53results about How to "Realize detection and identification" patented technology

The invention discloses a parking line parking space recognition method and device based on information fusion. The parking line parking space recognition method comprises the steps that a parking space angular point is recognized from an aerial view of the side face of a car body, when the parking space angular point and a camera are parallel, coordinates of the parking space angular point at themoment are recorded, and the parking space angular point is made as the first parking space angular point; an ultrasonic radar of the car starts to detect whether or not a barrier exists in the sidedirection of the car towards the first parking space angular point, if yes, the last step is executed, and if not, the next step is executed; similarly, a second parking space angular point is obtained; according to the two parking space angular points, the approximate parking space width of the parking line parking space and the later distance between the parking line parking space and the car are calculated. Detection recognition for the parking space with standard parking marking lines can be achieved, the ultrasonic radar is used for recognizing whether or not a barrier exists inside the parking space for detection, a running distance value obtained by a wheel speed sensor and visual information are fused to obtain coordinates of the parking space angular point, and finally recognitionof the parking line parking space is achieved.

The invention discloses a soil physical property classification recognition method based on geological radar. The method includes the data preprocessing step, the soil physical property information extraction step, the neural network training step and the soil physical property classification recognition step, wherein in the data preprocessing step, digital signals acquired by the geological radar are de-noised and filtered; in the soil physical property information extraction step, characteristic data for representing soil physical properties are extracted from data after the data preprocessing step; in the neural network training step, the characteristic data are used for training a neural network as a data set for training the neural network, and a mapping result corresponding to the characteristic data is obtained; in the soil physical property classification recognition step, the characteristic data to be recognized for representing the soil physical properties are input the trained neural network, and the classification of the soil physical properties is recognized according to the mapping result of the neural network. The invention further discloses a soil physical property classification recognition device based on the geological radar. Through the soil physical property classification recognition method based on the geological radar, the physical properties of soil of a region to be detected can be fast and accurately recognized based on radar detection data.

The invention relates to global satellite navigation system receiver autonomous integrity monitoring technology and discloses a parity vector method-based double-satellite failure recognition method, aiming at the problems of false positives and false negatives caused by fault deviation offsetting when the parity vector method is used for recognizing two fault satellites. According to the technical scheme, the parity vector method is used for recognizing one fault satellite; with the fault satellite as the basis, four fault-free satellites are found out, and the information of the fault-free satellites is used for roughly locating, so that the fault satellites can be recognized; the recognized fault satellites are removed, and then the position resolution is carried out again, so that the locating accuracy is improved; therefore, the problems of false positives or false negatives caused by fault deviation offsetting can be avoided. The method solves the problem of the fault deviation offsetting caused by parity vector residual error and realizes the detection and the recognition for a plurality of fault satellites. After the method is used for detecting and recognizing satellite failure, the locating accuracy is improved. The method is mainly used for monitoring the autonomous integrity of a global satellite navigation system receiver.

The invention provides a vehicle target joint cognition method and system based on point cloud and image data. The system comprises a data level combination module, a deep learning target detection wood block and a combination cognition module. The data level combination module obtains three-dimensional point cloud data and image data, and fuses the point cloud data and the image data. Fusion datais collected by the deep learning target detection module to be subjected to feature level detection and recognition, a detection result is output. The joint cognition module judges the feature levelfusion detection result and the data level fusion detection result by adopting an evidence theory method, reliability distribution is obtained to serve as output, and detection stability and robustness are improved.

The invention relates to a support vector machine based classification method of base-band time-domain voice-frequency signals, comprising the following steps of: firstly segmenting a base-band time-domain voice-frequency signal sequence to obtain initial segmented subsequences; then respectively subtracting respective mean value from each initial segmented subsequence to obtain zero-mean-value segmented subsequences; then carrying out windowing treatment on each zero-mean-value segmented subsequence, respectively carrying out Fourier transformation treatment on results to obtain the spectrum amplitudes of the zero-mean-value segmented subsequences, and respectively solving the standard difference of each spectrum amplitude to obtain a characteristic quantity; sequentially combining the zero-mean-value segmented subsequences into a long subsequence according to an order; then calculating a normalized autocorrelation matrix of the long subsequence, and carrying out singular value decomposition on the normalized autocorrelation matrix to obtain a demarcation point of a subspace; then calculating the signal to noise ratio parameter of an other characteristic quantity; and finally sending an input vector composed of the two characteristic quantities into a trained SVM (Support Vector Machine) classifier to identify the classification of base-band time-domain voice-frequency signals and distinguish a voice signal and a noise signal.

The embodiment of the invention discloses a network data flow detection method and device. The method can be applied to a malicious traffic detection scene. According to the method, through judging the type of a cluster according to the size of the cluster, the method does not depend on the universality and accuracy of a training set, does not need the support of a high-quality training set, and effectively reduces the cost problem caused by the high-quality training set. The method achieves the self-adaptive malicious traffic recognition in different network environments, and is less dependent on human experience, and is more adaptive to the network. The method comprises the following steps: extracting feature vectors of a plurality of network data streams for the plurality of network data streams; then clustering the plurality of data streams based on a preset clustering algorithm and the feature vectors of the plurality of network data streams to obtain one or more clusters; and determining the type of each cluster by comparing the feature information of the cluster with a first preset condition.

The invention belongs to the technical field of biomedical detection, and relates to an imaging method for early breast tumor ultra wide band microwave detection. The method comprises the steps of performing time delay displacement processing to all detection signals of an antenna array, arranging amplitudes of all groups of signals emitted by an identical transmitting antenna and received by different receiving antennas into a matrix and solving a covariance matrix, performing weighting addition processing to all detection signals of all transmitting antennas, ensuring that weights corresponding to each group of signals are multiplied by the group of detection signals and are added to the group of detection signals, so as to obtain one group of weighting tumor signals, performing windowing processing to the weighting tumor signals, solving squares of all amplitudes in a tumor reflected signal interval and adding the squares, taking a result as a reflection energy value, solving an energy value of a point r, performing smoothing processing to the energy vale of the point r, so as to obtain the weighting energy value of the point r, and performing scanning imaging to a whole breast tissue zone, so as to obtain an energy value distribution diagram inside a breast. The method has good anti-noise capacity.

The invention relates to an inspection target defect detection method based on feature point detection and an SVM classifier, and the method comprises the steps: obtaining an inspection target image which is shot in real time, and carrying out the gray value transformation of the inspection target image; processing the converted image by using a maximum between-cluster variance method and a SUSANedge detection method, and determining a candidate region of the to-be-detected target; screening and fusing the candidate areas according to the shape characteristics of the to-be-detected target; and performing LBP and LPQ feature extraction on the processed candidate region, fusing the LBP and LPQ features, and inputting the fused LBP and LPQ features into a pre-trained SVM classifier for classification and recognition. Compared with a traditional template matching method, the detection method disclosed by the invention does not need to carry out early-stage complex registration work on thetwo images, and meanwhile, by adopting a mode of combining LBP and LPQ characteristics, the target characteristics can be described more accurately, and the accuracy of a defect recognition result isimproved; The method is simple to operate, has high environmental adaptability, and can meet the requirement for identifying the integrity of parts of the oil extraction equipment.

The invention provides an image scale detection method and an image scale detection device, and relates to the technical field of home decoration design. The method comprises the steps: obtaining a to-be-detected image which comprises a target size marking graphic representation, and the target size marking graphic representation comprises a size text sub-graphic representation and a size boundarysub-graphic representation corresponding to the size text sub-graphic representation; identifying a size text in the target size annotation graphical representation to obtain an actual size; detecting a size boundary line position in the target size labeling graphic representation, and determining the size on the graph according to the size boundary line position; determining a scale of the to-be-measured image according to the actual size and the on-map size. According to the invention, the automatic identification of the house type drawing scale can be realized, and the efficiency of home decoration design is improved.

The invention discloses a technological method for achieving soil water content classified identification through a geological radar technology. The technological method comprises the four parts of data preprocessing, soil water content parameter extraction, neural network classified identification and result display. Data preprocessing comprises the steps of null line correction, wavelet transformation and lowpass filtering. Soil water content parameter extraction comprises the steps that the power spectrum of reflection signals is solved with an autoregression moving average spectrum estimation method, data normalization is conducted, feature vectors and feature values of the power spectrum are extracted with a principle component analyzing method, and a sample feature vector database is constructed. Neural network classified identification comprises the steps that a neural network is trained through sample feature vectors, the trained mature network is used for conducting classified identification on data to be identified. Result display comprises the step that classified results are mapped and displayed. According to the technological method for achieving soil water content classified identification through the geological radar technology, automatic fast classified identification of the water content of soil is achieved, and a guiding function is performed on land detection and land rehabilitation.

The invention discloses an unmanned aerial vehicle flight control signal visual recognition sorting method. The method comprises the steps of obtaining an unmanned aerial vehicle flight control signalto be analyzed; performing time-frequency analysis and image denoising on the signals and extracting signal parameters; and performing clustering analysis and time-frequency diagram reconstruction onthe signal parameters to obtain a final unmanned aerial vehicle flight control signal visual recognition sorting result. Technical design is carried out for solving the bottleneck problem of unmannedaerial vehicle investigation. Various algorithm technologies such as signal time-frequency analysis, image genetic algorithm segmentation and denoising, image connected region marking feature extraction, density peak clustering analysis based on kernel density estimation and time-frequency image reconstruction are used; the method realizes detection and recognition of the flight control signal ofthe unmanned aerial vehicle, is very convenient to implement, can effectively avoid the defects of other reconnaissance means, can effectively help a commander to analyze, identify and sort the radiofrequency hopping signal timely, accurately and visually, and provides powerful support for the operator to study and judge the signal property.

The invention discloses a potato defect detection and recognition system design based on machine vision. The potato defect detection and recognition system design is characterized in that defected potatoes are identified and classified on a ZYNQ platform by utilizing a machine vision library Open CV of an embedded Linux system; characteristic factors of the defected potatoes with green peels, dry rot, crust and mechanical damages are extracted and R, G and B discrete degrees of variable defect factors are analyzed to realize detection and recognition of surface defects of the potatoes, and the algorithm precision is greatly improved. Wavelet transform is applied to analysis and detection of potato shapes of the potatoes, and ellipse radiuses of the potatoes are extracted and are subjected to normalization processing; grading is carried out through a RBF (Radial Basis Function) neural network, so that the efficiency and precision of recognizing the defected potatoes by grades are improved; potato images are pre-processed by utilizing an FPGA (Field Programmable Gate Array) and an algorithm in the Open CV is subjected to accelerated processing; a calculation speed and the algorithm efficiency are remarkably improved. A testing result shows that compared with an existing defected potato recognition and classification technology based on software image processing, an image processing algorithm is innovated and optimized by a novel method based on a hardware structure platform, and the processing speed and the algorithm efficiency are greatly improved; theories and experiments show that the design has relatively ideal detection efficiency and speed on the recognition and classification of the defected potatoes in an actual process. The design has very great significance on a potato processing industry.

The invention discloses a target recognition method based on multi-source image joint shape analysis and multi-attribute fusion, and relates to a multi-source image target recognition method. The objective of the invention is to solve the problem of low accuracy of existing ship target identification. The method comprises: 1, obtaining a large number of suspected ship berthing wharf slices, and rotating the wharf slices to be horizontal according to the linear angle; 2, obtaining suspected ship coordinates, and extracting suspected ship slices corresponding to the coordinates; 3, classifying the suspected ship into a ship target and a non-ship target; 4, extracting optical slices from the targets classified into the ships, respectively detecting flight deck types, bow sharp corner positions, bow contour types and vertical launcher positions, extracting SAR slices, and detecting bridge positions; 5, performing multi-attribute fusion ship model identification; and 6, taking the class with the maximum voting result as a ship model identification result. The method is applied to the technical field of remote sensing image target detection and recognition.

The invention relates to a detection method of internal defects of thin-gauge cold rolled steel plates for automobiles to mainly solve the technical problem of unable identification, difficult positioning and long detection time of internal defects of present cold rolled steel plates for automobiles, with the thickness of 0.5-1.5mm. The detection method of internal defects of thin-gauge cold rolled steel plates for automobiles comprises the following steps: 1, marking a detection area on a plate sample to be detected; 2, positioning the defect position of the plate sample through using an ultrasonic scanner; 3, cutting the plate sample containing a defect part to make a metallographic sample; 4, observing the defect part of the metallographic sample by using an optical microscope; and 5, carrying out element analysis on the defect part of the metallographic sample by using an energy dispersive spectrometer. Defects are analyzed and detected through adopting combination of ultrasonic scanning and positioning, the optical microscope and the energy dispersive spectrometer to realize positioning and detection analysis of the internal defects of the thin-gauge cold rolled steel plates for automobiles; and the method has the advantages of simplicity, fastness, high precision, and meeting of mass quality examination requirements of the cold rolled steel plates for automobiles.

The invention discloses a transformer substation monitoring system based on edge computing. The system comprises an external monitoring device, an internal monitoring device, an acquisition device, aprocessing device, a judgment device, a storage device, a first alarm device and a supervision platform, and is characterized in that the external monitoring device is arranged outside a transformer substation monitoring point; the internal monitoring device is arranged in a transformer substation monitoring point; the acquisition device, the processing device, the judgment device, the storage device and the first alarm device are connected with one another and correspondingly arranged near a substation monitoring point; the processing device is used for preprocessing, matching and identifyingthe image data acquired by the external monitoring device; and the storage device is in wireless connection with the supervision platform, and the supervision platform comprises a database, a secondalarm device and a display terminal. High-quality image resources are obtained, detection and recognition of various different parts and defects are achieved, various factors of the transformer substation are comprehensively monitored, an alarm is given in time and backed up to a supervision platform, and the computing pressure of a cloud processing center is relieved.

The invention belongs to the technical field of biological detection, and relates to a small-molecule fluorescent probe, in particular to a beta-galactosidase near-infrared fluorescent probe, especially a BODIPY beta-galactosidase fluorescent probe, a preparation method and application thereof in preparation of a senescent cell imaging preparation. The fluorescent probe provided by the invention can detect beta-galactosidase according to the reaction mechanism, namely beta-galactosyl hydrolysis and intramolecular self-elimination mechanisms, is relatively low in biotoxicity, stable in photophysical activity and high in beta-galactosidase response sensitivity, and can be used for preparing a detection preparation for specific fluorescence imaging of senescent cells.

The invention discloses a method for identifying frequency-shift interference of a linear frequency modulated signal. The method comprises the following steps of: preprocessing the signals received bya radar, and dividing the signals into three paths before matching filters; passing the three signals through a complete matching filter and a designed half-bandwidth filter, and extracting a peak value of the output voltage of each half-bandwidth matching filter; setting a threshold; and determining whether the target is a frequency-shift interference false target according to the ratio of the matched output peaks of the target under different half-bandwidth matching filters and the set threshold. The invention has the following advantages: the radar can be used for real-time recognition ofmulti-targets; the application range is wide, and various false targets in an interference system can be identified; the shortcomings of the radar front-end tracking anti-interference method are compensated, and the detection and identification of the interference of an active advancing false target can be realized. The invention has few implementation steps and small calculation amount, can meetthe real-time identification of the radar for multiple targets, has no additional requirements on the hardware system, and is easy to implement in engineering.

The invention discloses a material bag for a beverage machine and a beverage machine and material bag detecting identification method. The material bag is provided with a trademark. The beverage machine is provided with a detecting device which can detect the trademark of the material bag. The detecting device is connected with a main control system of the beverage machine. Trademark information is preset in the main control system. The main control system carries out a beverage preparing process according to the detected trademark information and the preset trademark information. The trademark on the material bag is detected and is compared with the preset trademark information in the main control system, whether the material bag is placed on the beverage machine can be detected, the problem that the machine works without the material bag is avoided, the safety and reliability of the beverage machine is improved, and meanwhile the workability of the material bag is guaranteed.

The invention discloses a binder clip defect detection method and system based on deep learning, and belongs to the technical field of image processing, and the method comprises the following steps: S1, constructing a sample data set; S2, obtaining a pre-training model; S3, constructing a binder clip defect detection and identification model; and S4, carrying out detection and identification. The YOLOv4-Tiny network serves as a basic network, weight parameters in the pre-training network are shared through transfer learning, a global space attention mechanism module is added, the feature representation capacity is improved, and detection and recognition of binder clip defect images can be accurately achieved; and in an image defect detection effect comparison experiment, the method has the advantages that a good detection effect is shown, the mAP value index reaches 91.66%, detection and recognition of the binder clip defect image are achieved, a foundation is laid for follow-up implementation of binder clip detection and a feedback system, and the method is worthy of being popularized and used.

The invention discloses a social media platform false information identification system and relates to the technical field of false information identification. The system comprises an acquisition module and an recognition module. The acquisition module collects feature information of a social media platform and transmits the feature information to the recognition module. The recognition module isused for recognizing feature information of the social media platform and determining false information output, the recognition module comprises a false information detection unit, and the false information detection unit comprises word-level semantic emotion analysis and sentence-level semantic emotion analysis. Definition word level semantic sentiment analysis and sentence level semantic sentiment analysis are performed on the input feature information, and therefore, false information detection, identification and filtering can be realized, the accuracy of false information identification and the generalization ability of false information identification can be improved, and a wide application range can be realized.

The embodiment of the invention discloses a pathology critical value early warning method based on a pathology knowledge graph. The method comprises the following steps: acquiring pathology text information from a pathology report; extracting a target entity from the pathological text information; performing matching analysis on the target entity by utilizing a preset pathology knowledge graph, and determining whether a pathology critical value exists in the pathology report or not; if the pathological critical value exists, early warning reminding is carried out, so that timely early warning of the pathological critical value is realized, and a pathologist and a clinician are timely reminded to pay attention preferentially and early and carry out clinical treatment of the next step, and clinical treatment is timely carried out on the patient to the greatest extent and the timely treatment rate of the patient is greatly improved, and therefore, the pathological critical value early warning efficiency and the medical quality are improved. In addition, the invention also provides a pathology critical value early warning system based on the pathology knowledge graph, computer equipment and a storage medium.

The invention relates to a protocol hanging login account identification method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring account behavior data, and constructing a data set corresponding to a logged-in account according to the logged-in account to which the account behavior data belongs; performing similarity analysis on the data set corresponding to the logged-in accounts, and screening out an account to be monitored from the logged-in accounts according to a similarity analysis result; the preset data randomly selects a target account from an account set comprising the to-be-monitored account, and the preset data is issued to a login terminal of the target account, so that the preset data of the login terminal changes the account state of a login account on the login terminal; according to the method and the device, the account state change of the accounts in the account set is monitored, and the protocol hanging login account identification result is obtained according to the account state change, so that the protocol hanging login account is effectively detected and identified, the account safety is conveniently improved, and the account management is conveniently performed.