39 results about "Volumetric data" patented technology

The application discloses a data processing method and device for pig state monitoring. The method comprises the following steps: obtaining to-be-processed data in the application, the to-be-processed data being data for representing collected pig video frame images; performing three-dimensional reconstruction-based volume correction processing on the to-be-processed data to obtain pig corrected volume data, the pig corrected volume data being corrected pig volume data in different postures; performing feature extraction processing including breed characteristics on the pig corrected volume data to obtain to-be-processed feature data, the to-be-processed feature data being feature data for representing pig breed characteristics; and performing weight estimation processing based on a cross-breed weight estimation model on the to-be-processed feature data to obtain pig monitoring data, the pig monitoring data being data for representing pig weight. Through point cloud data feature extraction and breed characteristic extraction, the weight of cross-breed pigs is estimated, and the accuracy of pig weight estimation under multiple breeds is improved.

This invention discloses a method, apparatus, equipment, and storage medium for managing coal gas consumption, comprising: standardizing the initial calorific value data of sample coal gas to determine standard calorific value data, and storing the standard calorific value data in a calorific value dataset; determining the constituent coal gas of the sample coal gas from candidate coal gas according to the standard calorific value data; the candidate coal gas includes blast furnace gas, coke oven gas, and converter gas; determining the calorific value state volume data of the sample coal gas corresponding to the standard calorific value data according to the standard calorific value data and the unit volume heat data of the sample coal gas, and storing the calorific value state volume data in a volume dataset; training a machine learning model based on the calorific value dataset, the volume dataset, and the constituent coal gas of the sample coal gas, and determining a coal gas consumption evaluation model based on the training results; the coal gas consumption evaluation model is used to evaluate the consumption of the coal gas to be evaluated. This can improve the efficiency and accuracy of evaluating coal gas consumption.

This invention discloses a BIM-based method and system for calculating the quantity of outdoor pipe trenches, comprising: reading pipe parameters from the BIM model of the pipe components through a preset script program; automatically calculating the cross-sectional dimensions of the pipe trench based on the pipe diameter by calling a pre-constructed pipe trench cross-sectional parameter rule model; generating a pipe trench cross-sectional contour family by calling a parametric family library based on the pipe trench cross-sectional dimensions and the spatial direction coordinates of the pipe, and stretching the path along the pipe direction to generate a three-dimensional pipe trench model consistent with the pipe path; acquiring the volume data of the three-dimensional pipe trench model, calculating the excavation quantity of the pipe trench based on the volume data, and setting the excavation quantity into preset attribute fields to achieve dynamic statistics of the quantity. This invention can reduce the manual drawing and calculation process, improve the efficiency and accuracy of quantity calculation, realize the linkage update of model and data, and enhance the automatic adaptation capability to standard parameters.

The application discloses a kind of coal mine underground sealed roadway gas content real-time determination system and determination method, belong to coal mine gas content determination field;The method comprises: before roadway sealing, distribute distributed sensing optical fiber network and determine initial volume;After sealing, continuously monitor surrounding rock strain and internal gas pressure, temperature and gas concentration;Periodically inject known amount of inert gas into sealed space, use the change of gas concentration, pressure and temperature before and after injection, based on gas state equation to invert current absolute volume;Based on optical fiber strain data, calculate volume estimate through geometric and physical model, fuse the above two volume data, obtain continuous, high-precision optimal dynamic volume;Finally, fuse dynamic volume, concentration, pressure and temperature data, calculate gas total content and its change rate in standard state in real time, realize hierarchical early warning and gas resource, risk quantification management.

This invention relates to the field of cross-border trade technology, specifically to an intelligent order generation method and system based on dynamic container matching. It includes: acquiring a user's terminal access request and extracting the user's nationality metadata; mapping product information data in the source language to product description data in the target language that matches the nationality metadata; receiving the user's order request and generating a pending verification order, where each target product in the pending verification order is associated with real-time updated 3D geometric feature data; performing multi-dimensional spatial stacking simulation and volume superposition calculation to generate total order volume data including a recommended stacking map; dynamically matching the total order volume data with a preset set of volume parameters for various standard container types to solve for the optimal container combination scheme that fits the total order volume data, and sending it to the user's terminal for confirmation to complete the automated order entry. This invention significantly improves the accuracy of orders and the efficiency of container loading in cross-border trade.

A method and apparatus comprising computer code for mesh coding configured to cause a processor or processors to receive a dynamic input mesh representing a volumetric data of at least one three-dimensional (3D) visual content; determine, for a mesh at a first level of sub-division, a plurality of first vertices, wherein the plurality of first vertices are determined using a mid-point sub-division scheme and a plurality of previous vertices of a mesh at a previous level of sub-division, wherein the mesh at the first level and the mesh at the previous level are generated from the dynamic input mesh; determine a valence of a first vertex among the plurality of first vertices to be a first value based on whether a selected two vertices of the mesh at the first level; and generate a compressed bitstream for the dynamic input mesh based on the valence of the first vertex.

Provided herein are methods, apparatuses, computer program products, and systems for generating textured surfaces using computed tomography. One method can include generating data of an X-ray detectable feature represented in volumetric data of a reference object acquired using an X-ray scanner; determining a first transformation matrix using the data of the X-ray detectable feature; obtaining a reference image of an optically detectable feature included in the reference object captured using an optical camera; calculating a second transformation matrix using the reference image of the optically detectable feature; producing a calibration transformation matrix using (i) the first transformation matrix, (ii) the second transformation matrix, and (iii) a third transformation matrix; providing the calibration transformation matrix, which is used in aligning an image of a physical object obtained using the optical camera with a CT reconstruction volume of the physical object obtained using the X-ray scanner.

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.

A system and method of automatic cataract grading uses an optical coherence tomography ("OCT") device to generate three-dimensional OCT data of a lens. The system includes a controller having at least one processor and at least one non-transitory, tangible memory on which instructions are recorded. The controller is configured to divide the lens into a plurality of regions, and define segmentation lines for the plurality of regions based in part on predetermined reference values. The controller is configured to adjust the segmentation lines to fit respective areas adjacent to the plurality of regions, the respective areas having a relatively high gradient value. A respective mean opacity for the plurality of regions is determined based on the volumetric OCT data. The controller is configured to generate a cataract distribution trace of the lens based on the respective mean opacity in the plurality of regions.

A method of encapsulating a visual volumetric data bitstream into a media file, a method of processing a media file, a media file, a program product, a storage medium and a processing device. At least one embodiment of the method of encapsulating a visual volumetric data bitstream into a media file in a processing device, the visual volumetric data bitstream comprising a plurality of encoded sub-bitstreams corresponding to a plurality of components of the visual volumetric data, the method comprising: generating a single entity comprising the plurality of encoded sub-bitstreams; generating at least two decoder configuration data structures; and generating a media file comprising the generated single entity, the at least two decoder configuration data structures and an indication for indicating whether at least one of the decoder configuration data structures is associated with an encoded sub-bitstream comprised in the single entity based on association information.

The application discloses a two-phase immersion liquid cooling gas phase pressure regulation method and system based on PID control and relates to the technical field of liquid cooling gas pressure regulation.The two-phase immersion liquid cooling gas phase pressure regulation method and system based on PID control comprises the following steps: S1, collecting and preprocessing environmental temperature data, pressure and volume data and execution feedback data in a liquid cooling gas pressure regulation process, and constructing a standardized gas-liquid control data set; S2, evaluating the pressure state of a gas phase space and dynamically adjusting the charging and discharging operation strength of an elastic air bag; S3, analyzing the gas pressure regulation trend and adjusting the air inlet and exhaust rates of a bidirectional pump in real time; and S4, comprehensively analyzing the current state of the closed gas phase space and driving the amplitude adjustment of a volume regulation instruction.The problems that a target pressure value lacks a joint adaptive mechanism for altitude changes and load dynamics and is difficult to support precise matching control of the evaporation and condensation processes are solved.

This invention discloses a method for generating missing modalities in brain MRI based on hypergraphs and attention mechanisms. This method addresses the issue of missing modalities in multimodal brain MRI sequences such as T1, T1ce, T2, and FLAIR in clinical scenarios by constructing a unified multi-input multi-output translation framework. The method introduces hypergraph convolution and region-level self-attention into the generative network, aggregating group-level features from different tumors and healthy tissues and modeling structural relationships between sub-regions, preserving the spatial tissue structure of the tumor. Combined with bidirectional Mamba sequence modeling, it enables the 2D network to efficiently capture long-range dependencies between layers of 3D volumetric data, ensuring voxel-level spatial continuity. Through a teacher-student knowledge distillation mechanism, the student network learns structurally perceptual features without a tumor mask, achieving high-fidelity generation. This method can improve the overall quality of generated images and the detail fidelity of tumor lesions, thereby enhancing the performance of downstream tumor segmentation tasks and showing promising application prospects.

This invention relates to a three-dimensional defect segmentation method, system, and storage medium, belonging to the interdisciplinary fields of computer vision, deep learning, and nondestructive testing. The three-dimensional defect segmentation result is obtained by inputting the industrial CT volume data of the object to be inspected into a 2.5D segmentation network composed of an encoder, a spatial feature displacement module, and a decoder. This invention achieves efficient three-dimensional context awareness, significantly improving defect segmentation accuracy and three-dimensional morphological integrity. The segmentation result has topological connectivity and smooth boundaries, and its computational complexity and memory usage are far lower than those of a full 3D network. It can meet the real-time requirements of industrial online inspection and has broad application prospects in high-end manufacturing.

This invention relates to a three-dimensional defect segmentation method, system, and storage medium, belonging to the interdisciplinary fields of computer vision, deep learning, and nondestructive testing. The three-dimensional defect segmentation result is obtained by inputting the industrial CT volume data of the object to be inspected into a 2.5D segmentation network composed of an encoder, a spatial feature displacement module, and a decoder. This invention achieves efficient three-dimensional context awareness, significantly improving defect segmentation accuracy and three-dimensional morphological integrity. The segmentation result has topological connectivity and smooth boundaries, and its computational complexity and memory usage are far lower than those of a full 3D network. It can meet the real-time requirements of industrial online inspection and has broad application prospects in high-end manufacturing.

The invention relates to the technical field of computer graphics and virtual reality, and discloses an unstructured volume data hybrid rendering method based on WebXR and Gaussian splash technologies and a space interaction system. According to the method, a standardized visibility container protocol is constructed, a hysteresis space state machine is combined, and real-time logic cutting, efficient streaming rendering and smooth space interaction of unstructured volume data in any shape are achieved through general rendering entity abstraction, streaming zero-copy rendering pipelines and core algorithm innovation. According to the method, the problems of difficulty in geometric constraint of 3D Gaussian splashing data in the existing WebXR environment, bottleneck of rendering performance of a mobile Web end, single jitter of spatial state perception and the like are solved, and the method is suitable for various scenes such as AR transmission doors, photoscopes, holographic showcases and the like and has wide universality and practicability.

This invention provides an animal eye imaging method, apparatus, and electronic device based on SS-OCT. The method involves scanning the eye of a target animal using SS-OCT to acquire three-dimensional volumetric data of a designated region of the eye. The designated region includes at least the area from the anterior corneal surface to the retina. An imaging result of the animal eye is generated based on the three-dimensional volumetric data, and the imaging result includes at least one imaging data morphology. This method uses three-dimensional volumetric data as a unified geometric reference to generate at least one imaging data morphology of the animal eye, thereby achieving accurate imaging of the animal eye.

A method and system for node-based volumetric data generation and real-time rendering for DCC and Unreal Engine is disclosed. The method includes the following steps: creating and editing volumetric data based on the OpenVDB library in an external node-based editing tool; converting the edited OpenVDB volumetric data into a linearized NanoVDB buffer in real time; transferring the NanoVDB buffer from the external node-based editing tool to the UE5 plugin within the Unreal Engine via a memory-mapped file; receiving the NanoVDB buffer and uploading it to the structured buffer of the graphics processor; and performing real-time sampling and rendering of the volumetric data in the structured buffer within the Unreal Engine. The system includes a node-based volumetric editing module, a data format conversion module, a real-time data bridging module, and an engine-side rendering integration module. This invention directly utilizes UE5's native advanced rendering features such as Lumen and volumetric fog, solving the fundamental problem of poor compatibility in existing solutions.

This invention discloses a deep learning-based automatic classification and lesion detection method for magnetic resonance imaging (MRI), comprising: acquiring multi-sequence MRI three-dimensional volumetric data; preprocessing and dividing the data into training and validation sets; registering with standard anatomical atlases and resampling to obtain multi-scale anatomical prior feature maps; constructing an improved SegFormer model to generate preliminary multi-task joint diagnostic results; encoding the data into parameter vectors to be optimized, forming a parameter vector set; obtaining the optimal parameter vectors based on a sand cat swarm optimization algorithm; using the optimal parameter vectors to obtain the optimized improved SegFormer model; and obtaining the final multi-task joint diagnostic results using the multi-sequence MRI data of the patient to be tested. This invention achieves high-precision automatic classification and lesion detection grading of multi-sequence three-dimensional MRI images by improving the SegFormer model and combining it with sand cat swarm optimization of multi-level parameters.

The present application relates to a kind of dry electrode manufacturing method and its device.The dry electrode manufacturing method, the method includes the following steps: obtaining the thickness data of material film;Based on the thickness data of material film, obtain adjustment data;Wherein, the adjustment data includes the gap adjustment data of pressure roller, the rotational speed adjustment data of dosing shaft and the rotational speed adjustment data of feed shaft;Based on adjustment data adjustment pressure roller's gap, the rotational speed of dosing shaft and the rotational speed of feed shaft.As the further optimization scheme of the present application, obtain the volume data of material film in production per unit time;Obtain the consumption volume data of powder per unit time;Obtain the production efficiency data of unit time;Obtain the feeding data of dosing shaft surface;The dry electrode manufacturing method and its device, the thickness of product in production realizes automatic closed-loop control adjustment, realizes continuous adjustment without stopping, greatly improves product quality.

This application provides a dual-view CT reconstruction method based on geometrically guided diffusion and frequency domain awareness. Applied to the field of computer vision technology, this method acquires anteroposterior and lateral X-ray projection data of the target object; it then inputs these data into a dual-domain residual network based on discrete wavelet transform for feature extraction, obtaining a first projection feature map and a second projection feature map; the two-dimensional features of the first and second projection feature maps are projected onto three-dimensional space to obtain aligned three-dimensional spatial features; features from three adjacent layers of three-dimensional space are extracted to form a feature set, and these extracted features are then stitched and fused along the channel dimension to obtain a contextual condition feature map; this contextual condition feature map is used as a priori guided input diffusion model for analysis and processing to generate high-resolution three-dimensional CT volume data. This method improves the accuracy of medical image reconstruction under conditions of few samples.

The application discloses a film layer printing method and device, electronic equipment and storage medium; the application can obtain volume data of a printing nozzle of a printing device when printing material; based on the volume data of the printing nozzle when printing material, the printing nozzle is classified to obtain the category of the printing nozzle; based on the category of the printing nozzle, the printing nozzle is controlled to print material on a substrate to form a film layer. In the application, the volume data of the material when printing by the printing nozzle is analyzed, and the printing nozzle is classified based on the volume data; then the printing nozzle is controlled to print based on the category of the printing nozzle, so that the thickness of the formed film layer is more consistent. Therefore, the stability of the device can be improved.

Provided herein are methods, apparatuses, computer program products, and systems for generating textured surfaces using computed tomography. One method can include generating data of an X-ray detectable feature represented in volumetric data of a reference object acquired using an X-ray scanner; determining a first transformation matrix using the data of the X-ray detectable feature; obtaining a reference image of an optically detectable feature included in the reference object captured using an optical camera; calculating a second transformation matrix using the reference image of the optically detectable feature; producing a calibration transformation matrix using (i) the first transformation matrix, (ii) the second transformation matrix, and (iii) a third transformation matrix; providing the calibration transformation matrix, which is used in aligning an image of a physical object obtained using the optical camera with a CT reconstruction volume of the physical object obtained using the X-ray scanner.

Embodiments herein rapidly transform computed tomography angiography (CTA) data into an interactive, holographic visualization for clinical use. In one embodiment, a system for visualizing computed tomography angiography (CTA) images comprises a data interface configured to receive CTA image data in a Digital Imaging and Communications in Medicine (DICOM) format. The system also comprises a processor configured to render a plurality of two-dimensional CTA slice images into a three-dimensional (3D) volumetric dataset from the CTA image data, to filter the 3D volumetric dataset to resolve vascular structures relative to surrounding tissue and bone, and to generate an extended reality (XR) holographic representation of the filtered 3D volumetric dataset. The system also comprises an XR display device configured to present the holographic representation to a user for the user to manipulate the holographic representation and identify a vascular abnormality.

A method and system for using one or more sensors configured to capture two-dimensional and / or three-dimensional image data of one or more objects. In particular, the method and system combines one or more digital sensors with visible and near-infrared illumination to capture spectral image data of one or more objects in the visible and non-visible ranges. The captured spectral image data can be used to isolate and identify the one or more objects. Additionally, three-dimensional image data can be used to determine a volume of each of the one or more objects. The identification and volume data of the one or more objects can be used, individually or in combination, to obtain characteristics about the objects. The method and system provides a user with the ability to capture images of one or more objects and obtain relevant characteristics or information about each of the one or more objects.

This invention relates to the field of medical artificial intelligence software, and discloses an AI-assisted diagnosis and treatment system for refractive errors based on an internet hospital. The system comprises five modules: a patient information management module, an intelligent diagnostic assistance module, a remote monitoring module, a disease progression risk warning and prognosis prediction module, and an online consultation and eye health education module. The image segmentation model uses wavelet transform operators to decompose and extract multi-scale frequency domain features from the original 3D-OCT volumetric data of the eye. These multi-scale frequency domain features are then merged and concatenated with the original 3D-OCT volumetric data of the eye in the channel dimension to generate a multi-channel feature cube. This multi-channel feature cube is input into the Unet algorithm network unit, and after encoder, decoder, and hierarchical skip connection operations, a multi-channel probability map is generated. Finally, the multi-channel probability map is converted into a binary lesion segmentation mask for output. The intelligent image analysis module of this invention can improve the accuracy and efficiency of image screening for early identification of pathological myopia.

This invention relates to the field of remote sensing data processing technology, and discloses a remote sensing-based method and system for monitoring ecosystem carbon sinks. The method includes: preprocessing multi-source remote sensing data and constructing spatiotemporal volumetric data units carrying initial uncertainties, and storing them indexed; constructing a Gaussian process regression model to adaptively process time series data, suppressing the influence of outliers by iteratively correcting their uncertainties, and generating parameter estimates and corresponding uncertainties; using an inverse variance weighting method to fuse parameter estimates from different data sources, generating fused parameters and updated uncertainties; using the fused results to drive an ecosystem process model, and generating carbon sink estimation results and their final uncertainties through an uncertainty propagation algorithm. This invention solves the problems of data inconsistency, noise interference, and difficulty in assessing the reliability of results in traditional methods. By constructing an uncertainty quantification and propagation mechanism, it improves the accuracy and reliability of carbon sink estimation.

The application provides a CT image-oriented interactive three-dimensional reconstruction and classification method, device and equipment, relates to the technical field of image classification, and the method comprises the following steps: inputting a plurality of second CT images into a general volumetric medical image segmentation model for interactive segmentation, performing three-dimensional reconstruction on a target mask obtained to obtain a first target model; the smoothness of the surface of the first target model is optimized based on a geodesic active contour method, and a target region of a second target model is extracted; volume measurement is performed on the target region to obtain volume data information to classify the plurality of second CT images. The application uses a general volumetric medical image segmentation model to perform interactive segmentation on a plurality of second CT images, in order to improve the accuracy of model calculation, the application optimizes the smoothness of the surface of the first target model based on a geodesic active contour method, and the volume size of a target region representing lesion information is calculated based on the second target model to perform accurate classification.