105 results about "Image reconstruction algorithm" patented technology

The invention provides a method and system for dynamically monitoring the state of a lithium ion battery, and relates to the field of lithium battery dynamic monitoring, and the method comprises the steps: collecting the image data of the lithium battery at different time points, which is obtained through the reflection or attenuation after X-ray penetration; processing the acquired image data through a reconstruction algorithm to obtain three-dimensional images in the battery at different time points; key structure information in the battery is extracted through the three-dimensional image; the change information of the internal structure of the battery is obtained by extracting key structure information in the battery at different moments. According to the method, the microscopic CT and the thermal imaging technology are combined, and the rapid image reconstruction algorithm and the compressed sensing technology are combined, so that the efficiency of data acquisition and image reconstruction is greatly improved, the time interval of lithium ion battery state detection is remarkably shortened, and the detection accuracy of the lithium ion battery state is improved. And the dynamic real-time monitoring of the lithium ion battery is realized.

The invention discloses a compression ultrafast imaging device based on time domain discrete illumination. The device is composed of a time domain discrete illumination compression ultrafast imaging system, a time sequence control system and an image reconstruction system. Time domain discrete illumination is provided for a to-be-measured scene through a pulse sequence generator, dozens of time slices of the to-be-measured scene are uniformly intercepted, spatial random coding is carried out, then the time slices are transmitted into a streak camera for space-time deflection and superposition imaging, and finally the to-be-measured scene is restored by adopting an image reconstruction algorithm (TV-CD) combining a total variation noise reduction model and a cascade noise reducer. The invention relates to a time domain discrete illumination compression ultrafast imaging technology (DI-CUP) for short. According to the invention, not only can single multi-image ultrafast imaging be realized, but also the data compression ratio can be reduced, the spatial resolution can be improved, and the observation time window is flexible and adjustable. The above advantages provide an accurate and effective measurement tool for non-repeatable ultrafast processes such as light pulse propagation and plasma evolution, and are of great significance to the development of related research and technology of natural science.

The invention discloses an image reconstruction algorithm, an image processing method and device, a vehicle and a storage medium. The image processing method comprises the steps of obtaining a visible light image and an auxiliary modal image to be fused; and performing fusion reconstruction on the visible light image and the auxiliary modal image by using an image reconstruction algorithm to obtain a target image, the image reconstruction algorithm comprising a step of completing a feature extraction task of the associated visible light image by using a high-frequency attention mechanism and a Fourier convolution mechanism in the high-frequency attention block. Therefore, the high-frequency information in the visible light image with various image qualities can be rapidly and effectively extracted through the image reconstruction algorithm, so that the target image is obtained by fusing and reconstructing the visible light image and the auxiliary modal image based on the effectively extracted high-frequency information; and features in a visible light image and features in an auxiliary modal image are clearer. Therefore, it can be ensured that images with high quality can be obtained when shooting is carried out in various shooting environments.

The invention relates to the technical field of object imaging, and discloses a single-pixel imaging method, system, medium and equipment for object motion trail repetition. The method comprises the following steps: generating a modulation pattern sequence with different spatial distributions according to a preset imaging image reconstruction algorithm, and inputting the modulation pattern sequence into a light modulation device; the track detection device sends a track pulse signal, the light modulation device is synchronously triggered to carry out light modulation, the light modulation device simultaneously sends a modulation pulse signal, and the multichannel signal synchronous acquisition device is synchronously triggered to receive a plurality of sampling values; selecting a target sampling value from the sampling values as an imaging image reconstruction sampling value; performing image reconstruction by using the imaging image reconstruction sampling value sequence to generate a single imaging image of the to-be-imaged object; and repeating the steps until the number of the generated imaging images reaches a preset number. The imaging system provided by the invention has the capability of carrying out continuous long-time imaging on a high-speed motion trail repeated object with variable motion speed.

The invention relates to the technical field of photoacoustic imaging, and discloses a limited-view-angle photoacoustic image artifact suppression method, system and device and a medium. The method comprises the following steps: generating a reconstructed limited-view-angle photoacoustic image and a corresponding full-view-angle photoacoustic image through an image reconstruction algorithm; adding a sub-graph extraction module in each hierarchy except the first hierarchy of the U-Net model, and extracting a sub-graph sequence; optimizing artifact suppression model parameters based on the loss function of the structural similarity index and the average absolute value error of the limited view angle photoacoustic image and the corresponding full view angle photoacoustic image, and selecting an optimal artifact suppression model; and inputting a limited view angle photoacoustic image constructed based on an actually collected limited view angle photoacoustic signal into the trained artifact suppression model, and outputting a post-processing image after artifact suppression. The method has a good post-processing result for the photoacoustic image with the limited visual angle, artifacts can be basically and effectively inhibited, and part of loss information in the image is recovered.

The invention provides a wafer defect detection method and device, and belongs to the technical field of semiconductor manufacturing. The wafer defect detection method comprises the steps that defect data of discontinuous defects on the surface of each wafer are acquired, and the defect data comprise the positions, sizes and types of the discontinuous defects; processing the defect data by using an image reconstruction algorithm, and reconstructing the discontinuous defect into a defect in a complete form; analyzing the spatial distribution characteristics of the defects in the complete form by utilizing a spatial clustering algorithm, and judging whether a preset defect distribution mode exists or not; if the preset defect distribution mode exists, calculating a risk score of the wafer according to the defect distribution density, the defect size and the defect distribution rule by utilizing a defect identification model; and comparing the risk score of the wafer with a preset risk threshold, and if the risk score is greater than the preset risk threshold, determining the wafer as an abnormal wafer. According to the invention, the discontinuous defect of the wafer can be detected.

The invention relates to a cable defect nondestructive testing method and system based on multi-mode non-invasive imaging. The method comprises the following steps: scanning a cable line through an infrared thermal imaging technology to obtain a cable surface temperature distribution condition and a temperature abnormal area; an electromagnetic sensor array is arranged in the temperature abnormal area; exciting an electromagnetic sensor to generate an alternating magnetic field, and collecting an electromagnetic response signal by using the electromagnetic sensor; based on the electromagnetic response signal, an electrical conductivity distribution image in the cable is reconstructed by using an image reconstruction algorithm; and finally, according to the cable surface temperature distribution condition and the cable internal conductivity distribution image, in combination with multi-modal characteristic correlation analysis, determining the fault type and fault point in the cable, and realizing nondestructive detection of cable defects. Compared with the prior art, the device does not need to be in contact with a cable, is suitable for long-distance operation, can further check hidden dangers which cannot be accurately detected by infrared rays, and realizes rapid and efficient nondestructive detection of cable defects.

The invention provides an unsupervised low-dose photon counting CT (Computed Tomography) reconstruction method and an unsupervised low-dose photon counting CT reconstruction device based on optimal transmission. According to the method, a low-dose photon counting CT reconstruction problem is modeled as a Cantrovitch problem under a distribution consistency constraint, and the method comprises the following steps: constructing and training an optimal transmission-based unsupervised projection recovery network and constructing and training an optimal transmission-based unsupervised image noise reduction network; performing detail recovery on the photon counting CT low-dose projection by using the trained unsupervised projection recovery network to generate a denoised projection; reconstructing the denoised projection by using an image reconstruction algorithm to generate an intermediate image; and performing noise reduction on the intermediate image by using the trained unsupervised image noise reduction network to obtain a final de-noised image. According to the method, the problem that a high-quality pairing data set is difficult to obtain and a photon counting CT low-dose image is difficult to reconstruct can be solved.

The invention discloses a multi-target sensing and tracking method for detecting an unmanned aerial vehicle swarm through a single-photon laser radar, and belongs to the field of photoelectric detection and signal processing. The problem that a traditional image reconstruction algorithm and a tracking algorithm are difficult to adapt to ultra-low signal-to-noise ratio, high dynamic and multi-target complex sensing requirements is solved. The method comprises the following steps: carrying out systematic prepeak noise self-adaptive suppression on global photon arrival time data acquired by a single-photon laser radar; performing photon event physical statistical modeling and background noise suppression based on the suppressed data to obtain an enhanced residual signal; performing space-time consistency enhancement processing on the enhanced residual signal to realize extraction and reconstruction of a multi-target area; based on the extracted photon events in the multi-target area, performing trajectory fitting and prediction by adopting a Bayesian weighted RANSAC (Random Sample Consensus) fitting method; and designing a target tracking algorithm based on scale adaptive updating and template matching of an optical flow method and pyramid search assistance, and carrying out robust tracking on multiple targets. The method is used in target tracking field.

The present invention provides a generation method for calibration data. The calibration data is used for correction of image reconstruction of a scanning imaging device. The method comprises: placing a calibration phantom in a scanning area formed by rays, wherein the calibration phantom comprises M sections respectively composed of M materials, the M materials have M physical property theoretical values, respectively, and M is a positive integer greater than or equal to 2; by means of a detector, collecting rays passing through the scanning area so as to acquire actual projection data; on the basis of the actual projection data, using an image reconstruction algorithm to reconstruct the calibration phantom to obtain a reconstructed image; performing segmentation processing on the reconstructed image to obtain M reconstructed sub-images, wherein the M reconstructed sub-images respectively correspond to the M sections; for the M reconstructed sub-images, respectively calculating M physical property measurement values corresponding to the M sections; and generating calibration data on the basis of the M physical property theoretical values and the M physical property measurement values.

The invention relates to the technical field of medical image processing, in particular to a semantic medical image for 3D printing of an anatomical structure, which comprises the following steps: acquiring medical image data, performing automatic labeling and classification on the anatomical structure in the medical image data through a semantic segmentation model to obtain anatomical structure labeling information, according to the obtained anatomical structure labeling information, an image reconstruction algorithm is adopted to conduct three-dimensional reconstruction on each anatomical structure to obtain a three-dimensional mesh model, the three-dimensional mesh model is optimized on the basis of the obtained three-dimensional mesh model in combination with material characteristics and a mechanical model to obtain optimized three-dimensional printing model data, and a 3D printing technology is adopted to obtain the 3D printing model. And the three-dimensional printing model data are input into printing equipment, 3D printing of the anatomical structure is completed, and a physical model of the anatomical structure is obtained. According to the invention, the accuracy of medical image analysis is improved, and the precision and printing quality of the three-dimensional model are effectively improved.

The application relates to an image reconstruction method of an LSTM-based electrical capacitance tomography system, which comprises the following steps: (1) constructing an electrical capacitance tomography system model, obtaining a sensitivity field of the electrical capacitance tomography system through Comsol finite element simulation software, and obtaining electrical capacitance vectors under different positions and different shapes of an object field distribution; (2) obtaining a reconstructed image through a Landweber algorithm; (3) determining a ''time sequence'' sample according to ''rows'', and obtaining an image reconstruction result through an LSTM neural network model; (4) determining a ''time sequence'' sample according to ''columns'', and obtaining an image reconstruction result through an LSTM neural network model; and (5) fusing two image results to obtain a final image reconstruction result. Through the above method, the reconstructed image quality is improved, and the reconstructed medium distribution is closer to the real distribution.

The invention discloses a handheld rapid three-dimensional fundus blood supply imaging system and method.The system comprises an upper computer, a laser excitation module, a probe, a data collection module and a space positioning module, the laser excitation module, the probe, the data collection module and the space positioning module are connected with the upper computer, and the laser excitation module conducts wavelength conversion on input pump laser through the stimulated Raman scattering principle to generate excitation light; the exciting light is then transmitted to the probe for high-speed scanning, the probe receives real-time pose feedback of the space positioning module at the same time so as to eliminate the influence of operation jitter, the data acquisition module pre-processes a photoacoustic signal acquired by the probe and then transmits the photoacoustic signal to the upper computer, and a distribution diagram is generated through an image reconstruction algorithm and analyzed. According to the invention, four clinical troubles of poor molecular specificity, depth-resolution imbalance, low clinical adaptability and deficiency of quantitative standards in the existing imaging technology are fundamentally solved, and a universal tool is provided for early screening of eye ground ischemic diseases.

A single-pixel imaging method for an object retracing a motion trajectory, a system, a medium, and a device. The method comprises: a controller generating, according to a predefined formed-image reconstruction algorithm, a modulation pattern sequence having different spatial distributions, and inputting the modulation pattern sequence into a light modulation apparatus (S1); the light modulation apparatus receiving a trajectory pulse signal from a digital signal processor, and simultaneously sending a modulated pulse signal to a synchronous multi-channel signal acquisition apparatus (S2); the synchronous multi-channel signal acquisition apparatus receiving the modulated pulse signal, and being triggered to acquire, at a predetermined sampling frequency, a plurality of sample values of a sampled light signal illuminating an object to be imaged and detected by a first detector (S3); the controller selecting a target sample value from among the sample values as a formed-image reconstruction sample value, the formed-image reconstruction sample value corresponding to a target modulation pattern in the modulation pattern sequence (S4); repeating the above steps until each formed-image reconstruction sample value corresponds to each modulation pattern in the modulation pattern sequence on a one-to-one basis, and generating a formed-image reconstruction sample value sequence on the basis of each formed-image reconstruction sample value (S5); on the basis of the formed-image reconstruction algorithm, the controller performing image reconstruction on the formed-image reconstruction sample value sequence to generate a single formed image of the object to be imaged (S6); and repeating the above steps until a count of generated single formed images reaches a predetermined number (S7). The imaging system is capable of imaging, over an extended period of time, high-speed objects retracing a motion trajectory at varying velocity.

The invention discloses a flat panel detector and a method and device for using the flat panel detector. A flat panel detector is constructed on the basis of an amorphous silicon substrate on which a hexagonal pixel pattern is uniformly laid. The hexagonal pixels can be arranged more closely on a two-dimensional plane, and gaps among the pixels are reduced, so that a photosensitive area is maximized with a relatively high filling rate, and the spatial resolution of the detector is improved. And the hexagonal pixels enable a frequency space to generate an angle of 60 degrees, so that the influence of grid artifacts is reduced to a certain extent. Meanwhile, the hexagonal pixel array is effectively processed and optimized by adopting an image reconstruction algorithm, the signal-to-noise ratio of the single pixel of the flat panel detector is improved, and the definition and accuracy of the image are improved.

The application relates to the technical field of CT imaging, in particular to a finite-angle CT image reconstruction algorithm based on a repair matrix, which comprises the following steps: constructing a repair matrix according to a prior information set; updating a landslide artifact image according to the repair matrix, a wavelet tight frame transformation operator, a preset reconstruction image, a preset landslide artifact image and a first preset auxiliary variable to obtain an updated landslide artifact image; and updating a reconstruction image according to a system matrix, the wavelet tight frame transformation operator, the updated landslide artifact image and a second preset auxiliary variable to obtain an updated reconstruction image. In this way, the preset landslide artifact image is updated through the repair matrix, and then the preset reconstruction image is updated according to the updated preset landslide artifact image, so that the details and edge information blurred and degraded by the landslide artifact in the image are repaired, and the quality of the finite-angle CT image is improved. Meanwhile, in the iteration process, the noise is suppressed through the wavelet tight frame transformation operator, and the quality of the finite-angle CT image is further improved.

The present invention discloses a multi-scale hyperspectral image reconstruction algorithm and system from RGB images, which belongs to the field of computer vision hyperspectral images. The algorithm includes: processing the original RGB image through a multi-scale processing module, and outputting a feature map Y' i ; The feature map Y' i The feature image with multi-scale preprocessing information is added and stacked with the original RGB image itself in the spectral channel dimension to obtain a feature image with multi-scale preprocessing information; the feature image with multi-scale preprocessing information is passed through three spatial-spectral Transformer joint processing modules in sequence to jointly process the spatial-spectral dimensions to obtain a feature image with spatial-spectral feature information; the feature image with spatial-spectral feature information is processed through the spectral dimension Transformer to obtain a feature image with the spectral dimension feature information fully extracted by the Transformer; the feature image with the spectral dimension feature information fully extracted by the Transformer is passed through a 3×3 convolutional layer to adjust the channel dimension to the target 31-channel output, and finally a hyperspectral image is obtained.

The invention discloses a dynamic material flow monitoring method and system for cut tobaccos, and the method comprises the steps: uniformly arranging measuring electrodes on the inner wall of a cut tobacco conveying pipeline for secondary winnowing, so as to construct an electrode array for electrostatic charge detection; forming a polar plate corresponding to the capacitor by the measuring electrode and a set shielding electrode; the capacitance value of the capacitor is obtained through the electrostatic charges of the pipe wall, and the capacitance value correspondingly changes along with the distribution concentration of tobacco shreds in the tobacco shred conveying pipeline; obtaining the capacitance value change of the capacitor in real time, and obtaining a distribution image of tobacco shreds in the tobacco shred conveying pipeline by using an image reconstruction algorithm; and calculating the volume ratio of the tobacco shreds according to the distribution image, and further calculating the tobacco shred flow and the tobacco shred blanking mass according to the volume ratio and the tobacco shred flow velocity. According to the invention, the accuracy and convenience of dynamic flow monitoring of the secondary winnowing tobacco shreds can be improved.

The invention discloses a compression ultrafast imaging device based on instantaneous image reference. The compression ultrafast imaging device is composed of a dynamic scene acquisition system, an instantaneous imaging system, a coding compression imaging system and a control and processing system. According to the method, dynamic scenes including coding compression imaging and instantaneous imaging are recorded simultaneously through two different imaging models, and collected bimodal data are processed and reconstructed by using a bimodal information fusion image reconstruction algorithm based on a non-training neural network, so that a high-fidelity dynamic scene is recovered. According to the method, the image quality of compression ultrafast imaging can be effectively improved, the defect of a traditional compression ultrafast imaging technology in the aspect of image fidelity is overcome, the temporal-spatial resolution of an imaging system is remarkably improved, and the method is suitable for fine observation of ultrafast dynamic phenomena and particularly has important application value in the fields of scientific research, industrial application and military affairs.

According to the electrical capacitance tomography image reconstruction method based on the damping spectrum iteration method, an ill-conditioned nonlinear equation set is converted into a solvable linear equation set, the complexity of the solving process is greatly reduced, and meanwhile the accuracy and stability of understanding are remarkably improved. By means of the algorithm, artifacts in the electrical capacitance tomography reconstructed image are effectively reduced, the image quality is remarkably improved, and the reconstructed image is closer to the original flow pattern. Compared with a traditional method, the algorithm has the advantages that the imaging speed is remarkably increased while the imaging precision is improved, and the key problem that the imaging quality and the calculation efficiency are difficult to consider in an existing image reconstruction algorithm is successfully solved.

The application provides a rearrangement method, a CT scanning device and a readable storage medium. The rearrangement method comprises the following steps: transposing base data formed by a plurality of fan beam projection data, and calculating and outputting parallel beam projection data based on the transposed base data. In this way, the internal structure of the base data is changed by data transposition, so that the data related to the same parallel beam projection data exists in the same row of the base data, the access frequency of the first storage medium when generating one parallel beam projection data is reduced, the rearrangement time is reduced, and the problem that the CT rearrangement algorithm has frequent memory access, slow speed and affects the reconstruction speed of the whole image reconstruction algorithm in the prior art is solved.

The invention relates to a target reconstruction method for a sparse view angle image, belongs to the technical field of image reconstruction, and solves the problems of low quality and artifacts of a reconstructed image obtained by reconstruction based on the sparse view angle image in the prior art. The target reconstruction method comprises the following steps: detecting and collecting a target object through an X-ray machine to obtain a detection projection image with a small number of projection visual angles; based on a linear interpolation method, performing interpolation on the detection projection image in the projection visual angle direction to obtain an interpolation recovery projection image; inputting the interpolation recovery projection image into a pre-trained projection domain network model to obtain an optimized projection image; and reconstructing the optimized projection image based on a preset image reconstruction algorithm to obtain a target reconstructed image. And the quality of the image reconstructed by the sparse view angle image is improved.

The application discloses a plasma electron temperature two-dimensional distribution multi-time point diagnosis method and device based on an X-ray waveband sheet array, equipment and a medium, and comprises the following steps: acquiring two X-ray coded images under the same time signal; reconstructing the X-ray coded images through a coded image reconstruction algorithm to obtain a high-resolution X-ray intensity image corresponding to each X-ray coded image; constructing a corresponding relationship between the intensity ratio and the electron temperature of the two high-resolution X-ray intensity images at the same position based on the working principle of a multi-channel filter sheet method; determining the electron temperature two-dimensional distribution information at the time point according to a plurality of corresponding relationships, and expanding the electron temperature two-dimensional distribution multi-time point data. The application belongs to the field of plasma electron temperature diagnosis. The application can improve the light collection efficiency and the spatial resolution.

The embodiment of the invention provides an image processing method, a model training method and related equipment, and the method comprises the steps: obtaining a preview image in response to a starting operation of a camera application; in response to the shooting operation, determining a first image from the preview images, and obtaining a dynamic range compression (DRC) image corresponding to the first image as a second image; performing pyramid decomposition on the first image through a preset image processing model to obtain a first low-frequency image, and performing pyramid decomposition on the second image to obtain a second low-frequency image and a plurality of high-frequency images; performing pyramid decomposition on the mask image corresponding to the first image to obtain a third low-frequency image; fusing the first low-frequency graph, the second low-frequency graph and the third low-frequency graph to obtain a first fused graph; and based on an image reconstruction algorithm, obtaining a target DRC image according to the first fusion image and the plurality of high-frequency images. Through the preset image processing model, the preview image can be utilized to optimize the DRC image, and the brightness difference between the preview image and the target DRC image is reduced.

This invention discloses a method and apparatus for X-ray finite-angle CT image reconstruction based on generalized total variation, comprising: Step 1, using a finite-angle CT scan dataset p, and employing an image reconstruction operator R related to the scan geometry parameter set G. G Update estimated image u (k) Obtain the intermediate image u (k+1 / 2) k is the iteration number; Step 2, use the sparsity of the gradient to constrain the intermediate image u (k+1 / 2) The estimated image u is obtained. (k+1) Step 3: Determine if the iteration requirement has been met. If so, terminate the iteration and output the estimated image u. (k+1) Conversely, if the boundary is not clear, proceed to step 1. This invention overcomes the problem of blurred boundaries in existing finite-angle CT image reconstruction algorithms.

The invention relates to a method for operating a computed tomography device (150), wherein the computed tomography device (150) comprises at least one x-ray radiation source (131) configured for generating x-ray radiation cones (132) for irradiating an object (134), wherein the computed tomography device (150) comprises at least one detector (136) configured for detecting the x-ray radiation of the x-ray radiation cones (132) that have interacted with the object (134), wherein the x-ray radiation source (131) comprises at least one electron optic arrangement (138) configured for variably arranging at least one electron beam (140) onto a plurality of positions of focal spots on at least one target comprised by the x-ray radiation source (131) in a manner that a plurality of different x-ray radiation cones (132) emerging from the focal spots is generated in order to image different portions of the object (134); the method comprising:performing a projection image scanning sequence (PSS) by using an imaging focal spot pattern in order to generate a plurality of projection images, wherein the imaging focal spot pattern comprises a plurality of x-ray focal spot positions on the at least one target (144) such that a volume of the object (134) to be reconstructed is irradiated by the different x-ray radiation cones (132);performing a tomographic scanning sequence (TSS) by performing the projection image scanning sequence (PSS) at differing viewing angles;performing an image reconstruction algorithm using the projection images in order to reconstruct a 3D-image of the object (134).The invention further relates to a computed tomography device (150), a computer program and a computer-readable storage medium. The invention may be employed in order to extend the field of view for a specific viewing angle.

The invention relates to a multi-angle composite optical coherence tomography imaging system and method, the imaging system comprises an OCT system, a sample arm of the OCT system comprises a multi-angle scanning part and a Bscan scanning part, the OCT system emits parallel light beams to the sample arm, the multi-angle scanning part realizes multi-angle scanning of a sample, and the Bscan scanning part realizes Bscan scanning of the sample. According to the high-resolution image reconstruction algorithm, a plane wave delay accumulation beam forming algorithm is taken as a core, and signals after beam forming of echo data under plane wave emission of different angles are coherently compounded and processed into an image. According to the invention, a multi-angle scanning mode is realized on the system, a sample is kept immobile in a detection process, the system can be applied to the field of clinical diagnosis more favorably, and a coherent composite imaging method ensures that a high-resolution OCT image can be reconstructed under a limited scanning angle.

The invention provides a metallurgical mineral conveying process component real-time monitoring method and a metallurgical mineral conveying process component real-time monitoring system based on electromagnetic tomography. The method comprises the following steps: carrying out non-contact scanning on a conveyor belt by adopting a multi-frequency excited and eccentrically arranged EMT sensor array, and constructing a mineral-electromagnetic characteristic mapping database in combination with an electromagnetic tomography image reconstruction algorithm and a deep learning method; real-time mineral pixel-level identification is carried out through the trained machine learning model; the recognition result is divided according to grid areas, and the real-time mass ratio data of all minerals on the material section are calculated in combination with the pre-calibrated mineral density and the area weight factor corrected by the belt curvature; and signal drift compensation is carried out by fusing high-precision temperature sensor data. And finally, real-time mass ratio data are converted into control signals, downstream equipment such as a sorting mechanical arm and a batching valve is driven, online recognition, precise quantification and intelligent regulation and control of mineral components are achieved, and the resource utilization efficiency and the automation level in the metallurgical process are remarkably improved.

The application discloses a brain hemorrhage magnetic induction tomography image reconstruction method based on an improved NR algorithm, and comprises the following steps: obtaining coil detection phase data and a sensitivity matrix by using an established brain hemorrhage MIT finite element model; introducing a regularization penalty term based on a target function of a traditional NR algorithm and solving an iterative formula of the algorithm, determining optimization parameters in the algorithm by a v method, and taking a conductivity distribution calculated by using a linear back projection algorithm as an initial value of iteration of the improved NR algorithm; introducing a projection operator P Ensuring that the algorithm converges on a convex set each time; determining an optimal threshold value or a maximum number of iterations, and outputting a final conductivity distribution. Compared with a traditional magnetic induction tomography image reconstruction algorithm, the application has better image reconstruction quality, can effectively reduce image reconstruction artifacts, and can detect brain hemorrhage.

This invention discloses a three-dimensional resistivity imaging probe and system for ultra-deep directional boreholes, belonging to the field of engineering exploration technology. The downhole probe adopts an inner-lined scanning structure with longitudinal grooves on its outer shell surface. A probe array is installed within the grooves, and the exposed ends of the probes are radially scattering, forming inner-lined contact with the borehole wall. The probe integrates an attitude measurement and probe extension module, a power supply module, and a data storage and transmission module. The system includes a ground control and processing unit, a cable transmission unit, and the downhole probe itself. An excitation electric field is generated by the power supply electrodes, and the probe array collects borehole wall voltage and current data. Combined with a three-dimensional resistivity imaging model and image reconstruction algorithm, an image of the circumferential cylindrical resistivity distribution of the borehole is generated. This invention achieves in-situ, high-precision three-dimensional resistivity imaging of boreholes, accurately identifying the spatial distribution of faults, fissures, and weak interlayers around the borehole, providing reliable technical support for risk identification and assessment in deep earth engineering.