27 results about "Crop sample" patented technology

The invention discloses a method for detecting aspergillus flavus and aflatoxin B1 of crops based on an infrared spectrum. The method comprises the steps of crop sample material collection, rice multi-strain mould infection, spectrum collection, crop sample aflatoxin B1 determination, spectrum pretreatment, correction model construction and model verification. The invention aims at detecting the content of aspergillus flavus infection and toxin B1 thereof in crops by combining a near-infrared spectrometer and a stoichiometric method. The method has the advantages of being simple and easy to implement, high in analysis speed, high in detection precision, low in analysis cost, free of any pollution to the environment and the like, samples do not need any pretreatment, and the method has important practical value for guaranteeing the quality safety of agricultural products and reducing the carcinogenic risk of people.

The invention relates to the technical field of crop image quality inspection, and discloses a crop sample live-action image automatic warehousing and intelligent quality inspection system and method. An image acquisition module of the system acquires an initial real-scene image and preprocesses the initial real-scene image to generate a target real-scene image, and shooting interference is eliminated to guarantee the quality of basic data; the hierarchical analysis module performs multi-level feature analysis on the target live-action image, generates initial quality calibration, and divides the image into a plurality of sub-quality inspection areas when to-be-verified calibration is identified, so that accurate analysis from the whole to the local is realized; and the dynamic processing module extracts spectral feature values of the sub-regions, compares the spectral feature values with a standard threshold value, divides a feature set, performs correlation verification through adjacent feature values and performs statistics on an effective correlation number, so that the scientificity and objectivity of quality inspection are improved. According to the system, automatic warehousing and intelligent quality inspection of crop sample images are realized, manual intervention is reduced, the quality inspection efficiency and reliability are improved, and high-quality data support is provided for related work of national land change investigation.

The present invention relates to an agricultural harvesting machine (1) with an optical measuring device (17) for the spectral measurement of a harvested crop sample. The optical measuring device (17) comprises an integrating cavity (26), a light source (27), and a sensor (28) which is designed and configured to receive light from the integrating cavity (26). The integrating cavity (26) includes an optical aperture (18). A harvested crop sample located outside the integrating cavity (26) is measured by means of the sensor (28) in order to determine the proportion of at least one constituent of the harvested crop sample. The harvesting machine (1) is characterized in that the integrating cavity (26) is designed as a hemisphere and the optical aperture (18) is located in the cross-sectional area of ​​the hemisphere.

The invention provides a crop identification method and system based on a language large model and a remote sensing time sequence. The method comprises the following steps: acquiring a task area remote sensing time sequence image; a visual feature extraction module extracts visual information of the crop samples from the time sequence blocks and the corresponding curves thereof; the semantic feature extraction module is used for automatically generating time sequence text description based on a large language model; and finally, ensuring that visual information of the time sequence is highly aligned with the corresponding semantic knowledge in a potential space through comparative learning, and meanwhile, remarkably separating non-corresponding semantic knowledge, so that the classification performance and generalization ability of the model are improved. And classifying the task area remote sensing image to obtain a classification result of the task area remote sensing image. The embodiment of the invention is the first research for exploring the application of zero sample learning in crop classification, replaces a tedious and time-consuming manual labeling process, and can realize accurate classification of unknown crops of remote sensing images.

This invention relates to the field of plant transgenic detection technology, and discloses a method for rapid batch detection of transgenic crops, comprising: Step 1, placing centrifuge tubes containing crop samples to be tested in an array into a multi-well plate to complete batch plate arrangement of samples; Step 2, performing overall mechanized processing based on the multi-well plate, so that the crop samples in the centrifuge tubes are simultaneously ground into powder under mechanical force. This integrated operation process, which places independent centrifuge tubes in an array within a multi-well plate and uses a tissue homogenizer, batch liquid addition equipment, and a centrifuge to simultaneously process all samples, achieves a significant improvement in detection throughput and efficiency. Compared to existing technologies that rely on manual, one-by-one operation, this method overcomes the shortcomings of low detection efficiency and the inability to simultaneously process multiple samples, thus failing to meet the needs of large-scale crop sample screening.

The utility model relates to the technical field of test tables, and discloses a test table for pesticide residue detection, which comprises a table and a test tube, the top of the table is fixedly provided with a support plate, the top of the support plate is fixedly provided with a fixed shell, the front side wall of the fixed shell is fixedly provided with a slide rail, and the slide rail is fixedly provided with a slide groove. An oscillation assembly facilitating oscillation of a reagent in the test tube is arranged on the fixed shell and the sliding rail, the oscillation assembly comprises a motor, a crankshaft, a rack, a driving frame, a movable shaft, a gear and a placing block, and the motor is fixedly installed on the front wall of the fixed shell. According to the test table for pesticide residue detection, the oscillation assembly is arranged, after the oscillation assembly is used, under starting of a motor, a crankshaft rotates, a driving frame and a rack are pushed to transversely move in a reciprocating mode, a gear meshed with the rack can rotate forwards and backwards, and a test tube is driven by a placing block to rotate forwards and backwards; therefore, the crop sample and the detection reagent can be fused together quickly, and the fused reagent can be tested and detected conveniently.

The invention relates to the technical field of gene sequencing, in particular to a pretreatment method for gene screening based on pathogenic bacteria carried by food crops, a sequencing method and application thereof. According to the pretreatment method and the sequencing method for screening the pathogenic bacteria genes of the food crops, a liquid culture medium containing a potato extracting solution and a carbon source is used for carrying out enrichment culture on a food crop sample, enrichment of the pathogenic bacteria to be detected can be well guaranteed under the nutritional condition suitable for growth of the pathogenic bacteria, especially fungi, and the detection accuracy is improved. According to the method, fungi in the sample can be effectively prevented from being broken and cracked, the concentration and quality of total DNA extraction of the subsequent sample are improved, the sequencing effect is guaranteed, and then high-throughput sequencing is achieved.

The invention provides a crop variety classification method, device and equipment based on single nucleotide polymorphism, and relates to the technical field of crop analys.The method comprises the steps that gene sequencing is conducted on target crop samples for the target crop samples, and high-confidence-coefficient gene sequence data corresponding to the target crop samples are obtained; determining a target map corresponding to the target crop sample based on the high-confidence gene sequence data; inputting the target map into a convolutional neural network model to obtain a map vector corresponding to a target crop sample output by the convolutional neural network model; and inputting the atlas vector into a support vector machine classifier to obtain an identification result of the target crop sample output by the support vector machine classifier. According to the technical scheme, the gene sequence of the crop sample is converted into the map form, the difference between crop varieties can be visually recognized, high-efficiency and high-precision crop variety classification can be carried out without depending on professionals, and the cost is saved to a large extent.

The invention relates to the technical field of agricultural management, in particular to an intelligent irrigation management and control system which comprises the following steps: acquiring crop sample data, preprocessing the crop sample data, and extracting crop growth trend data from the processed crop sample data; constructing a self-attention mechanism model comprising three layers of Transform architectures, and training the self-attention mechanism model of the Transform architectures by using the crop growth trend data to obtain a basic model for detecting the crop growth condition; the method comprises the following steps: collecting sample data of a target area and an irrigation pipe network distribution map of the target area, segmenting the target area by using an irrigation pipe network, obtaining sample data of small areas, and preprocessing the sample data of the small areas. The plant growth condition of each region is accurately predicted, irrigation and fertilization are conveniently and specifically performed on crops, and the farmland fertilization accuracy in the region is improved.

The application discloses a crop detection method and system based on flow feature selection, which firstly solves the Euclidean distance of the crop samples on the earth surface by part of the crop feature information obtained, and obtains the adaptive neighborhood radius of various crops; secondly, the neighborhood relationship between the crop samples is obtained according to the adaptive radius neighborhood; finally, the flow feature selection method based on dependence and importance is used to evaluate the obtained crop feature information in turn, and the optimal feature subset for subsequent crop detection is obtained; the application can adaptively solve various crop samples in different regions and different geographical environments, improve the crop detection accuracy, and fully consider the decision of various crop samples, so that the interference of bad weather on crop detection is reduced.

The present invention relates to an agricultural harvesting machine (1) with an optical measuring device (17) for the spectral measurement of a harvested crop sample. The optical measuring device (17) comprises an integrating cavity (26), a light source (27), and a sensor (28) which is designed and configured to receive light from the integrating cavity (26). The integrating cavity (26) includes an optical aperture (18). A harvested crop sample located outside the integrating cavity (26) is measured by means of the sensor (28) in order to determine the proportion of at least one constituent of the harvested crop sample.The harvesting machine (1) is characterized in that the optical measuring device (17) comprises an optical sensor (32) for determining contamination of the optical aperture (18), wherein the optical sensor (32) is provided and configured to receive light emitted from the light source (27) of the optical measuring device (17) from the integrating cavity (26), to measure the optical aperture (18) and to determine the contamination of the optical aperture (18).

The invention discloses a crop yield prediction method, medium and system based on the daytime multi-temporal characteristics of an unmanned aerial vehicle, and the method comprises the steps: obtaining crop sample data of each partition of each time period of a specific date, the crop sample data comprises crop single-temporal characteristics of each subarea of each time period, crop cross-temporal characteristics of each subarea of each time period combination and crop yield of each subarea; screening an optimal time period combination from the time period combinations according to the sample data; controlling the unmanned aerial vehicle to fly above crops including a plurality of subareas in each time period in an optimal time period combination of a specific date, acquiring a crop image of each time period, and acquiring crop single-temporal characteristics of each subarea and crop cross-temporal characteristics of each subarea in each time period from the crop image of each time period; and inputting the crop single-time-phase characteristics and the crop cross-time-phase characteristics in the optimal time period combination into a prediction model, and outputting the predicted crop yield. According to the invention, balance between prediction precision and operation cost is realized.

The utility model discloses a grain crop sample moistureproof storage device, which relates to the technical field of grain moistureproof, and comprises a storage outer cylinder, a storage inner cylinder, a storage outer cylinder, a storage outer cylinder, a storage inner cylinder, a storage inner cylinder and a storage outer cylinder, a gap exists between the outer wall of the storage inner cylinder and the inner wall of the storage outer cylinder, a plurality of vent holes are annularly formed in the surface of the storage inner cylinder at equal intervals, and each vent hole communicates with the gap. According to the utility model, the material turning part on the side wall of the central shaft rotates around the inner wall of the storage inner cylinder, and food crop samples in the storage inner cylinder are turned through the material turning holes, so that air circulation ventilation gaps among sample particles are increased; water vapor generated by respiration of the food crop samples in the middle part can be timely discharged through the ventilation gaps, the food crop samples are prevented from mildewing and going bad after being placed for a long time, and the requirement for long-term and high-quality preservation of all the food crop samples is met.

A system, apparatus, method or non-transitory computer readable medium may include obtaining an input image and an inpainting indication, wherein the input image depicts a scene and the inpainting indication indicates a region of the scene to be inpainted and generating, using an image generation model, an intermediate inpainting result based on a global context of the input image. The image generation model then generates an inpainted image based on the intermediate inpainting result and a local context of the input image that includes a smaller portion of the input image than the global context, where the inpainted image depicts the scene with synthetic content in the region indicated by the inpainting indication.

The application provides a lodging monitoring method and device for target crops, electronic equipment and storage medium, and relates to the technical field of crop monitoring. The method comprises the following steps: extracting the target ground reflectivity of the target crops in the visible light green wave band in the monitoring range from a satellite remote sensing image; the target crops comprise at least one of corn and rice; inputting the target ground reflectivity into a decision tree model to obtain the lodging state monitoring result of the target crops output by the decision tree model; and the decision tree model is determined based on the ground reflectivity in the visible light green wave band in the target crop sample area. Through the above method, the significant difference in the target reflectivity of the target crops in the visible light green wave band is utilized to determine the target ground reflectivity in the visible light green wave band, the target ground reflectivity is input into the decision tree model, the lodging state of the target crops can be accurately judged, and the lodging monitoring precision of the target crops is improved.

The invention discloses a crop refined identification method based on multi-modal remote sensing data feature fusion. The crop refined identification method comprises the following steps: acquiring multi-modal remote sensing data and sample data of a research area; performing hole convolution and multi-scale feature fusion on the D-LinkNet model by using the obtained high-resolution remote sensing image and the cultivated land sample to obtain a D-LinkNet cultivated land segmentation model; a plurality of D-LinkNet cultivated land segmentation models are combined to carry out voting decision making, and prediction results of the D-LinkNet cultivated land segmentation models are integrated to extract cultivated land space pattern spots; constructing a multi-modal crop identification model by using the acquired multispectral remote sensing image, hyperspectral remote sensing image and SAR remote sensing image and crop samples to generate a multi-source feature fusion identification result; and carrying out superposition fusion on the cultivated land space pattern spots and the multi-source feature fusion recognition result to determine main crop types in each cultivated land space pattern spot, and obtaining a cultivated land crop classification map of the research area. According to the invention, accurate extraction of farmland crops in a large-scale range can be realized.

The invention relates to the technical field of crop management, in particular to a selenium-rich crop safety determination method and system and a storage medium. The method comprises the following steps: acquiring selenium element detection data of each detection part of a to-be-detected crop sample, and determining selenium form distribution corresponding to different existence forms in crops according to the selenium element detection data; calculating the relative proportion relation of organic selenium and inorganic selenium in the to-be-detected crop sample according to the selenium form distribution, and judging the safety risk level; collecting soil sample detection data corresponding to the to-be-detected crop sample, and determining the total selenium content and potential associated risk factors of the soil sample; and correcting the safety risk level judgment result according to the total selenium content of the soil sample and the potential associated risk factor, and determining the overall safety of the crop sample to be detected so as to output a corresponding safety determination report. The method is helpful for shortening the detection period and reducing the operation complexity, and is suitable for real-time monitoring and safety management of production and circulation links.

The utility model discloses a portable rice and wheat combine harvester which is mainly used for scientific researchers to collect a small amount of rice and wheat or similar crop samples. The device comprises a harvesting part, a threshing and cleaning part, a backpack type negative pressure storage part and a power system. The harvesting part is used for shifting rice and wheat ears into the cutting mechanism through an ear shifting mechanism to cut off ear stems and sending the ear stems into the threshing and cleaning part, the threshing and cleaning part is used for threshing and cleaning the ears through a rotating threshing roller and a fan, and the backpack type negative pressure storage mechanism is used for extracting threshed and cleaned grains through a fan and a conveying hose, removing impurities and storing the grains. The device is compact in structure, light in weight and convenient to carry, disassemble, assemble and clean through modular design, and meets the sampling requirements of various crops. The equipment is simple to operate, can efficiently complete the whole process of harvesting, threshing and storing, is high in sample purity and cleanliness, is low in loss, remarkably reduces the labor intensity, improves the working efficiency, and can be widely applied to the fields of agricultural scientific research, breeding tests, germplasm resource protection and the like.

The invention relates to a crop sample detection device which comprises a detection box and a discharging channel communicated with the top of the detection box, an inner cavity of the detection box is rotationally connected with a rotating table driven by a motor, and a plurality of placing grooves are formed in the surface of the rotating table; the invention relates to the technical field of crop sample detection. According to the crop sample detection device, through intermittent rotation of the rotating table and cooperation of the pressing block and the contact switch, opening and closing of the switch valve are automatically controlled, circulating and quantitative discharging of the multiple containing grooves is achieved, manual intervention is not needed, and the detection efficiency is greatly improved.

The application discloses a crop pesticide residue detection method and system based on a convolutional neural network, first, a hyperspectral image of a crop sample is collected, and data preprocessing is performed; then, the preprocessed hyperspectral image is input into a pesticide residue detection convolutional neural network for pesticide residue detection; the application combines a hyperspectral imaging technology and a deep learning method, and has the advantages of non-damage, automation and high efficiency.

The application provides a field plot level crop planting area early monitoring method, comprising the following steps: acquiring satellite image data and crop sample data set of a target area, and preprocessing the satellite image data to obtain reconstructed time series satellite data; determining classification features for crop classification based on a feature screening algorithm; based on an image segmentation algorithm, segmenting the satellite image data according to plot data to obtain object units; performing spectral aggregation on each object unit to obtain aggregated images; training and evaluating an initial machine learning classifier according to the aggregated images, the classification features and the crop sample data set to obtain a trained crop classification model; inputting remote sensing images of a target year into the crop classification model to obtain field plot level crop early monitoring results of the target year. The application can significantly reduce the uncertainty caused by pixel-based classification, and improve the accuracy and timeliness of crop classification.

The invention discloses a crop classification method based on semantic super-division edge three-drive, and belongs to the technical field of intelligent agriculture. The objective of the invention is to solve the problem of high-precision crop classification in medium and low-resolution remote sensing images. The method comprises the following steps: preparing various crop samples; building a feature extraction backbone network DeepHR to obtain high-level semantic features and low-level detail features extracted by the backbone network; a multi-scale feature fusion module STDASPP is designed, and STDASPP fusion features are output; a semantic segmentation head based on a segmentation decoder SEGDecoder is established, a super-resolution head based on a super-resolution decoder SRDecoder is established, low-level detail features extracted by a backbone network and STDASPP fusion features are input into the semantic segmentation head and the super-resolution head at the same time, training is carried out in combination with four kinds of losses, and the accuracy of the semantic segmentation head and the super-resolution head is improved. And obtaining a trained crop classification model based on semantic super-division edge three-drive, and outputting a final crop classification result.

The invention discloses pesticide residue sampling analysis equipment and a pesticide residue sampling analysis method, and relates to the technical field of agricultural product detection. The upper end of the mounting main body is provided with a through hole along the length direction, the crop sampling module and the sample analysis module are arranged at the through hole, the transfer module can slide left and right along the bottom end of the mounting main body, and a box door is arranged on the side wall of the mounting main body; the crop sampling module can complete collection switching of a liquid sample and a solid sample, parts do not need to be replaced or complex debugging is not needed in the whole process, the requirements of different detection standards for sample types are met, and residue detection scenes of various agricultural products such as fruits, vegetables and grains can be covered; after sampling, the transfer module directly receives the sample and transfers the sample to the lower part of the analysis cylinder for detection, so that not only is the multi-step flow of sampling, transferring, sample loading and detection in the traditional operation integrated, but also the risks of splashing and pollution in the sample transferring process are avoided.

A method and system are provided for determining a threshing loss in a threshing system. The method includes irradiating a crop sample downstream at least a portion of a threshing system with electromagnetic waves having a frequency in a range of 0.1-10 THz, measuring a reflection and / or a transmission of the electromagnetic waves by the crop sample, establishing, based on the measured reflection and / or transmission, an at least two-dimensional terahertz image of the crop sample, identifying at least one ear in the terahertz image, identifying at least one grain kernel in the identified ear, and determining the threshing loss based on the identified grain kernel.

This invention discloses a method for refined crop identification based on multimodal remote sensing data feature fusion. The method includes acquiring multimodal remote sensing data and sample data of the study area; using the acquired high-resolution remote sensing images and cultivated land samples, performing dilated convolution and multi-scale feature fusion on a D-LinkNet model to obtain a D-LinkNet cultivated land segmentation model; combining multiple D-LinkNet cultivated land segmentation models through a voting decision process, and integrating the prediction results of each D-LinkNet cultivated land segmentation model to extract cultivated land spatial patches; using the acquired multispectral remote sensing images, hyperspectral remote sensing images, SAR remote sensing images, and crop samples to construct a multimodal crop identification model to generate multi-source feature fusion identification results; and overlaying and fusing the cultivated land spatial patches with the multi-source feature fusion identification results to determine the main crop types within each cultivated land spatial patch, obtaining a cultivated land crop classification map of the study area. This invention can achieve accurate extraction of cultivated land crops over a large scale.

The utility model discloses a crop research sample preparation device, and relates to the technical field of crop research. The ultrasonic cleaning device comprises a cleaning assembly, the two sides of the cleaning assembly are fixedly connected with adjusting assemblies, one side of each adjusting assembly is fixedly connected with an overturning assembly, the cleaning assembly comprises a cleaning box, and the bottom of an inner cavity of the cleaning box is fixedly connected with an ultrasonic cleaner. By means of the innovative design that the ultrasonic cleaner and the turnover placing basket are integrated in the cleaning box, the device achieves three-dimensional cleaning operation of crop samples, high-frequency vibration generated by the ultrasonic cleaner can form a cavitation effect through a water medium, tiny pollutants such as soil and pesticide residues on the surfaces of the samples are effectively stripped, and the crop samples can be cleaned conveniently. And the gear transmission piece driven by the double-output-shaft motor can drive the placing basket to turn over by 360 degrees, so that complex surface structures such as leaf wrinkles and fruit recesses of the sample can be fully exposed in an ultrasonic action range.

The invention provides a crop FAPAR inversion method and system based on adaptive spectral unmixing, and the method comprises the steps: obtaining a close-range multispectral image and a full-coverage multispectral image of a crop sample field, and obtaining the per-pixel reflectivity of each multispectral image; according to the pixel-by-pixel reflectivity of the close-range multispectral image, constructing a simplified spectrum library containing foreground and background end member spectrums based on an adaptive end member extraction method; constructing a crop-oriented pixel-by-pixel unmixing model based on the multiple linear model; based on an exhaustion cross pairing strategy, solving the full-coverage multispectral image pixel by pixel by using a simplified spectrum library and a crop-oriented pixel-by-pixel unmixing model, and obtaining a pixel-by-pixel foreground abundance unmixing result; fitting a linear regression model of the foreground abundance and the FAPAR, and inverting the FAPAR of the crops in the sample field based on the linear regression model.