1450results about How to "Solve the detection speed is slow" patented technology

The invention relates to a microfabricated device for the rapid detection of DNA, proteins or other molecules associated with a particular disease. The devices and methods of the invention can be used for the simultaneous diagnosis of multiple diseases by detecting molecules (e.g. amounts of molecules), such as polynucleotides (e.g., DNA) or proteins (e.g., antibodies), by measuring the signal of a detectable reporter associated with hybridized polynucleotides or antigen / antibody complex. In the microfabricated device according to the invention, detection of the presence of molecules (i.e., polynucleotides, proteins, or antigen / antibody complexes) are correlated to a hybridization signal from an optically-detectable (e.g. fluorescent) reporter associated with the bound molecules. These hybridization signals can be detected by any suitable means, for example optical, and can be stored for example in a computer as a representation of the presence of a particular gene. Hybridization probes can be immobilized on a substrate that forms part of or is exposed to a channel or channels of the device that form a closed loop, for circulation of sample to actively contact complementary probes. Universal chips according to the invention can be fabricated not only with DNA but also with other molecules such as RNA, proteins, peptide nucleic acid (PNA) and polyamide molecules.

The disclosed electrochemical screening and early diagnostic device for malignant tumor comprises: an immune detection chip (1) connected to a time-resolution multichannel potentiostat (2) that connects to a data process and display system (3) by an interface. Wherein, the chip (1) comprises eight working electrodes fixed different antigen films and Ag wire (a), Ag / AgCl reference electrode (b), a carbon-pair electrode (c), and an insulation film (d). This invention needs low cost, has intelligence and fit to fast detection.

Improved methods and apparatuses are provided for use in face detection. The methods and apparatuses significantly reduce the number of candidate windows within a digital image that need to be processed using more complex and / or time consuming face detection algorithms. The improved methods and apparatuses include a skin color filter and an adaptive non-face skipping scheme.

The invention discloses a method and a system for authenticating a shielded face, wherein the method comprises the following steps: S1) collecting a face video image; S2) preprocessing the collected face video image; S3) performing detection calculation on the shielded face, evaluating a position of a face image by utilizing a three-frame difference method according to motion information of a video sequence, and further confirming the position of the face according to an Adaboost algorithm; and S4) performing authenticating calculation on the shielded face, dividing a face sample into a plurality of sub-blocks, performing shielding distinguishment on the sub-blocks of the face by adopting a SVM(Support Vector Machine) binary algorithm combined with a supervising 1-NN k-Nearest neighbor method, if the sub-blocks are shielded, directly abandoning the sub-blocks, and if the sub-blocks are not shielded, extracting a corresponding LBP (Length Between Perpendiculars) textural feature vector for performing weighting identification, and then using a classifier based on a rectangular projection method to reduce feature matching times. According to the method for authenticating the shielded face, the detection rate and the detection speed for the local shielded face are effectively increased.

The embodiment of the invention discloses a moving target behavior tracking method, a device, a device and a computer-readable storage medium. The method includes invoking the pre-constructed object detection model to detect the object in the moving object image so as to locate the position of the moving object in the moving object image. The target detection model is based on YOLOv3 algorithm andtrained with regularization and binary cross entropy as loss function. The target detection model selects the target boundary box satisfying the preset conditions according to the intersection ratioand non-maximum suppression algorithm, and determines the center coordinate of the target boundary box to locate the position of the moving target. The present application utilizes an object detectionimage model to locate a moving object in a captured moving object image, and for a plurality of successive frames of successive images, by locating a moving object in each frame of the images, tracking detection of a moving object behavior in a video is realized. The present application improves the detection speed and positioning accuracy of a moving object.

The invention requests to protect a multifunctional V2X intelligent roadside base station system. The system comprises roadside sensing equipment, an MEC server, a high-precision positioning service module, a multi-source intelligent roadside sensing information fusion module and a 5G / LTE-V communication module. An intelligent roadside device integrating C-V2X communication, environmental perception and target recognition, high-precision positioning and the like is designed, and the problem that multi-device information fusion and integration are inconvenient in intelligent transportation is solved. In the system, a C-V2X intelligent road side system architecture and a target layer multi-source information fusion method are designed. Road side multi-source environment cooperative sensing is combined, real-time traffic scheduling of the intersection is realized by using a traffic scheduling module in the MEC server, and communication and high-precision positioning services are providedfor vehicle driving, and finally the target information after fusion processing is broadcasted to other vehicles or pedestrians through a C-V2X RSU (LTE-V2X / 5G V2X and the like) according to an application layer standard data format, so the driving and traffic safety is improved.

The present invention puts forward a front vehicle information structured output method base on concatenated convolutional neural networks, for mainly solving the problem that a traditional method cannot quickly detect and identify a vehicle body, a license plate and a vehicle logo in one time in a complex environment. The realization process of the front vehicle information structured output method comprises the steps of: 1, acquiring a sample set and selecting a vehicle body initial sample set from the sample set; 2, training the vehicle body initial sample set through a BING (Binarized Normed Gradients) method; 3, respectively training convolutional neural networks of vehicle body, license plate and vehicle logo; 4, judging the area and color of the vehicle body according to the well trained convolutional neural network of vehicle body; 5, judging the area of the license plate and identifying a license plate number according to the well trained convolutional neural network of license plate; 6, judging the area and class of the vehicle logo according to the well trained convolutional neural network of vehicle logo; and 7, outputting the all obtained information to a frame image. The front vehicle information structured output method of the present invention can accurately detect and identify front vehicle information in a complex environment, and can be used for intelligent monitoring, intelligent traffic, driver auxiliary and traffic information detection.

The invention relates to the technical field of face recognition, in particular to a rapid detection method of a face in a high-resolution color image under a complex background. The invention comprises the following steps: building a face skin color mixed model which is composed of two color space restrictions of RGB and YCbCr according to a large amount of acquired skin color sample data to determine the skin color pixel; rapidly skipping non-face regions by adopting a whole skin color pixel ratio to improve the location efficiency of a face candidate region; then using the improved face rapid detection algorithm which is based on forward characteristic selection to realize face preliminary judging of the face candidate region; and finally utilizing a false alarm restraining method which is based on space restriction and geometric restriction to further lower false detection rate and complete face detection. The invention can realize rapid location of a plurality of frontal faces in images at a high detection rate under the condition of low false alarm rate; the good performances of the invention are proved by the results of the test set of Bao open database and a plurality of video frequencies and high resolution color images.

The invention discloses a wavelet transformation and deep learning-based rolling bearing weak fault diagnosis method. The method comprises the following steps: a rolling bearing vibration signal is obtained, and the acquired vibration signal is subjected to continuous wavelet transformation to obtain a time-frequency diagram; autocorrelation operation is performed on wavelet coefficients corresponding to each frequency on the time-frequency diagram to filter out noise interference and extract periodic fault components; the Hilbert transformation is used to perform envelope demodulation to obtain a fault characteristic frequency; a processed time-frequency diagram is input as a feature diagram, and categories of early faults are determined by training a deep learning classification model. Theoretical and experimental results show that fault categories can be determined accurately at an early stage when weak fault of a rolling bearing occur based on an improved wavelet time-frequency diagram used as the classification model for input training, right determination results can be given when the method is applied to different bearings, high training speed can be realized, and high actual application value can be achieved.

The invention relates to an aerial image insulator real-time detection method based on deep learning. The aerial image insulator real-time detection method based on deep learning includes the steps: handing a task of extracting characteristics to a deep convolutional neural network, extracting the deep characteristic information which is more comprehensive and can preferably describe an insulator,and inputting the deep characteristic information into a detector to perform prediction inference to obtain a detection result. For the aerial image insulator real-time detection method based on deeplearning, the whole process is an end-to-end quick detection channel; a target frame is obtained after the image is input; the efficiency of subsequent automatic fault diagnosis is improved; and theaerial image insulator real-time detection method based on deep learning is conductive to reducing the retrieval pressure and intensity when the line patrol staff retrieves the mass line patrol data at present. And at the same time, the aerial image insulator real-time detection method based on deep learning also utilizes the idea of transfer learning to transfer the knowledge obtained from the past task to the current target task, so as to enable the trained model to have inheritability; whenever new data is added into an image library, the target model can continue to train new data on the basis of a source model, so as to quickly achieve the expected effect and enable the old version of model not to be of no use at all because of updating of data; and the detection model can become moreand more powerful following increase of data as time goes on.

The invention discloses detection equipment and a detection method. The detection equipment comprises a sampling device used for collecting a sample to be detected, a preprocessing sample injection device used for preprocessing the sample from the sampling device, and a sample analysis device used for separating the preprocessed sample from the preprocessing sample injection device and analyzing the separated sample. The detection equipment is miniaturized, can quickly and accurately detect gas-phase matters or particulate matters without unpacking, and is high in accuracy and suitable for security check of airports, ports, metro stations and the like.

The invention provides a vehicle target detection method based on YOLOv2. The method comprises the steps of collecting pattern data and processing the pattern data to obtain a sample data set; constructing an improved YOLOv2 model, and improving the network structure of the YOLOv2 basic model; designing a loss function by adopting a comparison normalization thought; performing model training, wherein the training process of the whole network is divided into classification network training and detection network training; and model verification: verifying the model obtained by training by usingthe verification data set, and testing the recognition capability of the model. And the algorithm is subjected to experimental comparison with a recently popular algorithm to verify the effectivenessof the algorithm. The improved YOLOv2 model established by the invention can improve the recognition rate of small-scale vehicle targets. Under various complex conditions, most of target vehicles canbe detected, and the recognition speed and precision are higher than those of other conventional algorithms.

The invention relates to a method for detecting the defects of chain belts of a zipper on the basis of digital image processing, belonging to a novel technology in the technical field of appearance quality inspection of zippers in the hardware industry. According to the method, a detection device consisting of a target positioning and triggering device, an image acquisition sensor, a conveyor belt driving device, a background light source device, a feed belt, a sorting device and a PC (Personal Computer) machine or an embedded control system is utilized to carry out detection; and a zipper product to be detected is fed into a feed belt platform of the detection device and is then fed to a detection region under the drive of the driving device, then the zipper product is subjected to target positioning by the target positioning and triggering device, a chain belt digital image of the zipper is acquired by the image acquisition sensor, the image is transmitted to the PC machine or the embedded control system, the target image is processed by the PC machine or the embedded control system, and whether a chain belt region of the zipper has the defects is compared and judged according to a processing result and the judgment standard. The method has the characteristics of simple detection process, high detection speed, high detection accuracy and the like.

The invention provides a face detection method based on a Gaussian model and a minimum mean-square deviation, and relates to a face recognition technology. A face detection method based on the Gaussian model and the minimum mean-square deviation under the premise of a complicated background, a side face, a stopper and a plurality of faces. The method comprises the following steps of: building a YCbCr Gaussian model: building the YCbCr Gaussian model for face skin color distribution according to collected skin color sample data, and performing lighting compensation on the image, wherein in the YCbCr, Y is a brightness component, Cb is a blue chroma component, and Cr is a red chroma; performing skin color segmentation on the image by using the built YCbCr Gaussian model and the minimum mean-square deviation; performing binaryzation on a skin color region, and processing a binary image by opening to eliminate a small bridge and discrete points; rejecting detected non-face regions in the similar skin color or skin color according to future knowledge of a face; and finally marking a face position by using a rectangular frame.

The invention provides a video image processing method and a video image processing device. The method includes: acquiring a video image sequence; recognizing a target object from a video image frame in the video image sequence; tracking the target object, and determining a motion trail of the target object; acquiring video structural information on the basis of the target object and the motion trail of the target object; performing target object retrieval and / or video compression on the video image sequence on the basis of the video structural information. On the basis of the video image processing method and the video image processing device, quickness in target investigation is realized, target investigation is accelerated, and case cracking speed is increased.

The invention provides a multi-angle multi-target fast human face tracking method used in a video sequence, which belongs to the technical field of video processing. Through multi-angle human face fast detection and color histogram establishment in a human face region, a color probability graph of an image to be detected is calculated, Camshift arithmetic iterating results are used for updating the human face region position and simultaneously upgrading a human face moving model established by a Kalman filter, and at the same time, the human face prediction is carried out when a target is shielded: when the human face is shielded, the human region position is predicted by the Kalman filter, and then, the human face moving model is updated. The invention can fast eliminate the non-human face region so that the real-time multi-angle multi human face target tacking becomes possible. At the same time, through the introduction of the Kalman filter, the invention can use the prediction results of the Kalman filter for updating the position of the shielded target when the target shielding occurs in the video sequence, and the tracking difficulty caused by shielding can be perfectly overcome.

The invention provides a micro-fluidic device and a method for detecting circulating tumor cells on the basis of dimensions. The micro-fluidic device comprises a solution storage chamber, a micro-fluidic chip, a waste liquid collecting syringe and a power system which are connected in sequence, wherein the micro-fluidic chip is made of a glass substrate layer and a PDMS (Polydimethylsiloxane) chip layer in a laminated manner; the PDMS chip layer comprises an injection port, a block mass filtering area, a target sell screening area and a discharge port which are communicated in sequence; the block mass filtering area is formed by a column array; the target cell screening area comprises a plurality of main pipelines and side pipelines which are extended in a parallel manner at intervals and are communicated through filtering channels; the front ends of the main pipelines are opened; the filtering channels are formed in the rear ends of the main pipelines; the front ends of the side pipelines are sealed; the rear ends of the side pipelines are opened; the main pipelines and the side pipelines have a first height greater than the dimensions of the circulating tumor cells; the filtering channels have a second height smaller than the dimensions of the circulating tumor cells. The micro-fluidic device and the method for detecting the circulating tumor cells on the basis of the dimensions are good in sensitivity, simple to operate, low in cost, large in flux and short in time.

This invention provides an apparatus and method for preamble detection and integer carrier frequency offset estimation, which method comprises the steps of: determining the window of useful subcarriers in preamble transformed to frequency domain based on pre-determined possible integer carrier frequency offset and the length of the preamble, so as to select the useful subcarriers; extracting a plurality of subcarrier sequences having a length equal to that of the preamble from the useful subcarriers; calculating conjugative multiplications of each subcarrier and its neighboring subcarriers in the subcarrier sequences extracted; acquiring the real part of the conjugative multiplications; calculating the cross correlations between the real part of the conjugative multiplications and known preambles modulated by DBPSK, and outputting the calculated correlation values; and detecting preamble index of a target base station with the calculated correlation values to select a target cell, and estimating integer carrier frequency offset with respect to the target base station.

A light detector for use in a line scanning microscope and a microscope comprising such a light detector are described. The light detector comprises—a line array of avalanche semiconductor detectors; and an electronic trigger circuit that is adapted to operate the avalanche semiconductor detectors in at least one of a Geiger mode with internal charge amplification and in a linear mode. The trigger circuit further comprises a parallel counter that is designed to read out in parallel light pulses detected by the avalanche semiconductor detectors. The parallel counter is adapted to accumulate the light pulses detected by the avalanche semiconductor detectors over a preset counting time.

The invention discloses a face detection method and device adopting a cascade classifier, relating to the field of video monitoring. The face detection method comprises the following step of: carrying out face detection on rectangular windows with different positions and sizes in a current image to be detected by adopting a light type cascade-structure classifier to detect face windows, wherein each level of the light type cascade-structure classifier is a weak classifier. For a large quantity of windows to be detected in one image, relative to a scheme that a cascade-structure classifier is bound to eliminate partial non-faces after computing the results of all weak classifiers of a strong classifier, each weak classifier of the light type cascade-structure classifier can eliminate the partial non-faces, and therefore faster detection speed can be achieved, and the real-time detection of faces is further realized on megapixel high-definition videos.

The invention discloses a method for real-time detection of a road vehicle based on a deep learning SSD frame and mainly solves a problem of low detection accuracy of the existing technology under the conditions of traffic congestion and complicated weather. An implementation scheme of the method comprises the following steps that 1.shooting videos of a plurality of running vehicles at a vital communication line and grabbing window information of the vehicle in each frame of image in the video in a manual labelling way; 2.taking VGG-16 in a classification network as a basic network, constructing an SSD300*300 detection frame, extracting features of some feature extraction layers to carry out connection as recognized feature vectors and inputting the feature vectors into a loss function; 3.training through a training sample and taking a trained detection model into the detection frame; and 4.setting a correlation threshold and detecting the vehicles in the test videos by the trained detection model. According to the method, the detection accuracy is greatly improved and an effect of real-time detection is realized, and the method can be used for vehicle detection under the complex scene.

The invention relates to an on-line non-contact laser stereo scanning detection device for the internal screw threads of a tubing coupling, which is used for carrying out one-by-one all-around dynamic on-line three-dimensional stereo scanning detection on the tooth profile parameters of all the internal screw threads to be processed in the processing process of special purpose machine tools, suchas a threading machine tool of the tubing coupling and the like, to the internal screw threads. The on-line non-contact laser three-dimensional scanning detection device comprises an axial movement mechanism assembly, a radial rotation mechanism assembly and a laser detection probe assembly. The radial rotation mechanism assembly is fixedly connected with the end of the axial movement mechanism assembly, and the laser detection probe assembly is fixedly connected at the end of the radial rotation mechanism assembly. The invention has a three-dimensional stereo scanning detection function, cancarry out high-speed high-accuracy on-line laser stereo scanning on the tooth profiles of the sections of different radial axles of the internal screw threads of the tubing coupling and obtains the three-dimensional stereo geometric information of the tooth profiles of the internal screw threads of the tubing coupling. The invention can enhance the detection accuracy and speed of the parameters of the internal screw threads, lightens the labor strength of a detection worker greatly and avoids the influence of human factors to the measurement accuracy. Moreover, the invention can be used for on-line quality monitoring and prediction and enhances the product quality.

The invention discloses a blood metagenome sequencing data analysis method and device and an application thereof. The blood metagenome sequencing data analysis method comprises a data quality controlstatistics and splitting step, a humanized sequence removal step, a plasmid sequence removal and internal reference comparison step, a pathogen genome sequence library comparison step and a pathogen parameter annotation step. The invention provides a blood flow infection detection device based on a blood metagenome sequencing data analysis method. According to the method and device provided by theinvention, the free nucleic acid sequences in blood are detected through a metagenome sequencing method, a bioinformatics analysis method is combined, more than 8,000 pathogenic microorganisms such as bacteria, viruses, fungi and parasites possibly existing in a blood flow infection patient body are detected at a time, and a detection result can be obtained within 24 hours at the soonest. The speed, the sensitivity, the accuracy and the efficiency of blood flow infection detection are greatly improved.

The invention relates to a fake medicine discrimination and analysis device, a fake medicine analysis system containing the fake medicine discrimination and analysis device and a fake medicine analysis method. The fake medicine analysis method of the invention adopts model-free analysis method, makes an improvement on the basis of the already existing local linear screening method to ensure the method to be more stable and reasonable and combines with major constituent analysis method to form an integral fake medicine discrimination system. The fake medicine discrimination and analysis device, fake medicine analysis system and fake medicine analysis method of the invention only require the spectrum of a compound to be tested and few genuine tablets so as to realize fast and convenient discrimination of the tablets to be tested.

A method and apparatus for detecting infrared image abnormality of electric power equipment in substation The invention adopts the latest depth learning and the computer vision algorithm to automatically analyze the infrared data and detect the abnormal heat through the collected infrared image or infrared video, which will greatly improve the efficiency and accuracy of the infrared image or infrared video detection. In the substation patrol robot with infrared imager, such intelligent infrared abnormal heating area and fault equipment type detection algorithm based on depth learning are embedded in the upper computer control system such as substation fixed-point monitoring track robot. Real-time infrared image or video detection will further improve the intelligent degree of these intelligent equipment, so as to achieve the real intelligent patrol.

The invention provides a method for training a convolutional neural network classifier and an image processing device. According to the method for training the convolutional neural network classifier, global features and local features are extracted from an image for used training. The global features and local features are mapped to a feature map according to a predetermined mode as an input sample of the classifier. According to the predetermined mode, the global features are mapped to at least one first region, the local features are mapped to a second region, and each first region is connected with the second region. According to the training method provided by the invention, the speed and accuracy of detection are improved to a large extent.

The invention provides a non-contact detection system of a hollow cylindrical part and a detection method thereof. The detection system comprises: an illumination part, a transmission part and a datareceiving processing part, wherein the illumination part comprises a dual parallel light source and a slide way with a bracket and a base; the transmission part comprises a controller and an electriccontrol translational platform; and the data receiving processing part comprises a linear array CCD and a computer with a bracket and a base. One side of the electric control translational platform isprovided with the slide way; the parallel light source and the CCD are respectively arranged on the slide way by the bases thereof; the dual light source is symmetrically positioned relative to the CCD in x direction, and slantwise irradiated on the surface of a part A to be tested from the left upper direction and the right upper direction with angle Theta0<->; the width of the slit of the lightsource is adjusted according to the width upper limit d0<->; the CCD receives the reflected light of the surface of the part from the upper direction; and the data is transmitted to the computer to be processed. The detection method comprises the steps of: harmoniously controlling the translational platform and the CCD by the computer to equidistantly distantly acquire the data; preprocessing theacquired line image and conducting edge extracting; and fitting the circle center position and the circle radius of the outer circle with the circle center position and the circle radius of the innercircle, thus calculating the concentricity of the outer circle and the inner circle.