15 results about "Single voxel" patented technology

The invention discloses a voxel method-based tunnel over-excavation and under-excavation identification and over-excavation and under-excavation quantity calculation method, and belongs to the field of tunnel intelligent construction and blasting quality evaluation. According to the technical scheme, three-dimensional point cloud of exposed surrounding rock is obtained for noise reduction processing, and RANSCA is used for extracting tunnel face and tunnel side wall surrounding rock parts; generating a design contour point cloud, registering the design contour point cloud with the actual tunnel, and moving to the same coordinate system; projecting the actual point cloud and the design point cloud of the tunnel to the cross section, and converting into points on a plane; connecting the projections of the design point clouds into a closed polygon; judging an over-excavation and under-excavation area; the space is divided into tiny voxels, and the affiliation relation between each voxel and an over-excavation or under-excavation area is judged; the number of voxels in the over-excavation and under-excavation areas is accumulated and multiplied by the volume of a single voxel, and the over-excavation and under-excavation earthwork volume is obtained. The method has the advantages of high efficiency, accuracy, intuition, feasibility, accurate quantification, high adaptability, cost control and the like, the construction quality of tunnel engineering is effectively improved, and the engineering cost is reduced.

The invention relates to the technical field of image recognition, in particular to a magnetic resonance spectrum imaging automatic positioning method and device, equipment and a medium, and the method comprises the steps: obtaining historical imaging data of different historical brain diseases; constructing a focus recognition module based on historical iconography data; scanning a transection position, a sagittal position and a coronal position of the brain of the target patient to obtain a scanning result; based on the scanning result and a focus recognition model, performing preliminary recognition on the scanning result, and determining the focus level and area of the brain of the target patient; a mode recognition method is adopted to recognize the focus level and area, and the focus parenchyma center is accurately determined; according to the method, scanning is carried out by taking the focus parenchyma center as the single voxel center and taking the focus parenchyma center and normal tissue positions around the focus area as multiple voxels, positioning of magnetic resonance spectrum imaging is realized, a machine model training mode is adopted, the focus positioning speed can be increased, and thus the accuracy of single voxel and multi-voxel spectrum imaging positioning is improved.

The invention provides an efficient occupied grid prediction method based on multi-sensor fusion. The efficient occupied grid prediction method comprises the steps that vehicle surrounding image data and laser point cloud information data are collected; respectively extracting image features and point cloud features from the image data and the point cloud information data by using a convolutional network; performing view conversion by adopting fast ray transformation, and converting the image features into image BEV features; performing dynamic feature fusion on the image BEV features and the point cloud features to obtain a fusion feature map; and converting the fused feature map into an occupied grid feature map through channel height conversion, and performing semantic category prediction on single voxels in the space based on the occupied grid feature map. According to the efficient occupied grid prediction method based on multi-sensor fusion, multi-modal features from a camera and a laser radar can be integrated through dynamic fusion of a 3D / 2D module, and effective fusion of the features is achieved.

The application relates to a variational correlation evaluation method and device, which comprises the following steps: acquiring magnetic resonance image data to obtain to-be-processed data; determining an iteration position sequence of the to-be-processed data and extracting iteration features to obtain a training set and a test set; inputting the training set into a variational correlation evaluation classification model for iteration training and testing, judging whether the trained variational correlation evaluation classification model converges or not, and obtaining the variational correlation evaluation classification model when the model converges, and performing effective feature extraction based on the variational correlation evaluation classification model; determining each effective feature position sequence, converting the effective feature position sequence into a three-dimensional brain structure matrix, covering the three-dimensional brain structure matrix to a preset standard human brain template, and identifying effective features related to each stimulation condition. The application quantifies the contribution of a single voxel in the process of executing a specific cognitive function, and finally identifies and extracts the least amount of features that can best represent the target stimulation condition.

The invention discloses an ESDF map construction method and device based on priority dynamic updating, and relates to the technical field of intelligent driving, and the method comprises the steps: constructing a corresponding three-dimensional space model; dividing the three-dimensional space model into a plurality of single voxel grids, obtaining an initial distance of a nearest obstacle corresponding to a single voxel corresponding to each single voxel grid based on the initial pose information, and constructing an ESDF map; based on a preset processing view field range and the real-time pose information of the target vehicle, setting a dynamic update priority rule of each single voxel; based on the dynamic updating priority rule of each single voxel, an updating task list sorted according to the priority is formulated, and the ESDF map is dynamically updated. According to the method, the defects in the prior art are overcome, the map updating efficiency is improved through a priority-based dynamic updating mechanism, and support is provided for L4-level intelligent sanitation vehicle path planning and obstacle avoidance control.

The present invention provides an intelligent automatic recognition method and system for a transfer machine. The method includes: installing a variety of sensors on the transfer machine to collect multi-modal data; dividing a single voxel into multiple object regions to obtain voxel sets of different objects; analyzing the stability and state of the objects according to the enhanced environment model to form an object state characteristic vector, and integrating the object state characteristic vector into the enhanced environment model; generating a preliminary handling strategy suitable for each object according to the enhanced state model; using the state data of the objects collected in real time by the sensors on the transfer machine to generate a feedback vector, and adjusting and fine-tuning the handling parameters according to the feedback information; feeding back various parameters and adjustment data during the handling process, as well as the category data and stability factors in the handling data, back to the small-sample learning model to update the feature description of the category. The present invention overcomes the limitations of traditional transfer machines in a changing environment and can cope with the challenges of handling diverse objects.

The application discloses a diffusion-weighted magnetic resonance spectrum parallel acquisition and reconstruction method. The method comprises the following steps: adding a pair of diffusion gradients in a single voxel spectrum sequence to obtain a single voxel diffusion-weighted magnetic resonance spectrum sequence; performing point-by-point summation on single-band radio frequency pulses at each voxel position of interest to obtain multi-band radio frequency pulses; obtaining a multi-voxel diffusion-weighted magnetic resonance spectrum signal through the single voxel diffusion-weighted magnetic resonance spectrum sequence and the multi-band radio frequency pulses; obtaining a sensitivity map of each channel of a receiving coil; separating and reconstructing the multi-voxel diffusion-weighted magnetic resonance spectrum signal according to the sensitivity map; and finally obtaining a separated and reconstructed multi-voxel diffusion-weighted magnetic resonance spectrum signal. The application can simultaneously measure diffusion-weighted magnetic resonance spectrum signals of multiple voxels of a human body, and obtain a signal-to-noise ratio and an apparent diffusion coefficient equivalent to those of a single voxel diffusion-weighted magnetic resonance spectrum signal, thereby saving at least half of the scanning time.

A method for characterizing the microscale diffusion characteristics of a single voxel in magnetic resonance imaging, comprising: S1, constructing a probability density function of a plurality of single-voxel diffusion characteristic distributions; S2, designing a special sequence to scan and image a target object to obtain scan data for constructing the probability density function of the plurality of single-voxel diffusion characteristic distributions; and S3, calculating the probability density function of the plurality of single-voxel diffusion characteristic distributions in step S1 according to the imaging sequence parameters and the scan data in step S2 to obtain the microscale diffusion characteristic results of the single voxel. The method for characterizing the microscale diffusion characteristics of a single voxel in magnetic resonance imaging solves the problem of how to use a single voxel in millimeter-scale magnetic resonance imaging to characterize the complex diffusion characteristics associated with the microscale tissue structure in the single voxel.

The invention discloses a virtual joint calculation method for TGS efficiency scale and emission track length, and belongs to the technical field of radioactive waste detection, and the method comprises the steps: selecting a waste bin and a detector, dividing voxels of the waste bin, dividing regions of the voxels, setting a rotation position for the waste bin, and setting A scanning positions for the detector; establishing primary simulation; presetting an efficiency scale matrix E and a track length matrix T; traversing A scanning positions of the Y rotation positions, performing simulation at each scanning position of each rotation position, counting the full-energy peak count and the equivalent track length of each track voxel, and respectively storing E and T; and subsequently, the counting rate Di of the scanning position i can be calculated according to E and T. According to the method, errors caused by separate calculation of the efficiency scale and the track length can be reduced, the accuracy of track length calculation is improved, the edge efficiency error of the detector is eliminated, and the reconstruction quality of an emission image can be effectively improved while the calculation efficiency is improved under the condition that a single pixel is a multi-point source.

Embodiments of the present disclosure provide an image registration method, apparatus, device, and computer-readable storage medium. The method provided by the embodiments of the present disclosure extracts feature maps of the image pair to be registered at multiple scales, and converts the displacement vector of each voxel in the moving image of the image pair to be registered at each scale into a combination of multiple displacement basis vectors determined based on the feature vector corresponding to the voxel in the corresponding feature map, so as to learn the displacement field from the paired feature maps, and generate the final displacement field based on the displacement fields at all scales, so as to make full use of the image feature information at different scales to achieve efficient and accurate image registration. The method of the embodiments of the present disclosure can learn the displacement field from coarse to fine based on different scales, so as to make full use of the potential information of different representation subspaces by fusing the displacement fields at all scales without introducing dense continuous network calculations.

The invention provides an intelligent automatic identification method and system for a transfer machine. The method comprises the following steps: installing various sensors on the transfer machine to collect multi-modal data; segmenting a single voxel into a plurality of object areas to obtain voxel sets of different objects; performing stability and state analysis on the object according to the enhanced environment model to form an object state characteristic vector, and integrating the object state characteristic vector into the enhanced environment model; generating a preliminary carrying strategy suitable for each object according to the enhanced state model; a sensor on the transfer machine is used for collecting state data of an object in real time, a feedback vector is generated, and carrying parameters are adjusted and finely adjusted according to feedback information; various parameters and adjustment data in the carrying process are fed back to the small sample learning model, and category data and stability factors in the carrying data are fed back to the small sample learning model, and feature description of categories is updated. According to the invention, the limitation of a traditional transfer machine in a changeable environment is overcome, and the challenge of carrying diversified objects can be coped with.

The present invention relates to a method for constructing a crushable model of ballast for discontinuous deformation analysis of spherical units, including: a step of scanning the physical object of ballast particles to obtain a triangular mesh model of ballast; a step of voxelizing the obtained triangular mesh model to obtain a voxelized model; and a step of performing scaling processing according to the number of contacts on the obtained voxelized model to obtain a crushable model of ballast. The method of the present invention is simple. During voxelization, a model with an outer contour similar to that of real ballast particles can be obtained through three steps: conservative rasterization, flood filling method, and spherical unit replacement. On the basis of the voxelized model, by means of scaling according to the number of contacts, the internal sub-particles in the voxelized model that have the same arrangement rule and size and cannot reflect real ballast particles are randomly rescaled and arranged again, so as to obtain a crushable model for discontinuous analysis of spherical unit ballast with a real shape.

Embodiments of the present application disclose a medical image processing method and device, an image processing apparatus and a medium. The method comprises: determining an arterial input function of an arterial blood vessel for supplying blood to a target part and attenuation coefficient enhancement information of a single voxel corresponding to the arterial blood vessel according to a plurality of groups of dynamic enhancement CT images collected at different time points; inputting the arterial input function and the attenuation coefficient enhancement information into a preset estimation model to obtain a preset blood flow parameter of the target part, the preset blood flow parameter comprising a blood flow velocity and an average transit time, and the preset estimation model being constructed based on a box-type attenuation function. The technical problem that the prior art cannot accurately determine the blood flow parameter of the dynamic enhancement CT is solved.

This invention provides a multidimensional magnetic resonance imaging (MRI) method and apparatus, comprising: determining the acquisition sequence and acquisition parameters for MRI; performing full sampling of the sample under test based on the acquisition parameters to obtain full-sample one-dimensional signal data, and generating a full-sample one-dimensional distribution of the sample under test using a Laplace transform algorithm; performing sparse sampling based on the acquisition parameters to obtain a multidimensional magnetic resonance signal of the sample under test, and extracting multidimensional magnetic resonance sampling data of each monomer element based on the multidimensional magnetic resonance signal; determining the initial multidimensional magnetic resonance distribution of each monomer element based on the multidimensional magnetic resonance sampling data of each monomer element using a Laplace transform algorithm; iteratively updating the initial multidimensional magnetic resonance distribution to obtain the updated multidimensional magnetic resonance distribution of each monomer element; and generating a multi-parameter spectrum of the sample under test based on the updated multidimensional magnetic resonance distributions. This multidimensional magnetic resonance imaging method and apparatus improves the accuracy of the obtained multidimensional magnetic resonance distribution spectrum.

This invention provides a method and system for quantifying the volume of peripancreatic necrotic tissue based on enhanced CT images, belonging to the field of medical image processing technology. The method involves constructing and training a deep convolutional neural network model to automatically segment enhanced abdominal venous phase CT images, outputting a pixel-level probability map of peripancreatic necrotic tissue. The probability map is then converted into a three-dimensional segmentation mask using image morphology processing algorithms. The volume of peripancreatic necrotic tissue is calculated based on the number of voxels and the volume of a single voxel in the three-dimensional segmentation mask. This invention solves the problems of high subjectivity, low accuracy, and time-consuming and laborious manual layer-by-layer delineation in traditional manual estimation. It achieves full automation of the peripancreatic necrotic tissue segmentation and volume quantification process, providing an objective, accurate, and repeatable quantitative tool for assessing the severity of acute pancreatitis, selecting intervention timing, and dynamically monitoring treatment efficacy.