59 results about "Spatial reconstruction" patented technology

A spatial-type de-interlacing process to be applied to a digital image for obtaining a spatial reconstruction. Furthermore, to the digital image there are also applied one or more temporal-type motion compensation de-interlacing processes for obtaining one or more temporal reconstructions, and the spatial reconstruction and the one or more temporal reconstructions are sent to a decision module. The decision module applies a cost function to the spatial reconstruction and the temporal reconstructions and chooses from among the spatial reconstruction and the temporal reconstructions the one that minimizes the cost function. Preferential application is to display systems, in particular displays of a cathode-ray type, liquid-crystal type, and plasma type which use a mechanism of progressive scan.

The spatial resolution of captured plenoptic images is enhanced. In one aspect, the plenoptic imaging process is modeled by a pupil image function (PIF), and a PIF inversion process is applied to the captured plenoptic image to produce a better resolution estimate of the object.

The invention provides a method for predicating a coincident index between a distributed wind power generation output and a heating load, wherein the method relates to the field of wind power generation technology. According to the method, after phase spatial reconstruction is performed on a nonlinear time sequence of a system parameter of a wind-generated power heating system, distributed wind power generation output and heating load synchronous index mathematical modeling are performed through using the nonlinear time sequence as a sample set. A fuzzy neural network is utilized for solving the mathematical model. Predication is performed on system synchronism at a next time period for aiming at data after phase spatial reconstruction, and a predicated value of the coincident index between the distributed wind power generation output and the heating load. The method provided by the invention performs functions of performing real-time monitoring on a heat-and-power cogeneration system, measuring a system operation parameter and a geographical environment parameter of the system, predicating the coincident index between the distributed wind power generation output and the heating load, controlling the heat-and-power cogeneration system according to a calculation result, effectively using wind energy, and remarkably improving reliability and economical performance in operation of the heat-and-power cogeneration system.

To carry out de-interlacing of digital images there is provided a spatial-type de-interlacing process to be applied to a digital image for obtaining a spatial reconstruction. Furthermore, to the digital image there are also applied one or more temporal-type de-interlacing processes for obtaining one or more temporal reconstructions, and the spatial reconstruction and the one or more temporal reconstructions are sent to a decision module. The decision module applies a cost function to the spatial reconstruction and the temporal reconstructions and chooses from among the spatial reconstruction and the temporal reconstructions the one that minimizes the cost function. Preferential application is to display systems, in particular displays of a cathode-ray type, liquid-crystal type, and plasma type which use a mechanism of progressive scan.

A semantic textual information recognition system is provided. The system includes a memory configured to store instructions and results. The system includes a processor operatively coupled with the memory configured to receive a plurality of text elements along with respective text element coordinates, wherein the processor includes a spatial reconstruction module configured to identify the plurality of text elements on an information axis based on the text element coordinates. The processor also includes a semantic clustering module configured to determine a plurality of semantic clusters of the plurality of text elements using the plurality of text elements on the same information axis and a semantic data model. The processor further includes a rank clustering module configured to generate a plurality of rank clusters by ranking the plurality of semantic clusters. The processor further includes a machine learning module configured to update the semantic data model based on the feature set.

A plurality of image projections are acquired at faster than cardiac rate. A spatiotemporal reconstruction of cardiac frequency angiographic phenomena in three spatial dimensions is generated from two dimensional image projections using physiological coherence at cardiac frequency. Complex valued methods may be used to operate on the plurality of image projections to reconstruct a higher dimensional spatiotemporal object. From a plurality of two spatial dimensional angiographic projections, a 3D spatial reconstruction of moving pulse waves and other cardiac frequency angiographic phenomena is obtained. Reconstruction techniques for angiographic data obtained from biplane angiography devices are also provided herein.

The invention discloses an X-space magnetic particle imaging deconvolution method. The method comprises the following steps: collecting an X-space original image; a neural network structure is set, convolution and deconvolution layers are set, and a jump connection layer is arranged between the corresponding convolution layer and deconvolution layer; neural network training: network input is a simulated original image, a corresponding original clear image is used as a label to train a neural network, and a mean square error is adopted as a loss function; neural network detection: selecting three indexes of a root-mean-square error, a peak signal-to-noise ratio and a structural similarity index measure to carry out quantitative evaluation on image quality, and modifying network training parameters according to an evaluation result, so that a reconstructed image is closer to an original image; and X-space deconvolution: inputting a to-be-deconvolved original image into the trained and detected neural network model for prediction to obtain a deconvolution result. According to the method, the influence of system noise on the reconstruction process is greatly reduced, and the resolution of the magnetic particle imaging system for X-space reconstruction is improved.

A non-invasive scattering imaging method beyond a memory effect range based on connected component optimization, including: calculating an autocorrelation image of collected speckle information, and obtaining an autocorrelation graph according to the autocorrelation image; obtaining a reconstruction result according to the autocorrelation graph, and optimizing the reconstruction result; calculating and normalizing autocorrelation of the optimized reconstruction result, to calculate initial autocorrelation of an object; obtaining a reconstruction result according to the autocorrelation of the object obtained in the previous step, calculating autocorrelation of an optimized reconstruction result by using a connected component and performing normalization, and using the autocorrelation graph to calculate autocorrelation of another object; and repeating the preceding steps of calculating autocorrelation of the two objects until a predetermined loop count is reached, and then using a phase recovery algorithm and the calculated autocorrelation of the two objects to perform spatial reconstruction to achieve non-invasive imaging.

The invention relates to an incremental unmanned aerial vehicle aerial photography overlapping degree detection method and system. The overlapping degree detection method comprises the following steps: acquiring exterior orientation elements of all images in a shooting area of an unmanned aerial vehicle; constructing an image connection graph according to the exterior orientation elements; extracting feature points of all the images; matching the image pair according to the feature points, and determining multi-view matching points; obtaining a camera internal reference matrix, and establishing an object space initial model according to the camera internal reference matrix; iteratively optimizing the object space initial model by using an incremental motion recovery structure method SFM, and determining an object space reconstruction model; determining a projection image according to the multi-view matching point and the object space reconstruction model; and detecting an image courseoverlapping degree and a lateral overlapping degree according to the spatial overlapping relationship between the projection images of the projection images. By adopting the overlapping degree detection method or system provided by the invention, the overlapping degree detection efficiency and the accuracy of the detection result can be improved.

The invention discloses a hyperspectral image super-resolution realization method and system. The method comprises the following steps: amplifying an original hyperspectral image into a low-resolution hyperspectral image with the same size as expected output in an interpolation mode; inputting the low-resolution hyperspectral image into a spatial-spectral feature extraction network to generate a high-resolution hyperspectral image, the spatial-spectral feature extraction network comprising a spectral mapping network, a spatial reconstruction network and a spatial-spectral fusion network; inputting the low-resolution hyperspectral image into the spectral mapping network and the spatial reconstruction network, performing spectral feature extraction and spatial information feature extraction respectively in the two branch networks to reconstruct spectral information and spatial information; and using a spatial-spectral fusion network to fuse the spectral information and the spatial information output by the spectral mapping network and the spatial reconstruction network to generate a high-resolution hyperspectral image. Better performance is embodied in the aspects of spatial information recovery and spectral information storage.

The invention discloses an imaging method and device combining k space and image space reconstruction, and belongs to the field of magnetic resonance imaging. According to the method, firstly, a k space parallel imaging method is used for reconstructing an undersampling image frame with an automatic calibration signal, wherein the undersampling image frame is obtained in multi-frame imaging needed by magnetic resonance parameter measurement of a measured object; and then, for other under-sampling image frame data without an automatic calibration signal, carrying out reconstruction in an image space. According to the method, the accurate sensitivity graph required by the SENSE method is generated from the undersampled data, and additional acquisition is not needed. According to the method, an image which is almost consistent with a traditional GRAPPA method is generated, and no obvious artifact exists; however, the speed of the method is four times or above that of the traditional GRAPPA method. The method serves as a self-calibration reconstruction method, does not need a full sampling frame, and is particularly suitable for accelerating three-dimensional (3D) multi-frame magnetic resonance imaging.

The invention discloses a wave entropy of spontaneous dynamic activity based autism classification method. The specific implementation steps of the method are as follows: (1) cutting near infrared spectroscopy fNIRS time sequences according to sequence lengths, setting different sliding windows and step lengths, performing spatial reconstruction on each subsequence according to the sliding windowsand the step lengths, and obtaining reconstruction components; (2) performing sample entropy calculating on the reconstruction components obtained by the step (1) so as to obtain a wave entropy sequence; (3) extracting four characteristic values (including the variance, mean, maximum and minimum of the wave entropy sequence) of the wave entropy sequence to generate a new sample as the input variable of a support vector machine (SVM); and (4) inputting the new sample obtained by the step (3) into the SVM to judge ASD. The method realizes high classification on ASD diagnosis; and the method indicates that the wave entropy is a very sensitive index to distinguish the ASD and TD, which might be an fNIRS based biomarker for predicting the ASD in the future.

A method for generating an image data set of an image area located in a measurement volume of a magnetic resonance system comprising a gradient system and an RF transmission/reception system, comprises the following method steps: —reading out k-space corresponding to the imaging area, by: (a) activating a frequency encoding gradient in a predetermined spatial direction and with a predetermined strength G₀ by means of said gradient system, (b) after the activated frequency encoding gradient achieves its strength G₀, radiating a non-slice-selective RF excitation pulse by means of said RF transmission/reception system, (c) after a transmit-receive switch time Δt_TR following the radiated excitation pulse, acquiring FID signals with said RF transmission/reception system and storing said FID signals as raw data points in k-space along a radial k-space trajectory that is predetermined by the direction and strength G₀ of the frequency encoding gradient, (d) repeating (a) through (c) with respectively different frequency encoding gradient directions in each repetition until k-space corresponding to the image area is read out in an outer region of k-space along radial k-space trajectories, said radial k-space trajectories each having a radially innermost limit k_gap which depends on said switch time Δt_TR, (e) reading out a remainder of k-space that corresponds to the imaging area, said remainder being an inner region of k-space not being filled by said first region and including at least a center of k-space, in a read out procedure that is different from (a) through (d), and storing all data points read out in (d) and (e); and —reconstructing image data from the read out data points ink-space by implementing a reconstruction algorithm; In order to constrain image fidelity and optimize scan duration under given circumstances, the inner k-space region is subdivided into a core region and at least one radially adjacent shell region.

The invention relates to a method for realizing scene change video analysis and detection based on a high-speed dome camera. The method comprises the following steps: performing multi-angle high-precision detection and identification on a basic target, and performing unsupervised clustering learning according to the detected target and a driving track to complete space reconstruction of a traffic monitoring scene; analyzing the driving track model, determining a lane direction, and completing reconstruction of a traffic incident detection rule; detecting targets appearing in the traffic scene, establishing traffic flow data containing multiple target movement tracks, and judging traffic events through analysis of the traffic flow data. The invention also relates to a corresponding system and device, a processor and a computer readable storage medium. By adopting the method, the system, the device, the processor and the computer readable storage medium, difficult demands and technical problems existing in current traffic management are effectively solved, the current situation of traffic management is improved, technical bottlenecks confronted in the industry are effectively broken through, and updating and rapid development of the intelligent traffic industry are greatly promoted.