138 results about "Plant identification" patented technology

A method for providing an expanded name service for an industrial automation system, wherein name-address assignments between device names and communication network addresses are registered in a name service system to provide an expanded name service for an industrial automation system, where device names registered in the name service system have a hierarchical structure represented by a tree structure, where assignments between device names and plant identification codes are additionally registered in the name service system, where the plant identification codes are registered within the same tree structure as the device names, and where end nodes that are respectively assigned to the plant identification codes in the tree structure comprise either a reference to end nodes which are respectively assigned to the device names or intermediate nodes for plant identification codes comprise a reference to intermediate nodes that are respectively assigned to plant units.

Methods and apparatus for determining when plants require watering, and methods of attending to the watering of plants including signaling the grower that the plants are in need of hydration are provided. The novel methods include real-time measurement of plant metabolics and phytometric physiology changes of intrinsic physical or behavioral traits within the plant such as determining physiological flux measurement of enzyme flux due to environmental changes such as the wind and drought stress, soil and plant mineral deficiencies, or the interaction with a bio-control for organic disease control including, cell movement, signal transduction, internal chemical processes and external environmental processes including when plants require watering, and methods of attending to the watering of plants including signaling the grower that the plants are in need of hydration.

Methods of compiling a database of images of plant species and the use of the database to identify unknown plant species are described. Images of the apical complexes of the plant are obtained and stored in a database to allow a comparison of the apical complexes with unknown plant species. The invention provides a facile method for the identification of unknown or unidentified plant species.

The invention provides a semantic segmentation and point cloud processing combined plant recognition and model construction method. The method comprises the following steps: 1, generating an orthoimage according to a landscape image obtained by oblique photography; 2, training a deep learning network, and performing semantic segmentation on the orthoimage by a neural network to identify a plant region; 3, generating a point cloud corresponding to the image, and realizing coordinate correspondence between point cloud data and the orthoimage through coordinate system conversion; 4, segmenting the point cloud data to obtain a plant area point cloud; 5, in combination with oblique photography images and point cloud data, plant species are further recognized through k-means point cloud clustering, target detection and other methods; 6, establishing a plant model library; 7, processing the point cloud of the plant area, determining parameters including plant types, positions, sizes and the like, and importing a plant model to replace the point cloud; and 8, converting the plant model into a required format. According to the invention, efficient and accurate recognition of plant species and construction of a three-dimensional plant scene with a sense of reality can be realized.

The invention discloses a plant identification method and system based on a convolutional neural network. The method comprises the following steps of collecting plant images, classifying and marking similar plants in the plant images, and obtaining a plant database; inputting the plant images in the plant database to the convolutional neural network, and training the convolutional neural network to get a feature matching model; receiving to-be-recognized images, extracting the image eigenvalues of the to-be-recognized images by using the feature matching model, calculating the similarity between the image eigenvalues and the plants in the plant database, and judging the classification of the plants which the to-be-recognized images belong to according to the similarity. The plant identification method and system based on the convolutional neural network achieve the adaptability of plant identification, reduce the design difficulty and calculation amount, and improve the efficiency of the plant identification.

The invention provides a plant viewing method and device, an electronic device and a storage medium. The method comprises the following steps of step S11 starting the viewing and obtaining a first position of a target user; S12 determining the target plant species to be viewed selected by the target user, and marking each viewing place in the region where the first position is located in a first manner on the region map; S13 planning an ornamental route passing through each ornamental place in turn from the first position; S14 acquiring a plant picture uploaded by the target user, and identifying a plant species corresponding to the plant picture through a pre-trained plant identification model; S15 if the identified plant species belong to the target plant species, marking the current viewing place in a second manner on the area map, and returning the execution step S14 until all the viewing places are marked in the second manner, and the viewing is ended. The invention can solve theproblem of poor experience in plant ornamental in the prior art.

The invention discloses a plant identification method and device with a high identification rate. The method includes the specific steps that firstly, a plant organ digital image is collected through an image collection unit and serves as a test sample; secondly, the sample is preprocessed to obtain a gray level image; thirdly, feature extraction is carried out on the gray level image through a pulse-coupled neural network so as to obtain an entropy sequence capable of reflecting the gray level image; a high plant identification rate can be obtained through a support vector machine classifier with the entropy sequence as a main feature and the morphological features as auxiliary features. The plant identification method and device can achieve simple and accurate identification of large sample data (with a large number of plant species to be distinguished) and have a high identification rate and strong adaptability; tests on existing databases verify that the accuracy rate of the plant identification method and device reaches more than 98%.

The invention provides a plant species identification method based on a digital image. The method comprises the following steps: collecting a plant organ digital image as a test sample, and extracting a characteristic vector; inputting the characteristic vector into a first stage classifier, and obtaining first n species in a vote number ranking, wherein n is larger than 3 and smaller than 10; the first stage classifier is obtained through the following modes: carrying out classifier training based on a characteristic set of all training samples; inputting the characteristic vector into a second stage classifier, and obtaining an identification result; the second stage classifier is obtained through the following modes: extracting a characteristic set corresponding to the n species from the characteristic set of all training samples to carry out classifier training. According to the invention, through a grading SVM classifier, sensitivity of the classifier to sample kind quantity is effectively reduced, influence of sample species increase on identification accuracy is eliminated, a problem of low accuracy of large sample size identification by the SVM classifier is overcome, and plant identification accuracy is raised.

The invention belongs to the technical field of plant cultivation and relates to an Internet of Things-based intelligent maintenance system for a roof garden and a control method of the intelligent maintenance system. The Internet of Things-based intelligent maintenance system for the roof garden comprises an acquisition module (1), an image recognition module (2), a control module (3), a cloud server (4) and an execution module (5); the execution module (5) comprises a spraying system (6), a drip irrigation system (7), and a water and fertilizer mixing system (8). According to the control method of the Internet of Things-based intelligent maintenance system for the roof garden, a plant identification unit (12) is used for identifying plant species in the roof garden and the growth cyclesof the plant species; the acquisition module obtains the soil temperature value, soil moisture value, and soil electrolyte content value of the roof garden; the control module (3) compares the data and controls the operation of the execution unit; and therefore, death caused by dehydration and root rotting can be avoided.

The invention provides an automatically generating method and device of a power plant identification system code. The method includes the following steps that according to a selected system diagram, a page is drawn, and the machine group number of a power plant identification system is determined; according to a selected graphic primitive matched with the engineering design structure of power plant equipment, a power plant identification system classification code of the graphic primitive is read; for the system diagram drawn by the graphic primitive, a power plant identification system number corresponding to the system diagram is generated; according to the machine group number of the power plant identification system, the power plant identification system classification code and the power plant identification system number, the power plant identification system code of the system diagram is generated. According to the method and the device, automatic generation and automatic labeling of the power plant identification system code of the system diagram can be achieved through a computer system, the coding error rate, the repeat code rate and the labor cost are reduced, the digital management and safety operation level of an enterprise are improved, the working efficiency is improved, unified, scientific, correct and complete power plant identification system code data is provided for the application of the method and the device, and the integrated cost of the enterprise is largely reduced.

The invention provides a plant identification system and identification method. The plant identification system comprises an onboard device carried by an unmanned aerial vehicle and a ground device. The onboard device comprises a camera, a GPS module, an unmanned aerial vehicle image transmission module and an unmanned aerial vehicle data transmission module. The ground device comprises a ground image transmission module, a ground data transmission module, a target tracking module, an augmented reality module and a display module. The ground image transmission module receive a video stream transmitted by the unmanned aerial vehicle image transmission module; the ground data transmission module receives data information transmitted by the unmanned aerial vehicle data transmission module; the target tracking module detects the position of a target object on a screen in the video stream and provides the type of the object; the augmented reality module overlays a virtual model which needs to be displayed on the target object into the video stream and transmits the result to a display screen for display. The onboard device carried by the unmanned aerial vehicle is used for shooting, so that the system can be used for scenes which are inaccessible for many users, such as the centers of some lakes and wetland and can assist the users in identifying plants in the scenes.

The invention discloses a plant recognition method based on deep learning and plant taxonomy. The sample plant image is marked by the subject, the genus and the species; the sample plant image is input into a deep convolutional neural network for training. And the loss function are set as the weighted sum of the cross entropy loss of the subject, the genus and the type of tags, the weight of the neural network is updated through a random gradient descent algorithm, the training concludes after the deep convolutional neural network converges, and the weight of each layer without changing is fixed to obtain the trained deep convolutional neural network. According to the invention, deep learning is combined with plant taxonomy, and a subject label is introduced as a learning target, so that the recognition accuracy is improved.

The invention relates to a desert plant remote sensing identification method using object-oriented multi-source information fusion. The method comprises the following five units: a large-area multi-source information inlay unit, an object-oriented image segmentation unit, a multi-source information fusion unit, an interpretation rule making unit and a desert plant identification unit. In the prior art, the following conditions that desert plant distribution is sparse; growth spectrum information is weak; desert plants are easily influenced by diffuse reflection; and phenomena of a mixed pixel and a same object with different spectrums are remarkable are not considered. Aiming at the above problems, the desert plant remote sensing identification method using the object-oriented multi-source information fusion is researched and developed so that problems that desert plant types and space-time distribution can not be accurately identified in fields of ecological remediation, a climatic change, a biological diversity, genetic development, poverty elimination and the like can be solved. A technical support is provided for a correlation research mechanism, a commonweal organization, an enterprise and a government. A data analysis basis is provided for exploitation, construction and management of a desert plant industry in an arid region.

The present invention provides an animal / plant identification method and system for a mobile terminal. The method comprises steps of: acquiring a photo of a to-be-identified animal / plant that is taken by a mobile terminal; performing feature scanning on the to-be-identified animal / plant; comparing and matching a found feature with animal / plant photo samples in an animal / plant database; and if the matching is successful, acquiring a matching animal / plant photo sample from the animal / plant database, and displaying the matching animal / plant photo sample. Various animals and plants can be identified intelligently on the mobile terminal, which helps general users know new things rapidly.

The invention provides a plant identification method and device. The method comprises the following steps: S1, acquiring a plant image containing a to-be-identified target plant; S2, determining the attribute of the target plant according to the attribute information of the plant image; and S3, calling a plant identification model associated with the attribute of the target plant from a pluralityof plant identification models associated with different attributes of the plant to identify the plant image, and determining the plant information of the target plant, the plant identification modelbeing a neural network model. By applying the scheme provided by the invention, the accuracy of the plant identification result can be improved.

A plant container having a frustoconical sidewall extending outwardly and vertically from a bottom of the container to a top of the container, a lip positioned near the top of the container, and a tag-accepting slot formed in the lip. The container may also include a first nesting step located below the lip and extending circumferentially around the container, the nesting step extending outwardly to a maximum circumference and including a container-stacking stop surface extending between the sidewall and the maximum circumference and a extending vertically from the maximum circumference. Further, the slot may substantially be positioned above a slot area, the slot area being an area where the maximum circumference of the nesting step is reduced

A plant or garden marker assembly comprising a ground stake element, preferably constructed of rigid metal wire, and an identification plate element, preferably fabricated of sheet metal. A decal is applied to a flat portion of the plate for purposes of plant identification. Flanged front and rear sections of the plate feature holes through which the stake is threaded to enable the plate to be friction mounted thereupon. The plate may also be detached from the stake, allowing a single stake to be used with different plates displaying various plant identifications.

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 disclosure provides a method for extracting, separating, and identifying compounds from natural products, such as cannabis or hops, where separation uses gas chromatography (GC). The method includes spiking the composition to be identified with at least two markers that bracket the migration position of at least one of the compounds to be identified, where GC method uses more than one ramping step.

The invention provides a central device, an information processing system, an information processing method and a program. The central device can store a plurality of pieces of operation information of textile machines provided in a plurality of plants, and also can generate report information including the plurality of pieces of operation information of textile machines and abnormality information of each plant. A server computer receives from a client computer plant identification information, machine identification information, unit identification information and a plurality of pieces of operation information on operating states of a textile machine and units. The server computer stores the received a plurality of pieces of operation information in a storing section in association with the plant identification information, the machine identification information, and the unit identification information. When the operation information stored in the storing section exceeds a threshold, the server computer determines that the information is abnormal. The server computer also generates report information per plant identification information, including the operation information of each textile machine and each unit of the textile machine, and abnormality information to identify the determined abnormal operation information.

The invention discloses a plant identification method, and the method comprises the steps: carrying out the preprocessing: enabling a plant image to be converted into a binary image; feature extraction, which is used for extracting relative features in the image to form a feature data matrix; the classification and identification module is used for constructing a neural network model based on deeplearning, the model adopts a five-layer BP neural network and four full connection layers, and the last layer is a normalized layer; and the model is trained for subsequent plant identification. According to the method, the representative eight relative characteristics are adopted, so that the method can be suitable for identification of most plants, and compared with the prior art, more plant types can be identified to a greater extent, and the identification accuracy is improved.

The invention provides a method for extracting features of multi-temporal complete-polarization SAR images and a classification method of plant distribution regions. The method for extracting featuresof multi-temporal complete-polarization SAR images comprises steps of acquiring multi-temporal complete-polarization SAR images in the same region including various kinds of plants; segmenting the multi-temporal complete-polarization SAR images so as to obtain multiple targets; establishing multi-order tensors for each target, wherein the first stage and the second stage in the multi-order tensors represent lines and rows of coherence matrixes or covariance matrixes of the target respectively and the third stage in the multi-order tensors represent different time phases; and by use of a multilinear principal component decomposition algorithm, carrying out dimension reduction on the multi-order tensors of each target so as to obtain feature vectors of each target. According to the invention, by extracting features of the multi-temporal complete-polarization SAR images, difference between plants is improved. A DT classification result represents that even if a training sample is quite small, by use of the provided method, quite high plant identification precision can be acquired.

A plant information management system comprising: a seed identification information input device; an individual plant identification information retrieval device; an individual plant identification information input device; a new seed identification information retrieval device; a storage location information retrieval device; a project database management device; a seed database management device; a project database memory device; and a seed database memory device.

The invention relates to an automatic plant identification method and system. Plant point cloud data of different types and different single bodies are obtained to built a training set for plant identification, shape feature vectors of plants are calculated, parameters of a plant identification algorithm and the possibility that the to-be-identified plant single bodies belong to the plant types are calculated on the basis of the shape feature vectors, and the type having the highest possibility is selected to serve as the type of the plants. The automatic plant identification method is simple in process, convenient to use and practical, improves work efficiency of automatic identification of the plants, reduces work quantity, and is suitable for classification identification work of a large number of plants.

The invention discloses a method and device for implementing a light supplementing system of a plant light recipe based on artificial intelligence. The method comprises the steps of collecting a plant image; identifying and acquiring plant type information and growth stage information according to the plant image; calling corresponding light recipe data according to the plant type information and the growth stage information; and adjusting the light output ratio of plant lamps according to the light recipe data. The device comprises a high-definition image acquisition module; a plant light recipe database, a plant identification module, a plant lamp module and a control module. According to the invention, the growth conditions of different plants in different stages are identified, the plant lamps are accurately controlled to provide optimal light supplementing strategies for the plants, different requirements of different plant growth on spectrums are met, and the growth benefits of the plants are maximized.

The invention discloses a method for rapidly identifying scab resistance of a wheat. The invention provides an identification method for identifying the resistance characteristic of the detected wheat against gibberellic disease by utilizing change of physiological parameters of wheat photosynthesis organs related to photosynthesis before or after the wheat is infected with bacteria aiming at the defects of the identification method in the prior art that the identification process is time-consuming and the identification result is affected by artificial subjective factors. The concrete physiological parameters include an intercellular CO2 concentration value Ci, a limiting value Ls of stomata, relative difference degree of a stomatal conductance value Gs and a net photosynthetic rate value Pn, variation amplitude of the net photosynthetic rate value Pn, and the like. According to the technical scheme provided by the invention, one or more parameters are used for indentifying resistance characteristic of the gibberellic disease of wheat plants individually or all together. The invention also provides a preferable method in which wheatear parts are used as photosynthesis organs. The method is high in identification result accuracy, high in repeated reproducibility level, fast and efficient, and can be suitable for living plant identification.

The invention provides a plant identification and classification method based on a three-dimensional point cloud contour fractal dimension value. Three-dimensional information of the surface of the measured object is rapidly and efficiently obtained by using a three-dimensional laser scanner; a fractal dimension value of the plant contour point cloud data is calculated through a Minkowski dimension method; plant types are distinguished by utilizing a plant three-dimensional point cloud contour fractal dimension value; intelligent degree is high, plant identification is high in efficiency and accuracy, the method is a brand-new scientific and technological means for acquiring object space three-dimensional coordinate information; three-dimensional information of a plant is obtained througha three-dimensional laser scanner; the plant identification work is changed from outdoor to indoor; plant characteristics are extracted by utilizing three-dimensional information of plants, plant classification is realized by utilizing the plant characteristics, the plant identification and classification method based on the three-dimensional point cloud contour fractal dimension value is small inworkload, high in classification speed, high in efficiency, low in cost and few in errors, and the accuracy and reliability of plant identification and classification are greatly improved.