60 results about "Image stack" patented technology

The invention discloses a total primary productivity estimation method and system based on multi-model coupling deep learning, and the method comprises the steps: obtaining the multi-source data of meteorological data, remote sensing images, latent heat flux, sensible heat flux and solar radiation, carrying out the quality control, missing value processing and nearest neighbor interpolation of different data sources, and carrying out the prediction of the total primary productivity. Unifying to a target spatial resolution and a time resolution; in a light energy utilization rate (LUE) model family, a solar radiation phase factor is introduced into a photosynthetically active radiation absorption ratio (FPAR) to obtain a phase modulation type FPAR, drought duration is introduced into a water stress function f (W) to obtain an exponential decay type f (W), and a GPP time sequence of a plurality of improved mechanism models is calculated according to the exponential decay type f (W); extracting spatial texture features from a remote sensing image stack by using a convolutional neural network (CNN), and performing cross-modal fusion on the spatial features and the GPP estimated by the plurality of improved mechanism models in a gating mode to form fusion representation; carrying out learning and collaborative optimization on the fusion representation of the GPP and CNN spatial features estimated by the plurality of improved mechanism models by adopting a gradient lifting tree model; and high-precision estimation of the GPP is realized through multi-model collaborative optimization. The method aims at solving the problem that a traditional light energy utilization rate model is insufficient in response under the extreme environment conditions of drought and intense radiation, the adaptability limitation of a traditional single model under the complex environment is broken through, and therefore high-precision GPP estimation under the complex environment is achieved.

The invention discloses an adjacent foundation pit deformation prediction method for a dense building group and a support deformation prediction method, and the method comprises the steps: obtaining SAR satellite images of a to-be-processed region in a period of time sequence, and generating an image stack after registration; screening points of which the amplitude deviation indexes are lower than a threshold value as PS points; calculating the relative displacement sequence of each PS point, inverting the displacement variation and accumulating to obtain the accumulated settlement; before construction, a digital surface model (DSM) is generated through aerial survey of an unmanned aerial vehicle, feature points with stable displacement are recognized by combining SAR images, and the feature points are anchored to an absolute coordinate system of the unmanned aerial vehicle for correction. Therefore, permanent scatterer (PS) identification and time sequence analysis are carried out by utilizing SAR images of a long time sequence, absolute geographic reference is provided by a high-precision digital surface model (DSM) generated by aerial survey of an unmanned aerial vehicle, and reference correction is carried out on a relative displacement field acquired by the InSAR.

The invention discloses a land type intelligent identification and updating method and system for land investigation, and relates to the technical field of land investigation and remote sensing land type identification, and the method comprises the steps: carrying out the unified coding and weight fusion of optical, radar, terrain and auxiliary features on a standardized land block image stack through a feature fusion and dimension reduction model; generating plot-level fusion feature representation; jointly inputting the land block level fusion feature representation and the pixel statistical features in the land block into a land class recognition model, outputting a land block level land class category and confidence through a double-layer fusion structure, and generating a multi-temporal land class recognition result; and calculating a change credibility score of the land parcel based on a multi-temporal land class identification result and a time sequence observation index, and determining whether the land parcel belongs to a stable state, a suspected change or a confirmed change by comparing an index trend, class stability and space consistency. According to the method, collaborative identification of macroscopic structure information and microcosmic detail information is realized, and the accuracy and the spatial integrity of regional land class classification are improved.

A method includes capturing images of a surface of a workpiece using an optical sensor. Each image respectively images a region of the surface. Each image is assigned a defined 6-DOF pose of the optical sensor relative to the workpiece and a defined focal plane position of the optical sensor. The captured images form an image stack. The method includes determining a sharpness value for each picture element of each image of the image stack to generate a sharpness map for each image. The sharpness maps of the images form a sharpness map stack. The method includes transforming the sharpness maps of the sharpness map stack into a defined reference system based on the respective assigned 6-DOF pose and focal plane position of the optical sensor in order to generate a sharpness cloud. The method includes generating a surface profile of the workpiece based on the sharpness cloud.

The application discloses a digital image coding method based on metabolomics mass spectrum data. The method groups the mass-to-charge ratios in a preset mass range in the obtained first liquid chromatography-tandem mass spectrometry data according to preset division conditions; generates a full metabolome profile image according to the first mass-to-charge ratios and the first scan indexes in each group after grouping, and cuts and stacks the image to obtain a first multi-channel image; and screens a first target block based on the pooling signal intensity and the image entropy corresponding to the first multi-channel image, and the second multi-channel image stacked by the first target block is used to train a deep learning model for classifying biological samples. Thus, the metabolomics mass spectrum data can be converted into an image thereof through the digital image coding mode, the image can accurately retain the mass spectrum structure of the mass spectrum data of the metabolite species and level in the analytical metabolomics, and the deep learning model trained thereby can comprehensively reflect the original state of the metabolomics in LC-MS.

The invention belongs to the technical field of computer vision and light field imaging, and discloses a large-area highlight detection and repair method and system. The method comprises the following steps: imaging by using a light field camera array to obtain a multi-view-angle light field image, and calculating an initial parallax; the method comprises the following steps: obtaining a multi-view highlight area mask through highlight detection, removing the highlight area mask to obtain a light field image without a highlight area, carrying out light field refocusing to obtain a non-highlight refocusing image stack, applying the highlight area mask obtained through central view angle detection to an initial parallax image, and constructing a reliable parallax set to realize parallax layering; according to parallax layer information of a non-highlight area pixel adjacent to a highlight pixel space in the highlight area, carrying out adaptation on a parallax layer of the highlight pixel; and constructing a hierarchical restoration strategy based on observation conditions of different viewpoints when no-highlight refocusing image of the highlight pixel in the corresponding parallax layer is superposed and averaged at the pixel position, thereby realizing restoration of the highlight area. According to the method, high-quality and large-area highlight repair can be realized.

The invention discloses a structured layer module combination system and method for video generation, and relates to the technical field of video shooting and generation, and the method comprises the steps: S1, obtaining N continuous layers to generate a layer image stack, where N is a natural number and is greater than 2, and each layer comprises image data and focal length data of image data imaging of the layer; s2, through image segmentation, target detection and semantic annotation, constructing a layer mark with a spatial level, a shielding logic and a semantic mark, and providing a structural constraint for subsequent generation; s3, processing at least one image layer to generate an animation image layer; and S4, according to the layer mark, synthesizing the animation layer with other layers to generate a video sequence frame. The method has the beneficial effects that each layer has spatial depth, semantic label and shielding logic, and is suitable for structural modeling and expression of a complex scene; the animation can be visually smooth and semantically coherent on the basis of an inter-layer structure and action prediction model.

The application provides a method and device for soil microstructure dataset construction, and relates to the technical field of land resources and environment, and the method comprises the following steps: scanning a soil sample by using XCT to obtain a scanning image; generating a three-dimensional microstructure image of the soil based on the scanning data; extracting soil pore structure in the three-dimensional microstructure image of the soil, calculating soil pore related parameters based on the soil pore structure, and performing network analysis on the soil pore structure to generate network analysis related parameters of the soil pore structure; determining soil permeability according to the soil pore structure; generating a two-dimensional image stack based on the three-dimensional microstructure of the soil, and calculating soil morphological parameters and soil organic matter content based on the two-dimensional image stack. The three-dimensional microstructure of the soil is obtained by scanning through XCT, the soil microstructure dataset is generated based on the three-dimensional microstructure of the soil, and compared with the traditional soil structure research method, the application has the characteristics of nondestructive testing and high resolution.

A method for training an image processing system with a machine learning model to perform a virtual multi-angle reconstruction of image stacks recorded with a light-sheet microscope. The method includes: recording at least one light-sheet fine stack comprising multiple image stacks at different illumination angles; determining target outputs from the fine stack, the model, and a classical multi-angle reconstruction; determining learning inputs from a light-sheet coarse stack comprising one or more image stacks at different illumination angles using the model and the classical reconstruction; creating an annotated dataset of the target outputs and learning inputs; and optimizing the model for the virtual multi-angle reconstruction based on the dataset. The light-sheet coarse stack has fewer images than the fine stack, and a virtual reconstruction produced by the trained model exhibits fewer image artifacts than a reconstructed image stack computed from the same coarse stack by the classical multi-angle reconstruction.

The invention discloses a three-dimensional reconstruction method for a microbial rock structure. The method comprises the following steps: setting at least three non-collinear physical datum points in a shooting plane of a microbial rock mass sample; sequentially slicing the microbial rock mass sample, and measuring the actual thickness of each slice; performing high-resolution imaging on the new section after each time of slicing to obtain a sequence image comprising all physical reference points; arranging the sequence images to form an image stack and performing alignment operation; a registered image stack is obtained; establishing a three-dimensional space coordinate system; performing image segmentation on the registered image stack, identifying different rock structures, and converting the segmented image into a label image stack; and performing three-dimensional visual rendering based on the label image stack to generate a three-dimensional model of the microbial rock structure. According to the method, a complete and high-precision three-dimensional digital model of the microbial rock structure is constructed, and visualization, separation and quantitative analysis of different internal structures such as clots and lamina are realized.

The invention relates to a method for obtaining an image stack from a plurality of input images (IE), each input image depending on a respective original image (IB) representing the same scene (3) and each original image being acquired by a sensor (14) of a camera module (4) through an optical system (12) for a respective focus distance, the method being implemented by a computer, and for each input image, the method comprises the steps of: determining (26) at least one optical transfer function between the scene and the sensor for a focus distance corresponding to the respective original image; and calculating (28), for each determined optical transfer function, a corrected image (IC) by deconvolution of the input image using the optical transfer function to obtain a set of corrected images, the obtained image stack depending on the set of corrected images.

An advance in high-resolution optical metrology has been achieved by the introduction of incoherent holographic imaging. FINCH, an example of incoherent holography, is shown to simplify the process, eliminating many steps in metrology and at the same time increasing throughput, resolution and accuracy of the method. A proposed technique requires only a single image capture with a non-moving camera rather than the capture of multiple stacks of images requiring many camera exposures and movement of the camera or sample in the conventional techniques.

The present disclosure provides methods and systems for processing images of three-dimensional biological samples. In particular, the methods apply image processing algorithms to enable segmentation of label-free images of organoids in plates with microwells by segmenting only the samples and ignoring features of the microwells, such as the microwell walls. These methods further including projecting depth-spanning stacks of limited depth-of-field images of the samples into a single image of the sample that can provide in-focus image information about three-dimensional contents of the image. These methods further include applying filters to the stacks of images in order to identify pixels within each image that have been captured in focus. These in-focus pixels are then combined to provide the single image of the sample. Filtering of such image stacks can also allow for the determination of depth maps or other geometric information about contents of the sample. Such depth information can also be used to inform segmentation of images of the sample, e.g., by further dividing identified regions that correspond to the contents of the sample at multiple different depths.

A system and method for constructing a digital composite image of a three-dimensional biological sample. The system includes an optical system that captures images of cells and tissue presented on a specimen slide. The system systematically acquires a stack of images at different segments across the specimen slide. For each segment, the system dynamically calculates an optimal focal plane. Once an optimal focal plane is determined for each of the stacks of images, the system generates a composite image by copying the sharpest objects from each of the optimal focal planes.

A system and method for compressing temporal stacks of synthetic aperture radar (SAR) images while preserving interferometric properties. The system receives multiple SAR images acquired over time, aligns them through coregistration, and maintains phase continuity across the temporal sequence. A three-dimensional discrete cosine transform processes both spatial and temporal dimensions, creating hybrid subbands organized by frequency content and temporal change characteristics. The system employs a change-aware encoder that selectively uses differential encoding for small changes between frames and full encoding at adaptive keyframe intervals. A temporal coherence network with separate pathways for amplitude and phase information ensures consistency across the image stack. The compressed output preserves interferometric coherence properties essential for applications such as ground deformation monitoring and change detection. The system achieves compression ratios from 10:1 to 50:1 for static content while maintaining higher quality for rapidly changing features.

The invention relates to a method (100) for presenting a scene on a display medium (416) according to an image stack (PILS) of said scene, comprising at least one iteration of a display phase (110), the method comprising the following steps:-detecting (112) a target position of the scene; -identifying (114), in the image stack (PILS), an image that clearly displays said target position, the step of identifying comprising the following steps for at least one other image in the stack (PILS), referred to as a candidate image: # calculating (118), by means of a predetermined coordinate transformation function, a target position in said candidate image; and # displaying (126) the image on the display medium when the target location in the candidate image is within the clear area of the candidate image. The invention also relates to a computer program and a device implementing the method.

This invention discloses an image processing method and related components for decoupling the cross-modal migration point spread function. The method includes: selecting calibration samples and recording a first modal image stack and a second modal image stack; preprocessing the first modal image stack to obtain an emission field estimation result; spatially registering the emission field estimation result with the second modal image stack; using the registered emission field estimation result and the second modal image stack as physical constraints to establish an inverse problem model; optimizing and solving the inverse problem model to obtain the migration point spread function characterizing the mapping relationship from the first imaging modality to the second imaging modality; acquiring the first modal image stack of the tested sample, and performing inversion reconstruction based on the migration point spread function to obtain an equivalent image of the second imaging modality. This invention is based on a common emission field formation mechanism and achieves computational migration reconstruction from a low-performance imaging modality to a high-performance imaging modality by constructing sample priors and decoupling the migration point spread function.

Example methods, apparatus, systems, and articles of manufacture (e.g., physical storage media) to implement multi-plane image (MPI) compression are disclosed. An example apparatus disclosed herein includes an interface to access an input multi-plane image stack corresponding to a source camera viewpoint, the input multi-plane image stack including a plurality of texture images and a corresponding plurality of alpha images, each of the alpha images includes a pixel value representative of a transparency of a respective pixel in each of the texture images. The disclosed example apparatus also includes a compressed image encoder to at least one of (i) convert the plurality of texture images to a single composite texture image to generate a compressed multi-plane image stack, or (ii) convert the plurality of alpha images to a single composite alpha image to generate a compressed multi-plane image stack. In some disclosed examples, an interface outputs a compressed multi-plane image stack.

This invention discloses a method for detecting the glycerol content of black soldier fly oil using thin-layer chromatography coupled with image analysis. This method addresses the significant polarity differences among triglycerides, diglycerides, and monoglycerides by employing a differentiated developing solvent system for effective separation. The content of monoglycerides / diglycerides / triglycerides is determined separately using a thin-layer chromatography silica gel plate combined with image analysis technology. This invention utilizes a self-developed bottom-emitting light box for standardized imaging, and combines image stacking noise reduction and self-developed analysis software to achieve digital quantification of spots. The operation is simple and efficient, requiring only consumables and imaging equipment readily available in a standard laboratory, making it suitable for convenient detection and analysis of glycerol content in situations lacking advanced instrumentation.

The invention discloses an InSAR (Interferometric Synthetic Aperture Radar) atmospheric delay correction method based on meteorological product and synchronous image stacking, and belongs to the technical field of surface deformation monitoring. The method comprises the following steps: firstly, acquiring a multi-temporal SAR image sequence, constructing an interference pair based on a small baseline set SBAS technology, and performing phase unwrapping; then calculating a vertical layered delay correction value of the SAR image by using a meteorological product, and weakening a systematic seasonal delay signal related to terrain height; further adopting a synchronous image stacking method to carry out iterative optimization correction on the turbulence mixing delay and the residual layering delay; and finally, inverting a line-of-sight cumulative deformation quantity based on the corrected interferogram sequence, and generating an earth surface deformation time sequence and a deformation rate. The method is based on two correction strategies of meteorological products and image stacking, the precision of atmospheric delay estimation and the stability of InSAR time sequence deformation monitoring can be improved, and the method is suitable for earth surface deformation monitoring in complex terrains and non-linear deformation scenes.

Techniques for medical image stack retrieval from a server and display by a client are presented. The techniques can include: designating an aperture for viewing the medical image stack; retrieving, from the server, high resolution image data for inside a respective aperture region of each of a plurality of images of the medical image stack; retrieving, from the server, context image data for outside the respective aperture region for each of the plurality of images of the medical image stack; and displaying a plurality of display images derived from the plurality of images of the medical image stack, each of the display images comprising a high resolution image portion inside the respective aperture region and a context image portion outside the respective aperture region, where the high resolution image portion corresponds to the high resolution image data and the context image portion corresponds to the context image data.

The invention relates to a method for representing an imaged scene, called the method, comprising the steps of: - defining an area, called the the target area, of the imaged scene on the basis of a current image of the scene, - determining, from among a stack of images of the scene, an image of the scene, called the reference image, in which the target area has the highest sharpness, the stack of images comprising at least two images of the scene having a distinct focal distance, - selecting, from among the images of the stack of images, areas of the imaged scene that are located outside the target area and that have a blur strength greater than a blur strength of the target area, which areas are called blurred areas, - reconstructing a composite image of the imaged scene by concatenating the target area of the reference image and the selected blurred areas.

Example methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement multi-plane image (MPI) compression are disclosed. Example apparatus disclosed herein include an interface to access an input multiplane image stack corresponding to a source camera viewpoint, the input multiplane image stack including a plurality of texture images and a corresponding plurality of alpha images, ones of the alpha images including pixel values representative of transparency of corresponding pixels in respective ones of the texture images. Disclosed example apparatus also include a compressed image encoder to at least one of (i) convert the plurality of texture images to a single composite texture image to generate a compressed multiplane image stack, or (ii) convert the plurality of alpha images to a single composite alpha image to generate the compressed multiplane image stack. In some disclosed examples, the interface is to output the compressed multiplane image stack.

The present disclosure provides methods and systems for processing images of three-dimensional biological samples. In particular, the methods apply image processing algorithms to enable segmentation of label-free images of organoids in plates with microwells by segmenting only the samples and ignoring features of the microwells, such as the microwell walls. These methods further including projecting depth-spanning stacks of limited depth-of-field images of the samples into a single image of the sample that can provide in-focus image information about three-dimensional contents of the image. These methods further include applying filters to the stacks of images in order to identify pixels within each image that have been captured in focus. These in-focus pixels are then combined to provide the single image of the sample. Filtering of such image stacks can also allow for the determination of depth maps or other geometric information about contents of the sample. Such depth information can also be used to inform segmentation of images of the sample, e.g., by further dividing identified regions that correspond to the contents of the sample at multiple different depths.

The invention relates to an inspection device (1) for optically inspecting a component (2), comprising a camera device (3) for recording an image in a recording region (9) of the camera device (3); preferably an actuator mechanism (7) for moving the recording region (9) on the component (2); an adaptive mirror group (5) having an object surface (11) for moving the camera mechanism (3) in a recording direction; the invention relates to an inspection device (1) for a component (2), comprising a control device (10), said control device (10) being designed to actuate the inspection device (1) in such a way that an image stack having images with different object surfaces (11) is captured in a capture region (9) on the component (2); a combining device (12), wherein the combining device (12) is designed to form a combined image from the image stack of the recording region (9) on the basis of clearly imaged image regions of different images of the image stack; an evaluation device (14) is provided, said evaluation device (14) being designed to process the composite image in order to inspect the component (2).

The invention relates to the technical field of image detection, in particular to a glass surface flatness intelligent evaluation method based on deep learning, which comprises the following steps: acquiring four-dimensional light field data of a glass surface through a micro-lens array light field camera; performing digital refocusing processing on the four-dimensional light field data to generate a multi-focal plane image stack; and inputting the multi-focal plane image stack into a refraction compensation parallax network, performing ray tracing compensation by combining glass refractive index priori knowledge, generating a refraction correction depth map, and outputting a flatness evaluation result based on the refraction correction depth map. According to the method, a refractive index prior and differentiable ray tracing module is introduced in a depth estimation link, the problems of geometric misjudgment and depth distortion generally existing in transparent body detection in a traditional method are solved, and the physical credibility and calculation precision of a detection result are improved.

This invention discloses a super-resolution microscopic imaging method based on multi-channel modulation and demodulation. First, this invention utilizes the synergistic effect of a spatial light modulator and an electro-optic deflector to generate multiple hollow illumination spot arrays. Second, during the scanning of the target sample, fluorescence signals are acquired for the illumination area of ​​each hollow illumination spot, corresponding one-to-one with the multi-channel hollow illumination spot array according to the sampling time sequence. Then, pixel-level signal redistribution processing is performed on the acquired multi-channel images. The redistributed image stack is divided into at least three regions, and corresponding weighting coefficients are applied to the signals of different regions for linear or nonlinear combination. Finally, an inverse Fourier transform is performed on the weighted combined image to obtain the super-resolution image. This invention can extend the support domain of the optical transfer function, achieving a resolution superior to traditional confocal and single-point hollow excitation and detection methods.

A system and method for generating sample data for analysis provide an image capture unit configured to capture a stack of images in image layers through a thickness of a sample, each image layer comprising pixel data in two orthogonal planes across the sample at a given sample depth; a processing unit configured: a) to process the captured pixel data to determine therefrom a pixel value of the energy of each pixel of the image, b) to select from each group of pixels through the stack of images the pixel having a highest energy; and c) to generate an output image file comprising a set of pixel data obtained from the selected pixels, wherein the output image file comprises for each pixel, the pixel position in the two orthogonal planes, the pixel vale and the depth position of the pixel in the image stack. The depth position of the selected pixel is provided in a fourth channel of the output image file, which represents a topography of a sample. An analysis unit comprises an input for receiving the output image file and to determine therefrom sample data, including identification of constituents in the sample and / or quantity of said constituents in the sample; and preferably comprises an artificial intelligence.

The application discloses a light sheet microscope single-frame autofocusing method based on structured light illumination and deep learning, which comprises the following steps: shaping a light beam to form a composite multiple-depth and laterally staggered structured light illumination sample and keeping the sample fixed; moving a detection objective lens to shoot multiple image stacks and input the image stacks into a depth Fourier neural network for training; using the same depth composite structured light illumination sample to shoot a sample image and inputting the sample image into the trained network for out-of-focus prediction; and finally completing out-of-focus compensation according to the output result of the network. The application realizes the out-of-focus prediction of the light sheet microscope by using a single-frame image, solves the problem that multiple images need to be scanned in the traditional autofocusing scheme, and improves the long-time high-quality imaging capability of the system; the depth Fourier neural network is fast and high in precision in out-of-focus judgment, is beneficial to improving the imaging speed of the light sheet microscope, has a small number of required training sets and good network generalization, and is helpful to improving the availability of the network.