefficient between each sub-graph and the soil PH value under the RGB three color channels; the PH value, the correlation coefficient and the subgraph of the sample soil image form second input information; s4, constructing a soil image classification prediction model; S5, inputting the first input information and the second input information into the soil image classification prediction model, and training the soil image classification prediction model; and S6, obtaining an image of to-be-detected soil, determining first input information and second input information of the to-be-detected soil image through the steps S1 to S3, and inputting the first input information and the second input information into the trained soil image classification prediction model to obtain a final soil classification result.

This invention discloses a multi-parameter statistical matching rhizosphere soil microfluidic chip device and its construction method, belonging to the field of soil microfluidics and porous media visualization technology. The device includes a glass slide, a PDMS chip layer, a fluid inlet, an outlet, a branch-shaped flow distribution zone, a buffer zone, and a soil pore simulation zone, forming a heterogeneous pore network within the simulation zone. Based on real rhizosphere soil CT images, the method extracts pore diameter, pore throat width, porosity, tortuosity, and Euler number. A network skeleton is generated using a random seed lattice and polygon segmentation, combined with probability density sampling and iterative optimization, to match the chip to real soil in terms of pore / throat size distribution, porosity, tortuosity, and connectivity. Results show that the KS distances for pore diameter and pore throat width distributions are 0.0142 and 0.0010, respectively, and the porosity is approximately 0.15. This provides a visualization platform for studying gas migration and micro-seepage in rhizosphere soil.

A computer-implemented method is provided for facilitating agricultural operations in an agricultural field. In one example embodiment, the method includes identifying, based on spatial sampling of soil spectrum data for an agricultural field, ground sampling locations within the field to obtain physical soil samples representative of soil makeup for the field. The method also includes generating a soil model particular to the field by correlating soil properties for soil included in the soil samples obtained from the identified ground sampling locations to particular soil spectral bands included in the soil spectrum data for the field at the corresponding ground sampling locations. The method then further includes compiling, using the soil model, a soil map of the entire field visually illustrating particular seeds and / or populations of seeds to plant at different locations across the field and / or particular nutrient applications to apply at different locations across the field.

The subject of the invention is an arrangement for improving the input of substances in field plant cultivation comprising crops (16) and a geospatial information unit (5), the input side (5a) of the geospatial information unit (5) is connected to a soil scanner (1), an image transmitting satellite (2), and a soil probe (3) serving as a data source (20), its output side (5b) is connected to the testing unit (8), a soil map database (6) and a sampling unit (7) is connected to the testing unit (8). It is characterized in that the testing unit (8) is connected to a data processing unit (17), the data processing unit (17) has a signal transmission connection with a local control unit (10) through an improved zone map (9), the local control unit (10) is connected to an executing unit (18), a harvesting unit (14), and a feedback geospatial information unit (19).

The invention relates to a method for generating a semantically segmented ground map of at least part of a ground in an environment, on which ground in particular a mobile device, in particular a cleaning robot, moves or is intended to move, comprising: providing (204) one or more environmental images (202), each of which is or has been captured by a camera; performing (210) a semantic segmentation for the one or each of the plurality of environmental images (202), each for at least a part of the environmental image that includes at least a part of the ground, in order to obtain one or more semantically segmented intermediate images (212); determining, for the one or each of the plurality of intermediate images, one or more ground image regions based on calibration parameters (222) of the respective camera and based on intersection points at which straight lines originating from the camera intersect a plane corresponding to the ground;Determining (240) the semantically segmented soil map (242) based on the soil image areas; and providing (250) the semantically segmented soil map.

The present application relates to the field of solid waste treatment, and discloses a comprehensive treatment method for rural residual garbage, comprising: arranging sampling points in the area covered by the residual garbage to obtain soil samples of different depths, collecting garbage samples in the area covered by the residual garbage to obtain garbage samples; detecting and analyzing the soil data and the garbage samples to obtain the soil pollution degree level; collecting the utilization status map, the topographic map and the soil map of the area covered by the residual garbage and superimposing them, and dividing the superimposed area into multiple sub-regions; extracting the feature information of each sub-region, grouping the multiple sub-regions into multiple sub-region groups according to the feature information, and obtaining the multiple sub-region groups; for each sub-region group, generating the corresponding treatment mode according to the soil pollution degree level, the soil characteristics and the topographic information. The residual garbage is comprehensively treated according to the corresponding treatment mode. Thus, the garbage plot treatment with pertinence is realized.