181 results about "Multispectral data" patented technology

An automated method and / or system for identifying suspected lesions in a brain is provided. A processor (a) provides a magnetic resonance image (MRI) of a patient's head, including a plurality of slices of the patient's head, which MRI comprises a multispectral data set that can be displayed as an image of varying pixel intensities. The processor (b) identifies a brain area within each slice to provide a plurality of masked images of intracranial tissue. The processor (c) applies a segmentation technique to at least one of the masked images to classify the varying pixel intensities into separate groupings, which potentially correspond to different tissue types. The processor (d) refines the initial segmentation into the separate groupings of at least the first masked image obtained from step (c) using one or more knowledge rules that combine pixel intensities with spatial relationships of anatomical structures to locate one or more anatomical regions of the brain. The processor (e) identifies, if present, the one or more anatomical regions of the brain located in step (d) in other masked images obtained from step (c). The processor (f) further refines the resulting knowledge rule-refined images from steps (d) and (e) to locate suspected lesions in the brain.

A portable multispectral data acquisition system for use on a vehicle such as an aircraft comprises a plurality of gyroscope-stabilized remote sensing devices synchronized to simultaneously capture images of a common spatial area in both visible and invisible bands of the electromagnetic spectrum, a computer and digital recorder to record and correlate the captured images with temporospatial reference information, image processing software to stack or layer the images and to extract and compare the images in order to identify and filter hidden or subsurface anomalies that are invisible to the naked eye, and additional image processing software to orthorectify the images to a three-dimensional digital terrain map and to stitch adjacent images together into a mosaic. Methods for using the portable multispectral data acquisition system are also provided.

Analysis of multi-spectral data for extraction of chlorophyll content. Multi-spectral data is obtained from an imaging device. The multi-spectral data contains spectral response data for chlorophyll and background data. The background data is removed from the multi-spectral data to isolate the spectral response due only to chlorophyll. This is then presented as a chlorophyll absorption feature which may be analyzed by measuring the width of the feature, the surface area of the feature, or measuring various angular changes of the feature. These measurements may than be used for a variety of purposes including plant health analysis.

The invention discloses a barrier detection method in the vegetation environment based on multispectral and 3D feature fusion. The method comprises that 3D point cloud data is collected, and color and near-infrared images are collected at the same time; 3D point cloud data is registered with multispectral data to obtain multispectral 3D point cloud; a grid map is established, and candidate barrier grids are obtained via a height threshold; the scale of the near-infrared image is adjusted to normalize the infrared light intensity; the near-infrared intensity value and the visible light intensity of RGB color information within the grids are combined and serve as feature information, and 2D feature is obtained via calculation; and the candidates barrier grids are processed and filtered by utilizing a Gaussian mixture model to obtain a final barrier detection result. According to the method, influence caused by change of illumination condition is reduced by normalizing the infrared light intensity, and multispectral 3D features are sued to realize effective barrier detection.

The invention discloses a remote sensing image variation detection method based on region similarity. The detection method comprises the steps of: selecting tow-sence remote sensing images with different time phases in a monitored region, wherein the image data of the remote sensing images include multispectral data and panchromatic wave band data; carrying out the image preprocessing on the selected remote sensing images; combining all wave bands of the two remote sensing images in two periods after preprocessing into a one-scene image, dividing the one-scene image to establish the one-to-one mapping relationship of targets of the remote sensing images in two periods; establishing the feature set description of each target according to division results; calculating the region similarity between the targets according to the spectrum features of the targets, and carrying out algebraic calculus according to the textual features and NDVI features of the targets; building up a variable region detection criterion by setting a region similarity threshold value and combining the results of the algebraic calculus, and extracting the variable regions of the remote sensing images in two periods. The detection method can effectively eliminate the phenomenon of salt and pepper and improve the extract precision of the remote sensing image variable regions.

Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

The invention discloses a cross radiometric calibration method of a hyper-spectral sensor based on a multi-spectral sensor. The method is used for solving the cross radiometric calibration problem of the hyper-spectral sensor without a matched reference hyper-spectral image. The method comprises the following steps of: selecting cloudless hyper-spectral image data; selecting a multi-spectral reference image according to the hyper-spectral data; selecting a uniform ground object on the image as an interesting region; performing geometric precise correction of the two images; calculating entrance pupil radiances of various types of wave bands of the two sensors by using an atmospheric radiation transmission model; solving spectrum matching factors of various types of corresponding wave bands according to a certain rule; solving the entrance pupil radiances of the various types of wave bands of the hyper-spectral sensor by using the spectrum matching factors and the multi-spectral data; and linearly fitting pixel DN (Digital Number) values in the interesting region of the hyper-spectral image to be calibrated and the radiances of corresponding pixels of the multi-spectral reference image after being corrected through the spectrum matching factors to obtain calibration coefficients of the various types of wave bands of the hyper-spectral sensor. The method has the advantages of good stability, high reliability, high precision and the like.

The invention provides a method for obtaining a leaf area index based on quantitative fusion and inversion of multi-angle remote sensing data and multi-spectral remote sensing data, which is characterized in that a coefficient of a bidirectional reflectance distribution function (BRDF) of a vegetation type of the best matching pixel level of the multi-angle remote sensing data and a surface reflectivity is adopted, a surface soil reflectivity profile is obtained based on best matching of the multi-spectral data, and a canopy radiation transmission model is driven to obtain the leaf area index with high accuracy and large-scope coverage based on the multi-spectral data. The invention has the advantages that: the ranges of wave bands of the multi-angle data and the multi-spectral data need not to be overlapped, and approximate treatment can be carried out by adopting the similarity of the bidirectional function of the available wave bands; the coefficient of the bidirectional reflectance function and the best matching vegetation type obtained based on the multi-angle data is relatively stable along with changes in the time and the space, time sequence data can be made into a background library to be used as input for inversion of the multi-spectral data, and thus the large-scale leaf area index with high time resolution can be obtained; and the best matching surface soil reflectivity profile obtained based on the multi-spectral data is relatively stable, and historical time sequence data can also be made into a background library. The method can be applied in crop growth monitoring, rapid estimation of crop yields and the like.

A method for processing sensor data representative of a scene of interest. A plurality of sensor data outputs representative of the scene is selected from the group consisting of visible, VNIR, SWIR, MWIR, LWIR, far infrared, multi-spectral data, hyper-spectral data, SAR data, and 3-D LIDAR sensor data. The data is input to a plurality of graphics processing elements that are configured to independently execute separate image processing filter operations selected from the group consisting of spatial filtering, temporal filtering, spatio-temporal filtering, and template matching. A cross-correlation operation is performed on the filter outputs based on predetermined filter output characteristics which may then be used to annotate the scene with regions of interest (ROI) for display to a user.

The invention discloses a chlorophyll a concentration inversion method and system. The method comprises the following steps of: S1: acquiring multispectral remote sensing data of an environment satellite No.1; S2: judging whether the date of the acquisition of the multispectral data exists or not; if the date exists and is matched with a chlorophyll a concentration seasonal inversion model, selecting a chlorophyll a concentration seasonal inversion model according to the date to calculate chlorophyll a concentration; otherwise, selecting a waveband-optimization-based chlorophyll a model to calculate the chlorophyll a concentration. Through the utilization of the multispectral and hyperspectral data of the environment satellite No.1, the problem that an inversion model is limited by time and space can be solved, and the automatic operation and service operation of a computer can be realized.

The invention provides a forest aboveground biomass inversion method fused with spectrum and texture features and a forest aboveground biomass inversion system fused with the spectrum and texture features. The method comprises the following steps of calculating an aboveground biomass of a research region sample plot so as to obtain a sample plot biomass observation value; performing geometric correction and radiometric correction on high-resolution remote-sensing image panchromatic data and multispectral data; respectively performing statistical regression on the sample plot biomass observation value and a corresponding spectrum feature vegetation index, and selecting a spectrum feature inversion model; extracting various texture feature variables under different windows, respectively performing statistical regression on the sample plot biomass observation value and the corresponding texture feature variables, and selecting a texture feature inversion model; determining a weight through a sensitivity analysis of a spectrum key factor and a texture key factor, constructing a spectrum texture feature combination inversion model of the biomass, and realizing the forest aboveground biomass inversion. The method and the system provided by the invention have the advantages that the spectrum features and the texture features are fused, and the advantages of the spectrum features and the texture features for biomass inversion are fully exerted, so that the quantitative inversion precision of a forest aboveground biomass is effectively improved.

The invention relates to a multi-spectrum auto fluorescence fault imaging reconstruction method based on single view, which belongs to the optical molecular imaging field. The method is based on the diffusivity equation model, considers the uneven characteristics of small animal body, and simultaneously also considers the spectrum and the practical application characteristics of the auto fluorescence light source. In order to achieve the purpose, the multi-spectrum auto fluorescence fault imaging reconstruction method based on single view comprises the flowing steps: firstly, data acquisition; secondly, the dispersing processing of finite element; thirdly, the optimization of the selection of the feasible light source zone; fourthly, the reconstruction of the light source. The method overcomes the defects that the reconstruction light source of the auto fluorescence fault imaging reconstruction method is inaccurate, the reconstruction speed is low, the real-time processing is not convenient, and error can exist during the multi-spectrum data acquisition.

The invention provides a method for reconstructing a wide hyperspectral image based on fusion of mulspectral / hyperspectral images. The method for reconstructing the wide hyperspectral image based on fusion of the multispectral / hyperspectral images comprises the following steps that surface feature end members are synchronously extracted in an overlapping area of the multispectral / hyperspectral images; a fusion model among the multispectral / hyperspectral images is established according to the end members, a transformational relation is established, model parameters are resolved and calculated, and a model parameter base is established; selection of the model parameters is conducted through spectrum matching, and spectrum reconstruction is conducted on multispectral images pixels by pixels so that hyperspectral information can be obtained. According to the technical scheme, by means of data fusion, successive wide hyperspectral images which have high spectral resolutions can be obtained through reconstruction of other multispectral remote sensing data, the spectral resolutions of the hyperspectral images are identical to data of original hyperspectral images, the spatial resolution and the width are identical to the original multispectral data, the hyperspectral resolutions of the original hyperspectral images is kept, and the spatial resolution and the width of each of the hyperspectral images can be improved.

The invention relates to an object classification method based on a target characteristic graph. The object classification method comprises the steps of respectively acquiring object multispectral data and spatial structure data in a to-be-detected area by means of a laser radar, a visible light image camera and a near-infrared image camera; then extracting to-be-detected ROI areas; then performing characteristic extraction on each ROI object area, and combining the characteristics for obtaining a characteristic word; and finally determining the characteristic by means of a deep learning classifier based on CNN, thereby realizing quick and reliable classification of the object. The data which are acquired by the multiple sensors are complementary to each other, thereby effectively preventing a problem of insufficient detecting capability of a single sensor. Multilayer spatial characteristic extraction realizes more comprehensive description to characteristics of the object. Furthermore higher reliability of a classification result of the deep learning classifier based on the CNN is realized.

The invention discloses a lake water area information extraction method based on Landsat OLI multispectral image, and the method comprises the following steps: 1) preprocessing including calibration, geometric correction, atmospheric correction, clipping and embedding is performed on Landsat OLI multispectral data; 2) the preprocessed multispectral data is divided by adopting a multiscale image segmentation method; 3) two user-defined normalized difference water body indexes and MNDWI (Modified Normalized Difference Water Index) are constructed; 4) threshold values are separately set for three normalized difference water body indexes, and water area information is extracted; 5) series water area objects are exported, and water area vector data is generated; 6) the Landsat OLI multispectral image is cut by using the water area vector data, and the water area information data is obtained. According to the invention, the first and second waveband information of the Landsat OLI is comprehensively utilized, the water area information extraction speed and precision are improved, and essential data is provided for following scientific research.

The invention provides a multispectral calculation reconstruction method which comprises the steps of generating a two-way multispectral image and employing a photographing device toacquire the two-way multispectral image to obtainmultispectral information of sampling points; according to the multispectral information of the sampling points generating a corresponding multispectral information matrix of the sampling points and allowing the multispectral information matrix of the sampling points to be subjected to dictionary learning with sparse constraint to generate a spectral dictionary; and reconstructing the spectral information of non-sampling points in the two-way multispectral image under sparse prior constraint. The invention also provides a multispectral calculation reconstruction system which comprises an image acquisition device, a dictionary learning device and a spectral information reconstruction device. The method and the system provided by the invention employthe inherent law of the multispectral information, scene materials and the sparsity of light source spectrum, thus the reconstruction of the multispectral informationbeing simple and intuitive, the needed scene spectrum sampling points being less, and realizing high dimension multispectral data collection based on a compression perception theory.

The invention discloses an atmospheric correction method for multispectral data of a remote sensing satellite. The method comprises the following steps of: (1) reading data, and converting the data into apparent radiance data and apparent reflectivity data; (2) calculating decision factors, i.e. a ratio vegetation index, a soil adjustable vegetation index and a normalization water body index in adecision tree method according to the apparent reflectivity data; (3) acquiring apparent reflectivity data in a dark target area according to the apparent reflectivity data, and calculating air path reflectivity; (4) determining the aerosol optical depth of each multispectral waveband according to the relation among the air path reflectivity, a Rayleigh reflectivity ratio and the aerosol optical depth, and determining the total optical depth of a position of 550 nanometers according to the aerosol optical depth and the Rayleigh scatting optical depth of each multispectral waveband; and (5) acquiring an inversion parameter from a lookup table according to the total optical depth of the position of 550 nanometers, and solving land surface reflectivity through a radiative transfer equation to finish atmospheric correction.

The invention discloses a shallow sea water depth inversion method based on high-spectrum data of a blue-yellow wave band. Currently, models which perform depth inversion on clean water body through an optical remote sensing facility are mostly established for aiming at multiple-spectrum data. The algorithm is restricted by wide spectrum data wave band and little spectrum information. The inversion precision is largely affected by type of water body sediment. The invention provides a novel method for inversing shallow sea water depth of the clean water body through utilizing the high-spectrum data of the blue-yellow wave band (450-610 nanometers) according to a water body optical attenuation mechanism based on the high-spectrum data. The method can accurately extract shallow sea water depth distribution information within 30 meters. Furthermore one algorithm coefficient calibration is required for one remote sensor, thereby remarkably improving universality of the algorithm.

In order to solve the problem of low precision of crop remote sensing classification, the invention provides a crop remote sensing classification method based on multi-temporal SAR data and multi-spectral data, belonging to the field of agricultural technology. The invention comprises the following steps: S1, respectively acquiring multi-spectral data in the crop growing period and SAR data with obvious characteristics at different times in the crop growing period; S2, extracting the cultivated land range according to the multi-spectral data with prominent cultivated land information; 3, selecting that VV polarization data band combination of different time in the SAR data to obtain the multi-temporal SAR data, and combining the multi-temporal SAR data with the single-temporal multi-spectral data respectively; 4, creating a training sample; S5, the crops in the study area are classified by maximum likelihood method with the combination of multi-temporal SAR data and single-temporal multi-spectral data bands, multi-temporal SAR data and single-temporal multi-spectral data, which are masked by the extracted cultivated land range, combined with the spectral characteristic mean and covariance of the training samples.

The invention relates to a face recognition monitoring system and recognition method based on spectrum and multiband fusion. The system comprises a spectrum camera, a face spectrum image acquisition module, a face spectrum image data preprocessing module, a face spectrum image database and a face spectrum image recognition module. The spectrum camera comprises an optical lens and a silicon-based detector. The silicon-based detector comprises a photoelectric conversion substrate and a filtering film arranged on the photoelectric conversion substrate. The filtering film comprises N units; each unit comprises three areas, specifically a visible spectrum sensing area, a near infrared spectrum image sensing area and an RGGB image acquisition area; and the N units cover all pixel points on the photoelectric conversion substrate. According to the system, the purpose of obtaining reflection multispectral data, near-infrared band face images and RGGB face images of the face in the visible-near-infrared band can be achieved through one camera, the cost of the monitoring system is greatly reduced, and more accurate recognition of the face is achieved.

The invention relates to a method for reconstructing the spectral reflectance of a single-pixel detector based on sparse priors, which performs principal component analysis on the training sample set, and obtains the first three principal components of the spectral reflectance data of the training sample set as the reconstruction basis function Vector; through the single-pixel detector to collect the spectral energy of a single multi-spectral test color block, the energy value U is obtained; in the process of solving the training sample set, the basis function vector B, the basis function vector coefficient a and the specific coefficient of the measurement matrix are obtained The reflectance of the test sample is reconstructed by the obtained spectral energy U collection for a single multi-spectral test color patch. The present invention can make full use of the spatially sparse feature of spectral reflectance and the sparse prior knowledge of the relative spectral power distribution of the lighting source based on the principal component orthogonal basis, reduce the optical complexity of the multi-spectral data acquisition system, reduce the number of samples, and improve the spectrum of the reflectance Improve reconstruction efficiency and improve reconstruction accuracy.

A method of identifying endmember spectral values from multispectral image data, where each multispectral data value is equal to a sum of mixing proportions of each endmember spectrum. The method comprises the steps of processing the data to obtain a multidimensional simplex having a number of vertices equal to the number of endmembers. The position of each vertex represents a spectrum of one of the endmembers. Processing the data is conducted by providing starting estimates of each endmember spectrum for each image data value. The mixing proportions for each data value is estimated from estimates of the spectra of all the endmembers. The spectrum of each endmember is estimated from estimates of the mixing proportions of the spectra of all the endmembers for each image data value. The estimation steps are repeated until a relative change in the regularised residual sum of squares is sufficiently small. The regularised residual sum of squares includes a term which is a measure of the size of the simplex.

The invention discloses an individual tree automatic extraction method based on multispectral LiDAR data. The method comprises the following steps that the nearest neighbor search method is adopted on each laser point in the benchmark point cloud data with the point cloud of any band of the LiDAR data acting as the benchmark data, and band information of the nearest laser point is acquired in the data of other bands so that the single fusion point cloud data including multispectral information are generated; multi-perspective projection is performed along the Z-direction of the single fusion point cloud data including multispectral information, and the point cloud data are segmented into ground point cloud data and non-ground point cloud data; clustering and normalized segmentation are performed on the non-ground point cloud data, and segmentation is performed according to the geometric and spectral characteristics of the point cloud data so that semantically independent local point cloud blocks are obtained through separation; and a tree target overall characteristic description model based on the three-dimensional local abstract class characteristics is established to perform individual tree automatic extraction processing based on deep learning. The individual tree automatic extraction method based on the multispectral LiDAR data has the advantages of enhancing the tree identification accuracy.

The invention relates to the technical field of image processing, in particular to a remote sensing image registration algorithm. The registration algorithm comprises the following steps of: (1) reading primary remote sensing image data from a storage medium; (2) pre-processing each primary image; (3) performing binarization processing to realize image segmentation; (4) corroding and expanding the binary image; (5) extracting a monotropic edge from the eroded and expanded binary image by the Roberts cross gradient operator; (6) calculating the matching degree of the edge image and finding the optimal matching point; (7) conversing images; and (8) outputting registration information and registration images. The remote sensing image registration algorithm can be applied to multispectral data fusion and remote sensing image mosaicking.

The invention discloses a water bloom distribution and extraction method based on an environmental satellite No.1. The method comprises the following steps of: (S1) calculating a normalized vegetation index according to a multi-spectrum remote sensing graph of the environmental satellite No.1; (S2) distinguishing a water body and water bloom waterweed according to the normalized vegetation index to acquire binary graphs of the water body and the water bloom waterweed; (S3) acquiring a water bloom water body binary graph by combining an inversion result of high-spectrum data according to the binary graphs of the water body and the water bloom waterweed; and (S4) inputting a water body distribution map, carrying out the band calculation on the water bloom water body binary graph and the water body distribution map, generating trinary graphs of the water bloom, the water body and the land and extracting the water bloom distribution map. The method provided by the invention enriches the research contents extracted by the water bloom distribution of the current multi-spectrum data, has high automatic interpretation degree of the computer, and can be run in different software modes and be suitable for developing service operation monitoring work.

A spectroscopic detector includes a tunable light source, such as a continuously tunable, optical parametric oscillator laser; means for measuring the emitted radiation at a plurality of emission wavelengths to obtain a plurality of spectral measurement data; and a processor for processing the spectral measurement data, where the processor includes a multispectral data processing algorithm or is configured for 1) combining the plurality of spectral measurement data into a composite spectrum, and 2) applying the algorithm to the composite spectrum. The spectra such as resonant and near-resonant Raman Spectra that are acquired are more complete and contain more information. A powerful multispectral analysis code such as IHPS, CHOMPS, or ENN analyzes the acquired data points, examining details of the spectra that could not be handled by traditional methods.

The invention discloses a multi-mode small target detection method based on knowledge distillation, and the method comprises the steps of constructing a visible light-multispectral image data intrinsic knowledge migration model, carrying out the feature refining through a spatial-spectral combined non-local feature pyramid visual attention structure, and refining the multi-spectral and spatial-spectral combined features through a knowledge distillation model based on spatial-spectral combined feature migration to obtain a high-precision and high-efficiency deep neural network. According to the invention, target intrinsic knowledge can be migrated by using visible light big data to solve the problem of insufficient multispectral data samples, the detection and recognition robustness is improved through non-local attention, the number of neural network parameters after knowledge distillation is simplified, the computing resource overhead is reduced, and lightweight operation can be realized.

The invention discloses a multi-source remote sensing image surface object classification method based on a double-channel convolution step network. The multispectral data of regions to be classified obtained by a landsat-8 sensor and a sentinel-2 sensor are normalized by suing ENVI software so as to obtain the normalized multispectral data; 28x28 blocks around each element of the normalized multispectral data are taken to represent the original element value so as to form a feature matrix based on the image blocks; multiple blocks are randomly selected from each class to for training data sets L and S; a multi-source remote sensing image surface object classification model based on the double-channel convolution step network is constructed; the multi-source remote sensing image surface object classification model based on the double-channel convolution step network is trained by using the training data sets L and S; and test data sets are classified by using the trained multi-source remote sensing image surface object classification model based on the double-channel convolution step network. The high multi-source image classification accuracy can be acquired by only using less class tag samples so that the method can be used for target detection.