92results about How to "Achieve discrimination" patented technology

A multilane free-flow electronic toll collection method based on accurate position match is characterized in that electronic tag positioning and vehicle position detected results are matched to achieve multilane free-flow electronic toll collection. The method comprises the following steps: 1, obtaining vehicle-mounted electronic tag positions, vehicle positions and vehicle images to perform electronic on-stream toll collection; 2, accurately matching the vehicle-mounted electronic tag positions and the vehicle positions to distinguish legal vehicles and illegal vehicles; and 3, performing background data processing, storing images, license numbers and illegal passing records of the illegal vehicles to be used as the basis of toll collection. By accurately matching the vehicle detected results and electronic tag positioning results, the judgment of the legal vehicles and the illegal vehicles is achieved, and accordingly the multilane free-flow electronic toll collection is achieved.

The invention provides an intrusion prevention system of fiber grating perimeter and an alarm method thereof; the system comprises a piece of on-site optical fiber detecting equipment and a piece of control equipment; the on-site optical fiber detecting equipment comprises detecting passages, and each detecting passage comprises cascaded optical fiber vibration detectors; the control equipment comprises a fiber grating signal demodulator and an alarm management computer, which are connected with each other; and the detecting passages are connected with the fiber grating signal demodulator. The alarm method comprises the steps of: firstly, updating a fiber grating wavelength reference value; and then, performing time domain processing on the wavelength sequences received by the fiber grating signal demodulator to distinguish the operation states of the optical fiber vibration detectors, and entering a pre-alarm state if the operation states of the detectors are normal and an abnormal signal is captured; and distinguishing the frequency domain of the wavelength information of the abnormal signal at the pre-alarm state, and retaining the effective illegal intrusion behavior information to finish the alarm process. The intrusion prevention system of the invention has the advantages of high sensitivity, good alarm performance and low false alarm rate.

The present invention provides a system for automatically detecting the redundant object of the spaceflight electronic device and a detecting method. The system comprises the following components: a sound sensor 1, a rotating platform 2, a crank-rocker mechanism 3, an IO*amp;DA board card 4, a transducer 5, a three-phase machine 6, a sound signal regulating circuit 7, a real-time data collection card 8 and an upper machine processor 9. The sound sensor is adhibited on the external wall of the detected pice. The sound sensor 1 is connected with the sound signal regulating circuit 7 through a signal wire. The sound signal regulating circuit 7 is connected to the real-time data collection card 8. The real-time data collection card 8 is connected with the upper machine processor 9. The upper machine process 9 is connected with the control end of the transducer 5 through the IO*amp;DA board card 4. The transducer 5 is connected to the three-phase machine 6 which drives the rotating platform 2 through the crank-rocket mechanism 3. The invention settles the problems of no high detecting precision, no strong objectivity, no realization for automatic detection or automatic determining, only determination to the existence of the redundant particle, no determination to the material and characteristic of the redundant object and the like in the existing traditional PIND detection method.

The invention discloses a method and a system for monitoring garbage messages and a monitor processing apparatus. The method for monitoring garbage messages comprises the steps of receiving relevant information of the message sent by an external network element, determining the message is a garbage message or not based on a homophonic tone character rule or a homographic character rule, sending a feedback to the external network element to intercept the message if the message is a garbage message and sending a feedback to the external network element to issue the message if the message is not a garbage message. According to the invention, a character coupling is carried out with the pinyin of the message to be monitored and the pinyin of keywords to realize discriminating and intercepting garbage messages using homophonic tone characters and another character coupling is carried out with the message to be monitored and the variation fonts of the keywords to realize discriminating and intercepting garbage messages. Meanwhile, an acceptance and rejection list and short message flow control are combined to make the monitor more comprehensive so that the phenomenon of missing examinations is effectively prevented.

The invention relates to a vehicle overload automatic identification system, comprising a load transducer, a PC apparatus, a road port, a CCD cam, an image and data acquisition card. The output signal from load transducer, which is buried in advance in road paort, is lead out from a load transducer via preseted signal cable conductor, then a CCD cam gathers vehicle front and rear outline picture, while an image and data acquisition card pre-processes image signals and pressure sensing signals. The pressure load signals from a preseting signal cable conductor and image singals from picture video cable conductor of CCD cam are separately connected to analog signal ingate of image and data gathering cards and video signal ingate, while an image and data gathering card is connected to a PC apparatus via PCI bus.

The invention discloses a method for distinguishing a transformer magnetizing rush current based on weight mathematical morphology. The method comprises the following steps: (1) collecting a difference current signal of current transformers on two sides of a transformer differential protection according to a certain sample frequency, (2) judging whether a break variable among a plurality of continuous sampling values is larger a preset break variable limit value, if yes, collecting data of a half circle in a delayed mode and carrying out a step (3), or, continuing sampling, (3) selecting a data widow as a difference current signal value with the length of a half fundamental frequency, carrying out processing on the weight mathematical morphology and obtaining a processed signal waveform, and (4) obtaining a wave-shaped correlation coefficient, judging whether the wave-shaped correlation coefficient is smaller than a preset setting value of the wave-shaped correlation coefficient, if yes, judging that the interior of a transformer breaks, or, distinguishing the transformer magnetizing rush current. The method has the advantages of being simple in steps, small in calculated quantity, short in delayed time, easy to implement, strong in generality and the like.

The invention discloses a multi-dimensional time sequence classification method based on mahalanobis distance DTW, and relates to the multi-dimensional time sequence classification method. In order to solve the problems that aiming at satellite telemetry data, a fixed point segmentation effect is non-ideal, due to the facts that relativity exists between multi-dimensional time sequences and small deviation exists between the time sequences, a measuring result is not accurate, therefore a classification result is not accurate, and the multi-dimensional time sequence classification method based on the mahalanobis distance DTW is provided. The method comprises the steps that 1 a multi-dimensional time sequence X={x <1>, x <2>, ..., x<j>, ..., x<n>} used for training and a classification label L={l<1>, l<2>, ..., l<n>}are obtained; 2 a to-be-classified multi-dimensional time sequence X'={x' <1>, x' <2>, ..., x'<j>, ..., x'<n>} is extracted; 3 a DTW distance sequence between the X'={x' <1>, x' <2>, ..., x'<j>, ..., x'<n>} and the X={x <1>, x <2>, ..., x<j>, ..., x<n>} is calculated; 4 classification is conducted on the to-be-classified multi-dimensional time sequence X'={x' <1>, x' <2>, ..., x'<j>, ..., x'<m>} according to neighboring numbers of K which is set by using a KNN classification method based on the mahalanobis DTW distance, and the classification of the to-be-classified multi-dimensional time sequence is determined. The method is applied to the field of multi-dimensional time sequence classification.

Provided is a satellite orbit gesture visual three-dimensional displaying method. The satellite orbit gesture visual three-dimensional displaying method comprises the steps: (1) building a three-dimensional model, reading a 3DS model in a database, checking whether models are complete or not, sending the 3DS model to a state display if the models are complete, and if the models are not complete, building relevant models, and sending a data request data package to a server and receiving the data request data package at the same time; (2) checking and comparing data in the data package, finding out data needed by the state display, analyzing the data, and dividing the data into two parts, wherein one part of data are ground equipment data, and the other part of data are on-star remote sensing data; (3) for the ground equipment data, extracting time information, calculating sun and moon ephemeris, and calculating the positions of the sun, the earth and the moon, satellite orbit data and the like to be sent to the state display; (4) for the on-star remote sensing data, classifying the data into three types to be displayed, wherein one type of data are health state data, one type of data are component power source state data, and another type of data are gesture information. The state display adopts the OpenGL to carry out three-dimensional model drawing and display.

The invention belongs to the technical field of detecting equipment of soil tests and in particular relates to an automatic detecting and metering device and an automatic detecting and metering method for rock-soil permeability. The device comprises an automatic compensation water tank and a permeameter communicated with the automatic compensation water tank, wherein the permeameter is connected with at least one measuring cylinder unit; the measuring cylinder unit is provided with a vertically arranged measuring cylinder with uniform inside diameter; floaters capable of floating with the ascending of the liquid level are arranged in the measuring cylinder; a plurality of liquid level position sensors capable of sensing the positions of the floaters are arranged on the wall of the measuring cylinder at intervals; and the liquid level position sensors are connected with a programmed electronic control unit. Through the device and by the method, a variable head permeability test function can be realized; the test process completely satisfies the relative national standard and industrial standard regulation; the device can continuously work for 24 hours to automatically detect the record; the batch detection working efficiency of the permeability test is fully improved; and the labour intensity of workers, the detecting work cost and the influence of detection personnel on the detection result is reduced.

The invention relates to an aerial target classification method based on wind field disturbance characteristics. The method includes steps of resolving wind field disturbance characteristics; accurately extracting the wind field disturbance characteristic parameters of trailing vortex core position, vortex core radius, vortex core spacing and vortex circulation by an algorithm for resolving wind field disturbance characteristics of an aerial target; inversing type identification characteristics; inversing to obtain type identification characteristic parameters of target track characteristics, physical characteristics and motion characteristics by an algorithm of inversing the type identification characteristics of the aerial target; identifying attribute of the aerial target; and outputting the type attribute of a plane target to be identified by inputting the type identification characteristic parameters of the plane target to be identified. Extraction of wind field disturbance characteristics of the aerial target is achieved, inversion of the wind field disturbance characteristics to target characteristics is achieved, and the aerial plane target is classified and identified on the basis of laser radar detection for specific airspace atmospheric wind fields.

The invention discloses a cancer image prediction and discrimination method and system based on transfer learning. The method comprises two parts of training of a transfer learning model and image classification based on the transfer learning model. The first part comprises construction of a transfer learning model, construction of a data set and training and storage of the transfer learning model, and the second part comprises the steps: inputting an image to be judged for category prediction by loading a transfer learning classification model stored in the first part. The system comprises atleast one processor; at least one memory which is used for storing at least one running program and the to-be-identified medical image; when the program runs in the processor, at least one processoris enabled to realize prediction and identification of the medical image. The method and system are used for intelligent analysis and discrimination of medical image big data, and provides rapid and relatively accurate medical auxiliary diagnosis, thereby improving the accuracy and efficiency of clinical diagnosis.

The invention discloses a 6LoWPAN-based intelligent fire-fighting service system for colleges and universities and a design method of the 6LoWPAN-based intelligent fire-fighting service system. The service system comprises a data acquisition layer, a data transmission layer, a data control layer and a system application layer, good interoperability of the 6LoWPAN can solve information isolation, the 6LoWPAN supports the intercommunication with other IEEE (Institute of Electrical and Electronic Engineers) 802.15. 4 equipment and supports the interconnection with other IP networks; through designing a data control layer based on fire-fighting big data, intelligentized analysis of data, intelligent control on fire-fighting equipment, a visual service platform is established; through analyzingand mining fire-fighting big data, the fire situation is predicted and a solution is formulated, the fire prevention and control efficiency is improved, the intelligence of a service platform is realized, the purposes of equipment management centralization, fire-fighting construction underlying data management intellectualization and management system platformization are achieved, and the systemhas the characteristics of high feasibility, convenience in networking and easiness in maintenance and upgrading.

The invention provides a detection and recognition device for sprayed codes on the cylindrical surfaces of copper rings. The detection and recognition device comprises an industrial display screen, a left conveying belt mechanism, a servo sliding table mechanism, a right conveying belt mechanism, an industrial computer, an article grasping clamping air cylinder, an image collecting mechanism, light source equipment, a rejected product receiving box, a qualified product receiving box, a removing mechanism and a rotating mechanism. According to the detection and recognition device for sprayed codes on the cylindrical surfaces of copper rings, the machine vision technology is adopted to detect and recognize sprayed code character information on the cylindrical surfaces of copper rings, and the defects of low precision, high subjectivity, low judgment efficiency, high missed detection rate and false detection rate and the like of traditional manual detection are overcome; the automation degree is high, and automatic recognition and automatic sorting of sprayed codes on the cylindrical surfaces of copper rings can be completed. The invention further provides a detection and recognition method for sprayed codes on the cylindrical surfaces of copper rings. By means of the detection and recognition method, irregular sprayed code information on the cylindrical surfaces of copper rings on a production line can be continuously and automatically collected and distinguished, and the detection and recognition method is especially suitable for handling recognition of fuzzy and irregularly-shaped characters on the cylindrical surfaces and is high in detection and recognition rate.

The invention discloses a secondary cable checking method for a transformer substation. The secondary cable checking method for the transformer substation comprises the following steps: a, optionally selecting a cable core from a cable to be corrected as a public end, and diodes are respectively and oppositely connected at the end parts of the cable cores except the public end in series according to the predetermined service regulation numbers and in the same conducting direction; and b, testing the current value of each of the cable cores with the current range of a universal meter, determining the numbers of the cable cores corresponding to the corresponding measurement results of the current values according to the measurement results of the current values of different cable cores, and then taking corresponding corrective actions. The secondary cable checking method for the transformer substation can overcome the disadvantages that the cable checking method is greatly affected by environment and the accuracy is low in the prior art and realize the advantages that the cable checking method is lightly affected by environment, and the accuracy is high.

The invention provides a lighting control device and system, and relates to the technical field of household appliances. The lighting control device comprises an image collector, an image processor, a light controller and an illumination lamp group which are connected to each other in turns, wherein the illuminating lamp group comprises a plurality of lighting lamps positioned at different positions of a scene environment, and the image collector is used for collecting images of the scene environment; the image processor is used for conducting visual perception processing of the captured images, and dividing the images into person's areas and no person's areas; the light controller is used for adjusting the brightness of the illumination lamps corresponding to the person's areas and the brightness of the illumination lamps corresponding to the no person's areas, thereby effectively saving the use of energy in the scene environment.

The invention discloses a human vision-based image identification method. According to the method, an image identification structure capable of realizing cross-problem domain identification is established based on deep learning and human vision. By applying the model structure, images of a plurality of problem domains of a model can be identified, and a human vision system is further simulated. An original image is directly subjected to characteristic extraction by utilizing the property of human visual perception, namely, an HMAX method, so that heavy and complicated preprocessing steps are reduced and the calculation efficiency and feasibility of the method are improved. The number of parameters in the deep learning is reduced through an SDA (Stacked Denoising Autoencoder) method, so that the universality of an algorithm is enhanced and the training performance of general feed-forward BP is improved. An actual experimental result shows that the classification accuracy of the method is higher than that of other classification methods. Therefore, the method is an efficient and feasible image identification method, and has universal applicability in the field of image identification.

The invention relates to the technical field of blockchain, and discloses an account transfer method for preventing tracking of a transaction transfer-out party, which comprises the following steps that: during an account transfer transaction, generating real transaction information between the transaction transfer-out party PartyX and a transaction transfer-in party PartyM by a transaction transfer-out party PartyX; introducing n virtual transaction transfer-out parties PartyN, and generating virtual transaction information corresponding to a virtual transaction amount b between the virtual transaction transfer-out parties PartyN and the transaction transfer-in parties PartyM; generating a secret key KeyN which can be decrypted by a transaction transfer-out party PartyX, a virtual transaction transfer-out party PartyN and a transaction transfer-in party PartyM by a Pairing algorithm; and publishing the real transaction information and the virtual transaction information to the blockchain. The invention further discloses an account transfer device and equipment for preventing the transaction transfer-out party from being tracked and a computer readable storage medium. According tothe method, the purpose of hiding the identity of the transfer-out party is achieved by using a plurality of virtual transactions, and the transfer-out party of the real transaction can be identifiedonly by the transaction transfer-in party, so that the traceability of the identity of the transaction transfer-out party is ensured.

The invention discloses a GC-IMS pear production place distinguishing method based on an aromatic substance fingerprint spectrum. According to the invention, a headspace gas chromatography-ion mobility spectrometry instrument is used for detecting pears from different producing areas; GC-IMS sample data are obtained; the GC-IMS sample data is subjected to statistical analysis through LAV analysissoftware and GC * IMS Library Search Software qualitative software of the instrument, and GC-IMS fingerprint spectrums of volatile aroma components of the pears from all production places are obtainedfor distinguishing the production places of the pears. The GC-IMS technology is applied to collection and trace analysis of complex aroma substances in the pears from different producing areas, comprehensive fingerprint information is provided for distinguishing the producing areas of the pears, rapid and accurate distinguishing of the producing areas of the pears from different producing areas is achieved, and theoretical basis and data support are provided for identifying and tracing the producing areas of the pears.

The invention relates to an enhanced CT image rectal cancer staging auxiliary diagnosis system based on deep learning. The system comprises an enhanced CT image input module, an enhanced CT image and annotation database, an image preprocessing module, a rectal lesion area discrimination module, a lesion lymph recognition module, a focus feature extraction module, a comprehensive diagnosis module and a visualization module. Aiming at the problems that a rectum enhanced CT image is complex in data structure and difficult to distinguish cancerous areas and stages thereof, the rectum enhanced CT image rectal cancer data labeling and data set construction, rectal cancer lesion area discrimination based on a self-attention deep learning model and metastatic lymph node identification based on sequence adaptive feature fusion are researched. A rectal cancer staging intelligent auxiliary diagnosis system is designed and realized, and clinical application experiment verification is carried out, so that comprehensive data acquisition accuracy and efficiency before a rectal cancer operation are improved.

The invention discloses a vehicle dense target detection method based on deep learning. The method comprises the following steps: S1, constructing and training a multi-scale dimensionality reduction convolution feature extraction network; S2, extracting a multi-scale dimensionality reduction feature map of the to-be-detected image through a multi-scale dimensionality reduction convolution feature extraction network; S3, generating a priori knowledge anchor box based on the historical image; S4, generating all target candidate areas in the to-be-detected image; And S5, carrying out ROIpooling processing on the target candidate area to obtain a detection result with a vehicle dense target. According to the invention, the characteristic of large scale difference of the dense target is considered, and on the basis of the faster-rcnn network, the thought of multi-stage multi-resolution and multi-size dimensionality reduction convolution feature extraction and shape prior-based anchor window generation is provided, so that the detection capability of a multi-scale dense model is improved, the problem of information loss in the existing related detection method is effectively solved, and automatic identification and discrimination of dense targets are realized.

The invention provides an active polarization imaging target discrimination method based on polarization Fresnel reflectivity. According to the method, the zenith angles of the incidence direction and the detection direction are changed to obtain multiple theoretical and real polarization Fresnel reflectivities; related optical constants of a target object are recovered and obtained from the theoretical and real polarization Fresnel reflectivities; and then based on the optical constants, different materials can be distinguished to discriminate the target. The provided method can conveniently and effectively discriminate a target, and at the same time, robustness and universality of polarization in discrimination engineering application are improved.

The invention relates to a method and a system for determining transient voltage stability of a high-proportion new energy power system. The method comprises the following steps: acquiring transient voltage disturbed recovery data of each node in the high-proportion new energy power system after preset fault disturbance; performing discrete wavelet analysis on the transient voltage disturbed recovery data, and determining a wavelet decomposition coefficient of each layer corresponding to each node; determining a comparison threshold value corresponding to each layer; determining the node type of each node according to the wavelet decomposition coefficient of each layer corresponding to each node and the comparison threshold value corresponding to each layer; and when the nodes of which the node types are preset types exist, determining that the transient voltage stability of the high-proportion new energy power system is transient voltage instability. The method can be applied to a dispatching control center, provides decision support for power grid dispatching operation personnel to improve the power grid safety level and the voltage regulation capability and promote new energy consumption, and better guarantees safe and stable operation of a high-proportion new energy power system.

The invention discloses an underground structure crack disease discrimination method based on a deep learning algorithm, and the method comprises the following steps: obtaining optimized initial parameters based on a Mask R-CNN deep learning algorithm, carrying out the deep learning of a large number of underground structure crack images, obtaining an intelligent recognition model of image cracks, and achieving the automatic recognition of any crack. For automatically identified cracks, a skeleton extraction algorithm and a function fitting method are adopted to obtain geometric characteristic parameters such as the length and width of the cracks; and in combination with crack generation reason analysis, underground structure damage grade judgment based on combination consideration of multiple factors such as crack types, the number of cracks in unit area, the maximum crack width and the longest crack length is proposed. The method can effectively realize the intelligentization of crack disease detection of the underground structure, and has the advantages of long distance, no contact, rapidness, convenience and high accuracy.