404 results about "Volumetric data" patented technology

A method and apparatus comprising computer code configured to cause a processor or processors to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content; partition a plurality of vertices of the mesh into a plurality of groups; and decode the encoded volumetric data by predicting the vertices in each group of the plurality of groups based on a plurality of traversal orders depending on an adaptive reference vertex of the vertices, and the plurality of traversal orders includes a first order from the adaptive reference vertex to a first alternative reference vertex of the vertices, and wherein the plurality of traversal orders includes a second order from the adaptive reference vertices to a second alternative reference vertex of the vertices.

The invention relates to an electromagnetic shielding method and shielding system for power distribution, and belongs to the technical field of electromagnetic shielding. Comprising the following steps: establishing a shielding model corresponding to the shielded room according to volume data of the shielded room; simulating and positioning electromagnetic wave conditions in the shielded room in the shielding model; selecting key detection points; constructing a phase difference matrix; shielding requirements of different waveforms in the same frequency band are distinguished, leakage path positioning based on a waveguide equation is carried out, and a core leakage area and an auxiliary protection area are divided. According to the electromagnetic shielding method and shielding system for power distribution provided by the invention, the dynamic adaptability of electromagnetic shielding and the detection capability of transient electromagnetic pulses are remarkably improved, and a multi-dimensional risk quantification and differentiation reinforcement strategy is realized. Meanwhile, intelligent materials and a dynamic optimization mechanism are adopted, the material utilization rate and the protection effect are improved, and a reinforcing effect feedback closed loop is formed.

The invention discloses an early lung cancer screening method based on transfer learning. The method comprises the following steps: S1, obtaining preprocessed three-dimensional volume data; s2, generating a multi-scale enhanced feature map; s3, obtaining a preliminary micro-nodule detection result; s4, obtaining a first-stage optimization model; s5, performing second-stage training on the first-stage optimization model by adopting a double-normal-form transfer learning strategy to obtain a transfer optimization model; s6, embedding an adversarial domain adaptive module in the migration optimization model to obtain a cross-domain robust model; and S7, in a clinical reasoning stage, outputting a micro-nodule detection result for the new chest low-dose spiral CT original image data by using the cross-domain robust model. According to the invention, the model can adaptively emphasize the local gradient difference between the lung micronodule and the background texture, thereby improving the discrimination capability of the weak boundary region.

A method and apparatus comprising computer code configured to cause a processor or processors to obtain an input mesh comprising volumetric data of at least one three-dimensional (3D) visual content, derive a plurality of submeshes of the input mesh from a frame of the volumetric data, set bitdepths to a first submesh and a second submesh from the submeshes, a first bitdepth being different than a second bitdepth, quantize the first submesh and the second submesh based on respective ones of the first bitdepth and the second bitdepth, and signal a result of quantizing the first submesh and the second submesh.

Automatic volumetric quantification can be performed for various parameters of an object by providing volumetric data, such as three-dimensional image data, to at least one neural network. A network can extract features from the data that can be used to infer a point cloud representative of the surface of the object. One or more loss functions can be used to adjust the relevant network parameters. The network can also attempt to infer a segmentation mask for the object, indicating which data values correspond to the object of interest. Since the network performs the segmentation and point cloud generation in parallel, updates to the network parameters can impact the segmentation process, effectively constraining the segmentation based on the inferred shape of the object. Ensuring that the segmentation mask corresponds closely to the surface of the object can cause the segmentation process to be more accurate than conventional segmentation processes alone.

The invention discloses a volume grid construction method and a related device. The method comprises the following steps: creating initial volume data of a target shape, realizing rough shaping of volume grid construction, and improving the controllability of the volume shape during volume grid construction; for volume data in a target density range in the initial volume data, namely the volume data of which the data density of each voxel is greater than the sampling density, sparse sampling is performed to obtain a plurality of target sampling points, so that data selection of volume grid construction is realized, and the data volume of the volume data during volume grid construction is reduced; on the basis of a plurality of target sampling points with a small data volume, three inserts are constructed for each target sampling point to obtain a three-insert grid in a target shape, and three patches in each three insert of the three-insert grid are perpendicular to one another and intersect with one another, so that the three-insert grid is higher in construction speed and stronger in volume feeling, and the three-insert grid can be more accurately constructed. Grid construction of volume grid construction is achieved, the volume grid construction time is shortened, the resource consumption is reduced, and the volume grid construction efficiency is improved.

The invention discloses a vacuum cavity pressure maintaining test and leak rate rapid estimation method and system, and the method comprises the steps: achieving the test preparation of multiple sections through a public metering manifold and a multi-way isolation valve, and building a section volume database; the pressure and temperature data are synchronously collected in a fixed sampling period by exhausting air to preset pressure and isolating a pump end; obtaining an equivalent pressure change rate through temperature normalization and deflation baseline deduction in combination with filtering and regression algorithms, and performing conversion to obtain a standardized leak rate; step-by-step detection is carried out on each functional section of the cavity through a segmented bipartite isolation strategy and volume correction, and rapid positioning of a suspicious leakage section is realized; through double-threshold determination of an early warning threshold and an unqualified threshold, a detection report is automatically generated and written into a historical database, and a detection-determination-maintenance closed loop is formed. The method can improve the precision of leak rate detection, and is suitable for vacuum coating equipment, semiconductor process equipment and industrial vacuum treatment devices.

A system and / or method uses a trained U-Net neural network to remove flow artifacts from optical coherence tomography (OCT) angiography (OCTA) data. The trained U-Net receives as input both OCT structural volume data and OCTA volume data, but expands the OCTA volume data to include depth information. The U-Net applies dynamic pooling along the depth direction and weighs more heavily the portion of the data that follows (e.g., along the contours of) select retinal layers. In this manner the U-Net applies contextually different computations at different axial locations based at least in part on the depth index information and / or (e.g., proximity to) the select retinal layers. The U-net outputs OCT volume data of reduced flow artifacts as compared with the input OCTA data.

Volumetric quantification can be performed for various parameters of an object represented in volumetric data. Multiple views of the object can be generated, and those views provided to a set of neural networks that can generate inferences in parallel. The inferences from the different networks can be used to generate pseudo-labels for the data, for comparison purposes, which enables a co-training loss to be determined for the unlabeled data. The co-training loss can then be used to update the relevant network parameters for the overall data analysis network. If supervised data is also available then the network parameters can further be updated using the supervised loss.

A method for analyzing brain imaging data from a brain lesion patient and generating prognostic information is disclosed. The method includes obtaining imaging data of the brain of a patient from a scanner and classifying the data by acquisition plane and modality to select a data series of interest. The method further involves processing the data series of interest to generate brain masks and corresponding volumetric data. The brain masks and corresponding volumetric data are then co-registered to a common brain space, and registered volumetric data is generated. Lesion segmentation is performed to generate a lesion mask in the common brain space. The lesion mask data is applied to a trained prognostic model, which comprises a machine learning model configured to output a probability-based prognosis of the patient's brain lesion.

The invention discloses a personalized logistics service quotation method and system based on a rule engine. The method comprises the steps of (1) data acquisition and preprocessing, (2) rule matching and selection, and (3) pricing calculation. And (4) outputting and optimizing a result. The system comprises a data input module, an image processing module, a rule management module, a rule engine module and a result output module. The data input module is responsible for receiving logistics related information input by a user, including but not limited to weight, volume, order quantity and the like of articles. Volume data can be obtained by a user by uploading a picture or shooting an object in real time by using a camera; through a flexible pricing mode and an intelligent image identification technology, logistics cost calculation can be efficiently and accurately completed. The working process of the system covers key links such as data acquisition and preprocessing, rule matching and selection, pricing calculation, result output and optimization and the like, and the pricing demand in a complex scene is realized.

The invention relates to a material loading control method, which comprises the following steps of: acquiring volume data of loading materials in a time period, calculating volume according to the acquired volume data, and calculating a mapping relation by utilizing a fitting algorithm; installing a camera device, capturing a material flow image in real time, and calculating a fluidity parameter in a flow velocity vector field by using an algorithm; substituting the calculated fluidity parameters into the mapping relation, correcting the mapping relation, and establishing a corrected volume mapping relation model; the prediction result is compared with the volume of the material monitored in real time, the control parameters are dynamically adjusted according to the comparison result, and the deviation in the loading process can be found and corrected in time by monitoring the volume and fluidity parameters of the material in real time and dynamically adjusting the control parameters according to the corrected volume mapping relation model; and the control precision of material loading is improved.

A method that relates to a kind of novel approach for the utilization of NFTs (Non-Fungible Tokens) as the basis for motion capture file creation and storage means that every submission carries its own unique, immutable identity. This process grants users access to a unique decentralized, non-custodial digital document storage solution on the market. The proposed system remains focused on cultivating robust systems around minting, validating, retrieving & verifying NFT-based motion capture technology. This is accomplished by the described method to mint, archive and retrieve NFT documents using a blockchain as its basis. The invention is a combination of motion capture technology, volumetric data, AI, and distributed ledger technology. The motion capture technology allows for the capture and creation of expressive body movements, while the volumetric data enhances the realism of these movements. The AI helps in the creation of unique and expressive movements, and the distributed ledger technology ensures that the ownership and distribution of these movements are securely managed.

The invention provides a seed detection method, system and device based on a multi-modal intelligent algorithm. The method comprises the following steps: acquiring a raster image of a to-be-detected seed; rGB-D modal information of the raster image is collected; cutting an edge part in the raster image, and matching the cut image with the RGB-D modal information; performing target detection on the image by adopting a detection algorithm to determine a detection area of the seed in the image; establishing three-dimensional point cloud data according to the RGB-D modal information of the pixel points in the detection area; segmenting the three-dimensional point cloud data into point cloud data corresponding to each seed by adopting an adaptive density clustering algorithm; calculating volume data of each seed by using a point cloud convex hull algorithm according to the point cloud data; and clustering all volume data into real grain data and shriveled grain data by adopting a K-means clustering algorithm. According to the method disclosed by the invention, nondestructive seed test detection of the seeds is realized by adopting a multi-modal detection technology, and detection with higher precision is realized.

The invention relates to the technical field of data processing, and discloses a pipeline corrosion repairing method and system based on artificial intelligence and a storage medium. The method comprises the following steps: acquiring a corrosion image through a pipeline endoscope, and obtaining a standardized feature data set through Gaussian filtering and histogram equalization processing; inputting a semantic segmentation network for identification and segmentation to obtain corrosion three-dimensional coordinates and volume data; according to the coordinates and chemical factors, mortar proportioning parameters are obtained through calculation; inputting the volume data into a depth-thickness mapping network to obtain repair thickness distribution; and jet parameter setting and construction control are conducted according to the thickness distribution, and pipeline corrosion repairing is completed. The technical problems that in an existing pipeline corrosion repairing method, corrosion recognition precision is low, repairing parameters lack pertinence, multi-point corrosion collaborative optimization is insufficient, and the intelligent degree of construction control is low are solved.

The invention provides a DWS sorting control method and device based on multi-modal perception and logistics equipment, and relates to the technical field of logistics equipment, and the DWS sorting control method based on multi-modal perception comprises the steps that bar code image data, actual volume data and actual weight data of parcels to be sorted are obtained; mailing information is determined, and target volume data and target weight data are determined; comparing the actual volume data with the target volume data to determine a first difference value; comparing the actual weight data with the target weight data to determine a second difference value; acquiring three-dimensional point cloud data of the parcels to be sorted; reconstructing surface morphological characteristics of the parcels to be sorted, and extracting geometric parameters of abnormal regions; determining a sorting abnormity type of the to-be-sorted parcel; and a sorting deviation correction instruction is generated, and the sorting deviation correction instruction is sent to the sorting and transporting device so as to adjust the conveying path or the sorting target grid of the to-be-sorted packages. According to the method, the sorting abnormity response efficiency and the deviation correction precision can be improved.

A method for assigning train blocks at a railroad merchandise yard includes determining, using a first optimization model and historical train block volume data, a first list of train block assignments for a plurality of train blocks and a plurality of classification tracks of a classification bowl. The method further includes displaying the first list of train block assignments generated by the first optimization model if the volume of the train blocks is not greater than the total available track length of the classification tracks. The method further includes determining and displaying, using a second optimization model and the historical train block volume data, a second list of train block assignments for the plurality of train blocks and the plurality of classification tracks of the classification bowl if the volume of the plurality of train blocks is greater than the total available track length of the plurality of classification tracks.

The invention relates to an ore body volume prediction model training method, a prediction method, equipment and a medium, an ore body volume prediction model adopting a BP neural network is constructed, and based on a mapping relation between a BP neural network weight and an individual position in an individual position optimization algorithm, an individual position optimization algorithm is utilized to optimize the volume of an ore body. According to the method, the initial weight of the BP neural network is optimized, and the trained BP neural network can output the corresponding ore body volume predicted value result after inputting the normalized geological attribute strongly related to the ore body volume, so that the situation that the ore body volume data is obtained through large-scale geological exploration is avoided, manpower, material resources and time cost are saved, and the working efficiency is improved. The efficiency is greatly improved.

According to the ultrasonic imaging equipment and the pelvic floor section image generation method, three-dimensional volume data of a pelvic floor are obtained; identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volumetric data; or generating at least one two-dimensional section according to the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, and identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section; the spatial position of the key anatomical structure in the three-dimensional volume data is obtained; and imaging the section of the target tissue on the basis of the position of the key anatomical structure in the three-dimensional volume data to obtain a section image of the target tissue. Therefore, an ultrasonic doctor can obtain the section image of the pelvic floor target tissue only by completing the three-dimensional volume data acquisition of the pelvic floor, the operation is simple and convenient, and the working efficiency of the ultrasonic doctor is improved.

A system for processing an object using a programmable motion device is disclosed. The system includes an end effector of a programmable motion device for gripping objects from a feed container, and a control system for determining payload protection for selected objects. The payload protection includes point cloud data regarding volumetric data, the volumetric data including a volume occupied by the selected object, and the payload protection is determined in response to at least one characteristic of the selected object and provided specific to the selected object.

A method for assigning train blocks at a railroad merchandise yard includes determining, using a first optimization model and historical train block volume data, a first list of train block assignments for a plurality of train blocks and a plurality of classification tracks of a classification bowl. The method further includes displaying the first list of train block assignments generated by the first optimization model if the volume of the train blocks is not greater than the total available track length of the classification tracks. The method further includes determining and displaying, using a second optimization model and the historical train block volume data, a second list of train block assignments for the plurality of train blocks and the plurality of classification tracks of the classification bowl if the volume of the plurality of train blocks is greater than the total available track length of the plurality of classification tracks.

The present invention discloses a multi-modal autoencoder intelligent detection method and device for spare parts integrating 3D point clouds, which relates to the field of image processing. The method includes: S1, obtaining the volume, weight, and 3D point cloud data of spare parts of each model; performing normalization and 2D depth image conversion; S2, cropping and feature extraction on the 2D depth image, and performing feature fusion with the normalized weight and volume data to obtain multi-modal features; S3, performing grayscale processing to obtain a multi-modal feature grayscale image; S4, dividing the training set and the test set; training an autoencoder model using the training set; S5, inputting the test set into the trained autoencoder model to obtain the feature codes of spare parts of each model; S6, inputting the multi-modal feature grayscale image of the spare parts to be detected into the trained autoencoder model to obtain the feature codes of the spare parts to be detected, and performing feature comparison to obtain the model information. The present invention uses an autoencoder to extract multi-modal features integrating 3D point clouds, improving the accuracy of spare part detection.

The invention relates to a carrier rocket propellant liquid level measurement filtering method based on volume extrapolation. The method comprises the steps that the current section number of a liquid level sensor is judged; adopting a triangular wave fitting method to calculate the liquid level height of a non-inflection point area; performing inflection point area liquid level height calculation by adopting a volume extrapolation method: if the current section number is an odd number, when the triangular wave voltage is smaller than Umin + deltaV for the first time, or if the current section number is an even number, and when the triangular wave voltage is larger than Umax-deltaV for the first time, performing least square fitting and extrapolating a volume trend line by utilizing the liquid level volume data within the time T0 before the moment, the volume data within the time Tw after the moment are all replaced by the data on the volume trend line, and finally the volume is inversely transformed back to the height value. According to the method, the problem of inflection point distortion is eliminated under the condition that the height calculation precision is not reduced, input information does not need to be externally connected, and the implementation mode is relatively simple.

The invention provides a refrigerator cabinet polyurethane foam density test analyzer and a density test method. The density test analyzer is configured to obtain to-be-tested sample information input by a user; pre-treating the sample based on the information of the sample to be detected; putting the pretreated sample at a weight testing position for weighing to obtain weight data, and then putting the sample block into the volume measuring cup for volume measurement to obtain volume data; and calculating and displaying the density based on the weight data and the volume data. According to the invention, through cooperation of the automatic weighing module and the intelligent data processing system, high-precision rapid detection of the density of the polyurethane foam is realized, the measurement error is controlled within + / -0.5%, and the detection efficiency is significantly improved; and meanwhile, through information binding storage and dynamic analysis functions, a complete quality tracing system is constructed, so that the process abnormity response speed is increased by 70%.

Embodiments of the present disclosure are directed to providing fuel emissions monitoring and / or management for an aerial vehicle. In an example, fuel consumption data and carbon emissions data for an aerial vehicle is determined. The fuel consumption data provides a comparison between (i) first fuel consumption data associated with a first type of aviation fuel being utilized by the aerial vehicle and (ii) second fuel consumption data associated with a second type of aviation fuel that is not being utilized by the aerial vehicle. The carbon emissions data is based on (i) volume data indicative of a real-time volume of the first type of aviation fuel, (ii) a first carbon emissions factor for the first type of aviation fuel, and (iii) a second carbon emissions factor for the second type of aviation fuel. In another example, a rendering of the fuel consumption data is caused via a display.

A picking method, a picking vehicle and a picking system. The picking method includes: obtaining a current volume data and a current weight data of a box; generating a current arranging position data of the box based on the current volume data, the current weight data and an arranging position model of an artificial intelligence model. The arranging position model includes multiple arranging date each including a predetermined volume data, a predetermined weight data and a predetermined arranging position data that are corresponding to one another; and moving the box to a target arranging position via a picking vehicle based on the current arranging position data.

A method and apparatus comprising computer code configured to cause a processor or processors to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content, partition a plurality of vertices of the mesh into a plurality of groups by determining a face normal for each face in the mesh, classifying the groups based on their orientation to the face normal, and merging adjacent faces that share an edge between the plurality of groups, and decode the encoded volumetric data based on the plurality of groups.

The invention relates to an asphalt pavement pore and crack identification method and system based on a CT image, and a storage medium. The method comprises the following steps: obtaining an asphalt pavement two-dimensional image; wherein the two-dimensional image is obtained by scanning a core sample at the crack of the asphalt pavement through CT equipment; processing the two-dimensional image by adopting a three-dimensional reconstruction algorithm, converting two-dimensional image data into three-dimensional volume data, and generating a three-dimensional structure model of the asphalt pavement; extracting three-dimensional volume data in the three-dimensional structure model, and calculating a volume form factor; according to the volume form factor, classifying pores and cracks of the asphalt pavement by using an automatic classification algorithm; and outputting a classification result to realize the recognition of the pores and cracks of the asphalt pavement.

According to the tunneling control system and method of the slurry balance shield tunneling machine, the tunneling instruction is imported through the parameter setting unit, the equipment parameter threshold range of the slurry balance shield tunneling machine is generated, and the monitoring unit collects the equipment parameters of the slurry balance shield tunneling machine in the running state and sends the equipment parameters to the control unit; the management unit calculates a theoretical excavation volume and an actual excavation volume according to equipment parameters, the data analysis unit judges whether the actual excavation volume exceeds a preset threshold value range or not according to the theoretical excavation volume and the actual excavation volume, and when the actual excavation volume exceeds the preset threshold value range, the data analysis unit is started; the parameter regulation and control unit timely regulates at least one parameter of the theoretical excavation volume and the actual excavation volume at the next moment, equipment parameters are controlled to be within the safety threshold range so as to control tunneling of the slurry balance shield tunneling machine, compared with the prior art, manual parameter regulation is not needed, and the safety in the tunneling process is improved.

Provided is a method for labeling volumetric data, including obtaining, with a computing device, access to volumetric data in a hierarchical spatial data structure, displaying, with the computing device, a multiresolution representation of a three-dimensional image volume in an extended reality environment configured to display volumetric data using the hierarchical spatial data structure, receiving, with the computing device, a selection of a region of interest of the image volume, receiving, with the computing device, user input defining a brush trajectory within the region of interest, determining, with the computing device, which voxels within the image volume that intersect the brush trajectory within the region of interest; and labeling, with the computing device, the identified voxels in memory.