Patents
Literature
31results about How to "Simplify identification steps" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Multi-scale convolutional neural network based radio signal modulation identification method
ActiveCN107979554AOvercome the disadvantage of requiring a lot of prior knowledgeImprove universalityPhase-modulated carrier systemsSignal classificationCorrelation function
The invention discloses a multi-scale convolutional neural network based radio signal modulation identification method. The multi-scale convolutional neural network based radio signal modulation identification method comprises the steps of (1) generating a processed radio modulation signal; (2) generating a two-dimensional time-frequency diagram and performing Fourier transform on an instantaneouscorrelation function of the signal to obtain a Wigner-Ville time-frequency distribution diagram of the signals; (3) performing pre-processing on the time-frequency distribution diagram to generate atraining sample set and a test sample set; (4) building a multi-scale convolutional neural network module and training the model; and (5) testing the test set by utilizing the trained network model, calculating the correction rate, obtaining an identification accuracy rate and assessing the network performance. The multi-scale convolutional neural network based radio signal modulation identification method has the advantages of strong universality, no need for manual characteristic extraction and a plenty of priori knowledge, low complexity and accurate and stable classification results, and can be used in the field of signal classification identification technologies.
Owner:XIDIAN UNIV
Method and system for identifying heart-lung sound signals
PendingCN107798350AReduce volumeImprove portabilityStethoscopeCharacter and pattern recognitionNoise reductionComputer science
The invention relates to a method and a system for identifying heart-lung sound signals. The method includes the steps of acquiring heart / lung sounds initial detection signals, acquiring correspondingenvironment sound signals, and subjecting the heart / lung sounds initial detection signals to differential noise reduction processing, so as to prevent the influence of the peripheral environment on the cardio-pulmonary sound signals, prevent influence of signals irrelevant to the cardio-pulmonary sound signals on the identification precision, and effectively improve the collection and identification precision of the cardio-pulmonary sound signals. The heart sound simulation signals is processed through combination of EMD (Empirial Mode Decomposition) and a high-order shannon entropy algorithm, and a wavelet decomposition is used for processing the lung sound digital signals. Accurate recognition of the characteristics of the heart sound signals and the lung sound signals is achieved, andthe identification steps of the cardio-pulmonary sound signals are effectively simplified. The real-time performance is higher, and the cost is low.
Owner:SOUTH CHINA NORMAL UNIVERSITY
Antiforge fibre and antiforge paper using it
InactiveCN1343810AEasy to identifyOvercome the defect of being easily counterfeited by printing methodsNon-fibrous pulp additionFiberPulp and paper industry
An antiforge fibrk is disclosed, which features that it has opposite two surfaces with different colours. An antiforge paper using the said antiforge fibre features that one surface of the said antiforge filbre can be seen on one surface of the paper and another surface of the said antiforge fibre can be seen on another surface of the paper. Its advantage is high visually antiforge effect.
Owner:孙显林
Plant leave identification method based on android system
InactiveCN105631451AImprove recognition accuracyHigh speedCharacter and pattern recognitionNetwork connectionStart up
The invention discloses a plant leave identification method based on an android system. The plant leave identification method comprises steps of establishing network connection with a server terminal when the server terminal allow the access by an ARM device, receiving the image to be identified by an ARM device, extracting the leave part of the image to be identified and performing pre-processing, transmitting a service request after processing is finished, receiving and analyzing the service request of the ARM device terminal by the server terminal, starting up a recognition function module of a server terminal, responding the recognition request of the ARM device terminal to perform the leave identification, returning the identification result of the plant leave to the ARM device terminal after the recognition is finished, and obtaining the plant leave identification result transmitted by the server terminal by the ARM device and displaying the result. Compared with the prior art, the invention is wide in application field, high in identification accuracy, fast in speed, simple in operation and convenient in usage.
Owner:TONGJI UNIV
Method, device and apparatus for segmenting characters in video and computer storage medium
InactiveCN109543560AReduce labor costsSimplify identification stepsCharacter and pattern recognitionPattern recognition
Owner:BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Abnormal traffic light recognition method and device, equipment and computer storage medium
ActiveCN110533940ASimplify identification stepsRecognition Efficiency SimplifiedRoad vehicles traffic controlTraffic signalState sequence
The invention provides an abnormal traffic light recognition method and device, equipment and a computer storage medium in the field of automatic driving technologies. The method comprises the steps that a state sequence of a traffic light which a vehicle is about to pass by in a travel process is acquired; the state sequence of the traffic light is matched with preset abnormal characteristics, and when a matching result is acquired, it is determined that the traffic light is an abnormal traffic light; and position information of the abnormal traffic light is acquired and recorded. Through themethod, recognition steps of the abnormal traffic light can be reduced, and recognition efficiency of the abnormal traffic light is improved.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD
Method for identifying maize haploids
ActiveCN107278873AFast and efficient identificationSimplify identification stepsMaterial analysis by optical meansHybridisationAlgorithmTransmittance
The invention discloses a method for identifying maize haploids. The method for identifying maize haploids provided by the invention comprises the following steps: (1) taking whether each corn kernel in a training set is a real haploid or a real diploid as a dependent variable, taking a near-infrared transmittance spectroscopy absorption value of each corn kernel as an independent variable, and establishing a haploid identification model by using a machine learning algorithm, wherein the training set is composed of a plurality of corn kernels, one part of the corn kernels are the real haploids, and the other part of the corn kernels are the real diploids; and (2) taking to-be-detected corn kernels, acquiring the near-infrared transmittance spectroscopy absorption values, inputting the absorption values into the haploid identification model established in the step (1), and outputting the result that the to-be-detected corn kernels are predicted haploids or predicted diploids by the model. The method provided by the invention can be used for automatic identification and has significances for promoting the maize haploid breeding technique engineering.
Owner:CHINA AGRI UNIV
End-to-end license plate correction and recognition method
PendingCN114067300ASimplify identification stepsGuaranteed recognition accuracyCharacter and pattern recognitionNeural architecturesImaging processingFeature extraction
The invention discloses an end-to-end license plate correction and recognition method, and belongs to the technical field of image processing. The method comprises the steps of obtaining a license plate image, and taking the license plate image as the input of a license plate correction and recognition fusion model which comprises a backbone network, a license plate correction head and a license plate character recognition head, wherein the license plate correction head and the license plate character recognition head share the backbone network; the backbone network performs multi-scale low-level and high-level feature extraction and fusion on the license plate image to obtain a license plate feature map F; the license plate correction head performs license plate correction based on the license plate feature map F to obtain a corrected license plate; and the license plate character recognition head recognizes license plate characters based on the license plate feature map F. According to the invention, the license plate correction step and the license plate recognition step are fused into an end-to-end deep learning model, so that the recognition precision of a difficult license plate is improved while the license plate correction step is simplified.
Owner:ANHUI TSINGLINK INFORMATION TECH
Formula identification method and device
PendingCN111046751ASimplify identification stepsShorten recognition timeCharacter and pattern recognitionMachine learningHandwritingEngineering
The invention provides a formula identification method and device. The method comprises the steps of obtaining to-be-processed data; extracting handwriting features of the to-be-processed data; generating a user behavior chain corresponding to the to-be-processed data according to the input sequence of strokes in the to-be-processed data and the handwriting features, wherein the user behavior chain is used for indicating a time sequence relationship between symbols in the to-be-processed data; and inputting the user behavior chain into a preset formula identification model, and outputting a formula identification result of the to-be-processed data. The method comprises the steps of generating a user behavior chain capable of indicating a time sequence relationship between symbols in to-be-processed data according to an input sequence and handwriting characteristics of strokes in the to-be-processed data; inputting the user behavior case into a preset formula recognition model, outputting a formula recognition result by the formula recognition model, indicating a time sequence relationship through a user behavior chain, and considering the time sequence of the formula in the recognition process, so as to simplify the recognition steps, shorten the recognition time and improve the recognition accuracy.
Owner:HUAZHONG NORMAL UNIV
Radio Signal Modulation Recognition Method Based on Multiscale Convolutional Neural Network
ActiveCN107979554BOvercome the disadvantage of requiring a lot of prior knowledgeImprove universalityPhase-modulated carrier systemsSignal classificationCorrelation function
The invention discloses a multi-scale convolutional neural network based radio signal modulation identification method. The multi-scale convolutional neural network based radio signal modulation identification method comprises the steps of (1) generating a processed radio modulation signal; (2) generating a two-dimensional time-frequency diagram and performing Fourier transform on an instantaneouscorrelation function of the signal to obtain a Wigner-Ville time-frequency distribution diagram of the signals; (3) performing pre-processing on the time-frequency distribution diagram to generate atraining sample set and a test sample set; (4) building a multi-scale convolutional neural network module and training the model; and (5) testing the test set by utilizing the trained network model, calculating the correction rate, obtaining an identification accuracy rate and assessing the network performance. The multi-scale convolutional neural network based radio signal modulation identification method has the advantages of strong universality, no need for manual characteristic extraction and a plenty of priori knowledge, low complexity and accurate and stable classification results, and can be used in the field of signal classification identification technologies.
Owner:XIDIAN UNIV
A vehicle driving license picture self-adaptive correction and identification method
PendingCN112464852ASave human effortQuick and accurate identificationImage enhancementImage analysisComputer graphics (images)Engineering
The invention relates to the field of information identification, in particular to a vehicle driving license picture self-adaptive correction and identification method. According to the invention, thedriving license is photographed, the red seal is positioned by using the deep neural network for the photographed picture, the front page of the driving license is corrected and extracted based on the position state of the red seal, the front page of the driving license is processed by using multiple custom algorithms based on Hough transform, and the driving license information is identified byusing the Tesseract-OCR engine. According to the method, manpower is saved, the information of the driving license can be quickly and accurately identified automatically by utilizing a computer, the influence of noise, unclear pictures, large color difference of a shooting camera, black and vertically-arranged anti-counterfeiting lines on the front page of the driving license and colors on information identification can be eliminated, the shooting background of the driving license does not need to be considered, and the invention has excellent accuracy and high robustness.
Owner:CHONGQING UNIV
Lithology identification method based on machine learning
PendingCN114462471AImprove recognition efficiencyImprove accuracyCharacter and pattern recognitionMachine learningLithologyData set
The invention belongs to the technical field of lithology identification, and discloses a lithology identification method based on machine learning, comprising the following steps: acquiring a drilling machine historical operation data set, and normalizing the drilling machine historical operation data set to obtain a processed historical operation data set; according to the processed historical operation data set, an engineering blasting lithology identification model is established based on machine learning; real-time operation data of the drilling machine are obtained, normalization processing is conducted on the real-time operation data of the drilling machine, and processed real-time operation data are obtained; and inputting the processed real-time operation data into an engineering blasting lithology identification model for lithology identification to obtain a corresponding lithology identification result. The method solves the problems of low recognition precision, lack of sample data, complex steps, large workload, large hardware cost investment and low practicability in the prior art.
Owner:NORTH BLASTING TECH
A method for distinguishing maize haploid
ActiveCN107278873BFast and efficient identificationSimplify identification stepsMaterial analysis by optical meansHybridisationAlgorithmGenetics
The invention discloses a method for identifying maize haploids. The method for identifying maize haploids provided by the invention comprises the following steps: (1) taking whether each corn kernel in a training set is a real haploid or a real diploid as a dependent variable, taking a near-infrared transmittance spectroscopy absorption value of each corn kernel as an independent variable, and establishing a haploid identification model by using a machine learning algorithm, wherein the training set is composed of a plurality of corn kernels, one part of the corn kernels are the real haploids, and the other part of the corn kernels are the real diploids; and (2) taking to-be-detected corn kernels, acquiring the near-infrared transmittance spectroscopy absorption values, inputting the absorption values into the haploid identification model established in the step (1), and outputting the result that the to-be-detected corn kernels are predicted haploids or predicted diploids by the model. The method provided by the invention can be used for automatic identification and has significances for promoting the maize haploid breeding technique engineering.
Owner:CHINA AGRI UNIV
A method for quality detection of Zaoren Anshen capsules based on thin-layer chromatography
ActiveCN113109495BImprove quality controlEasy to prepareComponent separationPreparing sample for investigationMedicinal herbsSalvianolic acid B
The invention relates to a method for detecting the quality of Zaoren Anshen Capsules based on thin-layer chromatography. A , salvianolic acid B, schisandrin A, schisandrin A and other seven main active ingredients were qualitatively detected, specifically including the preparation of the test solution, the preparation of the reference solution, the preparation of the reference medicinal material solution and TLC retrieval steps. By optimizing the preparation method and development conditions of the test sample for Zaoren Anshen Capsule TLC, the simultaneous detection of the whole medicinal flavor of the compound was realized on one TLC board, which simplified the identification steps, improved the identification efficiency, and promoted the development of Zaoren Anshen Capsules. overall quality control.
Owner:PEKING UNIV
Primer pairs and kit for identifying mating type of Coriolopsis trogii protoplast monokaryon and application of primer pairs
ActiveCN112126701AFast and accurate identificationSimplify identification stepsMicrobiological testing/measurementDNA/RNA fragmentationBiotechnologyGenomics
The invention discloses primer pairs and kit for identifying the mating type of Coriolopsis trogii protoplast monokaryon and an application of the primer pairs. The invention discloses two primer pairs PMD_1 and PMD_2 for identifying the mating type of the Coriolopsis trogii protoplast monokaryon. According to the invention, genomic DNA of the to-be-identified Coriolopsis trogii protoplast monokaryon is used as a template, the primers PMD_1 and PMD_2 are used for amplification, and the mating type of the Coriolopsis trogii protoplast monokaryon is determined according to the size of a PCR product obtained by detection. The method provided by the invention is simple and easy to implement, shortens the identification time, simplifies the identification steps, has high accuracy, and can be suitable for research in the related fields of genetic breeding, genomics and the like of edible and medicinal fungi, especially Coriolopsis trogii.
Owner:广东省科学院生物与医学工程研究所
Underwater sound source target detection, identification and positioning method and device based on millimeter wave radar
PendingCN121955971ALarge range underwater target detectionLarge-scale surveillancePosition fixationRadio wave reradiation/reflectionSound sourcesEngineering
The invention discloses an underwater sound source target detection, identification and positioning method and device based on a millimeter wave radar, and belongs to the technical field of underwater target detection, identification and positioning. The method comprises the following steps: acquiring a water surface echo signal by using a millimeter wave radar, and performing Fourier transform to obtain a distance-time spectrum; extracting a slow time phase sequence of each range gate in a radar beam coverage range, and obtaining a sound-induced water surface vibration signal after unwinding and filtering; performing correlation calculation on the vibration signal and a preset target feature library, or realizing target recognition through a deep learning model; a multi-radar cooperation or single-radar digital beam forming technology is adopted for target positioning, and large-range water area searching is achieved. According to the invention, the millimeter-wave radar is used for detecting micron-sized water surface vibration with high phase sensitivity, the defects of short distance, complex arrangement and the like of traditional acoustic and optical detection are overcome, and the system has large-range, real-time and non-contact underwater target detection and positioning capability.
Owner:齐鲁空天信息研究院
Quick identification method and device for two-parameter time domain electromagnetic weak polarization effect
PendingCN110907997AQuick identificationImprove accuracyElectric/magnetic detectionAcoustic wave reradiationParticle physicsTime domain electromagnetics
The invention relates to a quick identification method and device for a two-parameter time domain electromagnetic weak polarization effect, and aims at solving the problems that weak polarization response characteristics in time domain electromagnetic detection data are difficult to identify, the interpretation precision is low and the like. Two parameters which have the greatest influence on a polarization identification result are screened; a polarization effect rapid classification model is established based on a support vector machine by taking the parameter with the maximum influence as input and whether polarization occurs or not as output; and rapid identification is carried out on the measured data through a polarization effect rapid classification model. According to the method, the weak polarization response in electromagnetic detection can be quickly and accurately recognized only by extracting the two parameters, and the accuracy of electromagnetic data interpretation is improved.
Owner:JILIN UNIV
QPSK (quadrature phase shift keying) signal and OQPSK (offset quadrature phase shift keying) signal recognition method
ActiveCN104639268ASimplify identification stepsEasy to operatePropogation channels monitoringPhase shiftedPhase difference
The invention provides a QPSK (quadrature phase shift keying) signal and OQPSK (offset quadrature phase shift keying) signal recognition method, which comprises the following steps that an instant phase is extracted from I / Q signals subjected to down-conversion; the phase difference of adjacent code elements is calculated on the basis of the instant phase; center normalization instant phase difference is calculated on the basis of the phase difference of the adjacent code elements; the absolute value standard deviation of the center normalization instant phase difference is calculated on the basis of the center normalization instant phase difference; the signal recognition is carried out according to the absolute value standard deviation, signals with the deviation greater than zero are QPSK signals, and signals with the deviation equal to zero are OQPSK signals. The technical scheme has the advantage that the QPSK signals and the OQPSK signals can be simply, conveniently and effectively recognized.
Owner:NO 50 RES INST OF CHINA ELECTRONICS TECH GRP
Primer pair, kit and application thereof for identifying mating type of protoplast monokaryon
ActiveCN112126701BSimplify identification stepsShorten identification timeMicrobiological testing/measurementDNA/RNA fragmentationBiotechnologyGenetics genomics
Owner:广东省科学院生物与医学工程研究所
Object recognition method and device
PendingCN112926683AAccurate identificationSimplify identification stepsImage analysisCharacter and pattern recognitionRadiologyNuclear medicine
Owner:CHINA CONSTRUCTION BANK
Tower signboard structural data obtaining method and device and electronic equipment
PendingCN112560586ASimplify identification stepsImprove recognition efficiencyImage enhancementImage analysisEngineeringIdentification plate
One or more embodiments of the invention provide a tower signboard structured data obtaining method and device and electronic equipment. The obtaining method comprises the steps of obtaining an original image; inputting the original image into a pre-trained target detection model to obtain a tower signboard image, identification information in the tower signboard image and a content sideline in the tower signboard image; obtaining the type of the tower signboard image according to the position relationship between the identification information; calculating the geometric transformation precision of the tower signboard image according to the content side boundary; and outputting the identification information, the type and the geometric transformation precision of the tower signboard. According to the embodiment of the invention, through the pre-trained target detection method, the signboard can be positioned and identified at the same time, the identification steps are simplified, andthe identification efficiency of the signboard structured data is effectively improved.
Owner:国家电网有限公司大数据中心 +1
A method and device for identifying cable partial discharge signals based on s-transform
ActiveCN106778692BSimplify identification stepsImprove recognition accuracyCharacter and pattern recognitionSingular value decompositionFeature vector
Owner:ZHUHAI POWER SUPPLY BUREAU GUANGDONG POWER GIRD CO
Identification method of qpsk signal and oqpsk signal
ActiveCN104639268BSimplify identification stepsEasy to operatePropogation channels monitoringPhase shiftedPhase difference
The invention provides a QPSK (quadrature phase shift keying) signal and OQPSK (offset quadrature phase shift keying) signal recognition method, which comprises the following steps that an instant phase is extracted from I / Q signals subjected to down-conversion; the phase difference of adjacent code elements is calculated on the basis of the instant phase; center normalization instant phase difference is calculated on the basis of the phase difference of the adjacent code elements; the absolute value standard deviation of the center normalization instant phase difference is calculated on the basis of the center normalization instant phase difference; the signal recognition is carried out according to the absolute value standard deviation, signals with the deviation greater than zero are QPSK signals, and signals with the deviation equal to zero are OQPSK signals. The technical scheme has the advantage that the QPSK signals and the OQPSK signals can be simply, conveniently and effectively recognized.
Owner:NO 50 RES INST OF CHINA ELECTRONICS TECH GRP
Method of identifying external electronic device based on power information and electronic device and storage medium for supporting same
PendingCN112639751ASimplified steps for device identificationShorten communication timeDigital data processing detailsData switching current supplyEmbedded systemEngineering
An electronic device is provided. The electronic device includes a connector including one or more signal terminals for communication with an external electronic device, at least one processor operatively connected to the connector, and a memory operatively connected to the processor, the memory stores instructions, when executed by the at least one processor, cause the at least one processor to identify a connection to the external electronic device through the connector, receive one or more pieces of information about power that is supported by the external electronic device from the external electronic device in the connection to the external electronic device through the connector, and identify the external electronic device, based on a part of the one or more pieces of power information. Other embodiments are possible.
Owner:SAMSUNG ELECTRONICS CO LTD
Method for quickly identifying Ligusticum sinense based on electronic nose
ActiveCN112710795AQuick judgmentHigh speedComponent separationGas analyser construction detailsEngineeringMechanical engineering
The invention relates to a method for quickly identifying Ligusticum sinense based on an electronic nose, which comprises the following steps: (1) respectively pulverizing a certain amount of Ligusticum sinense, ligusticum wallichii and a mixture of Ligusticum sinense and ligusticum wallichii mixed according to a gradient ratio to obtain a plurality of samples; (2) turning on an electronic nose instrument, wherein the electronic nose comprises a plurality of sensors, setting the parameters of the electronic nose as follows: the gas flow rate is 0.5-0.7 L / min, the cleaning time is 160-200s, the detection time is 100-150s, and starting sample introduction determination at 15-30 DEG C to obtain data of each sample in each sensor of the electronic nose; (3) finding out a group of data with the highest significance corresponding to different samples in different sensors, and taking the sensor corresponding to the group of data as a subsequent electronic nose detection sensor, grinding a sample to be detected into powder, and measuring the detection data of the sample to be detected in the sensor according to the conditions in the step (2); and (4) identifying the to-be-detected sample by taking the group of data with the highest significance as characteristic reference values according to the detection data of the electronic nose. The method is simple to operate, identification steps are simplified, and identification time is shortened.
Owner:江西景德中药股份有限公司
A method and device for realizing telephone transfer according to language
ActiveCN104580762BGuaranteed recognition accuracySimplify identification stepsSpecial service for subscribersSpeech recognitionHuman languageLanguage identification
The invention discloses a method and device for realizing telephone transfer according to language. The method comprises steps: the call center server transfers the called party to the first seat phone, and records the conversation process within a period of time; adopts the first The first recording file is identified and judged by the language recognition method; the first recording file is recognized and judged by the second language recognition method; after the caller completes the call, the caller is prompted and receives the feedback information of the caller; the caller hangs up, The call center server records the calling number and the corresponding agent phone number. The beneficial effect of implementing the method and device of the present invention is that it can be automatically transferred to the service group of the same language according to the language used by the customer. At the same time, the double language identification method is adopted, which not only ensures the accuracy of the calling language identification, but also simplifies the common The step of language recognition saves system resources of the call center.
Owner:SHENZHEN SEG SCI NAVIGATIONS CO LTD
Antiforge fibre and antiforge paper using it
InactiveCN1170034CEasy to identifyOvercome the defect of being easily counterfeited by printing methodsNon-fibrous pulp additionFiberPulp and paper industry
An antiforge fibrk is disclosed, which features that it has opposite two surfaces with different colours. An antiforge paper using the said antiforge fibre features that one surface of the said antiforge filbre can be seen on one surface of the paper and another surface of the said antiforge fibre can be seen on another surface of the paper. Its advantage is high visually antiforge effect.
Owner:孙显林
Primer pairs and kit for identifying mating type of ganoderma lucidum protoplast monokaryon and application of primer pairs
PendingCN112126700AFast and accurate identificationSimplify identification stepsMicrobiological testing/measurementMicroorganism based processesGenomicsGenomic DNA
The invention discloses primer pairs and kit for identifying the mating type of ganoderma lucidum protoplast monokaryon and an application of the primer pairs. The invention discloses three groups ofprimer pairs Glpm_1, Glpm_2 and Glpm_3 for identifying the mating type of the ganoderma lucidum protoplast monokaryon. According to the invention, genomic DNA of the ganoderma lucidum protoplast monokaryon to be identified is used as a template, the primers Glpm_1, Glpm_2 and Glpm_3 are used for amplification, and the mating type of the ganoderma lucidum protoplast monokaryon is determined according to the size of a PCR product obtained by detection. The method provided by the invention is simple and easy to implement, shortens the identification time, simplifies the identification steps, hashigh accuracy, and can be suitable for research in the related fields of genetic breeding, genomics and the like of edible and medicinal fungi, especially ganoderma lucidum.
Owner:GUANGDONG ACAD OF SCI INST OF BIOENGINEERING
A method for rapid identification of Chaxiong tea based on electronic nose
ActiveCN112710795BQuick judgmentHigh speedComponent separationGas analyser construction detailsBiotechnologyMedicine
The present invention relates to a method for quickly identifying Chaxiong based on an electronic nose, comprising: (1) powdering a certain amount of Chaxiong, Chuanxiong, and a mixture of Chaxiong and Chuanxiong mixed in gradient proportions to obtain multiple samples; (2) opening Electronic nose instrument, the electronic nose contains multiple sensors; set the parameters of the electronic nose to the gas flow rate of 0.5-0.7L / min, the cleaning time of 160-200s, the detection time of 100-150s, and start the sample injection measurement at 15-30°C. Obtain the data of each sample in each sensor of the electronic nose; (3) Find out a group of data with the highest significance corresponding to different samples in different sensors, and use the sensor corresponding to this group of data as the subsequent electronic nose detection sensor; The test sample is powdered and the detection data of the test sample in the sensor is determined according to the conditions of step (2); (4) According to the electronic nose detection data and a set of data with the highest significance as the characteristic reference value, identify the test sample . The invention has simple operation, simplifies identification steps and shortens identification time.
Owner:江西景德中药股份有限公司
Method, device and equipment for identifying abnormal traffic lights in automatic driving
ActiveCN110533940BSimplify identification stepsRecognition Efficiency SimplifiedRoad vehicles traffic controlTraffic signalSimulation
The present invention provides a method, device, device and computer storage medium for identifying abnormal traffic lights in the technical field of automatic driving. The state sequence is matched in the preset abnormal features, and when the matching result is obtained, it is determined that the traffic signal is an abnormal traffic signal; the position information of the abnormal traffic signal is obtained and recorded. The invention can simplify the identification steps of abnormal traffic lights and improve the identification efficiency of abnormal traffic lights.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD