88results about How to "Automatic Identification" patented technology

The invention discloses a coal-rock interface identifying method and system based on an image. The method comprises the following steps of: acquiring multiple color images of coal and rock on a coal mining working face; extracting a vector based on an image characteristic serving as a sample characteristic vector specific to each color image to obtain a known sample set of coal and rock; and establishing a coal-rock classifier model by adopting a Fisher linear judging method and taking the known sample set of the coal and rock as a training sample set. In the working process of a coal mining machine, a color image of the coal and rock which is cut by using a drum is acquired in real time, and the extracted characteristic vector is input into the coal-rock classifier model to identify a coal-rock type. The system consists of a light source module, an imaging module, a processing module and an anti-explosion shell. The coal-rock interface identifying method and the system provided by the invention have the characteristics of simple structure, easiness for distributing, high suitability and the like, the coal-rock type cut by using the drum can be automatically identified in real time, and reliable coal-rock interface information is provided for automatic heightening of the drum of the coal mining machine.

The invention belongs to the technical field of acquisition and analysis of urban traffic data and particularly relates to a processing method of cell phone signaling information for dividing traffic zones. The processing method comprises the following steps of washing cell phone signaling data and eliminating abnormal data; matching base station position information corresponding to the cell phone data with a road; establishing traffic semantic classification based on the cell phone signaling information; selecting and distinguishing cell phone base station characteristics according to the condition of the traffic semantic classification; extracting the cell phone signaling information to obtain the cell phone base station characteristics; carrying out clustering analysis on the cell phone base station characteristics so as to divide the traffic zones. The operation of carrying out traffic zone division on cities by using the cell phone signaling data is consistent with the tendency of big data digging in current; semantic division has a simplification effect on actual class division of base stations, and the attributes of regions and the base stations can be effectively and automatically identified; the urban traffic zones can be rapidly and directly divided; the processing method has the advantages that the data acquisition is easy, the division cost is low and the division is rapid and direct.

The invention discloses a biochip analysis method based on an active contour model and a cell neural network. The method comprises the following steps that improved Hough transformation is adopted to perform slant correction on a rectangular sampling point, and improved Radon transformation is adopted for a circular sampling point; initial positioning is performed on the sampling points by using a projection method, and an optimized network is generated; then the network is adaptively adjusted on the basis of neighborhood search, and secondary precise positioning is performed on the sampling points; the active contour model is optimized by using a greedy algorithm, and a CNN (Cable News Network) is utilized to classify the sampling points in accordance with signal strength; Multiple snakes are combined with the CNN, the CNN first learns about the convergence behavior of the sampling point snake with a strong signal and then guides the convergence of the sampling point snake with a weak signal, and finally, reasonable partition of the sampling points is realized; and signal data of microarray sampling points is extracted and output. By using the method, the problems of slant correction of a biochip image, difficulty in partition of sampling points with irregular shapes and sampling points with weak signals and the like are solved, automatic identification of biochip sampling points is realized, and the method is suitable for quick analysis of large-scale biochip sampling points.

The invention relates to a distance measuring method of a significant target in a binocular image. The distance measuring method of the significant target in the binocular image aims to solve the problem that an existing target distance measuring method is low in the processing speed. The method includes the steps that step 1, significant feature extraction is conducted on the binocular image through a visual significance model, and a seed point and a background point are marked; step 2, a weighed graph is established for the binocular image; step 3, a significant target in the binocular image is partitioned through a random walk image partitioning algorithm by means of the seed point and the background point in step 1 and the weighed graph in step 2; step 4, key point matching is conducted on the significant target separately through an SIFT algorithm; step 5, the significant target distance is worked out by applying a parallax matrix K' worked out in step 4 into a binocular distance measuring model. The distance measuring method can be applied to distance measurement of the significant target of the image in front of the vision in the intelligent automobile running process.

The invention discloses a crop pest monitoring method based on a multispectral remote sensing image of deep learning, and belongs to the technical field of satellite remote sensing image processing and application. The objective of the invention is to solve the problems of poor timeliness of crop pest monitoring, unstable single-index spectral information, difficulty in acquiring hyperspectral unmanned aerial vehicle data and the like in the existing method. According to the invention, combination of ten groups of characteristic band spectrums is adopted. An LSTM long short-term memory network is constructed. Crop insect pest disasters can be automatically and efficiently identified from the multispectral satellite remote sensing image, and certain technical support is provided for the fields of agricultural production disaster prediction and prevention, agricultural insurance claim settlement and the like. The method has the advantages that the crop insect pest disasters can be automatically and efficiently identified from the multispectral satellite remote sensing image;

The invention provides a method for identifying faces in videos based on incremental learning of face partitioning visual representations and belongs to the field of pattern recognition. According to the method, an Adaboost algorithm is used for detecting frontal face images in a first frame of the face videos, a Camshift algorithm is used for tracking, all face images are obtained, in the process of reading the face images in the videos, incremental cluttering is carried out on the face images, and a representative image is selected from each kind of face images; the representative images are processed, and a visual dictionary based on the piece visual representations is learnt; the visual dictionary is used for carrying out the representations on the face images; finally, according to similar matrices, the videos composed of the face images are identified. According to the method, an identification rate and robustness of the video faces can be improved under the state that illumination, postures and tracking results are not ideal. The faces in the videos can be detected, tracked and identified effectively, conveniently and automatically.

The invention relates to the technical field of vehicle charging and electricity conversion and particularly provides an automatic charging and electricity conversion method for an electric vehicle. Through the automatic charging and electricity conversion method, the problem of the low automation degree of existing charging and electricity conversion facilities is solved. In order to achieve the purpose, the automatic charging and electricity conversion method comprises the following steps that communication connection is established between the electric vehicle to be subjected to charging and electricity conversion and a charging and electricity conversion facility; the electric vehicle travels into a specific position within the service range of the charging and electricity conversion facility; the charging and electricity conversion facility conducts authentication on the electric vehicle; and if authentication is successful, the charging and electricity conversion facility starts charging or electricity conversion operation, and charging or electricity conversion is conducted on the electric vehicle. Through the automatic charging and electricity conversion method, full automation of the whole charging and electricity conversion process is achieved, and the automatic charging and electricity conversion method is suitable for automatic unattended charging and electricity conversion facilities.

An image restoration method and device are disclosed. The method comprises the following steps of: acquiring a face region of an image to be processed; segmenting the face region to obtain a first face region of the face region; acquiring a pixel point set whose gray value in the first face region is greater than a threshold value, and obtaining a first region to be repaired of the face region; repairing the first area to be repaired according to the first face area to obtain the repaired image. The first region to be repaired in the image to be processed, i.e., macula, is automatically recognized by the neural network. The first area to be repaired (macula) is filled with the skin of the first human face area which is intact around, and the macula in the image to be processed is repaired.In this way, there is no difference between the repaired area and the surrounding skin in the image to be processed, so that the repaired area is beautiful and natural.

The invention discloses a schizophrenia sMRI image classification method based on a multi-input convolutional neural network. The method comprises the steps of collecting structural magnetic resonanceimaging image data of schizophrenia patient and a normal person; preprocessing sMRI image data to obtain grey matter density images which are not subjected to smoothing processing and spatial smoothing respectively, and constructing an original data set; and sending the original data set into a multi-input convolutional neural network model for training, finally inputting sMRI image data into themulti-input convolutional neural network model, and finally outputting a classification result. According to the invention, the images which are not subjected to the spatial smoothing processing andimages which are subjected to spatial smoothing are input into a multi-input convolutional neural network, high-frequency information in an sMRI image lost in spatial smoothing can be compensated, andmeanwhile, the generalization ability of the convolutional neural network can be enhanced due to the noise contained in the images which are not subjected to smoothing processing, so that the problemof low accuracy in schizophrenia sMRI image classification can be effectively solved.

The invention discloses a method and a device for detecting network performance abnormity, equipment and a storage medium, and relates to the field of computers and communication. The method comprises the following steps: determining a confidence interval of a KPI by using historical data of a key performance index KPI for representing network performance; monitoring the KPI to obtain real-time data of the KPI; and determining whether the KPI is normal or not by using the confidence interval and the real-time data. According to the embodiment of the invention, operation and maintenance personnel can observe the current network state anytime and anywhere, obtain abnormal information immediately and adjust the network in time, so that the network always keeps the optimal state.

The invention relates to a speech recognition method and an electronic device of the speech recognition method. The speech recognition method includes the steps of inputting a feature vector acquired from a speech signal into a plurality of speech recognition modules, acquiring a plurality of word string probabilities and a plurality of candidate word strings from the speech recognition modules respectively, and selecting the candidate word string corresponding to the largest word string probability as the recognition result of the speech signal. With the speech recognition method, a language corresponding to the speech signal can be automatically recognized.

The invention provides a farmland incineration fire point monitoring method based on a remote sensing image. According to the invention, with utilization of infrared and multi-spectrum technologies, land utilization data, and a fire monitoring model, multi-dimension extraction of farmland incineration points is carried out, so that the low space resolution of the original monitoring sensor is improved. With the farmland incineration fire point monitoring method, the farmland incineration fire point can be identified automatically, quickly and accurately; the accuracy of farmland incineration fire point identification is improved substantially; and the high automation and precision of the farmland incineration fire point monitoring service are realized.

The invention relates to the field of medical image processing, in particular to a urine visible component recognition method based on an improved Alexnet model. The method comprises the following steps: 1, acquiring and expanding an image data set, and constructing a urinary sediment image training set and a test set; 2, constructing a urine visible component recognition network model based on anAlexnet network model; 3, setting training parameters of the urine visible component recognition network model; 4, training a urine visible component recognition network model based on an Alexnet network model; 5, testing a urine visible component recognition network model based on the Alexnet network model. The method is improved on the basis of an Alexnet network model and reduces the number ofnetwork training parameters. The method can automatically extract image features, has the characteristics of high recognition rate, short recognition time and strong generalization ability, and has important application prospects for assisting medical diagnosis and reducing the burden of doctors.

The invention relates to a leukocyte image detection and recognition model construction method based on transfer learning and application. The leukocyte image detection and recognition model is trained by constructing a leukocyte image detection and recognition model based on transfer learning, taking a coco data set and labeled leukocyte images as samples. The leukocyte image detection and recognition model extracts three-level fused feature pyramids, different prior contour frames are set corresponding to leukocytes with different size features, network convergence is accelerated, and the recognition efficiency and accuracy are improved. The leukocyte images are automatically and efficiently detected, recognized and counted based on the leukocyte image detection and recognition model, the detection and recognition precision is improved, human and subjective factors are eliminated, and fairness and objectivity are achieved. According to the method, the reasoning time for detecting andidentifying one image is 0.05 second, and analysis of 20 leukocyte images can be completed per second. And the identification accuracy of six normal types of leukocytes reaches 98%.

The present invention provides an accurate and efficient method of organizing circuitry from a net-list of an integrated circuit, by the steps of generating a reference pattern; identifying the potential matches in the net-list using inexact graph matching; further analyzing the matches to determine if they match the reference pattern; and organizing the net-list into a hierarchy by replacing the identified instances with higher-level representations.

The invention discloses an identity authentication system based on telecom operators. The system adopts various communication devices of a mobile terminal, such as near field communication (NFC), Bluetooth, wireless fidelity (WIFI), infrared rays, bar codes, ultrasonic waves and radio frequency identification devices (RFID) to receive information of identity authentication requested from an external or mobile network, utilizing information of mobile users provided by subordinate telecom operators of mobile devices, such as telephone numbers and other items to carry out comparison, returning results to authentication request providers or providing the telephone numbers of the users to the authentication request providers, and enabling the authentication request providers to voluntarily carry out comparison. The identity authentication system based on the telecom operators adopts the mobile telephone numbers as global identity tags, has the advantages of being easy to apply, unique, and open but not private, achieving the function of identity authentication of the mobile terminals bundled with third-party guarantee, thereby improving accuracy and convenience of the identity authentication, easily achieving the third-party guarantee and conveniently protecting personal data or personal accounts.

The invention belongs to the field of computer vision and the field of point cloud processing, and relates to a method for synchronously realizing human face three-dimensional point cloud feature point positioning and human face segmentation, which comprises the following steps: S1, point cloud initialization: inputting human face point cloud data; S2, projection: projecting the point cloud information with the texture onto a 2D image; S3, 2D feature point positioning: positioning face feature points on the projected 2D image; S4S4, solving 3D feature points: solving the feature points of theface three-dimensional point cloud according to the corresponding relationship; S5, segmentation: cutting the face point cloud data by using the feature point information; S6, trimming: removing pointcloud outliers; S7, iteration: returning to S2 to resolve the point cloud feature points, and performing iteration until the point cloud feature points are stable; and S8, outputting: outputting theclipped face point cloud and the clipped face 3D feature points. According to the method, the 3D human face feature points are synchronously positioned, the human face point cloud is cut, the two processes are mutually promoted, the human face point cloud feature points can be solved with high precision, and the method is simple, convenient, feasible, efficient and practical.

The invention provides a medical image processing apparatus capable of assessing each lumen in unbranched vessel sections of the lumen, and automatically identifying whether a narrow palace exists. The related medical image processing apparatus comprises a segmentation unit, a measurement unit, a reference identification unit, a determination unit, an expected value calculation unit and an identification unit. The segmentation unit is used for dividing a vessel tree in to a plurality of unbranched vessel sections through branch region of vessel tree in the lumen in volumetric data. The measurement unit is used for measuring characteristic parameters relative to a cross-section shape of the lumen in each unbranched vessel section. The index calculation unit is used for calculating lumen state indexes representing each unbranched vessel section according to the characteristic parameters. The determination unit is used for determining an abnormal region and a normal region in each unbranched vessel section according to the lumen state indexes. The expected value calculation unit is used for calculating an expected value of a characteristic parameter of the abnormal region according to a characteristic parameter of the normal region adjacent to the abnormal region. The identification unit is used for identifying whether a narrow palace exists in the abnormal region according to a measured value of the characteristic parameter of the abnormal region and the expected value.

The invention discloses a general wireless control method and system for electrical equipment, and the method comprises the steps: geographical position information of the electrical equipment in environment can be acquired through the general wireless control equipment; the geographical position information of the electrical equipment is saved; azimuth posture information of the general wireless control equipment which operates the electrical equipment is saved; the geographical position information and the azimuth posture information of the general wireless control equipment are acquired again, whether matched electrical equipment exists is judged according to the geographical position information or the azimuth posture information, if yes, a control interface of the electrical equipment is displayed on the general wireless control equipment, and the electrical equipment can be controlled based on the control interface. According to the invention, when the electrical equipment is operated, there is no need to select an application program of corresponding equipment or manually select the type of the equipment, and the controlled equipment can intelligently identify and control the electrical equipment operated and controlled by a user without needing to support specific wakeup and signal identification functions. The invention also discloses a general wireless control system of the electrical equipment.

The invention discloses a device and method for automatically detecting boundary dimension of an intelligent power meter. The device comprises a workbench component, a side face scanning and detecting unit, a top scanning and detecting unit, a control component and a data collecting and processing unit. The method comprises the steps that the intelligent power meter is placed on the workbench component; the top scanning and detecting unit moves to scan the boundary dimension of the upper surface of the intelligent power meter and dimension of relevant components; the workbench component moves, and the side face scanning and detecting unit scans positions and dimensions of a small hole and a large hole in the bottom of the intelligent power meter, and scans the position and the depth of a double-screw bolt in the large hole; all the data are collected into a computer, whether the dimension of the intelligent power meter is qualified or not is judged, and the dimension is displayed in a graph mode. By means of the device and method for automatically detecting the boundary dimension of the intelligent power meter, the important dimension of the intelligent power meter can be detected automatically, the data are processed, judged and displayed, efficiency and quality of detection production are improved, and accurate butt joint of detection ports of the intelligent power meter is ensured.

The invention discloses a forest fire point monitoring method comprising the following steps: using MODIS data to obtain parameter factors closely related to forest fire hazards like combustible moisture saturation capacity, temperature, humidity, and vegetation coverage rate; fully considering forest real conditions, organically combining all parameter factors, and building a fire monitoring model as fire point primary determining basis; eliminating water body and cloud interferences on said basis, thus obtaining real fire points. The forest fire point monitoring method can fast, automatically and accurately identify fire points, thus greatly reducing the error rate of abnormal interference points, and improving forest fire pint identification accuracy.

The invention relates to separation and characterization methods for heavy oil aromatic hydrocarbon components, two-dimensional liquid chromatography, and a device. The separation method includes: 1)dissolving the aromatic hydrocarbon components, and loading the sample to a coordination exchange chromatographic column of the two-dimensional liquid chromatography, the two-dimensional liquid chromatography further including a normal-phase chromatographic column at the downstream of the coordination exchange chromatographic column; 2) successively washing a first stationary phase of the coordination exchange chromatographic column and a second stationary phase of the normal-phase chromatographic column by means of a first moving phase, and bypassing the coordination exchange chromatographiccolumn, continuously washing the second stationary phase by means of the moving phase; 3) connecting the coordination exchange chromatographic column and bypassing the normal-phase chromatographic column, and washing the first stationary phase, in which sulfur-containing aromatic hydrocarbon, by using a second moving phase. By means of the separation method, light aromatic hydrocarbon components,medium aromatic hydrocarbon components, heavy aromatic hydrocarbon components and sulfur-containing aromatic hydrocarbons in heavy oil aromatic hydrocarbon components are separated high-effectively. The characterization method and device are high in speed and are high in automation degree.

The invention discloses a large intelligent sweeping robot, and belongs to the technical field of robots. A stretchable handrail is arranged above the front end of a robot body. A handle is arranged on the top of the stretchable handrail. A mechanical arm is arranged on one side of the robot body. The front end of the mechanical arm is connected with a trimming device. Universal wheels are arranged at the bottom of the robot body. A sweeping device is arranged in the middle of the universal wheel. A traveling data recorder is arranged on the front side of the robot body. A traffic light distinguishing device is arranged below the data recorder. An alarm device is arranged on the rear side of the robot body. A driving device is arranged inside the robot body. A center control chip is arranged on the driving device. A navigation device is connected with the driving device and the center control chip. The large intelligent sweeping robot is reasonable in structural design, convenient to use, good in flexibility, high in intelligent degree and capable of automatically distinguishing traffic lights, recording the whole driving process and trimming green belts, the road surface management efficiency is improved, the human cost is lowered, and popularization is facilitated.

The invention provides a fault detection method and device for a blockchain network, a computer readable storage medium and electronic equipment. The method comprises the steps of obtaining a currentblock of a distributed account book to be written into the blockchain network and block information thereof; determining that main node switching occurs when the current block is out of block based onthe block information of the current block; obtaining a current main node switching frequency and a current block level of the current block; determining a current fault node from current accountingnodes in a current accounting period of the blockchain network according to the switching times of the current main node and the current block hierarchy; and determining the current fault node of which the continuous fault frequency meets a fault recovery rule as a target fault node in the blockchain network. According to the technical scheme provided by the embodiment of the invention, the targetfault node in the blockchain network can be automatically and quickly detected.

The present invention relates to a hybrid vehicle managing method by means of a hybrid control device utilizing drive of an internal combustion engine and control of an electric motor depending on at least a charging state of an energy storer and position data of the hybrid vehicle. The position data of a traveled path is recorded; a path that is traveled for many times can be obtained by comparing the position data of the recorded paths, or comparing the position data of a recorded path and the position data of a traveled path; information of a flow of energy describing consumption / gain of energy along the path during travel on a route and depending on a position recorded with the position data is captured; the internal combustion engine and the electric motor are utilized to control participation of driving on a recognized path depending on need of energy / energy gain expected along the recognized path using the information. The invention also relates to a corresponding hybrid control device.

The embodiment of the invention discloses a single-hand touch control method and device. The method comprises the steps of detecting and acquiring a first movement track of a finger of a user in an area within the preset range on a touch screen of a terminal, and controlling the terminal to be switched to the single-hand touch control mode according to the first movement track. By the adoption of the single-hand touch control method and device, single-handle touch control is more intelligent, easier and more convenient.

The invention relates to an information extracting method for a remote sensing image continuous target field based on cluster analysis, and belongs to the technical field of information extraction. The method comprises the following steps: carrying out feature analysis on original image data to find a maximum reference value or a minimum reference value of area character data of the target field to be extracted; carrying out threshold segmentation on the image data according to the maximum reference value or the minimum reference value; carrying out cluster analysis on the image data subjected to the threshold segmentation; rejecting a false target field from a target continuous field obtained by the cluster analysis; and carrying out mask processing on the image subjected to the false target field rejection and an original image to obtain a result image subjected to information extraction. With the technical scheme, the continuous field target can be identified and extracted more automatically; by using the cluster mode, on the basis of a target object, the image features endowed by the continuous field targets in different images are fully considered and the target which is really needed to be identified can be identified and extracted, therefore, compared with the prior art, the information extracting method has higher accuracy.

The invention discloses a wireless network-based vehicle auto-identification warning system, comprising a on-vehicle child node and a control center for receiving information of the on-vehicle child node to perform identity identification and for issuing stroboscopic instruction, the on-vehicle child node is arranged in the vehicle and is connected with the control center by wireless communication; wherein the on-vehicle child node comprises a first wireless communication module, an identity data storage module, a first microcontroller unit and a stroboscopic drive module and is used for, in accordance with the received stroboscopic instruction, executing stroboscopic movement in the stroboscopic frequency of the instruction; the control center comprises a second wireless communication module and an identity identification module and is used for comparing the received identity data of the on-vehicle child node with approved data in a database; and a stroboscopic instruction issuing module is used for issuing, according to the result of the identification module, standard stroboscopic instruction when the identity data is legal. The inventive implements the identification automatically and vehicle identification management efficiently, and is safe and reliable.

The invention discloses an automatic melon seed peeling and detecting device which comprises a rectangular base, wherein the upper surface of the rectangular base is fixedly connected with a rectangular working box body; an automatic melon seed clinging mechanism is arranged in the rectangular working box body; an automatic detecting mechanism is arranged on the lower surface in the rectangular working box body and is located on the right side of the automatic melon seed clinging mechanism; a mobile walking mechanism is arranged on the lower surface of the rectangular base; a qualified product bearing mechanism is arranged on the upper surface of the rectangular base and is located on one side of the rectangular working box body; a waste bearing mechanism is arranged on the upper surface of the rectangular base and is located on the other side of the working box body; a controller is arranged on the side surface of the rectangular working box body. The automatic melon seed peeling and detecting device has the beneficial effects of simple structure and high practicability.