23results about How to "Realize automatic extraction" patented technology

The application relates to a target feature point extraction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a to-be-processed image; acquiring a template corresponding to the to-be-processed image and acquiring the position relationship between the template and standard feature points; the template is an image generated based on a sample image, and the standard feature points are located in the template; registering the template to the to-be-processed image; according to the position relationship between the template and the standard feature points and the position relationship between the registered template and the to-be-processed image, determining target feature points corresponding to the standard feature points in the to-be-processed image. The method can realize automatic extraction of target feature points.

The invention discloses a rock internal crack detection method and system based on fault enhancement, and the method comprises the steps: collecting an original image of a rock internal structure, and carrying out the multi-scale decomposition, and obtaining a low-frequency component and a high-frequency component; performing denoising processing according to the low-frequency component and the high-frequency component to obtain a denoised image; using an edge detection algorithm to extract crack boundary features in the de-noised image to obtain a boundary enhanced image; and obtaining a final crack detection result based on the boundary enhanced image. According to the method, the overall structure and detail features of the rock image are effectively separated through multi-scale decomposition, and the precision and integrity of crack recognition are remarkably improved in combination with targeted denoising and boundary enhancement processing; furthermore, on the basis of image segmentation and spatial analysis, automatic extraction and distribution rule quantification of the crack region are realized, so that a reliable and efficient technical means is provided for accurate evaluation of the internal structure of the rock.

This invention relates to a rapid, non-destructive testing method and system for lipid content and deterioration degree in red pine nuts based on hyperspectral imaging and deep learning. The invention belongs to the field of non-destructive testing technology for agricultural and forestry product quality and safety. It addresses the problems of existing methods for detecting lipid content and oxidation degree in red pine nut kernels, which generally suffer from complex operation procedures, high costs for large-scale testing, long processing times, and difficulty in achieving full-process testing during storage and transportation. Key technical points: The original near-infrared spectral data of pine nut samples are obtained through hyperspectral acquisition; the true values ​​of lipid reference content and reference degree of oxidation deterioration of pine nut samples at different sampling times are determined, and a database is established based on these values. The original near-infrared spectral data of red pine nuts are preprocessed, and the data from different batches of red pine nut samples are divided into training and validation sets. An improved one-dimensional dilated convolutional network based on a dynamic weight allocation module is designed to construct a deep learning model suitable for the spectral feature analysis of red pine nut kernels. The constructed model is trained using a backpropagation algorithm, and the network weight parameters are updated in reverse by minimizing the loss function. When the constructed model meets the requirements for rapid detection, it can be used for efficient and non-destructive simultaneous detection of lipid content and oxidative rancidity in red pine nuts.

The present application relates to the technical field of corpus collection control, and particularly relates to a corpus automatic collection and quality control method and system based on an intelligent algorithm, which constructs state representation by acquiring corpus attribute information and generates an adversarial collection strategy, extracts blind area corpus after execution, selects boundary corpus and collects, constructs feature mapping to determine associated corpus, transmits quality mark value to associated corpus to obtain a corrected quality value, transmits utility measurement value to boundary corpus to obtain a predicted utility value, and finally fuses quality and utility values to execute corpus quality control, thereby improving the comprehensiveness of corpus collection and the accuracy of corpus quality control.

The application belongs to the technical field of remote sensing earth observation, and particularly relates to a large-format remote sensing image multi-target extraction method and system, which comprises S1 large-format overlapping sliding window segmentation; S2 cross-modal space mapping and geometric prior prompt generation; S3 adaptive segmentation target function based on spatial prior constraint; S4 affine restoration of local pixel coordinates to global coordinates; and S5 overlapping area mask confidence weighted fusion and final result generation. A visual language multi-modal large model is used as a semantic analysis front end, and a segmentation large model is used as a pixel-level decoding back end, the two are connected through a spatial prior prompt, and the whole process is driven by a natural language multi-round dialogue, so that end-to-end high-precision automatic extraction of ground objects is realized.

The invention relates to the technical field of sports health monitoring, and particularly discloses a real-time running fatigue monitoring method and system, electronic equipment and a storage medium, and the method comprises the following steps: receiving real-time heart rate data in a running process; extracting a plurality of heart rate variability characteristics from the real-time heart rate data; inputting the plurality of heart rate variability characteristics into a fatigue monitoring model; wherein the fatigue monitoring model is obtained in advance based on indoor running data training, and is obtained by carrying out cross-scene optimization by adopting transfer learning and incremental training strategies and utilizing outdoor running data; the multiple heart rate variability characteristics are processed through the fatigue monitoring model, and a real-time fatigue quantification result is generated; and outputting fatigue state information according to the real-time fatigue quantification result. The technical problems that subjective evaluation is poor in real-time performance, the application of an existing sensing technology is limited, and the dynamic adaptability of a model is insufficient are solved, and the running fatigue state real-time monitoring capacity and the cross-scene adaptability are improved.

The application discloses a public space behavior interaction mode recognition method based on a heterogeneous graph, and comprises the following steps: collecting public space behavior data, constructing an initial public space behavior data set containing a space base map and behavior images; recognizing space information, forming a space element data set; recognizing behavior information, recording the local features of behavior grid units and corresponding individual behavior tracks as a behavior unit data set; constructing a space-behavior heterogeneous graph, constructing a space-behavior heterogeneous graph containing multiple types of nodes, multiple types of relationships and multiple dimensional attribute information; extracting a space-behavior interaction mode, determining the element correlation of the space-behavior interaction mode; constructing a public space behavior interaction mode database, and visually expressing the space distribution and behavior characteristics of different interaction modes. The application constructs a space-behavior heterogeneous graph structure containing multiple types of nodes and multiple topological relationships, and realizes automatic recognition and classification of typical space-behavior interaction modes.

The utility model relates to the technical field of capsule extraction, and provides a press-fit piercing device for a capsule extraction device, which comprises a machine body, one end of the outer wall of the machine body is fixedly connected with a capsule storage bin, and a press-fit piercing mechanism is arranged in the machine body and the capsule storage bin; the servo motor can drive the lead screw to rotate so as to control the water supply pipe at one end of the rectangular frame to be close to the capsule storage bin, the pressing plate and the needle inserting pipe can press capsules and puncture the capsules respectively, purified, filtered and heated water flow can flow into the capsules along the water supply pipe, automatic extraction of the capsules is achieved, operation is convenient, and efficiency is high. According to the capsule extraction device, the automation degree is high, manpower is saved, the extraction difficulty is reduced, capsules can be sequentially placed in the storage frames according to the up-down distribution sequence, the capsules on the bottommost layer can be taken away from the material taking opening, the capsules can be observed through the observation window so that the capsules can be supplemented in time, the remaining capsules can be well arranged, and the risk of losing or staining is avoided.

The invention provides a muck pile ground point cloud removing method and device, and relates to the technical field of underground metal mine blasting mining engineering. The method comprises the steps of obtaining original three-dimensional point cloud data of a muck pile and performing down-sampling to obtain a muck pile three-dimensional point cloud; determining a segmentation threshold according to the feature distribution of the muck pile three-dimensional point clouds, and performing segmentation by adopting a region growing algorithm to obtain a plurality of segmentation result point clouds; calculating and screening geometric feature vectors of each segmentation result point cloud; based on the screened segmentation result point cloud feature data set, ground class feature subsets are extracted through unsupervised clustering analysis, a ground point cloud joint judgment rule is constructed, and each segmentation result point cloud is judged as a ground point cloud or a non-ground point cloud; and all identified ground point clouds are removed, and all non-ground point clouds are subjected to denoising processing to obtain muck pile main body point clouds. The invention aims to improve the quality and availability of the three-dimensional point cloud data of the muck pile and ensure efficient and accurate identification and statistics of the muck pile lumpiness.

The utility model provides a quantitative proportioning device for producing a composite mineral admixture. The quantitative proportioning device for producing the composite mineral admixture comprises a box body, wherein the bottom of the box body is fixedly communicated with a discharge pipe; the storage box is arranged on one side of the box body, a plurality of partition plates are arranged in the storage box, and the storage box is divided into a plurality of storage cavities used for storing different raw materials by the partition plates; the automatic feeding mechanism is arranged on the box body and is used for pumping various raw materials into the box body in proportion; and the mixing mechanism is arranged on the box body and is used for mixing and stirring the raw materials. The quantitative proportioning device for production of the composite mineral admixture has the advantages that automatic feeding and mixing stirring of raw materials are achieved, production efficiency is improved, manual operation is reduced, labor intensity is lowered, and meanwhile proportioning errors caused by human factors are reduced.

The application discloses a three-dimensional space-time geographic entity intelligent extraction method based on a large language model and related devices, relates to the fields of three-dimensional geographic information systems and smart city digital twin technologies, and comprises the following steps: extracting a point cloud subset corresponding to a target geographic entity, and generating a point cloud sparse tensor; inputting the point cloud sparse tensor into an autoregressive generation model to generate a three-dimensional vertex and a mesh surface sequence; jointly checking the three-dimensional vertex and the mesh surface sequence to obtain a three-dimensional polygon mesh model of the target geographic entity; based on a semantic enrichment intelligent agent of the large language model, extracting semantic attributes associated with the three-dimensional polygon mesh model from multi-source heterogeneous data; based on geometric constraint information in the semantic attributes, checking the three-dimensional polygon mesh model; based on a geometric boundary of the three-dimensional polygon mesh model, performing semantic data checking on the semantic attributes; and storing the three-dimensional polygon mesh model and the semantic attributes in a spatial database after bidirectional checking to obtain a three-dimensional city model file conforming to standard specifications.

This invention relates to a multimodal intelligent review method for communication documents, specifically in the field of artificial intelligence. By performing deep fusion analysis of visual and linguistic elements on images of communication bidding documents, a document knowledge network rich in semantic associations is constructed. It then simulates expert thinking for automated reasoning and verification, accurately understanding complex content such as mixed text and images, and stamped annotations. This transforms unstructured information into a computable knowledge graph and supports rule-based and vector-based intelligent retrieval, significantly improving the objectivity, accuracy, and efficiency of the review process. It achieves automatic extraction of review elements, verification of logical consistency, and deep semantic querying, providing reliable and interpretable intelligent decision support for communication project review.

The application discloses a kind of based on three-dimensional fine data's cultural relic disease automatic high-precision extraction method, comprising: obtaining the orthographic image of cultural relic with projection parameter;According to the gray level co-occurrence matrix of image complexity calculation, the adaptive K value of orthographic image is carried out SLIC image segmentation clustering calculation, and the adaptive superpixel number K of orthographic image is calculated, and the superpixel segmentation is carried out to image according to the K value obtained by calculation;K-means clustering segmentation is carried out to superpixel segmentation result, and the disease pixel coordinates of cultural relic are extracted;The three-dimensional coordinate information of the disease pixel coordinates of cultural relic is converted, then three-dimensional reconstruction is carried out, and the three-dimensional geometric information of disease is obtained.The application combines image segmentation algorithm, realizes disease automatic extraction, simultaneously applies two three-dimensional data conversion, and automatically obtains three-dimensional information of disease, not only greatly saves the time of manual point selection, and simultaneously improves the accuracy of disease extraction.

The application provides a label extraction method, device and computer readable storage medium; the method comprises the following steps: receiving a video to be extracted and a title text corresponding to the video to be extracted; extracting a to-be-identified image from the video to be extracted; the to-be-identified image is a cover image of the video to be extracted or a video frame of the video to be extracted; identifying the to-be-identified image to obtain an image category label corresponding to the to-be-identified image; the image category label represents an object contained in the to-be-identified image; performing word extraction on the title text to obtain at least one candidate label corresponding to the title text; the at least one candidate label is a noun word in the title text; based on the image category label, selecting a label corresponding to the video to be extracted from the at least one candidate label. Through the application, the extraction efficiency of the label of the video can be improved through artificial intelligence.

The utility model relates to the technical field of agricultural planting and seedling raising, in particular to an indoor seedling raising device for agricultural planting, which comprises a base. The water drainage assembly is arranged at the rear end of the base and comprises a water storage tank, a water inlet tank, an auxiliary frame, a sliding rod, a floating ball, a top plate, a button, a connecting plate, a water suction pump, a water drainage pipe, a water drainage frame and a handle; by arranging the drainage assembly, when the water level in the water storage tank rises to a certain height, water flows into the auxiliary frame through the water inlet tank and pushes the floating ball to rise, and the floating ball drives the sliding rod to move in the auxiliary frame, so that the top plate triggers the button, the water suction pump is started to perform water suction operation within limited time, and the water is guided into the drainage frame through the drainage pipe; during cleaning, the handle can be pulled, the handle drives the drainage frame to be pulled out, centralized drainage treatment is facilitated, automatic pumping drainage of redundant water can be achieved through the design, water accumulation is effectively prevented, and the drainage efficiency and operation safety of the seedling culture device are improved.

The application discloses a kind of automatic driving data processing method, system and equipment. Among them, the processing method of automatic driving data includes: for each automatic driving related data, the corresponding relationship of automatic driving collection data and event is established;Event is synchronized to work order system, to create the work order of the event by the work order system;The event is analyzed by the work order, to carry out label annotation;When the state change of work order is monitored, the structured association relationship of label and the event is established, and the structured association relationship is written in association table, to complete the label structuring of the event.Using the present application, the data processing efficiency is improved, the repetitive operation of manual participation is reduced, the speed of problem discovery to data available is accelerated, the analysis result can be accurately fed back to data through automatic mapping of data and event, so that label can directly participate in query, statistics, clustering and data mining, support large-scale analysis.

The application discloses an Allen's total ginsenoside atomizing eye drop and a preparation process thereof, and relates to the technical field of eye drop preparation. The eye drop comprises 60-70% of total ginsenoside extracted from panax notoginseng leaves, 30-50% of total ginsenoside extracted from panax notoginseng flowers, 55-65% of total ginsenoside extracted from panax notoginseng roots and 5-10% of water-extracted total ginsenoside of panax notoginseng. The total ginsenoside extracted from panax notoginseng leaves is composed of ginsenoside Rg1, ginsenoside Rb1 and ginsenoside Rd. In the application, the Allen's total ginsenoside atomizing eye drop prepared by the process of S1-S4 is used, so that the ginsenoside Rg1, ginsenoside Rb1 and ginsenoside Rd in the eye drop are not lost, the quality of the prepared eye drop is improved, and the relief effect of eye dryness is effectively improved.

The invention provides a powder flow precise control and real-time adjustment method for quantitative powder packaging, which comprises the following steps of: identifying dynamic model parameters of an actuating mechanism by utilizing a recursive augmented least square method through periodically injecting lightweight excitation signals and accurately collecting input and output time sequence data; a preset nonlinear rule mapping relation is combined to automatically convert into an optimal PID control parameter, and exponential weighted average is adopted to realize smooth transition of the parameter, so that system disturbance is avoided; according to the method, the characteristic change of an executing mechanism can be matched in real time, and the powder flow adjusting precision and the system robustness are improved.

The utility model discloses a kind of servo electric spraying machines, including bottom plate, screw rod, servo motor, sliding rail, moving block, box and spraying device, the screw rod is movably connected at the top of bottom plate, the servo motor is fixedly installed at the left side of bottom plate.The utility model is by being set lubricating maintenance mechanism in the left side and right side of box, including mounting block, oil outlet head and oil supply mechanism, when equipment operation needs to lubricate screw rod, oil supply mechanism starts work, oil supply mechanism transports lubricating oil to oil outlet head, and oil outlet head is fixedly installed outside mounting block by pipe clamp, and is located directly above screw rod, lubricating oil drops from oil outlet head to screw rod surface, realizes the lubrication of screw rod, realizes automatic lubrication to screw rod, greatly reduce the cumbersome operation of artificial lubrication, solve the effective lubricating maintenance structure of above-mentioned equipment lack to screw rod, when operator maintains screw rod in actual operation, face many inconvenient problems.

The utility model discloses a bearing ring machining quenching device which comprises a quenching liquid container, a supporting frame is arranged above the quenching liquid container, a splash guard is arranged on the supporting frame, the splash guard is arranged in a guide groove of a transverse supporting piece on the supporting frame in a sliding mode, and bearing extraction pieces are arranged on the front side and the rear side of the supporting frame. The bearing extracting part comprises an air cylinder mounting supporting plate, an air cylinder telescopic assembly and a magnetic mounting plate, the air cylinder mounting supporting plate is horizontally arranged on the lifting support, and the air cylinder telescopic assembly is vertically arranged on the air cylinder mounting supporting plate. According to the high-temperature liquid conveying device, operators are protected from being injured by high-temperature liquid, meanwhile, environmental pollution caused by liquid splashing is reduced, safety and convenience are enhanced due to the use of the adjusting set, workpieces are automatically extracted and placed through the bearing extracting piece, the loading and unloading process is simplified, and the working efficiency is improved.

The application provides a reluctance motor and a reluctance motor for driving a compressor, comprising a shell; a stator and a rotor are arranged in the shell, and a rotating shaft is fixed in the middle of the rotor; a cooling cavity is arranged in the shell wall, and the cooling cavity is used for cooling liquid flow; heat dissipation mechanisms are fixed on both sides of the rotor, a liquid delivery part is arranged on one side of the heat dissipation mechanism, the liquid delivery part extends into the cooling cavity; a plurality of liquid brushing rings are arranged on the outer wall of the shell, the liquid brushing rings are connected with liquid injection mechanisms, and the liquid brushing rings are connected with a pushing mechanism through connecting rods. By arranging the heat dissipation mechanisms on both sides of the rotor and connecting the heat dissipation mechanisms with the liquid delivery part, when the motor operates, the liquid delivery part can automatically extract the cooling liquid in the cooling cavity and input the cooling liquid into the heat dissipation mechanism, the cooling liquid flows in the heat conduction pipes of the heat dissipation mechanism, can quickly absorb the heat transferred to the heat conduction disc by the rotor, and then carries the heat back into the cooling cavity, forming a circulating loop for heat dissipation of the rotor, effectively solving the problems that the heat of the rotor of the traditional reluctance motor is difficult to dissipate and is easy to accumulate.

The invention discloses an automatic site calibration system and method for airborne radar and optical detection equipment. The method comprises the following steps: determining the type and quantity requirements of calibration equipment and site constraint conditions according to calibration task parameters; a calibration service planning unit of the calibration service management module generates a calibration equipment position and a waypoint planning result; the calibration service management module controls the detection equipment to complete calibration equipment imaging according to a waypoint planning result; parameters of the calibration equipment are synchronously measured in the imaging process, and environmental parameters are collected through environmental parameter collection equipment; the ground preprocesses the imaging original data to obtain an SAR image of the radar detection equipment and an optical image of the optical detection equipment; inputting the image data into a calibration service management module, identifying the position of calibration equipment in the image and sending the position to a calibration processing module; the calibration processing module calculates and outputs a calibration coefficient K based on the position of the calibration device in the image in combination with the environmental parameters and the calibration device parameters.

The application discloses a land survey quality monitoring system for remote sensing image intelligent segmentation and ground object identification, relates to the technical field of remote sensing, and comprises an image identification module, a label comparison module and a monitoring module. Specifically, remote sensing images of land to be monitored are acquired through a remote sensing sensor, image regions are divided through structural complexity analysis, and the category probability vectors of the pixel positions of each region in the formed non-uniform region set are analyzed and acquired to construct a label map of the whole remote sensing image. Pixel-by-pixel category comparison is performed on the current label map and a reference label map to form a change mask map. Structural change regions are identified according to the change mask map. Through time sequence analysis, it is determined whether the corresponding candidate label inconsistent regions under different time phases are still structural change regions to acquire a judgment result. Based on the judgment result, an electronic map is updated.