320results about How to "Improve detection success rate" patented technology

The invention discloses a brain computer interface mouse control-based Internet browsing method, which comprises the following steps of: initializing a system; controlling a mouse to move to a target area in a browser interface based on motor imagery and P300 electroencephalogram potentials; if a target is a text input target, switching the interface to a P300 text input interface, inputting characters by using P300 signal detection, returning to the browser interface after finishing inputting the characters and writing text input results into a selected text input box; and if the target is not the text input target, judging whether to click the target or not according to the motor imagery and P300 electroencephalogram potential information, clicking the target to open a new interface if determining to click the target, otherwise, controlling the mouse to continuously move in the interface. The brain computer interface mouse control-based Internet browsing method has the advantages of high control speed, high accuracy, good effect, working stability and capacity of realizing continuous control, and can be used under the condition of irremovability of a body or the computer mouse due to external or internal factors.

The embodiment of the invention provides a face anti-counterfeiting detection method, a face anti-counterfeiting detection device and a multi-view camera. The face anti-counterfeiting detection methodcomprises the following steps: acquiring a depth image, an infrared image and an RGB image by using a TOF camera and an RGB camera; analyzing the RGB image through a preset face detection algorithm,and determining an RGB face region of a face in the RGB image and position information of the RGB face region; determining a depth face area of the face in the depth image and an infrared face area ofthe face in the infrared image according to the position information of the RGB face area; and when the depth face area, the infrared face area and the RGB face area respectively meet corresponding preset rules, judging that the face passes the detection. According to the face anti-counterfeiting detection method provided by the embodiment of the invention, face living body detection can be completed without the need for a user to cooperatively execute corresponding actions, the detection time can be saved, and the user experience is good.

The present application relates to the technical field of wireless communications, and particularly to a method, system and device for sending and receiving data, which are used for solving the problem existing in the prior art that the detection success rate is relatively low due to the fact that a UE at a receiving end cannot detect signals on a plurality of transmission resources sent by a UE at a transmitting end after combing same. The method of the present application comprises: determining, by a transmitting end, a first transmission resource used for conducting data transmission, and determining a second transmission resource from a second transmission resource pool corresponding to the first transmission resource; and sending data to be transmitted through the first transmission resource and the second transmission resource. Since the receiving end can receive data information on a first transmission resource and a second transmission resource related to the first transmission resource, it is guaranteed that the receiving end can detect signals on a plurality of transmission resources sent by a UE at a transmitting end after combing same, thereby improving the detection success rate and further improving the transmission performance.

The invention discloses a motor imagery and P300 electroencephalographic potential-based functional key selection method, which comprises that: a user executes corresponding motor imagery and P300 visual stimulation tasks according to randomly-occurring target attributes after causing a cursor on a working interface to reach a target by using brain-computer interface equipment; the brain-computer interface equipment transmits generated electroencephalographic signals to a computer; and the computer simultaneously performs data processing and analysis on P300 information and motor imagery information in the electroencephalographic signals respectively, and finally judges whether to select or refuse the target according to analysis results. In the method, motor imagery signals and P300 signals which are independent of each other are combined and applied in the field of brain-computer interfaces; and the method has the advantages of high detection success rate and short detection time, and can be applied to motor control in the fields of auxiliary devices for the disabled and electronic entertainment.

The invention discloses a method and a device for detecting an abnormal current of a circuit. The method comprises the following steps of: locating a specific position with abnormal current consumption by detecting an input current of an electronic product; adjusting the voltage of a precise power supply of the electronic product, observing the change situation of the current consumed by the product along with the input voltage, and quickly distinguishing that the abnormal current occurs in an LDO (Low Drop Output) circuit, a DC-DC switch power supply circuit or a direct battery-powered circuit. Furthermore, for a complex multipath LDO circuit, the current consumption on each path of the LDO circuit can be measured by an external power supply forced substitution method. The invention can simplify detection operations, shorten the detection time, reduce the analysis difficulty and increase the efficiency of detecting abnormal current in circuits and the detection success rate.

The invention provides a kit suitable for rapidly detecting AMH and INHB by using a double-tagging time resolution fluorescence immunoassay method. The kit comprises (1) a solid phase carrier coated by an AMH coating antibody and an INHB coating antibody; (2) a mixed calibration product of AMH and INHB; (3) an AMH detection antibody marked by using a lanthanide element 1; (4) an INHB detection antibody marked by a lanthanide element 2; (5) an immunoreaction accelerant liquid; (6) a concentrated washing liquid; and (7) a reinforcing liquid. The invention further provides a use method of the kit for rapidly detecting AMH and INHB by using the double-tagging time resolution fluorescence immunoassay method. By adopting a double-tagging time resolution fluorescence immunoassay technique, the defect that conventional AMH and INHB respectively need a single kit, that is, one kit can be only used for detecting AMH or INHB can be overcome, the detection steps can be reduced, the sampling time can be shortened, and the use amount of a blood sample can be reduced.

The invention relates to a control method and apparatus of exposure, and an unmanned aerial vehicle. The control method of exposure comprises the steps: acquiring an image output by a depth sensor according to current exposure parameters; determining an image of a target object from the image; and determining first exposure parameter according to the brightness of the image of the target object, wherein the first exposure parameter is used to control next time of automatic exposure of the depth sensor.

The invention discloses an injection attack detection method based on a gating loop unit and an attention mechanism, and the method is characterized in that the method comprises the following steps: step 1, extracting a statement related to a database in the Internet as a sample; preprocessing each sample, and obtaining a category label of each sample; step 2, inputting a result after sample preprocessing into an injection attack detection model, and predicting a category label corresponding to the result; wherein the injection attack detection model comprises an activation layer, a gating cycle unit layer, an attention mechanism layer and an output layer which are connected in sequence; step 3, training an injection attack detection model based on the sample data; and step 4, for a to-be-detected statement, preprocessing the to-be-detected statement, and inputting a preprocessing result into the trained injection attack detection model to obtain a category label of the to-be-detectedstatement, thereby judging whether the to-be-detected statement is an injection attack statement or not. The method is high in accuracy.

The invention relates to a key detection method and a device. The method is characterized by comprising the following steps: detecting a key to acquire a key signal; and carrying out the frequency-change sampling of the key signal, outputting a control signal when the frequency of sampling effective key signals reaches or exceeds a preset frequency, wherein the frequency-change sampling refers to the repeated process of progressively increasing a sampling frequency from a first frequency to a second frequency and progressively decreasing the second frequency to the first frequency, and preset time resides in each frequency of the sampling frequency. The invention decreases the interference frequency of the key detection by external signals.

An image-based hand detection apparatus includes a hand image detection unit for detecting a hand image corresponding to a shape of a hand clenched to form a fist from an image input. A feature point extraction unit extracts feature points from an area, having lower brightness than a reference value, in the detected hand image. An image rotation unit compares the feature points of the detected hand image with feature points of hand images stored in a hand image storage unit, and rotates the detected hand image or the stored hand images. A matching unit compares the detected hand image with the stored hand images and generates a result of the comparison. If at least one of the stored hand images is matched with the detected hand image, a hand shape recognition unit selects the at least one of the stored hand images as a matching hand image.

The method includes following steps: first the pixel feature of image waiting for test is extracted, and then it will be divided into 11X11 image sub-block; the pixel gray value of each image sub-block is extracted by using a mode as a Chinese character 'mi' to take it as input of support vector machine; then the tool of support vector machine LINSVM is used to construct sort learning machine of support vector machine; mass samples are used to train the support vector machine for making it correctly recognize subtitle block and non subtitle block; then pyramid type model is used to successively reduce the original image resolution, and the subtitle is checked by support vector machine at each stage; the checking results of all stages are restored to original image resolution for composition, and ultimate checking result is generated; finally all tested image sub-blocks are made post-treatment, clearing noise to get combined subtitle area.

The embodiment of the invention provides an LTE system cell detection method. Power sorting is adopted to ensure that the cell detected each time is the strongest cell, traverse detection on M suspected synchronization positions is avoided, the operation complexity is reduced, and the processing time for cell detection is shortened. Meanwhile, the validity of the ID of a detected cell is judged, the multipath position of the cell ID is calculated, the validity of a suspected primary synchronization signal position is judged according to the multipath position, and the ID detection probability of a false synchronization position is reduced. Moreover, the power value of a detected synchronization position is updated, and same-frequency interference elimination is adopted so as to improve the success rate of weak cell detection.

The invention provides a parking and garaging method, comprising the following steps: obtaining image information to obtain images of a plurality of labels; when the number of label serial numbers belonging to a target parking space is equal to a label threshold value, calculating the dimension of the target parking space; when the dimension of the target parking space is not smaller than a presetparking dimension threshold value, generating an indication message for indicating that the target parking space is available; after receiving an automatic parking instruction, detecting the state ofa vehicle after a preset duration; calculating a current position and a course angle of the vehicle under a coordinate system; calculating an optimal parking start point during parking of the vehicle; and generating a first planned path of the vehicle driving to the optimal parking start point and a second planned path of the vehicle driving to the parking space from the optimal parking start point, parking and garaging.

The invention discloses a first-stage license plate detection and recognition method based on deep learning. The first-stage license plate detection and recognition method based on deep learning comprises the steps: S1, inputting a to-be-detected and recognized color image, and enabling the color image to be zoomed into an image with the size of 300 * 300 through an image preprocessor; s2, inputting the zoomed image into a detection module and a recognition module for license plate detection and license plate character recognition; and S3, regarding the output result of the combined detectionmodule and the recognition module as the license plate detection and recognition output result of the whole system. The beneficial effects of the invention are as follows: first-stage license plate detection and recognition system integrating license plate detection and license plate character recognition into one model has the main advantages that the advantages are as follows: according to the license plate detection and license plate character recognition algorithm based on deep learning provided by the invention, higher detection accuracy and character recognition accuracy can be kept in acomplex natural scene, so that the stability and the accuracy which exceed those of other related systems are shown.

The invention relates to a signal detecting method and a signal detecting device that are based on broadcast-typed automatic related monitoring; wherein, the signal detecting method comprises the following steps: width detection of a received expanded intermittent oscillating signal is implemented, thus obtaining a pulse signal; leading edge detection of the pulse signal is implemented, thus obtaining a pulse leading edge indicating signal; time calibration of a position of the pulse leading edge indicating signal is implemented, and the calibrated pulse leading edge indicating signal is sent out; fore header detection of the calibrated pulse leading edge indicating signal that is received is implemented, thus determining whether the fore header is effective; the effective fore header is verified, and the expanded intermittent oscillating signal with effective fore header is determined as a final effective expanded intermittent oscillating signal. The signal detecting method and device that are based on broadcast-typed automatic related monitoring determine whether the expanded intermittent oscillating signal with effective fore header is a final effective expanded intermittent oscillating signal by further verifying the effective fore header, thus effectively raising the success ratio of signal detection.

The embodiment of the invention discloses a method and device for detecting a moving object, wherein the method and device are used for eliminating influences of sudden scene changes and rapid and gradual scene changes on detection of the moving object, decreasing the false detection rate and reducing operation cost. The method includes the steps of detecting a current scene, determining that the current scene is a stable scene or a variable scene, determining the type of the variable scene after the current scene is determined to be the variable scene, comparing the difference value between the gradient model vector similarity of a current frame and the gradient model vector similarity of an Nth frame with a preset threshold value if the variable scene is determined to be a rapidly and gradually changed scene, determining the type of the variable scene again, and renewing background modeling parameters of a Gaussian mixture model after the type of the variable scene is determined again and when the variable scene is determined to be a suddenly changed scene or a rapidly and gradually changed scene, wherein the variable scene can be the suddenly changed scene, the rapidly and gradually changed scene and a slowly and gradually changed scene, and N is a positive integer.

A method for detecting a high impedance grounding fault based on fault resistance nonlinear identification comprises the steps: collecting phase voltages of a detected feeder line and an instantaneous value of a zero sequence current, respectively calculating a correlation coefficient of each phase voltage and the zero sequence current, if the correlation coefficient of one phase voltage and the zero sequence current is larger than a threshold value R, fitting a current voltage characteristic curve composed of the phase voltage and the zero sequence current in a sectional and linear mode through a least square method, accordingly, calculating and obtaining a coefficient, namely, a fault resistance nonlinear coefficient which can effectively present characteristics of the high impedance grounding fault according to the slope of each fitting straight line, judging whether a suspected high impedance grounding fault exists by comparing the fault resistance nonlinear coefficient and the threshold value, continuously detecting the lasting time of the suspected high impedance grounding fault, and if the lasting time exceeds delayed time, finally judging that the high impedance grounding fault occurs. Compared with a detecting method based on a harmonic wave, the method achieves high sensitivity, and compared with a method simply based on the time domain amount, the method achieves a better noise resisting capacity.

The embodiment of the invention discloses a method and a device for processing operating system exceptions. The method comprises the steps of operating corresponding core detection threads; leading each core detection thread to enter a circulation calling procedure, updating time counting of a central processing unit in a circulation to be current time, using the core detection thread corresponding to one central processing unit to detect time counting of another central processing unit, and judging whether a difference value between the current time of the one central processing unit and the time counting of another central processing unit is larger than a first setting value or not; and conducting exception processing if the difference value is larger than the first setting value. By means of the mode, the method and the device can detect the operating system exceptions caused by the fact that deadlock happens or a plurality of central processing units in an operating system.

The embodiment of the invention provides a feedback control method, UE and network equipment, relates to the technical field of communication, and aims to reduce the bit overhead of indicating a PDSCHpacket to the UE by the network equipment and solve the problem that the correct rate of receiving feedback information by the network equipment is reduced. Specifically, the feedback control methodcomprises the steps that the UE receives first downlink control information DCI from the network equipment, wherein the first DCI comprises a first field, wherein the first field is used for indicating whether hybrid automatic repeat request acknowledgement (HARQ-ACK) information for at least one physical downlink shared channel (PDSCH) packet is carried on a first uplink control channel to be sent, and the first uplink control channel is indicated by a first DCI, wherein the first field occupies M bits, M is a positive integer smaller than P and P is the maximum number of available PDSCH packets of the UE. The method is specifically applied to a scene in which the UE sends feedback information to the network equipment.

The invention relates to a fully automatic ABS gear ring defect detection system based on machine vision. Two working tables on the ground are vertically placed in a right-angle form, and a manipulator and a base are located at the center; detection of gear rings is driven by grabbing of the manipulator and manipulator fixtures, defect detection software of an upper computer is used for cooperation, the type of defects of the ABS gear rings is detected, and the gear rings are placed in different material dropping frames according to the types respectively. The system adopts an automatic mode, can greatly reduce the investment of manpower and financial resources in the detection step, and improves the detection efficiency and the detection success rate.

The invention discloses a sensitive subgraph based on malicious android software re-packaging detection method. The sensitive subgraph based on malicious android software re-packaging detection method includes the steps that sensitive API weighting calculation is performed, sensitive subgraph establishment is performed based on an android program static function call network, then five different structure characteristics are established by utilizing the difference of sensitive API call structures of sensitive subgraphs in benign programs and malicious re-packaging programs, finally a characteristic space is established for a sample set, analysis and detection are performed by utilizing a machine learning method, and accordingly detection of the malicious re-packaging programs is achieved. A sensitivity coefficient calculation method TF-IDF-like is provided based on text vocabulary weighing detection TF-IDF, the method makes sensitive function coefficient calculation only limited to usage distribution of a function themselves in a malicious data set no longer but combine with usage distribution of the sensitive function in a benign data set, and accordingly false detection alarms caused by higher sensitivity coefficients due to the fact that a part of sensitivity functions in a malicious data set and a benign data set are simultaneously called in quantity are decreased.

The invention discloses a Hi-Fi tone quality identifying method based on pattern recognition. The method includes the steps: selecting a learning sample, converting a sample time domain signal into a frequency domain signal, and making a frequency attenuation mean value every 500Hz from 11050Hz to 22050Hz serve as a characteristic, wherein twenty two characteristics are provided and numbered from one to twenty two. Through statistical learning of a lot of already labeled lossy and lossless audios, a lossless audio condition probability corresponding to a lossless audio characteristic is obtained, a lossy audio condition probability corresponding to a lossy audio characteristic is obtained, Fourier transform is performed for a to-be-measured audio, and a combined probability can be calculated and then the probability of the specific tone quality of a given audio can be reckoned after condition probabilities between the characteristics and between the characteristics and the tone quality are obtained by extracting the frequency characteristics. Through the above algorithm, a high detection success rate of real lossless audios is achieved, and a relatively low misjudgement rate of false lossless audios is guaranteed. Moreover, compared with auCDtect, the method can reach the advanced level in the industry.