78 results about "Plant identification" patented technology

The invention relates to the technical field of vegetation remote sensing recognition, in particular to a multispectral and visible light remote sensing image fusion segmentation method and system and a medium. The method comprises the following steps: constructing a double-branch model comprising a visible light branch encoder, a multispectral branch encoder, a multi-scale feature fusion module and a shared decoder; inputting the visible light data into a visible light branch encoder to obtain a spatial feature map; inputting the multispectral data into a multispectral branch encoder to obtain a spectral feature map; the multi-scale feature fusion module applies a channel-space joint attention weight to an input feature map, then performs channel splicing according to scales, compresses the feature map to an original channel number by adopting 1 * 1 convolution, and then applies a channel attention weight to obtain a multi-scale fusion feature sequence; and the shared decoder analyzes the multi-scale fusion feature sequence and outputs an invasive plant segmentation mask image of the target detection area, so that high-robustness invasive plant identification under a complex background is realized.

The invention provides an automatic plant identification method and system based on a neural network model, and relates to the technical field of intelligent agriculture, and the method comprises the steps: inputting a composite feature map into a compressed and optimized lightweight convolutional neural network model, and outputting a plant type identification result and a confidence value in real time; dynamically binding a plant type identification result with a geographic information system (GIS) coordinate, generating an endangered plant space distribution thermodynamic diagram and triggering a real-time alarm; images are automatically collected and marked based on newly-added plant sample positions marked in the spatial distribution thermodynamic diagram, and weight parameters of the lightweight convolutional neural network model are periodically updated. The plant identification and protection capability is comprehensively improved through the links of data acquisition diversification and standardization, image processing high efficiency and scientificity, feature extraction and identification accuracy, endangered plant protection and dynamic monitoring, model continuous optimization and adaptability and the like.

Described herein are techniques for generating contextually rich plant images. A number of data captures of raw plant data are generated via a sensing unit configured to navigate a growing facility. Metadata is generated and assigned to the raw plant data including at least one of: plant location, timestamp, plant identification, plant strain, facility identification, facility location, facility type, health risk factors, plant conditions, and human observations. Images generated by the sensing unit are analyzed and pixel annotations are generated in the images based on their relation to one or more plant well-being features. Data tags are generated and assigned the data captures based on an analysis of the data captures. The data tags are text phrases linking a particular data capture to a specific threat to plant well-being.

The invention provides a plant classification labeling method. The method comprises the following steps: S1, acquiring an orthoimage of a target area through an unmanned aerial vehicle, and segmenting to generate plant pattern spots; s2, superposing the orthoimage and the base map of the electronic map, and establishing a composite coordinate system; s3, displaying the superposed map on the mobile terminal, and receiving a marking instruction of a user on the pattern spots; when the user cannot identify the plant type, calling a plant identification API to classify the plant image uploaded by the user, and associating the result to the corresponding plant pattern spot; s4, storing the labeled plant data to a database, and supporting statistics and management of the vegetation types, number and distribution of the target area through a geofence function; s5, a visual interface is provided, a user is allowed to check detailed information of the plants by clicking map marks, the detailed information comprises names, photos and statistical results, through the plant classification marking method, the types, the number and the distribution of the vegetation in the statistical area can be systematically analyzed, data are accurate, and presentation is visual.

The invention refers to a system, device, and method for identifying and analyzing the plants, pests, insects, and other elements of a crop to control the spraying of agrochemicals in real time, monitor and analyze planting conditions, and present data to the user for decision-making.The system comprises a device (7) on the spray boom of the agricultural vehicle that communicates with server (5) in the cloud that communicates with the user interface platform (8) and with the operator interface (10) in the cabin of the sprayer vehicle. The device (7) captures the images during operation, processes and decides the need for spraying, and controls the solenoid valves (3) of the spray nozzles, stores the images and information acquired in the field in memory, and sends them to the server (5) via the Wi-Fi connection.

A plant recognition method and related devices. The plant recognition method includes: obtaining a plant image and question text about recognizing the plant in the plant image; inputting the plant image and the question text to a plant recognition model, the plant recognition model includes a first visual model and a multimodal large language model, the first visual model is configured to receive the plant image to extract first image features of the plant image, the multimodal large language model is configured to receive the first image features and the question text to recognize the plant in the plant image, the plant recognition model is trained with multimodal data, the multimodal data includes plant images, questions about recognizing plants in the plant images, and answers to the questions; and outputting answer text provided by the plant recognition model about recognizing the plant in the plant image.

The invention relates to a parameter control method and device of a plant growth cabin, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a plant identifier and a corresponding growth stage of a plant in a plant growth cabin, weather prediction data and current environment data collected by different environment sensors in the plant growth cabin; determining expected environment data of the plant growth cabin according to the plant identifier and the growth stage; generating an initial control strategy of the plant growth cabin according to the difference between the expected environment data and the current environment data; generating environment change prediction data of the plant growth cabin according to the weather prediction data; and according to the environment change prediction data, adjusting the initial control strategy to obtain a target control strategy. By adopting the method, the intelligent level of environment regulation and control in the plant growth cabin can be effectively improved.

A plant marker with integrated insect monitoring capability. The plant marker includes a base layer having a rectangular segment and a pointed segment configured for soil insertion. The rectangular segment includes an upper surface coated with adhesive material for capturing insects and an underside surface formed of markable material for receiving plant identification information. A removable liner covers the adhesive material prior to use. The device enables simultaneous plant identification and pest assessment.

The invention discloses an immature bitter orange-based original plant identification method based on an InDel molecular marker and a special primer combination, and belongs to the technical field of traditional Chinese medicinal material identification. In order to solve the problem of uncontrollable quality of medicinal materials caused by miscellaneous immature bitter orange base (lime, sweet orange and Yichang orange) in the prior art, two pairs of specific primers YCC-F / R (SEQ ID NO: 1-2) are screened out through genome re-sequencing and are used for specific identification of the Yichang orange (amplifying a single bande-1000bp); the invention relates to a specific primer for identifying three primary plants, in particular to a specific primer for identifying three primary plants, namely SC-F / R (SEQ ID NO: 3-4), which is used for distinguishing acid orange (single bande-1300 bp) and sweet orange (double bande-1200 bp / 1300 bp), and triple accurate identification of the three primary plants can be realized by combining PCR (Polymerase Chain Reaction) amplification and gel electrophoresis analysis. The method is simple and convenient to operate, low in cost, short in period and suitable for large-scale source tracing and quality control of medicinal materials.

The invention discloses an urban green plant identification method and device, a medium and equipment, and relates to the technical field of image identification, and the method comprises the steps: obtaining a to-be-identified remote sensing image; deep features in the remote sensing image are extracted, multi-scale spectral features in the deep features are obtained, the deep features and the multi-scale spectral features are fused, and a multi-spectral feature map is generated; wherein the deep features comprise color features and texture features; extracting strip features and multi-scale shape features in the remote sensing image, and fusing the strip features and the multi-scale shape features to generate a multi-shape feature map; performing weighted fusion on weights corresponding to the multi-spectral feature map and the multi-shape feature map to determine a fused feature map; and recovering the resolution of the fused feature map to the size of the original image, and classifying the feature map with the recovered resolution to obtain a final urban green land classification result.

The invention discloses a minimum population wild plant identification and early warning method and system. The system comprises: an environmental DNA monitoring network unit, which analyzes environmental DNA through automatic sampling, evaluates the state of species and triggers a first early warning; the biological voiceprint monitoring and recognition unit is used for monitoring related acoustic activities and illegal intrusion behaviors of the target species by using intelligent recording nodes deployed in a gridding manner and a voiceprint recognition model, and triggering second early warning; and the multi-source information fusion and causal inference unit is used for integrating the environment DNA, the voiceprint and the meteorological data, analyzing the causal relationship among the ecological factors based on a causal inference model, generating protection measures and outputting comprehensive early warning. According to the invention, all-weather, interference-free and precise monitoring of the extremely small population wild plants is realized, the problems of low efficiency, many blind areas, large interference and the like of a traditional monitoring mode are solved, and effective technical support is provided for protection of rare plants.

The invention relates to the technical field of tobacco plant identification and counting, and discloses an unmanned aerial vehicle tobacco plant identification and counting method and system based on improved deep learning, which combines technologies of image classification, image segmentation, feature point extraction, machine learning, target detection and the like with refined intelligent identification of tobacco. According to the method, high-precision image recognition and analysis are realized by utilizing the efficient feature extraction and calculation capability of the method, point plant counting can be accurately performed, the efficiency and precision of agricultural production are greatly improved, the problem of calculation complexity of a traditional method in large-scale high-resolution image processing is solved, and powerful technical support is provided for precision agriculture. Therefore, the invention provides an unmanned aerial vehicle tobacco plant identification and counting method based on improved deep learning target detection and multi-dimensional post-processing, and high-precision and robust detection and counting of tobacco plants in large-scale tobacco field orthoimages are realized by constructing a three-stage assembly line of image preprocessing, improved target detection and multi-dimensional post-processing.

The application discloses a plant specimen identification method, and relates to the technical field of plant identification, which comprises the following steps: extracting multi-dimensional data information in a plant specimen image, performing feature recognition on the extracted multi-dimensional data information, and obtaining corresponding multi-dimensional data features; performing feature coding based on the obtained multi-dimensional data features, obtaining a corresponding feature matrix, performing feature fusion on the obtained feature matrix, and obtaining corresponding multi-modal features; performing feature classification on the obtained multi-modal features by using a classification model, comprehensively deciding a classification result, and obtaining an identification result of the plant specimen; the application effectively fuses data of two different modes of images and texts, overcomes the problem of limited single-mode identification information, and can significantly improve the automation level and accuracy of plant specimen identification.

A farming machine moves through a field and includes an image sensor that captures an image of a plant in the field. A control system accesses the captured image and applies the image to a machine learned plant identification model. The plant identification model identifies pixels representing the plant and categorizes the plant into a plant group (e.g., plant species). The identified pixels are labeled as the plant group and a location of the pixels is determined. The control system actuates a treatment mechanism based on the identified plant group and location. Additionally, the images from the image sensor and the plant identification model may be used to generate a plant identification map. The plant identification map is a map of the field that indicates the locations of the plant groups identified by the plant identification model.

The utility model belongs to the technical field of plant identification, and particularly relates to a simple number plate for trees, which comprises a mounting plate, a fixing plate and a fixing plate. The inner walls of the two sides of the containing groove are each provided with a clamping groove, and a limiting inclined plate is further arranged outside each clamping groove. The rear end of the limiting inclined plate is fixed on the rear wall plate of the accommodating groove, and the front end is provided with an inclined surface; the number plate main body comprises a first plate body and a second plate body; the first board body is located in the containing groove, and the two sides of the first board body are each provided with a first guide groove. A buckling piece is arranged in the guide groove I, and is matched with the clamping groove in the corresponding position; the second board body is located at the front end of the first board body, and two sides of the second board body exceed two sides of the first board body. The utility model can solve the problem that the number plate is inconvenient to take out and replace due to too tight insertion in the mode of inserting and fixing the number plate in the prior art, and has a better market application prospect.

The application relates to the technical field of base station survey, and discloses an intelligent terminal automatic survey data analysis and processing method and system based on deep learning, which comprises a server, an intelligent terminal and a monitoring device; the server is used for receiving base station information corresponding to each base station collected by the monitoring device; the intelligent terminal comprises a data acquisition module, a data calling module, a plant identification module and a processing module; the processing module is used for determining the base station influence degree of main plants corresponding to each base station according to surrounding environment data corresponding to each base station, plant standard growth demand information, base station basic information and base station surrounding plant growth video information; and the analysis module is used for adjusting and optimizing base station equipment corresponding to each base station based on a preset base station equipment adjustment strategy according to the base station influence degree of main plants corresponding to each base station, and outputting a corresponding base station equipment adjustment scheme.

A tree and shrub identification tag device is provided. The device is comprised of a tag designed for efficient and adaptable plant identification while promoting environmental sustainability. The device comprises eco-friendly materials, including biodegradable and recyclable plastics, to ensure durability and weather resistance through UV protection additives and waterproof coatings. The tag body is available in various sizes and features a rubberized texture for enhanced grip. A notched slot at one end allows for secure attachment and easy removal, while perforations facilitate damage-free detachment from around a plant. The device may also be comprised of a color-coding system for categorizing plant types and includes a customizable surface for detailed labeling. Additionally, the tag may incorporate QR codes for accessing digital resources such as care guides and supplier information, enhancing overall plant management and user experience.

The application belongs to the technical field of vegetable breeding, and provides a SSR primer for identifying purity and authenticity of cucumber Jingyan Dongmei No.9 hybrid. The SSR primer provided by the application has polymorphism among parents, and all shows co-dominance, and shows clear, stable and parent complementary band type in hybrid offspring, and has strong specificity, and can be used to distinguish mixed maternal, paternal and other variety seeds; the application provides a convenient, accurate and efficient identification method for identifying purity and authenticity of Jingyan Dongmei No.9 variety, and can completely replace field planting identification to avoid resource waste, save land and manpower and material resources.

A laser-based weed control module (1) and a device and a method for laser-based weed control, which permit targeted control of weed plants (17) on agricultural areas (15) with high effectiveness and simultaneously high efficiency. The weed control module (1) comprises an image detection unit for providing three-dimensional image data, a laser unit (4) for generating and orienting a laser beam (5) and a data processing and control unit (6), wherein the data processing and control unit (6) contains a trained artificial intelligence that detects weed plants (17), identifies survival essential plant part of the weed plants (17) and controls the weed plants (17) by targeted laser-irradiation the survival essential plant part of the weed plants (17) in an environmentally friendly and chemical-free manner. The generated laser beam (5) has a light wavelength (A) in the range from 955 nm to 995 nm.

The application provides a rape seedling stage hetero-plant positioning method and a hetero-plant removing method, wherein the rape seedling stage hetero-plant positioning method comprises the following steps: obtaining an image containing a plurality of seedling stage plants in a plot; identifying all the seedling stage plants in the image to obtain plant pictures, and configuring index information for each plant picture; extracting features of each plant picture based on high-dimensional features of a preset dimension to obtain a feature vector; calculating the Euclidean distance between any two feature vectors to determine the outlier index of each feature vector; presetting an outlier index threshold to screen plant pictures corresponding to feature vectors whose outlier indexes exceed the preset outlier index threshold; and determining the position information of the screened plant pictures according to the index information to obtain the position information of the hetero-plant. The application is used to solve the problem that in the prior art, a large amount of variety and feature data is required in the database, and it is still difficult to achieve high-precision hetero-plant identification.

The application discloses a kind of molecular markers for Camellia genus Camellia reticulata group plant identification, which is composed of 3 Camellia reticulata specific DNA sequences.The application also provides a Camellia reticulata identification method based on the molecular markers, and the operation process is as follows: total DNA extraction is carried out on the sample to be tested, then high-throughput sequencing is carried out, the sequencing reads obtained are compared with the molecular markers, and if the sequencing reads can completely cover the molecular markers, it can be determined that the sample to be tested belongs to Camellia reticulata.

This invention relates to the field of plant identification technology and discloses a method for single-plant identification and stem-leaf separation based on 3D point cloud data processing technology. The method includes: acquiring multi-view 3D point cloud data of the target plant region to obtain raw point cloud data; preprocessing the raw point cloud data to obtain preprocessed point cloud data; determining the single-plant point cloud dataset based on the preprocessed point cloud data and a single-plant segmentation model; extracting features from the single-plant point cloud dataset to obtain the geometric, texture, and color features of each point cloud; determining the type of point cloud based on its geometric, texture, and color features; and obtaining the stem-leaf separation result based on the point cloud type. For plants with complex and narrow structures, this method accurately segments single plants and distinguishes stems and leaves through multiple features, improving the accuracy of separating stems and leaves from special-shaped crops.

The present invention relates to an agricultural implement (1) for cultivating an agricultural area (LF), in particular an agricultural spreading implement (1) for spreading agricultural material onto the agricultural area (LF), wherein the agricultural implement (1) comprises at least: - a recording device (2) which is designed to record the agricultural area (LF) and to output recording data (14), - a working device (8) which is designed to work the agricultural area (LF), - a control device (17) which is arranged - for evaluating the recording data (14) of the recording device (2) and for determining plants (P) on the agricultural area (LF) on the basis of the evaluated recording data (14), - for identifying plant rows (5) based on the identified plants (P), - for determining a plant row area (6) based on the identified plant rows (5) and an intermediate area (7) between the identified plant rows (5), and - for controlling the working device for processing the determined plant row area (6) and / or the determined intermediate area (7). The invention is characterized in that the control device (17) comprises a first computing unit (3) and a second computing unit (4).

The invention provides a method for efficiently removing abnormal plants in the rape seed production and cultivation process, and belongs to the technical field of agricultural seed production. The method comprises the steps that the shape and area parameters of a rape field are obtained, grid-shaped division is conducted in combination with the optimal plant spacing and the size of an intelligent mobile robot, grids are sowing blocks, and a rape seed is sown; when the rape seeds grow to a preset stage, an intelligent mobile robot carrying an image recognition and impurity removal execution module is moved to the front of a typical rape plant which is manually confirmed, an image recognition module recognizes an image and extracts features, and target image features are obtained; the robot is driven to move along the moving path, the image recognition module recognizes all rape plants in the field according to target image features, and when the rape plants are recognized as abnormal plants, the impurity removal execution module is started to remove the abnormal plants. According to the method, through accurate planning, standard plant calibration and automatic identification and impurity removal, the efficiency, precision and cost control of impurity plant removal are considered, and technical support is provided for intelligent and large-scale development of rape seed production.

The invention belongs to the technical field of plant identification, and relates to a ginseng appearance quality detection method fusing multi-scale feature extraction and knowledge distillation, which comprises the following steps: 1, data acquisition: uniformly and respectively shooting ginseng samples from multiple angles to obtain a ginseng sample data set; 2, data enhancement: dividing a ginseng sample data set into a training set, a verification set and a test set in proportion; 3, constructing a YOLOv11n network; according to the method, efficient operation can be realized on edge equipment, so that the method is particularly suitable for being deployed under field conditions with extremely high requirements on real-time analysis; the capability greatly improves the accuracy and reliability of crop monitoring and management, and makes an important contribution to the development of intelligent agriculture.

The application discloses a kind of urban green plant identification method, device, medium and equipment, it is related to image recognition technical field, including obtaining remote sensing image to be identified;Deep feature in remote sensing image is extracted, obtain multiscale spectral feature in deep feature, deep feature and multiscale spectral feature are fused, generate multispectral feature map;Wherein, the deep feature includes color feature and texture feature;Strip feature and multiscale shape feature in remote sensing image are extracted, and strip feature and multiscale shape feature are fused, generate multi-shape feature map;By corresponding weight of multispectral feature map and multi-shape feature map is weighted fusion, determine the feature map after fusion;The resolution of the feature map after fusion is restored to original image size, then the feature map of recovery resolution is classified, obtains the final urban green classification result.

The application discloses a plant carbon fixation amount measuring and calculating method based on a UAV oblique photography technology, and comprises the following steps: 1, collecting and scanning image data of a plant scene; 2, obtaining a vector model of the plant scene by adopting an oblique photography technology to vectorize the collected image data and derive a vector model; 3, screening and identifying different plants in the vector model; 4, identifying and screening different parts of the plant tissues; 5, calculating the volume of the different parts of the plant tissues; and 6, calculating the carbon content of the plant. The application is based on a UAV and an oblique photography technology, and is assisted by a ground shooting technology, so that accurate analysis of the carbon fixation amount of arbor greening resources can be realized, timely and fast data comparison can be provided, and the application can also be used as an important review method for calculating the carbon fixation amount in the field of greening carbon sink.

A method for calibrating performance characteristics of a farming machine using a performance report is described. The farming machine accesses images of plants in a field captured during the calibration pass. The images are input into a performance model to generate a performance report by identifying plants in the images using a plurality of identification sensitivities and determining expected performance characteristics of the farming machine for each of the identification sensitivities. As such, the performance report includes expected performance characteristics for each identification sensitives. The farming machine accesses a target performance characteristic (e.g., from an operator) for the farming machine corresponding identification sensitivity. Images are input into a plant identification model during a treatment pass which identify a plant in the field using the identification sensitivity corresponding to the target performance characteristic. The farming machine treats the plant in the field using a treatment array of the farming machine.

This invention discloses a multi-source remote sensing identification method for allergenic wormwood based on FSDAF spatiotemporal fusion. It integrates high-resolution remote sensing satellite imagery (optical and radar images) combined with UAV data and multi-source data from ground meteorology and vegetation monitoring. Utilizing advanced technologies such as FSDAF spatiotemporal fusion, it constructs an identification model for allergenic wormwood based on the spectral, texture, density, and geometric characteristics of the plant's growth period. This model identifies severely invaded areas of allergenic wormwood, achieving high-precision automatic identification and spatial distribution mapping of allergenic wormwood over large areas. Based on the identification model and growth status analysis model, it accurately analyzes the distribution area and severity of damage of allergenic wormwood within different administrative divisions, providing a basis for implementing targeted wormwood control measures.

The embodiment of the invention relates to the technical field of computer vision and deep learning, and provides a construction method of a field plant identification model and a field plant identification method, and the method comprises the steps: obtaining a field shot image, carrying out the image preprocessing, and constructing an image data set; constructing an initial feature extraction network by using the lightweight bottleneck structure; dividing a feature map channel into a plurality of subgroups by adopting a spatial feature enhancement mechanism in the initial feature extraction network, improving the network by adopting average pooling and maximum pooling in each subgroup, obtaining a target feature extraction network, constructing an initial field plant identification model, and performing model training to obtain a target feature extraction network; an Adam optimizer is adopted for optimization training in the model training process, the model training effect is evaluated through a plurality of preset comprehensive evaluation indexes, when the comprehensive result of the plurality of comprehensive evaluation indexes is optimal, it is determined that model training is completed, and the target field plant recognition model is obtained. And efficient, robust and low-calculation-cost plant detection and identification are realized.