78 results about "Particle identification" patented technology

Methods, storage mediums, and systems for image data processing are provided. Embodiments for the methods, storage mediums, and systems include configurations to perform one or more of the following steps: background signal measurement, particle identification using classification dye emission and cluster rejection, inter-image alignment, inter-image particle correlation, fluorescence integration of reporter emission, and image plane normalization.

The invention provides an aerosol particle laser analyzer which online and continuously detects the aerodynamic diameter and particle quantity of the aerosol particles in the air one by one in real-time and identifies whether the particles are biological particles; the aerosol particle laser analyzer comprises a particle beam queuing acceleration sampling system wrapped by shell flows, a dual-peak laser aerodynamic diameter measurement system, a biological particle fluorescent detection system induced by ultraviolet laser, an ineffective and superposed particle identification circuit, data processing, displaying and memorizing software, and a communication module. The aerosol particle laser analyzer can not only detect the physical parameters such as aerodynamic diameter, particle quantity and the like of the aerosol particles, but also can judge whether the particles are active biological particles or not according to the natural characteristic that the active biological particle emits bioluminescence when being induced and can measure the parameters of the active biological particles such as the quantity, the concentration and the like; the aerosol particle laser analyzer has exact detection results and can be used conveniently and fast for detection; and the parts have long service life and the volume of the aerosol particle laser analyzer is small, thus being convenient for movable usage.

An in-line holographic microscope can be used to analyze on a frame-by-frame basis a video stream to track individual colloidal particles' three-dimensional motions. The system and method can provide real time nanometer resolution, and simultaneously measure particle sizes and refractive indexes. Through a combination of applying a combination of Lorenz-Mie analysis with selected hardware and software methods, this analysis can be carried out in near real time. An efficient particle identification methodology automates initial position estimation with sufficient accuracy to enable unattended holographic tracking and characterization.

A method of particle detection includes optically trapping a single particle having an averaged linear dimension of between 0.10 microns and 50 microns in a focal region optical trap formed from a trap visible to near-infrared wavelength. The trap is proximal to a substrate having a discontinuous metal coating so as to exploit a surface plasmon resonance generated electric field caused by irradiation of the metal coating. The single particle is then exposed to an interrogation wavelength to yield scattering spectrum relating to the particle. A particle identification digital database containing scattering spectra from a variety of different single particles that vary in spectral features facilitates identification of unknown spectra. A microfluidic cell is detailed to facilitate the automated scanning of numerous particles from a sample.

A system and method for developing and utilizing particle-based n-multiplexed assays that include three or more reporters utilizes n particle sets that are associated with particle identification images or labels (IDs) that differ between sets. The encoded particles for a given set are coated with a specific binding member, or in the case of the sandwich assay with coupled capture and detector binding pair members, to form particle types. The sets of particle types are then pooled, and aliquots of the particle types are removed to assay vessels. Next, samples with three or four reporter molecules are supplied to the respective vessels. After one or more incubation periods, the particles are supplied to a reader system, which determines the particle IDs to identify the particle types and also detects the reporter signals. The reader system includes multiple excitation lasers that excite the various reporters in sequence or in parallel, to supply associated signals to one or more detectors. Emission filters and wavelength discriminators are included such that a given detector receives at a given time the signals associated with a single assay binding label. The system further develops greater capacity sandwich assays by assigning subsets of capture and detector antibody pairings to the three or four reporters, respectively. The system performs greater numbers of differential RNA expressions based on the use of the three or more reporters, with one or more reporters assigned to the reference sample and the other reporters assigned to respective test samples. The system and method are also capable of performing greater numbers of SNPs utilizing primer extension reactions, by assigning different color reporters to the respective nucleotides or terminators.

An apparatus and method for performing mass spectroscopy uses an ion interface to provide the function of removing undesirable particulates from an ion stream from an atmospheric pressure ion source, such as an electrospray source or a MALDI source, before the ion stream enters a vacuum chamber containing the mass spectrometer. The ion interface includes an entrance cell with a bore that may be heated for desolvating charged droplets when the ion source is an electrospray source, and a particle discrimination cell with a bore disposed downstream of the bore of the entrance cell and before an aperture leading to the vacuum chamber. The particle discrimination cell creates gas dynamic and electric field conditions that enables separation of undesirable charged particulates from the ion stream.

The invention discloses an FPGA-based particle detection statistical system and an FPGA-based particle detection statistical method. A particle analysis module comprises a filter circuit, a particle identification circuit, a decoding circuit and a statistical circuit. An A/D converter is connected with the filter circuit; the filter circuit is connected with the particle identification circuit; the particle identification circuit is connected with the decoding circuit and the statistical circuit; the decoding circuit is connected with the statistical circuit; the statistical circuit is connected with a main controller through an SPI interface circuit; and the decoding circuit is connected with the main controller through the SPI interface circuit. The system and the method have the advantages that: an interference signal and a normal signal can be distinguished; superposed signals (M signals) which are very close to each other can be identified; due to the adoption of a programmable apparatus, problems during identification of analog signals are solved; the complexity and cost of a practical circuit can be greatly reduced; and the counting accuracy of the identification rate of particle signal can be improved.

The invention discloses a development method for a mechanical wear system on the basis of an abrasive particle wear mechanism. The development method comprises an abrasive particle image preprocessingmodule, a characteristic extraction module and an abrasive particle identification module, wherein the image processing module is mainly used for processing an abrasive particle image; the abrasive particle characteristic extraction module is mainly used for extracting the geometric and textural characteristics of the abrasive particle; an image identification module is used for distinguishing atype to which the abrasive particle belongs; and a mathematic model for monitoring a mechanical wear state on the basis of abrasive particle characteristic identification is put forward on the basis of a situation that the abrasive particle has different shapes and textural characteristics under different wear mechanisms by aiming at the problem the monitoring accuracy of a mechanical equipment wear state is low. Through shape characteristics, spherical abrasive particles and cutting abrasive particles are identified, fatigue abrasive particles and severe sliding wear particles are identifiedby the combination of shape and textural characteristics, a characteristic vector for mechanical wear state monitoring is established on the basis of the extracted characteristic parameter, and through a support vector machine classifier model, a mechanical wear state is monitored and distinguished.

The invention belongs to the geotechnical engineering miniature test field, and discloses a particle identification and tracking method based on a spherical harmonic function invariant; the method comprises the following steps: a, carrying out CT scanning for a particle sample original state and a deformation state so as to obtain each CT image maps; b, processing the CT image maps; c, using the spherical harmonic function to represent the three dimensional form of each particle in the CT image maps of the original state and deformation state; d, calculating a spherical harmonic function invariant 2-norm distance so as to match with the particles under two different states, thus identifying the particles. The method can effectively identify the sand particles in different loading phases ofa miniature mechanics test under the in situ X ray high precision CT scanning, thus accurately tracking motion behaviors of all sand particles; the method is wide in application scopes.

The invention discloses a particle focusing glare point speed measuring method based on correlation matching. The method is characterized in that a particle IPI focusing glare point of the time sequence is recorded, on the basis of a centroid method and a sequence template matching method, particle positioning of sub-pixels is realized, candidate particles are searched according to a maximum displacement and speed direction criterion, then on the basis of a cross correlation method, particle recognition matching with the high accurate recognition rate is achieved, the effect is that the methodis provided for the particle speed measurement based on the IPI focusing point, moreover, quite high speed measurement precision and quite high matching accuracy are achieved, and the method can be used for speed distribution measurement of the of particle fields such as sprayed mist, bubbles and flow fields.

The invention discloses an aggregate particle identification method. The method comprises the following steps: shooting a high-definition image for aggregate at an appropriate position (such as a coldmaterial pile, a discharge hole and a conveyor belt); carrying out numerical processing on the image information by utilizing a matlab program; selecting an appropriate filtering technology for preprocessing the image according to the image acquisition effect in multiple filtering technologies; pre-segmenting and binarizing the image; performing morphological processing on the image by using opening and closing operations; performing preliminary segmentation on the image by using a watershed algorithm based on distance change; and carrying out fine calibration and secondary segmentation on the particles by using morphological characteristics such as pits. According to the method, the sampling positions of the aggregate particles are not limited, and only the image quality needs to meet the requirements. The result shows that the method can effectively segment aggregate particles to obtain particle information, and provides technical support for aggregate detection and grading controlin subsequent construction of the asphalt mixture.

The invention discloses a mechanical wear particle identification method, which comprises the following steps of: inputting a training sample of mechanical wear particles into a convolutional neural network (CNN) model for training to obtain a CNN feature extractor for the mechanical wear particles; extracting a feature vector in the training sample according to the CNN feature extractor; inputting the feature vectors into a support vector machine (SVM) classifier for training to obtain a hybrid convolutional neural network model; and through the hybrid convolutional neural network model, inputting the feature vector of the to-be-tested sample of the mechanical wear particles into a trained SVM classifier to identify the abrasive particle type of the to-be-tested sample. In addition, the invention further discloses a mechanical wear particle recognition device, electronic equipment and a storage medium. By the adoption of the method and device, screening of wear particle characteristic information in a manual mode is avoided, and the type of the wear particles can be accurately identified.

The invention discloses a cloud precipitation refined inversion method based on a cloud radar. The method comprises the steps of extracting cloud radar data, firstly, performing quality control on thecloud radar data, then automatically identifying the height of a cloud precipitation melting layer by utilizing an independently designed melting layer detection algorithm; and then carrying out classification and identification on hydrometeor particles in the cloud precipitation by adopting the steps of fuzzification, rule judgment, phase state classified limitation check, maximum integration method integration, defuzzification and the like, carrying out refined inversion on the phase state and distribution of the hydrometeor particles, and finally outputting a refined inversion result of the cloud precipitation. Refined inversion of the hydrometeor particles in the cloud precipitation and automatic identification of the height of the melting layer are realized. According to the method,the phase state and distribution of the hydrometeor particles in the cloud precipitation can be inversed only by means of the cloud radar data, and the identification and inversion rate of the hydrometeor particles in the cloud precipitation is improved. Meanwhile, particle phase state limitation check is added on the basis of a common fuzzy logic method, and the identification accuracy of the phase state of the hydrometeor particles is improved.

The invention discloses a nano-particle identification system device and an identification method thereof. The nano-particle identification system device comprises a light scattering system and a data processing system, and further comprises a detector tank, wherein the light scattering system comprises at least two groups of laser sources which are arranged in sequence and parallel, a short-focus lens, an optical grating, a long-focus lens, an optical grating filter and a multi-point scattered light receiver; the detector tank is arranged between the long-focus lens and the optical grating filter; the data processing system comprises a photoelectric conversion module, a data processing module and a display; and curve similarity and particle concentration quantitative data are acquired by the data processing module through calculation, and then a result is displayed on the display. The method adopts a laser particle size detector to carry out laser radiation on target particles and interference particles in a solution, so as to achieve the identification on characteristics of nano-particles in the solution by calculating the curve similarity, and to further carry out targeted identification detection on particles with similar particle diameters in an aqueous solution.

The invention discloses an early warning method of a hailstorm in a complex terrain area and relates to the field of early warning methods. The method includes the following steps of (S1) collecting relevant data, (S2) performing quality preprocessing on the above data, (S3) performing moisture variable particle analysis on preprocessed data by using a fuzzy logic particle recognition algorithm toobtain the number, distribution height, thickness, and change rate with time of key particles, and finally obtaining a hailstorm forecast index of the key particles, and (S4) issuing a correspondinghailstorm warning or canceling a hailstorm warning according to the hailstorm forecast index. The collected data is preprocessed by the data preprocessing, the moisture variable particle identification is carried out to obtain the distribution, number and change rate of the key particles, finally, the hailstorm forecast index is obtained, whether the hailstorm happens can be accurately judged according to a stage where the hailstorm forecast index is located, and the forecast level of hail weather in the complex terrain area is improved.

The invention relates to a coarse-grained soil filler gradation automatic identification method based on image matching and an application system, and the method comprises the steps: collecting coarse-grained soil filler images with various particle sizes, forming coarse-grained soil particle identification templates with various particle sizes, and constructing a template library; collecting filler images including various gradations, respectively identifying and matching each filler image with a coarse-grained soil particle template in the template library to obtain the particle size, distribution and shape category of coarse-grained soil particles in the filler image, and packaging each unit program into a program capable of running independently; collecting a filler image of a roadbedrolling construction site, and processing the filler image through a packaging program to obtain coarse-grained soil gradation in the filler image of the construction site. According to the method, efficient and accurate segmentation and recognition of a single particle are achieved by establishing the matching template, the automation degree is high, no complex image processing algorithm is needed, no human intervention is needed, no experience of operators is relied on, the environmental adaptability is high, and the precision is high.

The invention discloses a single bioaerosol particle identification system based on laser capture and microwave radiation. A laser tweezer is used for fixing and applying directional microwave radiation to distinguish biological and non-biological particles in the atmosphere; meanwhile, a digital camera is combined to record the change of fixed states of the particulate matters to identify singlebioaerosol particles, thus realizing single capturing, fixing, screening and subsequent recording and analysis of biological and non-biological aerosol particles; and the system can be widely appliedto in-situ detection of atmospheric particulates contained in indoor and outdoor environment air, especially in-situ screening and recording of biological particles and non-biological particles in theatmospheric particulates.

The invention discloses a bed surface particle identification tracking method based on motion image backtracking. An identification and tracking task is completed through nine steps. And carrying out resolution adjustment preprocessing on the qualified bed surface particle motion image by using a binary method. A two-dimensional Gaussian mixture model is adopted to carry out background removal on the moving particles; a motion backtracking method is used, based on an inter-frame particle identification model, target particle motion positions in continuous frames are determined, and a dynamic threshold value and a spot analysis method are used for filtering data noise. Through active and inert state identification and establishment of an effective active particle data set, a particle trajectory sample set and a space coordinate data set with all behavior characteristics of motion and waiting are screened out. Moving particles are tracked in continuous frames of images to form a coordinate trajectory chain, and multi-scale motion information is obtained; a particle positioning error elimination and optimal identification link technology is adopted, so that the quality of effective active particle motion data is improved; fine identification, multi-dimensional information acquisition and whole-process tracking of target particle motion are realized.

The invention discloses a knowledge-guided CNN-based small sample similar abrasive particle identification method, which comprises the steps of marking key features of an abrasive particle height graph in a binary graph form according to an abrasive particle generation mechanism; on the basis, constructing a U-net network of a VGG16 model to automatically extract typical characteristics of the abrasive particles; fusing the output of the U-Net network with the convolution layer of the full convolution CNN network through a weighting mode, guiding the training of the full convolution CNN network, and enabling the full convolution CNN network to quickly locate the distinctive features of similar abrasive particles. According to the constructed network model, the weighted sum of Focal loss and binary classification cross entropy loss is adopted as an overall loss function, parameter training is conducted through an SGD optimization algorithm, a final similar abrasive particle classification model is obtained, and identification of typical similar abrasive particles is achieved. According to the method, the abrasive particle knowledge experience and the CNN network are effectively combined, and the problems that in the existing abrasive particle analysis field, the number of similar abrasive particle samples is small, and the recognition accuracy is low are solved.

The invention discloses a ferrographic image multi-abrasive-particle identification method based on a single-stage detection model yolov3. The invention provides a ferrographic image multi-abrasive-particle identification method. The method comprises the following steps: firstly, improving a backbone network of a yoov3 model; adding a spatial pyramid pooling module; replacing an IOU loss functionof an original yov3 model with a GIOU loss function, expanding a yoto layer scale is expanded, and the like. And by improving a yov3 backbone network, the problems that in the ferrographic abrasive particle recognition process, the recognition rate of similar abrasive particles is low, and the omission ratio of small abrasive particles is high are effectively solved. According to the ferrographicimage multi-abrasive-particle identification method provided by the invention, the BN layer and the convolution layer of the model are fused, so that the network structure is simplified, the additional calculation amount brought by module addition is limited, and the real-time performance of the lowest detection speed of the yolov3 model is ensured. According to the ferrographic image multi-abrasive-particle identification method provided by the invention, an intelligent identification result can be obtained only by inputting the multi-abrasive-particle picture into the trained module, more manual operations are not needed, and intelligent identification is realized.

Disclosed herein is a novel, compact optical particle identification and characterization system and method of use within both gaseous and liquid media. The system can implement both elastic and inelastic light scattering techniques simultaneously under the same sensor platform. By separating the sensing components from the electro-optical unit and using optical fibers for interconnection, only the sensing components need to be exposed to the environmental conditions. This reduces the design constraints on the electro-optical unit and permits the incorporation of optical components into the sensing probe that can withstand high-temperature, high-pressure, and corrosive environments. Thus, the system can be used in benign, moderate, and harsh environments.

Aspects of the present disclosure include methods for characterizing particles of a sample in a flow stream. Methods according to certain embodiments include detecting light from a sample having cells in a flow stream, generating an image of an object in the flow stream in an interrogation region and determining whether the object in the flow stream is an aggregate based on the generated image. Systems having a processor with memory operably coupled to the processor having instructions stored thereon, which when executed by the processor, cause the processor to generate an image of an object in a flow stream and to determine whether the object is an aggregate are also described. Integrated circuit devices (e.g., field programmable gate arrays) having programming for practicing the subject methods are also provided.

The invention discloses a Mask R-CNN-based starch particle identification method, and the method combines hot stage-polarized light microscopic observation with a computer image identification technology, and intelligently identifies the change of the number of particles in a starch gelatinization process: collecting starch gelatinization image data based on hot stage-polarized light microscopic observation; sequentially carrying out starch gelatinization data set construction, Mask R-CNN model construction and training, starch gelatinization process particle detection and starch particle number statistics through an algorithm, wherein the algorithm comprises a starch image binarization algorithm, a starch gelatinization data set construction algorithm, a neural network training algorithm, a starch particle detection algorithm and the like. According to the method, the Mask R-CNN is used for intelligently detecting starch gelatinization, the automation degree is high, the detection efficiency is good, and the particle detection accuracy rate reaches 95% or above. The invention provides a novel quantitative method for intelligently detecting starch particles and evaluating starch gelatinization.