38 results about "Image reconstruction algorithm" patented technology

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 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 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 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.

This application provides a method and system for digitizing pathological slides using low-resolution imaging. The method includes the following steps: imaging a multi-resolution calibration template using both low-resolution and high-resolution imaging systems to acquire low-resolution and high-resolution images; constructing high / low-resolution image pairs of pathological tissues using information provided by the multi-resolution calibration template; training a super-resolution image reconstruction algorithm in a supervised manner using multiple high / low-resolution image pairs to establish a computational model; imaging the pathological slides using the low-resolution imaging system, and then converting the low-resolution images into high-resolution images using the computational model. Through low-resolution imaging and computational model conversion, a new digitization technique for pathological slides based on low-resolution imaging is established, solving the problems of slow speed, local defocusing, and geometric distortion in current high-resolution imaging digitization, saving digitization time, and improving image quality.

A photoacoustic temperature imaging method based on a delay signal dispersion weighting factor belongs to the technical field of photoacoustic / ultrasonic imaging, and comprises the following steps: S1, constructing a dual-bandwidth photoacoustic imaging system based on photoacoustic and ultrasonic dual modes; s2, a pulse laser of the imaging system emits laser, and a central computer of the imaging system preprocesses the ultrasonic modal signals; s3, calculation and linearization processing of an SDDP factor are carried out; s4, weighting of SDDP factors and temperature reconstruction are carried out; and S5, system verification and application. According to the method, by introducing the SDDP weighting factor, weighting calculation is provided for the reconstructed image, and the phenomena of high artifacts and multiple side lobes existing in a traditional image reconstruction algorithm are effectively inhibited. The invention provides a new method for reconstructing a photoacoustic temperature image, which obviously improves the non-intrusive temperature imaging resolution ratio based on the photoacoustic effect and improves the temperature measurement precision. Compared with other non-linear weighting factors, the SDDP factor provided by the invention can reconstruct photoacoustic temperature image information better in real time through linear processing.

A framework for output validation of an image reconstruction algorithm. The framework receives original input data and reconstructed image data generated by the image reconstruction algorithm based on the original input data. Analytical forward projection is performed on the reconstructed image data to generate an algorithmic version of the original input data. The original input data and the algorithmic version of the original input data are applied as input to a likeness discriminator to generate a validation value that validates the image reconstruction algorithm.

This invention provides a high-resolution computational imaging system and method for multi-structure electron irradiation and data fusion. The system includes: an electron beam source module that generates an electron beam of at least one wavefront shape and irradiates the sample under test; a sample platform module that carries the sample under test and, in conjunction with the electron beam of each wavefront shape, controls the relative displacement between the sample and the electron beam for zoned illumination; an electron detection module that, during zoned illumination, acquires diffraction patterns formed by the electron beam of the corresponding wavefront shape passing through the corresponding zone of the sample under test at each zone location; and a data processing module that stitches together the diffraction patterns of the wavefront-shaped electron beams corresponding to each zone location and uses an image reconstruction algorithm to perform phase recovery and complex amplitude reconstruction on the diffraction information of the stitched patterns to determine the sample transmission information and obtain a sample transmittance image. This invention achieves high-resolution imaging, has a simple overall structure, and low equipment cost.

The invention discloses a photoacoustic calculation tomography system based on a dual-band focusing type optical fiber transducer array. Pulse focusing laser generated by a nanosecond pulse laser is guided by a light transmission beam to irradiate an imaging object; an imaging object generates a photoacoustic signal after absorbing light and being heated to expand; the optical fiber transducer array around the imaging object converts the received photoacoustic signal into an optical signal; the photoelectric detector converts a received optical signal into an electric signal, then the electric signal is transmitted to the data acquisition card for digital processing, and finally the computer processes the acquired data by using an image reconstruction algorithm to obtain a two-dimensional tomographic image. And controlling the cross section of the imaging object through the linear displacement table to obtain a three-dimensional tomographic image. According to the dual-band focusing type optical fiber transducer, frequency response and focusing modes can be flexibly controlled, targeted adjustment can be made according to different imaging requirements, and therefore the application range of the dual-band focusing type optical fiber transducer is greatly widened.

The application discloses a photoacoustic imaging method and system, relates to the technical field of medical imaging, and independently designs a fast photoacoustic imaging system of a ring-shaped fiber fusion ring-shaped array ultrasonic probe in the hardware aspect; the system can perform nondestructive imaging on a tissue; the imaging method is that laser pulses are emitted by a laser system; laser pulses are focused into a ring-shaped light spot by beam shaping; when the ring-shaped light spot irradiates a sample, local temperature rise caused by light absorption in the sample forms transient thermal expansion, and then ultrasonic waves are generated; the ultrasonic waves contain internal structure information of the sample; a plurality of ultrasonic sensors at the ring-shaped position simultaneously receive photoacoustic signals propagating back from different directions; the collected photoacoustic signals are processed, an image reconstruction algorithm is used, and the processed signals are converted into a three-dimensional photoacoustic image.

The invention discloses an ERT inversion image imaging method and system based on sensitivity optimization, and the method comprises the steps: classifying boundary measurement values, constructing an initial sensitivity matrix with a full air field as a reference, and carrying out the targeted zero setting and enhancement optimization of a column vector and a row vector according to liquid level information, according to the method, the problem of measurement failure caused by the fact that an electrode makes contact with a gas phase when a sewage pipeline is in a non-full-field state is solved, the problem of inapplicability of the ERT technology under the non-full-field working condition is solved, the problem that the imaging speed and the imaging precision cannot be achieved at the same time is solved, a sensitivity self-adaptive adjustment algorithm is used, and the measurement accuracy is improved. In combination with an image reconstruction algorithm of one-step iteration, the resolution of an inversion image can be effectively improved while the imaging speed is ensured, so that real-time and high-precision detection of a detected field domain is realized.

The invention provides a calculation gating three-dimensional imaging method and a calculation gating three-dimensional imaging device, which can be applied to the technical field of three-dimensional imaging. The method comprises the steps that a laser pulse is emitted to a target object, an echo signal formed after reflection of the target object is received, and the echo signal comprises a plurality of subframe signals; performing coded modulation on the plurality of sub-frame signals based on a digital micromirror device to obtain a plurality of modulated sub-frame signals; receiving the K modulated sub-frame signals in different delays by using a gating shutter according to preset gating delays to obtain K gating sub-frame signals, and the K gating sub-frame signals have different gating delays; determining a coded modulation image based on the K gating subframe signals; carrying out decoding recovery on the coded modulation image by using a compressed sensing image reconstruction algorithm, and calculating K reconstructed gating sub-frame images; and performing three-dimensional inversion reconstruction on the K reconstructed gating sub-frame images through a stepping delay gating three-dimensional imaging algorithm to obtain a three-dimensional image of the target object.

This invention discloses a defect detection device and method based on phase differentiation. The device includes an coded illumination module, a microscopic imaging module, a motion platform module, and a signal detection module. The method uses striped structured illumination to perform multi-frame phase-shift imaging of the surface under test, calculates the complex amplitude, extracts phase information, and performs high-order differential calculations on the phase to achieve simultaneous super-resolution detection of intensity-type and phase-type defects. The advantages of this invention are: it utilizes a structured illumination defect detection device to acquire images and construct complex amplitudes; combined with high-frequency signals amplified and extended by high-order phase differentiation, it overcomes the diffraction limit of the optical system; it also acquires sensitivity to phase-type defects; and it eliminates the need for complex spectral separation and image reconstruction algorithms, significantly reducing system complexity and data processing time.

The present disclosure relates to systems and methods for image reconstruction. The method may include obtaining original raw data acquired by a medical device, obtaining an initial image, and generating a target image based on the original raw data and the initial image according to an image reconstruction algorithm.

The present application relates to an image reconstruction method, device, storage medium, generation method and imaging system. The method comprises: obtaining scan data of an imaging target; determining whether DOI information exists in the scan data, and if the DOI information exists, applying the DOI information to image reconstruction; and if the DOI information does not exist, using a system response matrix to perform image reconstruction. By utilizing the DOI information, an image reconstruction algorithm support is constructed for different requirement scenarios, so that a reconstruction image meeting different requirements is obtained, and the problem of internal shrinkage during image reconstruction is solved.

The application relates to a handheld millimeter wave multi-channel three-dimensional imaging radar system and an imaging method. The method receives trigger time information of a hardware synchronization controller, radar sampling data of a radar module and position and posture data of a posture sensor; the radar sampling data and the position and posture data are mapped in a time dimension according to the trigger time information to obtain a sampling data set; the sampling data set is filtered through adaptive filtering to obtain a sampling point subset; a three-dimensional image of a target object is obtained through image reconstruction according to the sampling point subset; and the three-dimensional image of the target object is denoised through a dynamic adaptive threshold to obtain a denoised three-dimensional image. The method has the advantages that high synchronization accuracy is realized through a hardware synchronization controller, and the technical effect of improving image quality is realized through adaptive filtering and denoising.

The invention relates to a system and method for image reconstruction. The method may include obtaining original raw data collected by a medical device, obtaining an initial image, and generating a target image based on the original raw data and the initial image according to an image reconstruction algorithm.

The invention relates to a method and system for detecting dam defects based on muon rays, and belongs to the technical field of dam detection.The method comprises the steps that muon projection data obtained when muon beams penetrate through a dam to be detected are divided according to a plurality of projection directions, and a density distribution curve of each projection direction is calculated; obtaining a density distribution matrix for representing the density distribution of the dam to be detected according to the density distribution curves in all the projection directions and a pre-constructed geometrical relationship matrix between the detector and the pixels of the dam to be detected; based on the density distribution matrix, calling an image reconstruction algorithm in which a SART algorithm and a POCS algorithm are fused in advance, and performing reconstruction optimization on the muon imaging process to obtain a reconstructed dam image; defect position identification is carried out on the reconstructed dam image, a dam defect detection result is obtained, the characteristics of high penetrability and weak interaction of muons are ingeniously applied, an image reconstruction algorithm in which data driving updating and prior constraint projection are alternately carried out is combined, and the dam defects can be accurately detected.

The application discloses a resource scheduling method for an image reconstruction algorithm. The method splits an image reconstruction task into subtasks, calculates resource requirements of the subtasks, intelligently allocates computing resources according to the number of the subtasks and the resource requirements, combines algorithm characteristics and hardware performance, optimizes computing resource utilization, changes a strategy of simply stacking hardware quantity to improve computing capacity, and improves reconstruction efficiency.

The invention relates to a method for operating a computed tomography apparatus, the computed tomography apparatus comprising at least one X-ray radiation source, the computed tomography apparatus comprising at least one detector; the method comprises: performing a projection image scan sequence to generate a plurality of projection images by using an imaging focal spot pattern comprising a plurality of X-ray focal spot positions on at least one target such that a volume of an object to be reconstructed is illuminated by different X-ray radiation cones; performing a tomoscan sequence by performing the projection image scan sequence at different viewing angles; an image reconstruction algorithm is performed using the projection image to reconstruct a 3D image of the object. The invention also relates to a computed tomography device, a computer program product and a computer readable storage medium. The present invention can be employed to expand a field of view for a specific angle of view.

The described techniques generally relate to improving in-plane image resolution in computed tomography (CT) systems. A combination of a system geometry arrangement in combination with a multi-integrator design on the detector data acquisition system, in combination with information available in the signal processing stage, may be utilized to restore resolution while ensuring minimal impact on image noise. Furthermore, the focus position may be introduced into an image reconstruction algorithm to further mitigate factors that reduce image resolution and thereby achieve enhanced in-plane image resolution. Various embodiments can improve the image resolution (e.g., in-plane) of the system without any change to the tube / detector design / specification.

A three-dimensional ventilation image generation method, and a controller and an apparatus. The method comprises: generating a three-dimensional ventilation image by means of a signal extraction algorithm and an image reconstruction algorithm and according to an electrical impedance signal obtained by performing electrical impedance measurement on a target region to be measured, wherein performing electrical impedance measurement on said target region is implemented by using an electrode array that is three-dimensionally distributed on the periphery of said target region.

The invention provides a wearable physiological signal monitoring method and system based on electrical impedance tomography and electrocardiogram monitoring. The method comprises the following steps that multi-channel EIT original voltage data and electrocardiogram signals are synchronously obtained and preprocessed; carrying out RIME-VMD optimization separation on the preprocessed data to realize parameter optimization, signal decomposition and component identification and reconstruction; for the reconstructed perfusion signals, clustering static blood perfusion image sequences by adopting a clustering algorithm, and performing superposition according to classes so as to separate blood perfusion information of the heart and the lung on an image level; and imaging the separated ventilation and perfusion signals by adopting an EIT image reconstruction algorithm, and synchronously displaying in real time. Through the common electrode and the RIME-VMD algorithm, deep fusion of EIT and electrocardiosignals is achieved, pulmonary ventilation blood flow signals are accurately separated, the advantages of noninvasive and real-time bedside monitoring are achieved, and the method has important clinical value in diagnosis and treatment of pulmonary embolism, ARDS and other diseases.

The invention discloses a continuous frequency modulation near-field millimeter wave imaging method based on fractional Fourier transform, and relates to the field of near-field millimeter wave imaging. Compared with a traditional typical two-dimensional millimeter wave imaging algorithm, the method has the advantages that fractional order fast Fourier transform is introduced into an image reconstruction algorithm for the first time, and multi-frequency scanning data is combined to ensure the imaging quality. Experiments show that the method can be effectively applied to a near-field millimeter wave imaging system, better imaging effects can be achieved on various data sets compared with a typical two-dimensional imaging algorithm (BP algorithm), and the method is superior to the BP algorithm on quantitative indexes such as a point spread function (PSF), a dynamic range and calculation time.

The invention discloses an algebraic iteration photoacoustic image imaging method based on an acoustic transmission model, and belongs to the technical field of photoacoustic / ultrasonic imaging. Comprising the following steps: S1, designing a photoacoustic imaging system based on photoacoustic and ultrasonic bimodal; S2, discretizing an ultrasonic signal forward propagation equation; s3, calculating a forward model; and S4, constructing a forward propagation equation and iteratively solving the initial sound pressure. A traditional photoacoustic reconstruction method is influenced by limited bandwidth and limited visual angle of a transducer, so that reconstructed images are often influenced by artifacts. According to the method, the iterative reconstruction method based on the sound transmission model is introduced, so that the phenomena of high artifacts and multiple side lobes existing in a traditional image reconstruction algorithm are effectively inhibited. The invention provides a new method for reconstructing the photoacoustic image, and the resolution of the reconstructed image based on the photoacoustic effect is remarkably improved. In the process of iteratively solving the forward propagation equation, the regularization method is introduced, the convergence direction of the iterative solution is controlled by the L2 norm information of the initial sound pressure, and the robustness of the reconstructed image influenced by noise is effectively enhanced.