128 results about "Crop species" patented technology

The invention relates to the technical field of temperature control, in particular to a temperature control method and system for a crop greenhouse cultivation environment, and the method comprises the following steps: calculating the growth rates of crops under various temperature conditions based on the variety information of greenhouse crops, recognizing ideal temperature ranges of a plurality of growth stages, and calculating the temperature of the greenhouse crops according to the ideal temperature ranges; and a crop temperature management model is constructed by integrating ideal temperature range data of a plurality of stages. According to the invention, through calculation of growth rates of crops under various temperature conditions, identification of temperature requirements of the crops in multiple growth stages, calibration of control parameters of a temperature adjusting device, improvement of adaptability and efficiency of a temperature control system, and analysis of an illumination intensity change trend, prediction of internal temperature of a greenhouse is realized. The temperature regulation meets the actual illumination condition, energy is saved, the growth environment is optimized, it is ensured that the environment in the greenhouse is kept in the optimal state, and the market competitiveness of crops and the economic benefits of agricultural producers are improved.

The invention provides a crop planting strategy optimization method and system under a multi-constraint condition and a cloud platform, and the method comprises the steps: inputting crop data into a constructed improved mixed integer linear programming agricultural model, and taking the maximization of the total planting profit as an objective function; setting a planting area constraint, a yield constraint, a continuous cropping planting limitation constraint, a plot spacing constraint, a rotation value constraint, a land type constraint and a special planting requirement constraint of crop classification; dynamically optimizing the model through an improved genetic algorithm, and iteratively solving a needle planting strategy; crop types in the crop data are classified through a K-means clustering method, and a planting strategy is optimized and adjusted in combination with a loss coefficient of an expected sales volume; a K-S test method and a Spearman correlation coefficient analysis method are used to analyze the relationship among the planting cost, the sales price and the expected sales volume, and the planting strategy is further optimized. The economic benefit of the planting scheme is improved, and the planting efficiency is improved by optimizing resource allocation through centralized planting.

The invention relates to a field water and fertilizer intelligent control method based on the Internet of Things, and the method comprises the steps: carrying out the crop type recognition and growth stage recognition through collecting crop images, soil water and fertilizer data and meteorological prediction data, and generating an initial water and fertilizer control scheme of a current time node; a soil water and fertilizer prediction model is created to predict the soil water and fertilizer change trend in a specified time period, the initial water and fertilizer control scheme of the current time node is adjusted according to the predicted soil water and fertilizer change trend, growth cycle characteristics corresponding to crop types are obtained based on big data, and a dynamic water and fertilizer control scheme is formulated. A water and fertilizer adjusting control scheme is executed at a current time node, a dynamic water and fertilizer control scheme is executed at a specified time node, the field water and fertilizer intelligent control method integrating Internet of Things sensing, intelligent identification, trend prediction, dynamic planning and closed-loop feedback is realized, the whole process intelligence from data acquisition to scheme execution is realized, and the water and fertilizer utilization efficiency is improved. The agricultural production cost is reduced.

The invention provides a credit management method and related equipment based on multi-temporal satellite remote sensing, and the method comprises the steps: determining a to-be-analyzed land parcel in response to a credit management instruction; acquiring a multi-temporal satellite remote sensing image of the land parcel to be analyzed; analyzing the multi-temporal satellite remote sensing image by using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the land parcel to be analyzed; determining crop species of the to-be-analyzed plot according to the NDVI sequence of the to-be-analyzed plot; inputting the NDVI sequence into a pre-constructed yield analysis model to obtain a crop yield prediction result of the crop variety; and carrying out credit granting on the credit granting object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type. By applying the method provided by the embodiment of the invention, the credit can be accurately granted to the customer.

The invention provides an intelligent control method and system for an agricultural planting greenhouse, and relates to the technical field of intelligent control of the greenhouse, and the method comprises the steps: obtaining environment data in the greenhouse at a plurality of moments in a control period through sensors disposed at sampling sites, the environment data comprises temperature data, humidity data and illumination data; obtaining types and crop data of crops planted in the greenhouse; determining a first control discrimination parameter according to the crop type and the illumination data; determining a second control discrimination parameter according to the crop variety and the temperature data; determining a third control discrimination parameter according to the environment data and the crop data; and determining whether to control the greenhouse or not according to the first control discrimination parameter, the second control discrimination parameter and the third control discrimination parameter. According to the invention, the accuracy and effectiveness of intelligent control of the greenhouse can be improved.

The invention belongs to the field of computer vision, and discloses a plant disease identification method and system based on a three-branch deep neural network, and the method comprises the steps: firstly extracting global, local and middle-layer multi-scale positioning features through employing Vision Transformer, ResNet50 and YOLO in parallel; secondly, aligning and fusing the three paths of features, carrying out interactive enhancement through Transform block, and then respectively predicting crop types and disease types through a double-end stacking classifier; and finally, by setting a proper loss function combination and a joint training strategy, performing end-to-end optimization on the whole network, so as to improve the recognition capability of difficult-to-judge samples and small-scale lesions. According to the invention, accurate identification of plant diseases in a natural scene can be realized. Experimental results show that the method provided by the invention obtains classification performance equivalent to or even better than that of the most advanced plant disease identification method in the prior art.

The invention relates to the technical field of agricultural intelligent equipment, and discloses an intelligent pesticide spraying robot and a control system thereof.The robot comprises a movable chassis, a pesticide storage box is fixedly connected to the rear side of the top of the movable chassis, a mounting table is fixedly connected to the top of the movable chassis, and a conveying pesticide spraying mechanism is arranged at the top of the mounting table; a mounting frame is fixedly connected to the top of the mounting table, an adjusting mechanism is arranged on the outer side of the mounting frame, a mounting box is fixedly connected to the front side of the top of the movable chassis, and the mounting table is arranged between the pesticide storage box and the mounting box; the system comprises a data acquisition module, a data processing unit, a pesticide spraying control unit, a navigation control unit, a servo motor control unit and an obstacle avoidance control unit. Cooperative operation of a camera, a laser radar and an ultrasonic sensor in the environment sensing mechanism is matched with a data processing unit of the central control system, so that crop types and growth states can be accurately recognized, and obstacles can be comprehensively detected.

The invention provides an intelligent diagnosis and decision-making method and system for crop diseases in intelligent agriculture, and the method comprises the steps: extracting spatial features through employing a convolutional neural network based on standardized remote sensing image data in a unified multi-source data set, generating preliminary positioning data of a scab region, and carrying out the preliminary positioning of the scab region; the scab area preliminary positioning data comprises scab position coordinates and range boundaries; inputting the key time weighted sequence data and the scab area preliminary positioning data into a space-time attention mechanism, and fusing spatial position coordinates and time environment features through attention weight distribution to generate comprehensive disease feature vector data; and based on the preliminary prevention and control prescription data, adopting a drug resistance evaluation model to analyze the drug use frequency, the disease type and the crop variety in the historical drug use data, generating optimized prevention and control prescription data, and adjusting the drug variety or dosage to reduce the drug resistance risk.

The invention relates to the field of intelligent greenhouse management, and particularly discloses an intelligent greenhouse management system based on computer vision and deep learning, and the system comprises a data collection module which obtains environment data and soil data in a greenhouse in real time; the image acquisition module is used for acquiring crop growth images; the core controller preprocesses the data acquired by the data acquisition module and the image acquisition module and uploads the data to the cloud database; the computer vision and deep learning analysis module is used for identifying crop types and pest and disease damage conditions based on the crop images; the water-fertilizer control unit comprises an intelligent control module, a water-fertilizer all-in-one machine and a drip irrigation system; the user interaction module provides remote monitoring and control functions for a user; according to the system and the method, the condition of economic loss caused by the fact that crop diseases and insect pests cannot be correctly treated due to insufficient experience in traditional agriculture is overcome, environmental visualization is realized, a farmer can conveniently monitor the greenhouse in real time, precise irrigation and fertilization are realized, the agricultural production efficiency is improved, and resource waste is reduced.

The invention provides a rendering display method, a rendering display device, electronic equipment and a storage medium. The rendering display method comprises the steps that area information of a target terrain area on a virtual earth surface is recorded in a Mask channel of a virtual texture RVT during operation, the area information comprises crop type information, and different crop type information corresponds to different combinations of crop types and crop growth states; and in the rendering stage, obtaining the region information from the Mask channel, if the distance between a target terrain region corresponding to the region information and the virtual camera is greater than or equal to a preset distance threshold value, obtaining a first map corresponding to the crop type and the crop growth state based on the crop type information, and generating a crop effect in the target terrain region based on the first map. According to the rendering display method provided by the embodiment of the invention, the rendering performance of real-time updating change of the target terrain area along with the change of the crop growth state is realized on the basis of the RVT during the long-range view.

The invention discloses a self-adaptive power generation optimization control system for a greenhouse photovoltaic ceiling, relates to the technical field of ceiling power generation control, and is used for solving the problem that photosynthetic efficiency and yield are affected due to the fact that crops are in a state of insufficient illumination or excessive illumination in a growth stage. The method comprises the following steps: calculating illumination deviation by combining an illumination demand library and an illumination sensor; judging an illumination level according to deviation and photosynthetic response characteristics; collecting a leaf potential and a transpiration rate to calculate photosynthetic efficiency; comprehensively judging whether to adjust the angle of a photovoltaic panel, outputting an execution instruction, setting different control mechanisms, and executing a balance optimization strategy when the power generation efficiency is high. And when the power generation efficiency is low, an intelligent switching strategy is executed, the productivity is preferentially improved, the crop illumination tolerance is considered, the angle is dynamically adjusted, collaborative optimization of agriculture and energy is realized, and the adaptability and the operation efficiency of the system are improved.

The invention relates to the technical field of environmental data monitoring, and discloses a farmland plot intelligent segmentation and crop distribution big data analysis system and method, and the method comprises the steps: taking the boundary information of a to-be-operated plot as a farmland segmentation layer; generating a planting environment code of a plant species information query condition based on farmland segmentation layer associated plot planting information; collecting a peripheral planting area of the to-be-operated land parcel through a satellite, and analyzing to obtain a crop selection list; querying plant planting indication information corresponding to crop types in a crop selection list in a vegetation science big database through the planting environment codes, and evaluating and analyzing the plant planting indication information and initial planting indication information in the crop selection list to obtain target planting indication information; selecting and adjusting crop types of the to-be-operated land parcels based on the plant planting indication information; on the basis of segmentation and identification results, multi-source data are collected and integrated, correction and denoising processing are carried out, and the accuracy and credibility of analysis are improved.

A crop species identification system based on satellite telemetry data is disclosed, which includes: a receiver module, receiving plural telemetric vegetation indexes of a target area; a data cleaning module, cleaning anomalous data in the telemetric vegetation indices, to correspondingly generate cleaned index data; a feature extraction module, including at least two different convolution kernels for mapping the cleaned index data into at least two feature scale mapping data which respectively correspond to the convolution kernels, performing a pooling operation of the feature scale mapping data to generate a pooled data, and concatenating the at least two feature scale mapping data and the pooled data into concatenated data; and a classification module, including a fully-connected layer, for extracting features of the concatenated data, to generate a species classification result for the target area.

The invention belongs to the technical field of seedling cultivation, and discloses a cadmium telluride power generation glass three-dimensional multilayer seedling raising greenhouse and an illumination regulation and control system. Comprising a layered illumination sensing module which constructs an interlayer illumination distribution map and an interlayer illumination profile map based on the photosynthetically active radiation density of each seedling raising layer; the light-requiring threshold generation module is used for generating a target illumination intensity upper and lower limit curve of each seedling raising layer based on seedling raising crop types, growth stages and environmental parameters; the illumination comprehensive judgment module is used for identifying seedling raising layers with insufficient illumination or excessive illumination based on the interlayer illumination distribution map and a target illumination intensity upper and lower limit curve, and generating a dimming priority sequence in combination with the interlayer illumination profile map; the illumination intelligent control module is used for generating and executing a distributed dimming instruction set by combining the dimming priority sequence based on the output power of the cadmium telluride power generation glass and the consumed power of the seedling raising greenhouse; according to the invention, distributed self-adaptive light supplement is realized in the seedling raising process in the cadmium telluride power generation glass seedling raising greenhouse.

The invention provides an end-cloud collaborative agricultural condition image acquisition system based on 5G communication and machine learning, and relates to the technical field of end-cloud collaboration of 5G communication and machine learning. A data acquisition end is used for acquiring multispectral image data of a farmland to be observed, and compression preprocessing is carried out, so that the data transmission burden is reduced; the compressed image is sent to a data processing module, and the data processing module carries out denoising and feature extraction on the image, constructs a feature data vector and transmits the feature data vector to a cloud server; the cloud server analyzes feature data vectors by using a random forest algorithm model, judges crop types and classifies the crop types, and finally returns an analysis result to the data display module, and the data display module generates an instrument panel by using a Flask framework and visually displays agricultural condition data including key indexes such as crop types and coverage conditions. Data transmission is carried out through 5G communication to realize a terminal-cloud collaborative architecture, and efficient and real-time data transmission and processing are realized.

The invention provides a saline-alkali soil crop multi-water-source irrigation control method and system, and belongs to the technical field of agriculture, and the method comprises the steps: determining an irrigation water salinity target threshold value and a target total irrigation amount according to soil salinity data and crop physiological parameters; determining a water distribution strategy based on the salinity concentration data, wherein the water distribution strategy at least comprises irrigation priorities and collocation of different types of water sources; based on the target irrigation total amount, the irrigation water salinity target threshold value and the water distribution strategy, the target water taking amount of each type of water source is determined; and generating an irrigation control instruction according to the target water intake amount. According to soil salinity, crop types, crop physiological parameters and salinity concentration of multiple water sources, the irrigation water salinity target threshold value and the irrigation water total amount are dynamically and accurately determined; and meanwhile, a priority water distribution strategy is formulated, so that flexible allocation of irrigation among multiple water sources and fine management of the salinity concentration of crop irrigation water can be realized, and soil salinization and crop salinity stress are effectively avoided.

The invention belongs to agricultural machinery, and mainly relates to a detachable movable and fixed cutter stubble-cutting soil-avoiding root-cutting ridge shape repairing device, which comprises a stubble-cleaning device, a root-killing device and a soil-covering device, according to the stubble cleaning device, crop types are recognized in real time through an observation camera, crop type information is provided for a controller, the controller controls a movable cutter shaft and a sliding block to move all movable blades to form a novel combined movable and fixed cutter, the combined split type movable and fixed cutter can adapt to crushing of different crop stubbles, the adaptability and the stubble crushing quality of the stubble cutting cutter are improved, and the stubble cleaning efficiency is improved. According to the root-killing device, root-killing wheels move up and down through a cylindrical cam structure, soil between stubbles is avoided, large-area turning of the soil is avoided, soil moisture can be effectively preserved, the root-killing wheels are designed by imitating spiked clubs, the arrangement mode of the tips of the root-killing wheels is innovated, the root-killing wheels better conform to the distribution condition of corn root systems, high-quality root breaking is achieved, and the root-killing efficiency is improved. The soil covering device drives a soil covering plate to be opened and closed through a gear mechanism, and efficient repairing of the ridge shape of an area after root killing is achieved.

The invention discloses an agricultural insurance claim risk assessment method and system, and the method comprises the steps: obtaining agricultural insurance contract data, extracting key information, such as an insured crop type, a growth cycle and an insurance amount, carrying out the matching of a risk assessment result with the contract information through a natural language processing technology, and automatically calculating the claim risk of each contract; according to the level of the claim settlement risk, performing level-to-level management on the contract, and taking corresponding risk control measures for the high-risk contract, such as adjustment of underwriting conditions, improvement of insurance premium and starting of a manual checking process for the contract with the claim settlement risk exceeding a preset threshold value; obtaining claim settlement case data, adopting a decision tree algorithm, analyzing a relationship between case characteristics and claim settlement results, summarizing a claim settlement law, optimizing a risk assessment model and a claim settlement process, and improving risk prevention and control and claim settlement efficiency.

The application provides a crop disease precision identification method and system, and relates to the technical field of crop disease identification. The method comprises the following steps: establishing standard lesion feature image datasets of different crops and different organs; constructing a background feature database of common crop diseases; forming a crop type and organ identification algorithm model and an organ lesion identification algorithm model; determining the crop type and the organ of the crop in an image to be identified based on the crop type and organ identification algorithm model; determining the disease range of the image to be identified based on the organ of the crop and using the organ lesion identification algorithm model corresponding to the organ of the crop, and outputting a lesion disease with similar features; outputting a matched crop disease type based on the background feature database of common crop diseases; and obtaining a common disease type in the determined lesion disease and the determined crop disease type, so as to realize the precision identification of the disease. The application classifies and grades to form a structured disease identification process, and improves the identification precision.

Soybean, one of the world's most significant protein and oil crops, has been enhanced through genetic engineering and mutagenesis to introduce or enhance agronomic traits. Both transgenic modification and mutagenesis have shown considerable variation in phenotypes observed in crop species. The effects of these methods on soybean seed composition and gene expression were determined by subjecting stable transgenic soybean lines to mutagenesis, generating 100 mutagenized lines with altered GFP expression, which were subsequently analyzed for protein and oil content.

The invention relates to a crop disease identification method based on wavelet transform and residual network fusion. According to the method, a CBAM attention mechanism, wavelet transform and a residual network are fused, and a disease identification model (CropNet) for non-specified crop types is provided. According to the CropNet, firstly, Haar wavelets are utilized to perform four-stage decomposition on disease images, frequency domain features are deeply extracted, and the frequency domain features and spatial features extracted by a residual network are continuously fused; then different weights are given to the fused feature layer by using CBAM, and the attention of the model to a disease area is increased; and finally, a dual transfer learning training model is utilized to improve the accuracy and generalization of the model for identifying diseases of non-specified crop types. The identification accuracy of the CropNetA is 99.76%, the identification accuracy of the CropNetA is 99.85%, and the identification accuracy of the CropNetA is 99.86% on the PlantVillage data set, the identification accuracy of the CropNetA is 99.85% on the AI Challenger 2018 data set and the identification accuracy of the CropNetA on the self-built data set. The result shows that the method can obtain clearer and more sufficient disease characteristics while reducing the noise, improves the disease recognition precision, and provides reference for intelligent agriculture and precise recognition, prevention and control of crop diseases.

The invention discloses a rice field robot cluster remote cooperative control system based on edge computing, and relates to the field of program control, and the system comprises a master control module which serves as a central control end, issues a control instruction to distributed edge nodes, and receives state feedback; the crop identification module is deployed at an edge node and acquires attribute data of crop types, growth stages and distribution density of each region of the target rice field through an image sensor; the environment acquisition module is used for being deployed at an edge node and acquiring rice field meteorological data and soil environment data in real time; the crop growth environment and the machine state are monitored and responded in real time, when an abnormal environment event is detected, crop identification data can be rapidly integrated to generate an influence event and evaluate an influence coefficient, and a nearby automatic machine is immediately matched and scheduled for intervention, so that the timeliness of operation is ensured, crop loss can be effectively prevented, and the working efficiency is improved. And the efficiency of agricultural production is improved.

The application discloses a method for evaluating rice field and dry land crop removal of soil heavy metal flux based on model estimation, relates to the field of agricultural environmental science and technology, and determines the planting mode characteristics and the estimation range of the crop removal of soil heavy metal flux under various planting modes in a target region through a standardized field test, and constructs a standardized crop heavy metal absorption parameter database, wherein the planting modes include single-cropping rice, double-cropping rice, rice-oil rotation, rice-tobacco rotation and leafy dry land crops, and the planting mode characteristics include planting cycles and crop types. Through the construction of the standardized crop heavy metal absorption parameter database, the combination of the planting mode characteristics and the dynamic change data of the heavy metal form of rhizosphere soil, the removal ability of crops to soil heavy metals can be more accurately quantified, meanwhile, the crop heavy metal absorption parameter database integrates the biomass, heavy metal concentration and flux calibration data, eliminates the interference of environmental variation, and forms a reliable heavy metal removal flux estimation range.

The invention relates to the technical field of laser illumination, in particular to a laser diode agricultural illumination system and method based on a combined spectrum, and the system comprises a light source module, an illumination intensity adjustment module, an illumination time control module, a spectrum monitoring module and a feedback adjustment module. According to light quality requirements of leaf vegetables and solanaceous crops in different growth stages, a spectrum combination proportion is determined, a specific wavelength spectrum is supplemented, illumination intensity is dynamically adjusted according to a plant growth state, illumination time is set according to crop types and growth stages, the spectrum is monitored in real time, optimal parameters are compared, and a spectrum combination is adjusted according to deviation. Spectrum, light intensity and illumination time are accurately matched with crop requirements, light energy waste is reduced, it is guaranteed that crops obtain proper illumination conditions in all growth stages, photosynthesis efficiency is promoted to be improved, and efficient and accurate development of agricultural production is promoted.

The disclosure relates to isolated microorganisms—including novel strains of the microorganisms, microbial consortia, and agricultural compositions comprising the same. Furthermore, the disclosure teaches methods of utilizing the described microorganisms, microbial consortia, and agricultural compositions comprising the same, in methods for imparting beneficial properties to target plant species. In particular aspects, the disclosure provides methods of increasing desirable plant traits in agronomically important crop species.

The present disclosure relates to isolated microorganisms, novel strains including microorganisms, microbial consortia, and agricultural compositions comprising the same. In addition, the present disclosure teaches methods of utilizing the microorganisms, microbial consortia, and agricultural compositions comprising the same in methods of conferring beneficial properties to target plant species. In particular aspects, the disclosure provides methods of enhancing desired plant traits in agronomically important crop species.

The invention provides a method for biomimetic directional construction of crop growth-promoting synthetic bacteria and application, and belongs to the technical field of microbial screening. According to the method, optimized microbial communities are naturally selected based on wild sibling species, a species composition feature table is determined through high-throughput sequencing data analysis, core bacteria are calculated, and core bacteria composition feature tables of amplicons and metagenomes are obtained respectively; and then a hybrid correction strategy of a machine learning algorithm is adopted to obtain a high-quality core bacterium composition feature table of the wild related species of the crops, and growth-promoting synthetic bacteria are designed according to the core bacterium composition feature table, so that candidate microorganisms are directionally screened from the wild related species of the crops in a targeted manner, and the growth-promoting synthetic bacteria of the cultivated species of the crops are constructed. According to the method disclosed by the invention, interaction between crop species specificity and synthetic bacteria is considered, the method has the advantages of high efficiency, accuracy, orientation and the like, and construction of crop synthetic bacteria composition is converted from artificial random combination to bionic oriented construction.

A method for identifying plant diseases and their severity based on a multi-label strategy includes: 1. constructing a training set, a validation set, and a test set; 2. building a multi-label classification network; 3. selecting a batch of crop disease images and inputting them into a multi-label feature extraction module. Feature extraction is performed on the crop disease images to obtain features containing disease spatial information. These features are input into an information fusion and communication module for modeling to obtain disease semantic features. The disease semantic features and spatial features are fused through a multi-scale information fusion module and input into a multi-label prediction and decoding module to obtain a multi-label classification result; 4. iteratively training the multi-label classification network; and 5. testing the multi-label classification network. This invention can equally identify crop species, diseases, and severity. The multi-label classification approach combines the advantages of a multi-task network with the low classification complexity of a single-task network and the lack of additional branches.

The invention provides an unsupervised domain adaptive crop variety identification method based on information entropy and a remote sensing device, and relates to the technical field of crop fine segmentation, and the method comprises the steps: constructing an unsupervised domain adaptive crop variety identification network comprising a generator, a main domain discriminator and an auxiliary domain discriminator; the generator obtains spatio-temporal characteristics of the source domain and the target domain based on the four-dimensional time sequence remote sensing images of the source domain and the target domain, predicts a probability graph, and calculates a weighted self-information distribution graph based on information entropy according to the prediction probability graph; sending the weighted self-information distribution map into a main domain discriminator, and sending the spatial-temporal characteristics into an auxiliary domain discriminator to obtain a domain prediction probability result and a domain prediction confidence coefficient; and optimizing the identification network, the main domain discriminator and the auxiliary domain discriminator to realize domain adaptation. According to the method, the information entropy thought and the two domain discriminators are utilized to minimize the difference of inter-domain feature distribution, so that the common representation of the same kind of crops in different domains is more accurately captured and utilized, and the crop variety identification performance under the condition of no label in the target domain is improved.

The invention discloses a crop determination method and system based on combination of a scene recognition model and target detection, and belongs to the technical field of agricultural information, and the method specifically comprises the steps: collecting crop image data, recording time-space information, and carrying out the preprocessing of a crop image; the method comprises the following steps: extracting crop image features, constructing a scene classification model and a target crop detection model, taking a to-be-detected image as input, firstly determining a scene category through the scene classification model, and then loading corresponding target crop detection model optimization parameters for detection; and carrying out weighted fusion on confidence scores of target detection and scene classification, matching with a crop growth cycle model database in combination with spatio-temporal information, and finally determining a crop variety and outputting a result. And the accuracy and efficiency of crop identification are improved.