31 results about "Field corn" patented technology

The invention discloses a method for accurately identifying sweet-waxy corn germplasm, and particularly relates to a method for identifying sweet-waxy corn germplasm, which comprises a first tracking process: a process from F3-generation seed budding to F4-generation seed maturation, including sweet-waxy gene DNA tracking marking after seed budding; sampling once 28 days after pollination, and measuring the thickness of soluble sugar, amylose, amylopectin and pericarp; extracting DNA (deoxyribonucleic acid) and RNA (ribonucleic acid) of F3-generation plants in a After the F4-generation seeds are mature and picked, determining sweet-waxy gene DNA, determining amylose and amylopectin, and determining single-plant grain weight, hundred-grain weight and endosperm / embryo dry weight; a second tracking process: a process from germination of the F4-generation seeds to bearing of fresh sweet-waxy corn, including observation and recording of a field corn plant growth process; measuring the thickness of soluble sugar, amylopectin, amylose and pericarp 15 days after pollination; determining and analyzing the traits of the indoor test species; data analysis and germplasm scoring: comparing and analyzing the data obtained in the second tracking process, scoring the F4-generation seeds, and determining the germplasm quality of the F4-generation seeds.

The invention relates to the field of intelligent identification, and more specifically relates to a three-dimensional phenotype segmentation and labeling system for field corn crops, comprising: an initialization module for executing opening, loading and preprocessing tasks of field corn point cloud data files; the ground segmentation module is used for executing an automatic segmentation task of the corn plant population and the ground; the single plant identification module is used for executing a task of accurately segmenting single plants in the plant population and generating identification information; the skeleton classification module is used for executing skeleton calculation and data point category division tasks of the single-plant corn point cloud; the organ labeling module is used for executing stem and leaf organ structure division and labeling tasks of the single-plant corn point cloud; and the result interaction module is used for executing visualization of output data of the key steps of the modules and storage tasks of projection, segmentation, labeling and classification result data output by the modules.

The invention belongs to the technical field of three-dimensional measurement data processing, and particularly relates to a corn seedling stage community plant distribution and characteristic parameter extraction method based on point clouds, which comprises the following steps: segmenting a field corn seedling plant community point cloud to obtain a point cloud cluster of a stem part; clustering the projection points of the point cloud cluster of the stalk part on the XY plane based on DBSCAN; adopting a DBSCAN clustering result to initialize K-means clustering, and obtaining a plant distribution diagram; on the basis of the plant distribution diagram, data information between rows and columns is calculated through a threshold value method, and the data information between rows and columns comprises the number of plants, the number of rows and columns and data between rows and columns; based on the plant distribution diagram and the data information between rows and columns, the positions of seedling missing points are judged through a threshold value method; and calculating the plant height based on the distribution map and the dynamic fluctuation of the ground points. The functions of precise detection, plant counting, row-plant spacing measurement and missing seedling detection of densely distributed seedling-stage corn plants are realized, and particularly, the extraction of point cloud data of serious leaf staggering under the condition of dense planting is realized.

The invention relates to a field corn row detection method, device and equipment based on line Anchor and a medium, and the method comprises the steps: carrying out the multi-head self-attention operation of a horizontal compression matrix and a vertical compression matrix, so as to generate a first feature matrix and a second feature matrix, performing broadcasting operation on the first feature matrix and the second feature matrix, and adding the first feature matrix and the second feature matrix to generate a third feature matrix; the query matrix, the key matrix and the value matrix are spliced in a context enhancement module and then subjected to convolution operation to generate a fourth feature matrix, and the third feature matrix is subjected to convolution and then multiplied by the fourth feature matrix to determine an attention matrix; and adopting a preset loss function to regress seedling strip lines in the to-be-detected corn field image as a whole according to the first line Anchor and the attention matrix so as to determine a corn row detection result. According to the invention, the method can adaptively focus on the key area of the corn row, thereby improving the precise recognition of the corn row.

The invention relates to a field corn plant phenotype measurement method and system, and the method comprises the steps: firstly employing an image collector to shoot an RGB image and a depth image of a field corn plant, then extracting a mask image from the depth image based on a clip module added in a YOLOv8 model, carrying out the mask processing of the RGB image, employing the YOLOv8 model to carry out the target recognition of the RGB image after the mask processing, and carrying out the measurement of the phenotype of the field corn plant. Then key point pixel coordinates output by the recognized target are determined, coordinate depths corresponding to the key point pixel coordinates are extracted from the depth image, camera coordinate system coordinates of the key points are calculated and then converted into world coordinate system coordinates, key points belonging to the same plant are determined through coordinate matching and pairing is carried out, and the target is obtained. And finally, according to the world coordinate system coordinates of the paired key points, calculating the ear height and the leaf included angle of the corn plant. According to the method, accurate analysis of the spike height and leaf included angle phenotype of the low-resolution image can be realized.

The utility model relates to the technical field of corn planting, in particular to field corn deinsectization equipment which comprises a base plate, the bottom of the base plate is fixedly connected with a water storage tank, the top of the base plate is fixedly connected with a transmission box, an inner cavity of the transmission box is movably connected with a rotating rod in a penetrating mode through a bearing, and the top of the transmission box is fixedly connected with a supporting cylinder. An inner cavity of the supporting cylinder is movably connected with a driving screw through a bearing, the surface of the driving screw is sleeved with an installation sliding block in a threaded mode, and the front side and the rear side of the installation sliding block penetrate to the outer side of the supporting cylinder and are fixedly connected with an inserting mechanism. The driving screw rotating forwards or reversely enables the mounting sliding block sleeved with the surface in a threaded mode to move upwards or downwards, the deinsectization lamp moves upwards or downwards along with the mounting sliding block, due to the fact that the heights of corn in all growth stages are different, the deinsectization height of the deinsectization lamp can be adjusted by rotating the rotating wheel, the deinsectization lamp and the corn are kept at the most ideal deinsectization height all the time, and the deinsectization effect is good. The deinsectization effect is more ideal.

The invention relates to the technical field of agricultural irrigation, in particular to a field corn well irrigation water and fertilizer integrated device and system.The field corn well irrigation water and fertilizer integrated system comprises a water source system, a head hub system, a water conveying and distributing system and an irrigation system which are sequentially communicated; the filtering unit is provided with different filter combination modes according to different silt contents of a water source system; when the water quality is high-silt well water, the filtering unit adopts a combination of a centrifugal filter and a screen filter / laminated filter; when the water quality is high clay / colloid well water, the filter unit adopts a combination of a gravel filter and a screen filter / laminated filter; the water quality type of the filtering unit is configured to be one of a full-manual mode, a semi-automatic mode and a full-automatic mode. The system is used for solving the problems that an existing drip irrigation system is poor in applicability, not thorough in filtering, low in water and fertilizer integration degree and high in cost in a small-scale farmland.

Combine harvesters are provided for use in harvesting seed corn from corn plants in fields. In connection therewith, a method of using such a combine harvester to produce seed corn for use in growing corn plants includes removing, by the combine harvester, ears of corn from corn plants in a field and separating the corn kernels from cobs of the ears of corn onboard the combine harvester while in the field. The method also includes collecting, by the combine harvester, a supply of the separated corn kernels for use as seed corn. In connection therewith, cold germination of the collected supply of corn kernels is at least about 75% and warm germination of the collected supply of corn kernels is at least about 75%.

The invention provides a remote sensing and crop growth model-based field corn irrigation water demand calculation method. The method comprises the following steps of: constructing a microwave scattering model based on microwave remote sensing data, and constructing a thermal inertia model based on thermal infrared remote sensing data; learning a non-linear mapping relation between remote sensing data and ground actually-measured multi-layer soil moisture through a deep neural network, optimizing key parameters of a multi-source fusion model, and establishing calibration parameter values and soil moisture content parameter values of the multi-source fusion model under different hierarchies; on the basis of the difference of different soil layer moisture demands in different growth stages of the corn, the water amount needing irrigation is calculated in combination with a multi-layer soil moisture calculation result; according to the possible rainfall in the preset time period, combining the area of the region to obtain predicted rainfall; according to the intelligent irrigation decision-making system for the field corn, the remote sensing technology, the crop physiological model and meteorological prediction are organically combined, and a complete and practical intelligent irrigation decision-making system for the field corn is formed.

The application discloses a kind of corn population photosynthetic capacity index construction and estimation method, it is related to the field of agricultural products monitoring, comprising the following steps: S1: obtaining corn Pn, Gs, Ci and Tr four photosynthetic parameters, S2: using Akima spline curve interpolation method Pn, Gs, Ci and Tr measurement interval is shortened to one hour, S3: the fitting curve of four parameters is obtained, S4: the projected area under fitting curve is calculated, S5: the projected area is normalized, determine the weight of each projected area, S6: calculate the new index ODP of photosynthetic capacity, while providing ODP index feasibility verification method and estimation method.The application has the advantages that, more accurately reflect population photosynthetic capacity, consistent with the actual situation, can truly reflect the growth state of field corn.In addition, using unmanned aerial vehicle hyperspectral can quickly and accurately estimate the index, improve the efficiency of photosynthetic capacity identification.

The invention discloses a method for accurately and efficiently evaluating nitrogen absorption and soil nitrogen supply conditions by measuring the nitrate content of bleeding sap of corn stalks. The method comprises the following steps: 1) culturing corn seedlings to grow to V8-V10 periods; 2) collecting stem bleeding sap in the morning of the second day after the plant is fully irrigated: transversely cutting the vertical stem in the second internode by using a blade until the stem is completely cut off; after standing for 5-60 minutes, bleeding sap seeps from the xylem from the cross section of the stalk, and after 5 minutes, the bleeding sap is condensed into liquid drops; using a sterile syringe to suck bleeding sap and transfer the bleeding sap into a centrifugal tube; after the bleeding sap is collected once and 3-10 minutes later, the bleeding sap is condensed into liquid drops again; collecting for multiple times to obtain bleeding sap meeting NO3 <-> determination requirements; 3, the NO3 <-> content of the stem bleeding sap is determined.According to the method, used consumables are simple and easy to obtain, the operation process is simplified, the method is easy to master, time is saved, and the method is especially suitable for obtaining nitrogen absorption phenotypes of large groups of corn in the field.

This invention belongs to the field of maize seedling information research technology, specifically involving an automatic method for extracting maize seedling absence rate information. The method includes: S1, creating a dataset by taking images of maize seedlings in the field using a drone; S2, labeling the dataset and training a deep learning model; S3, using the trained deep learning model to identify and detect maize seedlings in the field images; S4, fitting the seedling root position to the deep learning output detection information; S5, determining the maize seedlings in the same row based on density distribution; and S6, determining seedling absence based on kernel density estimation and calculating the absence rate. By using a drone to randomly sample a portion of the field and applying steps S4 to S6, the overall maize seedling absence situation in the drone-collected images can be obtained. This invention can solve the problem of how to achieve accurate and rapid seedling absence detection during maize growth and has good market application prospects.

The application provides a method for predicting corn yield based on a multi-modal unmanned aerial vehicle, so as to accurately predict the corn yield in a farmland, and on one hand, provides a new method for yield evaluation of a corn crop, and on the other hand, provides a new idea for yield estimation of other crops. Compared with traditional research which is mainly based on single type remote sensing data and traditional machine learning methods, the yield prediction model obtained has poor robustness, and the multi-modal fusion unmanned aerial vehicle remote sensing data can effectively improve the yield prediction efficiency.

The utility model relates to a movable field corn phenotype identification device which comprises two or more first gear shafts, first supporting rods are arranged at the two opposite ends of each first gear shaft in a penetrating mode, motors are fixedly arranged at the two ends of each first supporting rod, and the outer sides of the output ends of the motors are sleeved with first baffles. One or more second supporting rods are fixedly arranged on the inner surface of the first baffle, the outer surfaces of the second supporting rods are sleeved with second gear shafts, the outer surfaces of the second gear shafts are sleeved with third gear shafts, the contact parts of the second gear shafts, the first gear shafts and the third gear shafts are all in an engaged state, and the third gear shafts are sleeved with first caterpillar bands. The outer surface of the middle of the first gear shaft is sleeved with a second crawler belt, a balancing weight is fixedly arranged on the lower surface of the inner side of the second crawler belt, a connecting rod is fixedly arranged on the lower surface of the outer side of the first crawler belt, and a phenotype sensor set is fixedly arranged at the lower end of the connecting rod.

The invention belongs to the technical field of corn planting, and particularly relates to a field corn online harvesting and threshing integrated treatment method which comprises the following steps: S1, selecting an early-maturing corn variety for field sowing; s2, field water, fertilizer and chemical control management is carried out on the corn, chemical vigorous growth control is carried out in the early growth stage, irrigation and topdressing are not carried out in the 5-leaf to 9-leaf period, management in the middle growth stage is the same as common field management, and irrigation is completely eradicated in the milk-ripe stage and the mature stage in the later growth stage; s3, the corn kernel content x is measured in the physiological mature period of the corn, and the cut length of the straw is determined according to the kernel content and the width of the wide and narrow rows; when the water content of the corn kernels is less than or equal to 25%, mechanically harvesting the corn kernels by using a harvesting and threshing all-in-one machine; according to the method, technical guidance is provided for mechanical grain harvesting of corn, mechanical grain harvesting of field corn is facilitated, the labor efficiency is improved, meanwhile, the integrity of corn grains is improved, and the grain harvesting loss is reduced.

The application discloses a neural network model and system for corn LAI estimation, relates to the technical field of deep learning, and a multi-source feature extraction network performs deep layer representation on input feature information, and enhances the fusion expression capability between different sources and different scale features. Then, inversion prediction values and trend prediction values are obtained through a physical inversion branch and a phenology trend branch, so that the model can not only maintain the physical interpretability of LAI estimation, but also reflect the timing law of continuous change of the corn LAI along with the phenology process. Meanwhile, the adaptive gating fusion network dynamically generates weights by taking accumulated temperature as a condition, can automatically adjust the contribution proportion of the physical inversion result and the trend prediction result according to different growth stages, thereby reducing the problem of large estimation deviation of a single model in a specific growth period, improving the stability, continuity and precision of the corn LAI estimation, and being suitable for field corn growth monitoring and farmland intelligent management.

The invention discloses a corn elongation stage water stress identification and segmentation method based on an unmanned aerial vehicle image, and belongs to the field of precision agriculture and image processing, and the method comprises the following steps: S1, collecting a field corn canopy image according to preset flight parameters through an unmanned aerial vehicle, and synchronously recording initial image information; s2, sequentially performing correction processing, illumination optimization processing, image segmentation and data enhancement processing on the initial image acquired in the step S1, and performing normalization processing to generate a data set; and S3, on the basis of the data set in the step S2, a corn moisture stress segmentation network model CornWS-Net with lightweight coding-decoding as a core framework is constructed, the model is composed of HFPM, MCAE, DPAE and SRD, a segmentation prediction result of the corn elongation stage moisture stress leaves is obtained through training, and a moisture stress level is output. By the adoption of the method, field corn water stress monitoring and precise irrigation can be achieved, and technical support is provided for intelligent management.

The utility model discloses a field corn inter-row root system in-situ observation device relates to corn root system observation technical field, including root window (1), top cover (2), movable inner shell (3), movable fixer (4) and shooting device (5), shooting device (5) includes image acquisition equipment (8) and controller (9), root window (1) top is provided with the opening, and one side surface is transparent observation window (7), and the top of root window (1) is provided with the opening. The top cover (2) is arranged at the top of the root window (1), the movable inner shell (3) is arranged in the root window (1), and the movable fixator (4) is arranged on the side, opposite to the observation window (7), in the movable inner shell (3). The utility model solves the problems that the plant growth environment is damaged due to the installation or overlarge volume of the existing device, the multi-site rapid observation through a larger observation surface in a smaller operation space cannot be realized, and the investment cost is higher.

The present application relates to the field of intelligent identification, more particularly to a three-dimensional phenotype segmentation and labeling system for field corn crops, comprising: an initialization module for performing opening, loading and preprocessing tasks of field corn point cloud data files; a ground segmentation module for performing automatic segmentation tasks of corn plant groups and ground; a single plant recognition module for performing accurate segmentation of single plants in the plant group and generating identification information tasks; a skeleton classification module for performing skeleton calculation and data point category division tasks of single corn point clouds; an organ labeling module for performing stem and leaf organ structure division and labeling tasks of single corn point clouds; and a result interaction module for performing visualization of output data of key steps of each module and saving projection, segmentation, labeling and classification result data output by each module.

The invention discloses a reverse beating and airflow directional separation coupling type corn straw cleaning and picking device, and relates to the technical field of agricultural machinery, the reverse beating and airflow directional separation coupling type corn straw cleaning and picking device comprises a picking shell, a picking hammer claw mechanism, a reverse beating mechanism, an airflow directional separation mechanism and an auger conveying and smashing mechanism, the picking hammer claw mechanism is installed on the front side of the picking shell, and the reverse beating mechanism is installed on the rear side of the picking shell; the reverse beating mechanism is arranged at the upper position of the middle side of the picking shell and located between the picking hammer claw mechanism and the auger conveying and smashing mechanism, the airflow directional separation mechanism is installed in the reverse beating mechanism and coaxially arranged with the reverse beating mechanism in a differential mode, and the auger conveying and smashing mechanism is arranged on the rear side of the picking shell. The pickup hammer claw mechanism picks up and conveys field corn straw and entrained soil backwards, the reverse beating mechanism continuously stirs, combs and flaps a straw mixture through elastic teeth, mechanical stripping of attached soil and the entrained soil is achieved, the built-in airflow directional separation mechanism rotates at a differential speed to generate directional airflow, and the directional airflow is separated from the straw mixture through the reverse beating mechanism. And the separated fine soil is blown away in time and discharged out of a conveying area.

The application discloses a crop growth evaluation method based on a depth image and belongs to the technical field of crops. The crop growth evaluation method based on the depth image comprises the following steps: S1, growth classification model training: widely obtaining RGB images of field corn in different growth periods in the vertical direction, and ensuring that samples under various growth environments and conditions are covered; accurately and comprehensively labeling corn leaf positions and regions on the RGB images by professional personnel, and the labeling should include detailed information such as the outline, size and position of the leaf; using a large amount of data after labeling, training a target recognition model by using an advanced machine learning algorithm, and enabling the target recognition model to accurately and efficiently recognize the corn leaf; and the application is used to solve the problem that the adaptability of the existing image acquisition mode is also relatively limited, the obtained samples are not rich and diversified enough, and the generalization ability of a subsequent evaluation model is affected.

The utility model discloses sprinkling irrigation equipment for field corn planting, which comprises a water tank, a mounting frame is fixedly mounted at the rear end of the water tank, a threaded rod is rotatably connected in the mounting frame, a vertical seat is sleeved on the outer side of the threaded rod in a threaded manner, the top end of the vertical seat extends out of the mounting frame and is fixedly provided with a mounting seat, and sleeves are rotatably connected to two sides in the mounting seat. Spraying rods are fixedly mounted in the two sleeves, the ends, away from each other, of the two spraying rods extend out of the mounting base, the outer sides of the two spraying rods are fixedly sleeved with gear rings, the bottom ends of the two gear rings are in meshed connection with gears, and a plurality of spraying heads are fixedly mounted at the rear ends of the two spraying rods. According to the sprinkling irrigation equipment for field corn planting, in the walking process of a worker in a field, sprinkling irrigation operation can be automatically completed, the worker does not need to hold a spray gun by hand for sprinkling, the irrigation work is more convenient and labor-saving, meanwhile, the heights and sprinkling angles of the multiple nozzles can be adjusted according to use requirements, and different irrigation use requirements are met.

The application relates to a field corn fertilization system based on an IPSO-LSTM algorithm, and relates to a field corn fertilization system based on an IPSO-LSTM algorithm. The application aims to solve the problem that no existing technology can determine accurate fertilizer application amount according to different soils. The system comprises a collection module, a relay module, a main controller module and a remote monitoring module. The collection module acquires soil parameters of a fertilization area, performs first-stage processing, and sends the processed data to the relay module. The relay module performs second-stage processing on the data to obtain optimal fusion results. The main controller module takes the optimal fusion result data as input, predicts the fertilizer application amount through a trained IPSO-LSTM fertilizer application amount prediction model, controls the fertilizer ratio, and thus completes the function of autonomous fertilization. The remote monitoring module interacts with the main controller module to realize the function of remote monitoring. The application is used in the technical field of agricultural water fertilization.

A field corn plant phenotype measurement method and system, the method first uses an image collector to shoot an RGB image and a depth image of a field corn plant, then extracts a mask image from the depth image based on a clip module added in a YOLOv8 model, and performs mask processing on the RGB image, then uses the YOLOv8 model to perform target recognition on the RGB image after mask processing, then determines the key point pixel coordinates output by the recognized target, then extracts the coordinate depth corresponding to the key point pixel coordinates from the depth image, converts the camera coordinate system coordinates of the key points into world coordinate system coordinates after calculating, determines the key points belonging to the same plant through coordinate matching and pairing, and finally calculates the ear height and leaf angle of the corn plant according to the world coordinate system coordinates of the paired key points. The present application can realize accurate analysis of the ear height and leaf angle phenotype of low-resolution images.

The utility model relates to the technical field of agricultural machinery, and discloses a field corn planting device which comprises a tractor, a soil loosening mechanism and a soil crushing mechanism. The soil crushing mechanism comprises a soil holding cage, a soil crushing assembly and a first roller; the soil holding cage comprises an arc-shaped cage body and a soil shoveling plate located on the cage body. The cage body is provided with an opening facing the soil loosening mechanism, and filter grooves are formed in the cage body and the soil shoveling plate; the soil crushing assembly comprises a soil stirring column coaxially arranged with the cage body and a plurality of soil crushing blocks arranged on the inner side of the cage body at equal intervals, at least two soil stirring grooves extending in the axis direction of the soil stirring column are formed in the soil stirring column, and a plurality of receding grooves allowing the soil crushing blocks to penetrate through are further formed in the soil stirring column; rotating shafts which penetrate through the two ends of the cage body and are rotationally connected with the cage body are arranged at the two ends of the soil shifting column, and the first rolling wheels are fixedly connected to the rotating shafts. The purpose of the utility model is to timely crush hard soil blocks to realize fine integration and better soil preparation effect when soil turning and loosening are carried out on a field.

The present invention relates to a method for detecting and counting corn seedlings and weeds in UAV remote sensing images, including: collecting farmland images and performing preprocessing to obtain the cut images; constructing a crop row detection model and performing masking processing to obtain the masked image with only inter-row weeds; establishing a training sample set for corn seedlings and weeds; constructing a detection model for corn seedlings and weeds to obtain the optimal detection model for corn seedlings and weeds; detecting corn seedlings and weeds and performing data analysis. The present invention fully considers the characteristics of the distribution of corn seedlings and weeds in the field, and obtains two characteristics: the number of corn seedlings is much larger than that of weeds, and corn seedlings basically grow within the corn seedling rows; based on these characteristics, a method for masking the corn seedling rows is proposed, which solves the two problems of consuming time cost for a large number of corn seedling annotations on the original image and the imbalance in the total data volume of weeds and corn seedlings.

This invention belongs to the field of maize planting technology, specifically relating to an integrated online harvesting and threshing method for field maize, comprising the following steps: S1, selecting an early-maturing maize variety for field sowing; S2, implementing field water, fertilizer, and chemical control management for the maize, using chemical control to regulate excessive growth in the early growth stage, and refraining from irrigation and topdressing during the 5-9 leaf stage; managing the mid-growth stage as usual for field maize, and prohibiting irrigation during the milk-ripe to maturity stage in the later growth stage; S3, determining the maize kernel content x at the physiological maturity stage, and determining the straw cutting length based on the kernel content and row width; when the maize kernel moisture content x ≤ 25%, using an integrated harvesting and threshing machine to mechanically harvest the maize kernels; this method provides technical guidance for achieving mechanical harvesting of maize kernels, facilitates mechanical harvesting of field maize, improves labor efficiency, enhances kernel integrity, and reduces harvesting losses.

The invention discloses a corn whole growth period leaf area index prediction method and device, equipment, a medium and a product, and relates to the field of crop leaf area index prediction. The method comprises the following steps: acquiring information data; the information data comprises a label ID based on a target field corn inbred line, and full-growth-period time sequence multispectral image data acquired from each corn cell according to a set acquisition interval; carrying out preprocessing and pixel extraction on the information data and determining various vegetation indexes; inputting the processing information data into a leaf area index prediction model to obtain a predicted leaf area index; the processing information data comprises pixel quantity data, various vegetation indexes and multispectral image data; the leaf area index prediction model is obtained based on a random forest model, taking processing information data obtained historically as an independent variable, taking ground measurement data as a dependent variable, and adopting a machine learning method for training. The method can achieve the accurate prediction of the leaf area index in the whole growth period of corn.

The invention discloses a system and a method for intelligently identifying corn leaf diseases, and belongs to the technical field of crop disease identification, and the method comprises the following steps: establishing a database, receiving and storing input image information by the database, establishing a database, receiving and storing the input image information by the database, a convolutional neural network model is trained through sample images stored in a database, spatial correlation is carried out on features of frequency domain attention by using spatial attention, the trained convolutional neural network model is verified, and the convolutional neural network model with accuracy meeting a detection standard is used as a final processing model. After the to-be-detected image is received, the to-be-detected image is input into all the final processing models to obtain disease information, the disease information with the highest occurrence frequency is selected and displayed, and the effect that the disease information of the field corn leaf diseases can be accurately recognized through the image is achieved.

The present application relates to a kind of pest semi-supervised target detection method of combining active learning and multiscale view learning, comprising: constructing semi-supervised target detection data set;Data augmentation is carried out to semi-supervised target detection data set;Semi-supervised model is constructed and pseudo label is generated;Multi-scale view learning is carried out by student model, and multi-scale view prediction result is obtained;Semi-supervised training is carried out;Active learning is carried out, and semi-supervised target detection data set is updated;The field corn image to be detected is input into the teacher model after final training, and the final pest detection result is obtained.The present application combines active learning to select some data beneficial to model, which can effectively improve performance to label, maximize the use of labeling cost;Add multiscale view learning structure, capture effective information;Finally, more than 80% of the detection accuracy of labeled data can be realized under the condition of limited 20% of labeled data, which greatly saves the labeling cost.