97 results about "Source imaging" patented technology

The invention discloses a ginkgo leaf extracting solution state real-time monitoring method based on image processing, and relates to the technical field of ginkgo leaf extracting solutions. The method comprises the following steps: constructing a multi-light-source imaging environment to shoot a ginkgo leaf extracting solution image; obtaining an extracting solution mask through a U-net segmentation model, and obtaining an extracting solution foreground image in combination with the ginkgo leaf extracting solution image; segmenting the extracting solution foreground image through an adaptive threshold method to obtain an extracting solution block graph, and optimizing through a watershed boundary optimization method to obtain an optimized extracting solution block graph; a block boundary probability value is calculated through a boundary probability model with double distance changes, a block gradient magnitude is calculated through a Sobel operator, block boundary confidence is obtained by combining the block boundary probability value and the block gradient magnitude, and block boundary pixels are determined; and collecting a boundary gradient feature vector sequence of the block boundary pixels, inputting the boundary gradient feature vector sequence into the extracting solution evolution trend model, outputting to obtain an oxidation risk index, and performing early warning if the oxidation risk index is greater than a preset threshold value.

The invention discloses a brain power supply imaging method and system based on a physical information neural network. The method comprises the following steps: establishing a three-layer boundary element method head model based on a Maxwell equation set under quasi-static approximation and calculating a lead matrix; carrying out filtering, artifact suppression and standardization processing on the multi-channel electroencephalogram signals; inputting the standardized signal into a neural network encoder to extract a time sequence feature tensor, estimating the source current density based on the feature tensor, and performing forward calculation by using the lead matrix to obtain a predicted scalp potential; constructing a mixed loss function consisting of a data fidelity item, a physical consistency item and a physical heuristic regularization item, and performing network training and optimization by taking minimization of the loss function as a target; and when the training meets a convergence condition, outputting a visualization result of the brain endogenous current density spatial distribution. According to the method, electromagnetic physical constraints are introduced, so that the physical consistency, interpretability and stability of electroencephalogram inversion are improved.

The invention discloses an epilepsy region positioning method and system based on brain power supply imaging and a dynamic brain network, and the method comprises the steps: obtaining T1 weighted magnetic resonance imaging data of a user, and constructing an individual three-dimensional head model through a boundary element method; acquiring scalp electroencephalogram data of a user, and preprocessing the scalp electroencephalogram data; based on an individual three-dimensional head model, performing inverse problem solving on the preprocessed scalp electroencephalogram data by using a standardized low-resolution brain power source imaging algorithm to obtain source current density signals of 68 brain regions; decomposing into six frequency bands, calculating the power spectrum density of each brain region and carrying out normalization processing, and screening effective frequency bands; based on the source current density signals of the 68 brain regions of the effective frequency band, information flow directions and intensities of different brain regions are calculated by adopting a directional transfer function method, a directional transfer function matrix of the effective frequency band is formed, and a directed brain network is constructed; and calculating a graph theory index and / or an epilepsy index of each brain region, carrying out maximum value normalization analysis, and determining an epilepsy region positioning result.

The embodiment of the invention provides a flip chip offset measurement system and method, the measurement system comprises a first light source and a second light source which are different in emergent light beam wavelength, an imaging assembly and a processing assembly, and the first light source is controlled to emit a first light beam which penetrates through a flip chip and irradiates a first target in a deep layer; obtaining a first image containing the first target from the first detector; controlling a second light source to emit a second light beam to irradiate a second target on the surface of the flip chip, acquiring a second image containing the second target from a second detector, and finally acquiring a first offset and a second offset of the flip chip relative to the substrate based on the first image and the second image by a processing assembly, and obtaining the bonding offset of the flip chip according to the first offset and the second offset. According to the invention, the dual-wavelength light source is adopted to cooperatively irradiate the flip chip in a time-sharing / wave-band-sharing manner, so that the penetrability-reflectivity contradiction of single-wavelength detection is broken through, and the accuracy and reliability of lamination offset detection are improved.

The invention discloses a fast iteration deconvolution sound source imaging method and system, and the method comprises the steps: obtaining an audio signal and a video signal generated in a partial discharge process, and extracting the frequency domain information of the audio signal to construct a cross spectrum matrix; a propagation path of sound waves in a scanning plane area is simulated, a steering vector is generated, and the scanning plane area is key parameters initialized according to sound source positioning requirements; modeling the sound field response characteristic of each point in the scanning plane area to generate a point spread function; optimizing and solving the point spread function by adopting a fast iterative shrinkage threshold algorithm to obtain an optimal sound source distribution diagram, wherein a step length factor and an intermediate variable are updated based on the steering vector and a residual vector constructed by the cross spectrum matrix in an iteration process; according to the invention, high-quality sound field distribution data can be rapidly and accurately obtained.

The invention discloses a surface defect detection system based on a microcrystalline glass panel finished product, and relates to the technical field of surface defect detection. The defect full-dimensional dynamic state map construction module is used for constructing and updating a defect full-dimensional dynamic state map containing defect three-dimensional coordinate information, multi-modal feature confidence information, virtual-entity parameter deviation information and feature definition-registration precision linkage threshold information in real time; the structured light three-dimensional contour acquisition module is used for acquiring three-dimensional contour data of the surface of the microcrystalline glass panel; the multi-modal feature fusion module is used for collecting two-dimensional image data of multi-light-source imaging and extracting multi-modal feature information; the digital twin virtual debugging module is used for constructing a virtual detection environment based on the defect full-dimension dynamic state graph; the problem of feature confusion caused by light source combinational logic solidification in an existing multi-light-source switching system is effectively solved.

The invention belongs to the technical field of excitation detection, and provides a movable seismic source system carried by a deep mine heading machine and a positioning excitation detection method, which are characterized in that the excitation time delay of each seismic source unit in an array is accurately controlled by utilizing a controllable seismic source, so that the seismic source units form synchronous superposition in a specific direction, and the detection of an active source is realized; in the aspect of passive source detection, vibration generated when the jumbolter cuts surrounding rock is used as a vibration source, a pilot sensor installed near an anchor rod drill is used for recording an original vibration signal, namely cutting vibration, when the jumbolter works, and signals collected when the jumbolter works and signals collected by the pilot sensor are subjected to cross-correlation processing, so that the original vibration signal is obtained. And reconstructing a virtual seismic source, and then carrying out data processing and passive source imaging. And the active source detection result and the passive source detection result are combined to interpret the unfavorable geologic body, so that the detection of the position is realized, and the geological interpretation of the whole space of the mine can be realized.

The invention relates to the technical field of computer vision, and discloses a computer vision-assisted dental restoration adaptation system, which comprises an image acquisition module, an image processing module, an adaptation evaluation module, a central control module and a feedback optimization unit, high-resolution image data, including visible light images, three-dimensional scanning data and infrared images, of the interior of the oral cavity and a restoration body are obtained through multi-source imaging equipment of the image acquisition module, the form, texture and temperature distribution characteristics of the oral cavity environment are captured, and the image contrast and the alignment precision are enhanced in combination with the illumination control unit and the positioning calibration unit. Data integrity and detail visibility are ensured, and a reliable basis is provided for subsequent image processing; the image processing module performs preprocessing, feature extraction and segmentation on the acquired image data, so that the accuracy and efficiency of adaptive state analysis are improved.

The invention provides a fundus camera system integrated with adaptive optics and a correction method, and relates to the technical field of ophthalmology imaging. The fundus camera system comprises a beacon light source, an imaging light source and an imaging sensor; the device comprises a wavefront sensor, a wavefront correction device and a control module, and the wavefront correction device comprises a focusing lens group and a deformable reflector; the focusing lens group and the deformable reflector are arranged in the same light path from the beacon light source to human eyes and from the human eyes to the wavefront sensor; moreover, the control module executes a two-step closed-loop control strategy of first focusing and second correction: firstly, based on a first measurement result of the wavefront sensor, the focusing lens group is driven to move so as to compensate low-order aberration; and after the focusing is completed, the deformable reflector is driven to deform based on the subsequent measurement result of the wavefront sensor so as to compensate the high-order aberration in a closed-loop manner. On the basis of inheriting the advantage of rapid focusing in the prior art, the self-adaptive optical technology is further integrated, so that the limitation of high-order aberration on resolution is solved.

The invention discloses a very high frequency broadband radiation source positioning method based on energy weighted subspace fitting, and relates to the technical field of signal processing and radiation source imaging, and the method comprises the steps: carrying out the DFT processing of a lightning very high frequency broadband signal collected by an array, and obtaining any narrowband component; then characteristic decomposition is carried out on covariance matrixes of X-axis and Y-axis sub-arrays according to array receiving signals, main characteristic vectors are taken as signal sub-spaces, in order to emphasize the signal sub-spaces with higher energy, characteristic values are used for weighting, weighted signal sub-spaces are constructed, then the signal sub-spaces are fitted by using a least square method, and the signal sub-spaces with higher energy are obtained; the method comprises the following steps: further constructing a sub-band energy weighted spatial spectrum adapted to a very high frequency broadband signal, then carrying out spectrum peak search on the weighted spatial spectrum to obtain a spatial angle of a spectrum peak, and finally calculating the direction of arrival of a radiation source according to a spatial angle relation to obtain an azimuth angle and an elevation angle. According to the invention, aiming at a lightning very-high-frequency weak radiation source positioning problem, a lightning channel can be inverted more clearly.

The invention relates to the technical field of multi-channel imaging, and discloses a composite light source for dual-channel imaging, an imaging system, an imaging method and a control terminal. The first lamp bead group is arranged on the light source lamp panel, and the center of the light emitting area is arranged on the central axis of the light source lamp panel; the second lamp bead group is arranged on the light source lamp panel, the center of the light-emitting area is arranged on the light-emitting boundary of the first lamp bead group, and the light-emitting surface width of the second lamp bead group is larger than that of the first lamp bead group; the first lamp bead group and the second lamp bead group are respectively connected to an external time sequence trigger signal through a lead, and on and off of the first lamp bead group and the second lamp bead group are controlled based on the time sequence trigger signal. According to the invention, the realization difficulty of a dual-channel imaging light field in a narrow space can be reduced, and the precision and real-time performance of multi-channel image registration can be improved.

The small-size lens defect classification detection system comprises a light source imaging system, a defect simulation data set and a defect detection and identification system, the light source imaging system comprises a first light source located under the lens, a second light source surrounding the horizontal periphery of the lens, a third light source projecting from the side of the lens at a low angle and having an irradiation angle lower than that of the second light source, and an image acquisition device for acquiring front or cylindrical surface images of the lens; generating lens defect images in batches by the defect simulation data set; the defect detection and identification system takes a lens defect image and a real image collected by the light source imaging system as training data, and after model training, defect identification and classification are carried out on the lens image collected by the light source imaging system in real time. The defect imaging contrast ratio is effectively improved through multi-light-source combined illumination, the problem that defect samples are scarce is solved in combination with simulation data, and efficient, accurate and automatic detection of multiple defects of a small-size lens is achieved.

The application discloses a mobile fire detection system and method, and belongs to the technical field of fire detection. The system realizes over-distance accurate positioning and sub-pixel level precision. Through a unique "polynomial fitting + extreme value calculation" algorithm, the system can perform three times curve fitting on the signals of 2-3 detection units covered by the fire source imaging, and can analyze the sub-pixel level center coordinates by derivation. In combination with a preset coordinate mapping table, the fire source positioning precision can be improved to within 0.3 meters at a distance of 150 meters, and the specific tunnel post number and lane position can be accurately output, so that the limitation of the traditional detector that can only give an area alarm is completely changed. In terms of adaptability to complex environments, the application not only solves three major pain points of the traditional flame detector, i.e., positioning loss, weak anti-vibration and high false alarm rate, but also provides a complete set of high-reliability, intelligent and practical fire monitoring and emergency command tools for tunnel safety.

This invention discloses a high-precision density reversal method and system for gravity anomalies based on regular, stable, and high-speed solution. [Solution] Based on the above-mentioned field source regularization solution, we propose using data with false anomalies at the field source imaging depth as boundary value conditions. Again, by solving the upper space of the first class boundary value problem of Laplace's equation, we calculate gravity anomalies on the ground and perform least-squares optimization iterative solution with the actual ground anomalies to obtain high-precision anomaly imaging data at the field source depth that does not contain false anomalies due to the Gibbs effect. This depth is used as the top interface of the field source, and the top interface is divided into grid prisms to construct the field source morphology. Density inversion is performed on each prism top surface in the frequency domain to obtain the density distribution of the field source morphology. Since this algorithm is implemented in the frequency domain and the inversion is performed at a known field source depth, the present invention is a gravity density inversion method with high speed, high precision, and high resolution characteristics, and provides a new concept for realizing the solution of gravity field source density parameters.

The embodiment of the application provides a flip chip offset measurement system and a measurement method, the measurement system comprises a first light source and a second light source with different wavelengths of outgoing light beams, an imaging assembly and a processing assembly, the first light source is controlled to emit a first light beam to penetrate the flip chip and irradiate a first target in a deep layer, and a first image containing the first target is acquired from a first detector; the second light source is controlled to emit a second light beam to irradiate a second target on the surface of the flip chip, and a second image containing the second target is acquired from a second detector, finally, the processing assembly acquires a first offset and a second offset of the flip chip relative to the substrate based on the first image and the second image, and obtains a bonding offset of the flip chip according to the first offset and the second offset. The application adopts a dual-wavelength light source to irradiate the flip chip in time sharing and wave band sharing, breaks through the penetration-reflectivity contradiction of single-wavelength detection, and improves the accuracy and reliability of the bonding offset detection.

The invention discloses a polymer foam product defect detection method and system based on machine vision, and belongs to the technical field of image processing and analys.The method comprises the steps that optical parameters and surface images of a product are obtained; calculating and generating a structured light source instruction and controlling the light source array to image to obtain a multi-modal image; decoupling to generate surface reflection and internal transmission characteristic patterns; fusing the light source instruction and the feature map, and positioning a suspicious area; applying micro-vibration and collecting a high-speed image sequence; extracting dynamic response data, and aligning and splicing the dynamic response data with the decoupling feature map to generate a fusion defect feature vector; and analyzing and outputting defect types, positions and three-dimensional size parameters. By adopting the technical scheme of self-adaptive structured light source imaging and optical mechanics multi-modal feature fusion, accurate identification and three-dimensional quantitative analysis of surface and internal defects of the polymer foam product can be realized.

This invention discloses an adaptive threshold-based depth-unfolding brain-source imaging method and system, relating to the field of brain-source imaging technology. The method includes: acquiring a training EEG signal observation matrix and a real source signal matrix; inputting the training EEG signal observation matrix into an initial iterative shrinking threshold depth-unfolding network, outputting a training reconstructed source signal matrix; determining a loss function value based on the real source signal matrix and the training reconstructed source signal matrix, and determining a target iterative shrinking threshold depth-unfolding network by minimizing the loss function value; acquiring a measured EEG signal observation matrix, solving for the measured EEG signal observation matrix using the target iterative shrinking threshold depth-unfolding network, and outputting a target reconstructed source signal matrix. Unfolding the traditional ISTA algorithm into a trainable deep neural network helps improve the reliability of brain-source imaging.

The application discloses a real-time visual image matching positioning method for an optical communication module, relates to the field of optical visual positioning, and aims to solve the problem of accurate matching positioning of the module. The application constructs a unified transformation relationship from a multi-source imaging unit image coordinate system to a device mechanical coordinate system, fuses template matching and feature matching technologies, combines a structure model preset area region of interest, and drives adaptive distribution of an imaging mode and collection parameters, performs high-quality feature extraction and redundant supplementary collection based on multi-source images, improves a transparent window in a complex area, introduces a geometric model constraint and a residual error elimination mechanism in a fusion process, realizes high-confidence fusion of features of each area, and finally obtains an overall six-degree-of-freedom attitude through a rigid body registration and pose solving algorithm and outputs key structure coordinates, so that the recognition precision and engineering implementability of the optical communication module in positioning, assembly and detection and other links are improved.

This disclosure pertains to the field of exploration geophysics and presents a method and system for combined active and passive source reverse time migration imaging of metallic minerals. The method includes: performing time difference correction on active and passive source seismic data from the same subsurface structure; performing wavefield separation on the time-aligned active and passive source seismic data to reconstruct the P-wave and S-wave fields of the active source and the passive source; performing active and passive source wavefield extrapolation based on the two-way wave equation; obtaining active and passive source PS-converted wave imaging results using cross-correlation imaging conditions; and performing weighted superposition and fusion to obtain the combined active and passive source imaging results. This disclosure leverages the high resolution advantage of active sources combined with the deep detection capability of passive sources, replacing the limitations of single-source detection and achieving high-precision deep reverse time migration imaging.

The invention relates to the technical field of optical three-dimensional reconstruction, in particular to a three-dimensional fingerprint microstructure reconstruction method and system based on illumination self-calibration and sparse integration, and the method comprises the following steps: constructing a multi-light-source imaging system, and arranging a standard spherical reflector in an imaging field of view to perform illumination direction self-calibration; performing multi-angle illumination acquisition on the surface of the finger to obtain a finger image sequence under multi-frame illumination variation; a reconstruction area of the finger image sequence is limited; carrying out vectorization solution on the pixel brightness change of the reconstruction region under the multi-illumination condition, and obtaining a global continuous normal gradient field based on the surface normal vector and reflectivity of each pixel; the normal gradient field is converted into a depth constraint equation, sparse matrix optimization and least square integral solving are adopted, and global consistent reconstruction of the depth map is achieved. According to the method, high-fidelity three-dimensional reconstruction of the finger surface microstructure is realized through an integrated technical framework of physical calibration, photometric solution and sparse integration.

The invention discloses a sensor array error evaluation method for magnetocardiogram source imaging, which relates to the technical field of biomedical signal analysis, and comprises the following steps: performing tissue segmentation and three-dimensional reconstruction on a CT image to generate a CT model; carrying out registration on the 3D scanning model and the CT model; error types existing in the information of the magnetocardiogram sensor array are set; simulating and generating a magnetocardiogram signal containing error influence; and evaluating the influence of the error on the source imaging performance. The method can systematically and comprehensively quantify the influence of crosstalk, gain error, sensitive axis angle error and position error on the imaging performance of the magnetocardiogram source and three core dimensions of positioning precision to construct a unified multi-dimensional evaluation system, overcomes the defect of lack of comprehensive evaluation standards in the prior art, can also provide priority guidance for error calibration of an MCG system, and improves the accuracy of the MCG system. And the imaging accuracy, the clinical availability and the application value are obviously improved.

The invention relates to the technical field of image processing and multi-source imaging data fusion, in particular to a multi-modal image diffusion fusion method based on imaging physical feature constraint. According to the technical scheme, the method comprises the following steps: acquiring data of a plurality of original images of the same target object in different imaging modes, and preprocessing the data of the plurality of original images to obtain a spatially aligned multi-mode image; according to the method, in the reverse diffusion sampling process of multi-modal image diffusion fusion, pixel-level constraint weights based on imaging physical characteristics are introduced, and spatial self-adaptive fusion updating control is achieved; updating is restrained in a structure boundary area to keep a geometric contour clear and stable; the specific modal response salient region is enhanced and updated to fully integrate detail information, the problem that structural integrity and detail richness are difficult to consider in a data scarce scene in a traditional method is effectively solved on the premise that a diffusion model does not need to be trained again, and the quality of a fused image is remarkably improved.

To enhance the accuracy in black level correction.SOLUTION: An imaging element comprises: an imaging region that has a plurality of first pixels each including a first photoelectric conversion part and a first circuit part and arranged in a first direction and a second direction, a first control line to which signals for controlling the plurality of first pixels are outputted, and a first output line for outputting signals generated at the plurality of first pixels; and a plurality of light-shielding pixel regions each of which has a plurality of second pixels each including a shielded second photoelectric conversion part and a second circuit part and arranged in the first direction and the second direction, a second control line to which signals for controlling the second pixels are outputted, and a second output line for outputting signals generated at the plurality of second pixels. The light-shielding pixel regions are arranged outside a region incorporating all first pixels included in the imaging region. The imaging element has: an imaging pixel region in which different control conditions can be respectively set for the plurality of imaging regions; and an optical black pixel region in which the same control condition as a reference source imaging region can be respectively set for the plurality of light-shielding pixel regions.SELECTED DRAWING: Figure 6

The invention relates to the technical field of biological magnetic signal detection and imaging, and discloses a thoracic conductor modeling and signal attenuation compensation method and system for magnetocardiogram imaging. The method comprises five steps of multi-modal data synchronous acquisition and registration, personalized thoracic conductor model construction, personalized magnetic field attenuation transfer matrix construction, signal inverse compensation and general high-precision source imaging. According to the method, the high-precision personalized thoracic conductor model is constructed to carry out front-end pre-compensation on the original magnetocardiogram signal, and the quasi ideal signal diagram with corrected individual conduction attenuation is generated, so that any subsequent standard source imaging algorithm works on the basis of fair and real signals, and the precision and consistency of final imaging are improved from a data source.

The invention relates to a high dynamic range sound source imaging method based on a double attention mechanism, and the method comprises the steps: receiving a space sound field signal through a microphone array, and processing the space sound field signal into a frequency domain signal; performing cross-spectrum matrix characteristic filtering processing on the frequency domain signal to obtain a complex frequency domain signal vector; performing adaptive enhancement on a real part and an imaginary part of the complex frequency domain signal vector by using a double attention mechanism; fusing the enhanced real part with the enhanced imaginary part to obtain an enhanced signal vector; and performing beam forming calculation by using the enhanced signal vector to generate an acoustic image. According to the invention, the real part attention module and the imaginary part attention module are introduced in parallel at the front end of beam imaging, and the amplitude and phase characteristics of the acoustic signal are subjected to adaptive weighted enhancement, so that the spatial information in the array signal is fully mined, the dynamic range of acoustic imaging and the robustness in a noise environment are significantly improved, and the method is suitable for wide application. And a better solution is provided for precise fault diagnosis and acoustic monitoring.

This invention discloses a device for evaluating the therapeutic effect of sleep modulation based on cortical brain energy. It utilizes an EEG acquisition system to obtain EEG and electrooculography (EOG) data of sleep following both true and false stimulation. Independent component analysis (ICA) is used to preprocess the acquired data to filter out signal artifacts. Brain energy imaging is used to calculate the distribution of neural activity and extract the time series of sleep-related cortical brain energy. The YASA algorithm is used to segment sleep based on the time series of sleep-related cortical brain energy and the EOG data, and the difference in sleep efficiency after true and false stimulation is calculated. A correlation model between stimulation parameters and the difference in sleep efficiency is established. The device includes a data acquisition module and a processing module. This invention provides a scientific basis for evaluating the therapeutic effect of sleep modulation and is of great significance for the optimal selection of stimulation parameters, which can improve the therapeutic effect of sleep modulation.

The present invention discloses a method and system for high-precision density inversion of gravity anomalies based on regular stable fast solution. [Solution] Based on the above source regularization solution, we propose using data containing spurious anomalies at the source imaging depth as boundary value conditions. Then, through the upper half-space solution of the first-class boundary value problem of Laplace's equation, we calculate the gravity anomaly on the ground, and perform a least-squares optimization iteration with the actual ground anomaly to obtain high-precision anomaly imaging data at the source depth without spurious anomalies caused by the Gibbs effect. This depth is used as the top interface of the source, and the top interface is divided into grid prisms to construct a source configuration. Density inversion is performed on each prism top surface in the frequency domain to obtain the density distribution of the source configuration. Because this algorithm is implemented in the frequency domain and the inversion is performed at a known source depth, the present invention provides a gravity density inversion method with high speed, high precision, and high resolution, and provides a new concept for solving gravity source density parameters.

The invention discloses an automatic multi-modal image registration method and system. The method comprises the following steps: initializing and preprocessing a registration image; extracting feature points of the registered image, and calculating descriptors; matching descriptors of the registered image pairs; calculating an affine matrix; and performing affine matrix processing on the to-be-registered image to obtain a registered image. According to the method, the registration problem of an endogenous imaging technology, a light field imaging technology, a tissue slicing technology and the like which cannot be solved in the prior art can be solved at the same time, fine adjustment is not needed for different modes, zero sample learning can be achieved, and the method can be suitable for imaging conditions of different scales from mesoscopic imaging to microscopic imaging and the like.

A frequency encoded source imaging system includes an EEG or MEG sensor array and a processing system for analyzing the signals from the sensor array in at least two different frequency bands, where the analysis is localized with respect to a three-dimensional grid corresponding to the portion of the human body. Alternately, a frequency encoded source imaging system includes an EEG or MEG sensor array and a processing system for analyzing the signals from the sensor array in a high-definition frequency band comprising frequencies greater than 70 Hz, where the analysis is localized with respect to a three-dimensional grid corresponding to the portion of the human body.