1847results about How to "Efficient determination" patented technology

The embodiment of the invention discloses a lane line data processing method and a lane line data processing device. The method comprises the following steps of: obtaining an original image and positioning data of the original image; using a deep neural network model for calculating the pixel confidence degree of each pixel, conforming to lane line features, in the original image; determining the lane line outlines from the original image, and using the lane line outlines as candidate lane line; calculating the lane line confidence degree of the candidate lane lines; screening the candidate lane lines according to the lane line confidence degree of the candidate lane lines; recognizing the attribute information of the lane line by aiming at the screened lane line; and determining map data of the lane line according to the attribute information of the lane line and positioning data during the original image shooting. The lane line data processing method and the lane line data processing device provided by the embodiment have the advantages that the lane line data can be efficiently and precisely determined; the labor cost in high-precision map production is greatly reduced; and the large-scale high-precision map production can be realized.

A pattern matching unit performs pattern matching on present data obtained this time in clinical examination of a part of a subject and previous data obtained last time in the clinical examination of the part with reference patterns. Reference patterns that are most closely approximate to the present data and the previous data are selected. A distance calculator calculates a distance between selected reference patterns. A determining unit determines whether a re-examination is necessary based on the distance.

The present invention is suitable for use in determining symmetry in images, namely 2D images or 3D images, which comprise 2D images slices. In a preferred form, a method is disclosed for extracting a midsagittal plane MSP of human brains from radiological images. The method includes the steps of: 1) determining axial slices to be processed from said radiological images; 2) analysing said axial slices to determine fissure line segments; and 3) calculating plane equation of MSP from said fissure line segments.

The invention discloses active video acquiring method and device based on binocular camera shooting. In the technical scheme, a main camera, a slave camera and an embedded intelligent analysis control system are installed in a same monitor scene; when a system works, a valuable target region which possibly exists is rapidly extracted from a monitor scene global video picture acquired by analyzing the main camera by the embedded intelligent analysis control systems at the front end, control parameters needed by the slave camera is calculated according to the target region position, and the slave camera is rapidly controlled to acquire high definition detail information from the camera. The invention can efficiently determine the valuable target region in the monitor scene, continuously trace a motion target and realize multi-target dynamic continuous tracing.

The invention discloses an inspection system and an implementation method for the electrical equipment of an unmanned aerial vehicle photovoltaic power station. The inspection system includes an airborne terminal, a ground terminal, and a wireless communication module. The camera or monitoring equipment collects the image data of the electrical equipment of the photovoltaic power station, and at the same time receives the control commands sent from the ground terminal to the airborne terminal; the ground terminal is set on the ground platform to process the data collected and sent back by the airborne terminal , to control the flight and shooting operations of the unmanned aerial vehicle on the ground; the wireless communication module completes the functions of transmitting flight control instructions, flight status data, and video return data between the airborne terminal and the ground terminal. The inspection system provides real-time high-definition viewing of infrared images and visible light images, which is convenient for timely resolution of faults. The images are analyzed on the ground side through pattern recognition. repair.

The invention discloses a method for screening traditional Chinese medicine effect related ingredients and a model building method. The method comprises the steps as follows: taking the researched traditional Chinese medicines as objects for preparing multiple sets of sample solutions containing chemical components with different concentrations; selecting part of the chemical components for HPLC (High Performance Liquid Chromatography) analysis, and investigating linear relations between the peak areas and the concentrations; selecting the multiple sets of sample solutions in the linear range, and determining the respective HPLC fingerprint spectrums and the medicine effect indexes of the sample solutions; and obtaining relations between the peak areas and the medicine effect indexes of the ingredients by adopting a linear regression analysis method in the linear relation range, and confirming the actions of the medicine effect related ingredients on the medicine effect indexes according to the positive value and the negative value of the standard regression coefficients and/or the t check results of the ingredients so as to screen out the traditional Chinese medicine effect related ingredients. The method is simple, convenient, easy to implement, reliable and good in commonality, can embody the characteristics of comprehensive actions of the multiple ingredients on the medicine effect indexes, is suitable for screening the traditional Chinese medicine effect related ingredients, and provides a technical data support for discovering and screening traditional Chinese medicine active ingredients.

The invention relates to a method of recognizing boarding of a passenger in taxi taking service and a related device. According to the method of recognizing boarding of a passenger in taxi taking service provided by the embodiment of the invention, after a first client and a second client receives an order, whether the second client is located in a preset region range is continuously detected; when the second client is located in the preset region range, whether the passenger finally boards the vehicle is determined further according to the vehicle driving state; and when the passenger is determined to board the vehicle whose driver receives the order, the second client and the first client automatically enter a to-be-paid state and a metering state respectively. The whole process is completed automatically, the driver or the passenger does not need to participate, operation of the two is simplified, the boarding time and the boarding site of the user can be accurately and effectively determined, metering is accurately carried out, and use experience of the user is improved.

The invention discloses a device and a method for testing a gas-liquid sulfur phase permeation curve of a high-temperature high-pressure high-sulfur-content gas reservoir. The testing device comprises a displacement system, a stratum condition simulation system, a back-pressure system, a data testing system and a data acquisition system. The testing method comprises the following steps: selecting and treating a rock core; preparing rock core saturated stratum water and liquid sulfur; simulating a high-temperature and high-pressure environment of the stratum; determining the condition of liquid sulfur phase permeability under irreducible water saturation; performing a phase permeation test on filling of gas-liquid sulfur according to a set ratio; recording the amount VSi of liquid sulfur and the gas amount Vgi generated totally; correcting the stratum condition; calculating the relative permeability Krs of the liquid sulfur phase, the relative permeability Krg of the gas phase and the gas saturation Sg of a rock sample at each moment and the like. The device and the method disclosed by the invention can be used for safely, conveniently, rapidly, accurately and efficiently measuring the high-temperature high-pressure gas-liquid sulfur phase permeation data and providing scientific data support for making a reasonable development scheme for the high-sulfur-content gas reservoir.

The invention relates to autonomous localization and navigation of mobile intelligent equipment such as service robots, unmanned aerial vehicles, automatic guided vehicles and indoor three-dimensionalmodeling equipment. Compared with the existing system, image-text recognition and semantic binding for indoor symbols are introduced. The characteristics are that (1) the recognized result of image-text recognition is high in accuracy compared with laser radar or road signs for visual recognition; (2) only a camera is required to be added, and the cost and the weight are low; (3) an accumulativeerror of sensors (an IMU, laser radar, vision, etc.) is effectively eliminated, and the accuracy of loop detection is improved; (4) the robot localization and navigation accuracy is improved on the whole by combining image-text recognition, and commercial use of robots is enabled to become possible; and (5) tool software provided by using the method combines a result of image-text recognition, endows an environment map with semantic information through manual binding, can promote man-machine communication and helps the robots to complete advanced tasks.

A method, a device and a computer program product for determining an electromagnetic near-field of a field excitation source of an electrical system are provided, in particular for analysis and/or optimization of an antenna radiation, of a cross-talk problem, of a signal reflexion/transmission, of a stray field, of an irradiation problem or the like. The method includes defining electrical and magnetic properties of the material distribution of the system, defining at least one field excitation source, and determining the electromagnetic near-field components within at least one and in particular all partitions by solution of the Maxwell's equations of the near-field, where each near-field component of each partition can be represented by a linear position of M predetermined ansatz functions P_i orthogonal to one another with regard to a scalar product and weighted with field coefficients v_i, and the spatial and/or time derivative of the near-field component can be determined as a linear position of these ansatz functions P_i weighted with derivative coefficients w_i, and where each coefficient w_i can be determined from a quantity of previously determined field coefficients v_i and derivative coefficients w_i, so that the determination effort of the near-field of the system rises in substantially linear manner to the number N of partitions in the domain under consideration and to the number M of ansatz functions P_i used in the linear position.

An apparatus for classifying a liquid patient sample includes at least one sample container having a quantity of a sample that is aggressively acted upon so as to create a flow field. A measurement mechanism includes at least one low angle light emitter aligned with a measurement window of the at least one sample container and a detector oppositely disposed relative to the measurement window. Measurement of the scattered light detects particle characteristics of a moving flow field from the sample to determine, for example, the amount of agglutination of the sample so as to perform blood typing or other classifications without spatial separation.

The invention discloses a regional early warning method based on a limited location. According to the divided geographic location ranges of different danger levels, a plurality of electronic fences used to represent different danger levels are set up, and the electronic fences are polygonal; each electronic fence is established. The outermost minimum rectangle of the electronic fence; take each side of the electronic fence as a diagonal line, and establish the minimum outer rectangle for each edge, according to the smallest outer rectangle as the leaf node, the outermost smallest rectangle of the electronic fence as the root node and the preset R The tree construction rules establish an R tree; obtain the position of the target in real time, and use the ray algorithm based on the R tree index to judge whether the position of the target is located in a certain electronic fence area; according to the judgment that the target is in a certain electronic fence, In this way, the danger warning level of the target position is divided. Notifications are made through Beidou satellite signals, enabling relevant personnel to leave the dangerous area in time.

The invention relates to an electromechanical device nonlinear failure prediction method, comprising the following steps: 1, obtain data which can represent the running state of a device and select a section continuous vibration signal which has a long course and is sensitive to the failure to analyze; 2, respectively carry out exceptional value elimination and missing data filling to the vibration data by a 3 sigma method and an interpolation method; 3, carry out noise reduction to the vibration signal by a lifting wavelet method; 4, decompose the vibration signal after the noise reduction to corresponding characteristic bandwidths; 5, obtain a low dimension manifold character by utilizing a typical predicted characteristic bandwidth and adopting a nonlinear manifold learning method through decoupling of topological mapping and non-failure energy information; 6, carry out intelligent failure prediction with long course trend in a time domain by utilizing a recurrent neural network which has the dynamic self-adaptive characteristic and a first dimension of the low dimension manifold character as a neural network input. The lifting wavelet method is adopted in the invention, the algorithm is simple, the arithmetic speed is high, and the used memory is less, thereby being suitable for the characteristic bandwidth abstraction of failure character. The electromechanical device nonlinear failure prediction method can be widely applied to the failure prediction of all kinds of electromechanical devices.

The invention provides a dish name recognition method based on OCR, which belongs to the technical field of OCR. The method comprises the following steps: taking a photo of a menu; lining a region to be recognized on the menu photo conforming to the definition requirement; carrying out intelligent regulation on the region to be recognized; and using an OCR engine for recognizing the regulated recognized region to obtain recognition texts. The method utilizes a dish name knowledge base for correcting the recognition texts, selects results with the maximum matching degree as dish name recognition results, and filters out meaningless recognition results. The rectangular region to be recognized is determined according to specified coordinate points, and the intelligent regulation is carried out on the basis, so the noise in the recognition process is filtered out to the maximum degree, and the recognition effect of the OCR engine is improved. Users can upload the recognition results to the web pages of catering industry through network for propaganda and reservation after the web pages issue more dish name information, and at the same time, the invention also brings convenience for lots of gastronomists to know and select the respective delicacies.

The invention provides a gait recognition method based on a partitioned matrix. Firstly, extracting single-frame images from a video, then carrying out grey scale transformation on the single-frame images, using the background subtraction method to extract person body targets, using mathematical morphology to fill the holes of binary images, and extracting profiles of the person by means of single connection analysis so that the person bodies are positioned in the middle and are uniformly in the size of 64 * 64 pixels; observing the periodic change of the gait according to elliptical short axis and eccentricity fitted in image regions after the standard centralization of each frame image in a gait video sequence; using a gait energy diagram to extract the integral characteristic of the gait in the one period, dividing GEI into sub-blocks by means of the partitioned matrix, eliminating the sub-blocks which are useless to classification in a self-adapting manner, and adopting the method, which combines the two-dimensional principal component analysis of a sub-block mode with the two-dimensional linear discriminant analysis, to further extract local characteristics; and integrating the characteristics of each effective sub-block into a whole during the classification recognition, and adopting a nearest neighbor classifier to perform identification judgment. The method is effective for the recognition of the gait of knapsack change.

The invention discloses a distributed video based highway traffic incident influence range dynamic monitoring method. The method comprises steps as follows: a plurality of high definition cameras are arranged on a traffic section of a highway at intervals; information of highway vehicle traffic state video images shot by the cameras are preprocessed with a video recognition method, and video characteristics are extracted; a fuzzy controller is established and used for detecting the traffic flow state; whether a traffic incident happens is judged; the queueing state is detected; a dynamic vehicle queueing length prediction model is established, and the vehicle queueing length is calculated through the model; the real-time queueing state is detected by the cameras finding the queueing event; and when the queueing phenomenon disappears, the traffic incident influence range is dynamically predicted by the dynamic vehicle queueing length prediction model. According to the method, the influence range and the queueing scattering time of the event can be determined by means of the estimated vehicle queueing length, and dispatch and decision bases are provided for highway traffic management staff.

The invention aims to provide a method and equipment for establishing map information and vehicle positioning. The method comprises the following steps: acquiring route information of a target road; on the basis of the route information, confirming a reference point of the target road; confirming coordinate position information of the reference point; and on the basis of the coordinate position information of the reference point, establishing a mapping relationship of the coordinate position information of a target and map positioning information. Compared with the prior art, the method has the advantages that the cost of map information establishment can be effectively reduced, the data processing time can be shortened, furthermore a vehicle driving technique on the basis of map information application can be promoted, and particularly development and popularization of an automatic driving technique can be promoted.

In a recording medium storing MPEG stream, flag information (encode_condition) indicating that the stream is recorded in a format enabling easily the first stream (MPEG transport stream) to be converted into the second stream (MPEG program stream) is provided. Such a flag information is included in Tip packet which is a control packet, in the medium. Thus it can easily determine whether the data is recorded in this format without analysis of data stored in the recording medium.

The embodiment of the invention discloses a detection method and device of an ONU (optical network unit) as well as a passive optical network system. The method comprises the following steps: in an uplink null window or blank timeslot, detecting an identification code of the ONU; and determining that the ONU corresponding to the identification code of the ONU as a rogue ONU according to the identification code of the ONU. The embodiment of the invention also provides a corresponding device and a passive optical network system. In the passive optical network system, fast and efficient detection is realized, the fast and efficient detection is realized, the rogue ONU is determined, and the influence on uplink business is reduced.

The invention relates to a character recognition method and device. The character recognition method includes the following steps that: a convolutional neural network is adopted to perform feature extraction on a character image to be recognized, so that a character feature value is obtained; and an MQDF classifier is adopted to perform classification processing on the character feature value, so that a character corresponding to the character image to be recognized can be obtained. According to the character recognition method and device provided by the embodiments of the invention, the convolutional neural network is adopted to perform feature extraction on the character image to be recognized, so that the obtained character feature value is more precise and has high anti-interference ability, and therefore, the accuracy rate of the character recognized by the MQDF classifier according to the character feature value is high.

The invention discloses a structured light measuring system calibration method based on sinusoidal grating. The method includes producing coding grating, setting up measuring system to capture calibrating board flat images, projecting coding grating, collecting, storing, confirming phase-unfolding initial points, solving wrapped phase and unfolding, restoring the calibrating board flat images of projector imaging planes, calibrating projectors according to the multi-group projector calibrating board flat images at different positions, calibrating cameras according to multiple camera calibrating board flat images at different positions, and acquiring rotation matrixes from projector coordinate systems to camera coordinate system according to calibrating results of the projectors and the cameras. The phase-unfolding initial point can be effectively confirmed by utilizing coding disc images, and image quality of image region is guaranteed to be high; and the designed phase-unfolding method has a noise-proof function, 'line-pulling' conditions in conventional phase-unfolding methods are overcome, and the designed structured light measuring system calibration method has the advantages of simple operation, strong robustness, high measurement accuracy and the like.