544results about How to "Make up for limitations" patented technology

The invention discloses a crossroad traffic event automatic detection system based on multi-source information fusion. The invention aims at urban crossroad traffic management, establishes audio-video traffic information acquisition, traffic information analytical processing and traffic event automatic alarming three subsystems. The invention mainly comprises: designing and realizing an acquisition subsystem of multi-source traffic information (traffic audio information, traffic video information, multi-angle video information, elevation angle video information); realizing a traffic parameter automatic extractive technique based on traffic audio and traffic video; realizing a traffic event (car crash, illegal parking, jam and retrograde motion) automatic detection technique based on the multi-source information fusion; and realizing a software system for traffic event report, traffic event associated video information transmission, and traffic control center display and processing, and forming an integrated crossroad traffic event automatic detection system.

The invention relates to a pipeline detection robot. The pipeline detection robot mainly comprises a laser detection mechanism (1), a traction mechanism (2), an electromagnetic ultrasonic detection mechanism (3) and an electronic cabin (4), all of which are connected through connecting hinge shafts; the traction mechanism (1) adopts a single-motor all-drive mode and is driven by a turbo-worm synchronous belt to supply a walking power to the robot; the laser detection mechanism (2) comprises a laser displacement sensor, a rotating arm, a counterweight, a support body and the like and is used for measuring surface corrosion and deformation of a pipeline; the electromagnetic ultrasonic detection mechanism (3) comprises a support assembly, a probe and a fixing plate and is used for measuring the wall thickness and the crack defect of the pipeline; the electronic cabin (4) is used for carrying auxiliary components, such as a stepping motor controller, a servo motor driver, a power supply and an FPGA (Field Programmable Gate Array) control panel. The pipeline detection robot disclosed by the invention can be used for finding the defects, such as pipeline corrosion, cracks and deformation, carrying out in-service detection on an oil and gas pipeline in a working process, carrying out targeted repair, maintenance and replacement according to a detection result, reducing the maintenance cost and guaranteeing safe and stable operation of the oil and gas pipeline.

The invention belongs to the technical field of signal processing, and particularly relates to an electroencephalogram emotion recognition method based on a graph convolutional neural network. The electroencephalogram emotion recognition method provided by the invention comprises the following steps: firstly, constructing an emotion-related function connection mode according to the correlation between electroencephalogram channel signals; then modeling each extracted single-channel electroencephalogram feature into a graph signal based on a function connection mode structure, and establishinga graph convolutional neural network model; inputting a training set graph signal to carry out iterative optimization training on the model, and optimizing network parameters by adopting a back propagation algorithm and a cross entropy loss function; and finally, inputting a test set graph signal into the trained graph convolutional neural network, and performing classification recognition on thetiter, wake-up and dominance three-dimensional emotion model. According to the electroencephalogram emotion recognition method, the spatial and functional relationship of the electroencephalogram datais restored, so that electroencephalogram emotion features with higher discriminability can be extracted; and the channel electrode most relevant to emotion can be selected according to the channel correlation, and processing time and hardware cost are reduced while the number of channels is reduced.

An image-based character recognition method is characterized by comprising steps as follows: an acquired image is divided into multiple areas; character areas in the multiple areas are detected to acquire the position information of the character areas and types of characters in the character areas; the character areas are screened to determine the to-be-recognized character area; on the basis ofthe types of characters in the to-be-recognized character area, characters in the to-be-recognized character area are recognized by use of a designated recognition model.

The invention discloses a real-time traffic condition judging method based on a time window. The method comprises the following steps of: performing data preprocessing; performing traffic state clustering initialization through a two-step clustering algorithm; updating the time window to obtain the traffic flow base data of a current time interval; and updating two-step clustering algorithm parameters and a clustering center, and judging the real-time traffic state of the current time interval. According to the invention, based on historical traffic flow base data, the traffic state clustering initialization is performed by a two-step clustering algorithm, and the optimal classification of the traffic state is obtained through primary selection of the optimal cluster number and determination of the optimal cluster number respectively; then, based on the initialization result, the real-time data is introduced, and the data is updated dynamically by use of a storage structure of the time window; and finally, the two-step clustering algorithm parameters and the clustering center are calculated and updated in real time, the optimal classification of the traffic state is re-determined, and the real-time traffic state of the current time interval is judged. The method makes up for the limitation of the conventional traffic state judging algorithm, and is of positive significance to promoting the construction of the urban intelligent transport system.

The invention discloses a method for evaluating the quality of a traditional Chinese medicine product, belonging to the technical field of traditional Chinese medicine. The method includes the following steps: obtaining a fingerprint atlas of a target traditional Chinese medicine product; calculating the equality degree according to a formula I based on the obtained fingerprint atlas and the standard fingerprint atlas of the traditional Chinese medicine product; and comparing the equality degree and a preset threshold value, if the equality degree E is not less than the threshold value, the traditional Chinese medicine product being qualified, otherwise, the traditional Chinese medicine product being defective. The formula for calculating the equality degree, provided by the method of theinvention, is a comprehensive improvement for each similarity calculating method in the prior art, can compensate for a plurality of limitations of the present similarity calculating method in the practical application of the traditional Chinese medicine, has a plurality of advantages, is suitable in a plurality of complex circumstances existing in the actual present situation of traditional Chinese medicine, and has wide application value.

A method for monitoring fatigue strength of driver includes shining driver eye with infrared ray to obtain multiimage of different retina image at the same time, carrying out difference processing for collected images to obtain pupil images, using kalmen filter to trace pupil in real - time to obtain pupil characteristic parameter, processing the parameter to obtain maximum value of pupil size and real - time coroclisis percentage of pupil, calculating out PERCLOS value f and using BP network sorter to judge fatigue strength of driver based on obtained value f. The monitoring device is also disclosed.

The invention relates to a virtual camera and real camera switching system and method. The system comprises a real camera, wherein the real camera is connected with a chroma key device, a synthesis rendering server is connected with a virtual camera controller, a virtual camera parameter generating device connected with the real camera and the virtual camera controller is arranged inside the synthesis rendering server, a virtual camera and the virtual camera parameter generating device are connected with a synthesis device, the synthesis device is connected with the chroma key device, and a foreground generating device, a background generating device and an output device which are connected with the synthesis device are further arranged inside the synthesis rendering server. According to the method, virtual foregrounds, virtual backgrounds and virtual persons are fabricated in field and are fast synthesized, the switching of a field real scene and a virtual scene is realized through the operation of the virtual camera controller to the scene, the limitation of the real camera when the real camera shoots a virtual object is compensated, and the program expressive force of a virtual studio is greatly improved.

An engine operated generator is provided with an engine, a generator driven by the engine, and a power control unit for controlling the power generated by the generator. A fuel gas stored in fuel bottles set in a case for the engine operated generator, is supplied to the engine though a fuel pressure regulator. The fuel bottles and the fuel pressure regulator are disposed adjacent to the power control unit to enable heat exchange with the power control unit provided with an inverter. Thus, heat is mutually utilized between the power control unit and at least one of the fuel bottles as fuel receptacles and the fuel pressure regulator.

The invention discloses an application multidimensional privacy leak detection method and system for iOS platform; privacy leak detection is provided for iOS applications from the three dimensions, static analysis, dynamic analysis and data analysis, wherein the static analysis incudes the steps of application decrypting, app storage path locating, disassembling, and disassembly source code sensitive API (application program interface) analysis; the dynamic analysis includes the step of allowing Hook-sensitive API function to acquire a log record by running an application, and acquire a sensitive API calling sequence through log analysis; the data analysis incudes the steps of capturing application network data packets, and analyzing data packet protocol, address and content. The method and system of the invention can provide comprehensive detection for data privacy leaks of iOS applications to obtain complete privacy leak event data.

The invention discloses a pneumatic / structure / static aeroelasticity coupling optimizing method for a high-aspect-ratio wing. The pneumatic / structure / static aeroelasticity coupling optimizing method is based on the system decomposition strategy in multidisciplinary optimization for system-level decomposition and subsystem-level decomposition. In pneumatic subsystem-level decomposition, the pneumatic performance under the cruising appearance serves as an optimal object, and the rigidity-appearance pneumatic performance in traditional pneumatic optimization is replaced; after pneumatic subsystem-level decomposition is completed, and pneumatic loads, pneumatic appearance design parameters and structural configuration parameters serve as the input conditions for structure subsystem-level optimization; after pneumatic subsystem-level decomposition and structure subsystem-level decomposition are completed, the target quantity of system-level decomposition is output, system-level decomposition is returned, and therefore the pneumatic / structure / static aeroelasticity multidisciplinary comprehensive optimization design process is achieved through iterative optimization of the pneumatic appearance parameters and the structure parameters.

The invention provides a tendency analysis method of a public opinion based on word2vec. The method comprises a vector training phase, a key sentence extraction phase and a tendency discrimination phase; by extracting news key sentences, the discriminant feature space is reduced, contents with relatively large relevance with the original theme are remained, useless information is eliminated and the accuracy of tendency analysis of the public opinion is improved; a depth learning model word2vec is introduced into the tendency analysis of the public opinion, and used for comparing the semantic similarity between words and comparing the semantic similarity through word vectors, so that words with the same emotional tendency but not in an emotion dictionary can be well identified, thus even if the emotion dictionary is not complete, a better analysis effect can be obtained, and meanwhile, weighted calculation is performed on the emotional tendency of the key sentences by fusing a grammatical rule; and combined with contextual information, the limitation of simply using the semantic similarity is compensated, and the tendency is analyzed integrally from the sentences, so that the emotional tendency and emotional intensity of news texts of the text level are accurately discriminated.

A lightweight common webpage topic crawler method based on a search engine comprises the steps as follows: initializing seeds, namely extending a small amount of given related seeds describing specific topics to a series of seeds according to a certain rule; discovering websites, namely converting the initialized seeds into query words, and obtaining a plurality of related websites through an interface of the search engine; downloading the websites, namely downloading the related websites to a local machine and storing the related websites into a database; analyzing web pages, namely analyzing the downloaded websites to obtain link information in the websites; updating the seeds, namely analyzing crawled new websites, extracting topic related words from the crawled new websites, creating new seeds by the topic related words, and guaranteeing a crawling process to be continuously proceeded; updating the crawling process, namely, calculating a re-crawling cycle according to the update information of the crawled websites, and enabling the crawled websites to be automatically updated in a self-adaption way. The method has the characteristics of low cost, simplicity for realization, high efficiency, accuracy and the like.

The invention discloses a POI (Point of interest) and remote-sensing image integrated urban function zone division method. The method comprises the following steps of (1), obtaining POI data, remote-sensing images and space geographic entity data of a region; (2), selecting classes sensitive to urban function zone division from class attributes of the POI data, thereby forming evaluation classes,forming function POI data based on the POI data corresponding to the evaluation classes, matching the function POI data with the space geographic entity data, thereby obtaining an initial distributionstructure of each class of POI data in each geographic entity; (3), extracting land cover data from the remote-sensing images of the region; (4), making a decision tree classification rule based on the initial distribution structure of each class of POI data in the (2) and the land cover data in the (3); and (5), dividing urban function zones of the region according to the decision tree classification rule. According to the method, on the basis of a decision tree classification algorithm, the POI data and Landsat remote-sensing data are combined, so the urban function zones are rapidly divided.

The invention relates to the technical field of battery detection, and discloses a method and system for quantifying the health state of a battery based on SOC section estimation, so as to improve thefunctions of a battery management system and to provide convenience for the battery management system to evaluate the battery state in real time. The method of the invention comprises comprehensivelyevaluating the health of the battery by using an analytic hierarchy process by using a charging rate as a core in combination with the internal resistance of the battery, and based on the remaining power based on SOC section estimation and the temperature factor. The method and the system for evaluating the battery health state comprehensively evaluate various factors that affect the battery performance, reduce a battery performance change probability during the later use of the battery, and can easily evaluate the performance state and the service life of a battery pack. In addition, the evaluation method can be integrated into the battery management system to improve the functions of the battery management system. The battery management system can conveniently perform routine maintenance detection and evaluation on the battery state in real time.

A method and a system for processing a reflected microwave signal generated by a radar level a gauge system arranged to transmit microwaves towards the material in the tank, and receive a reflection of said microwave signal as a tank signal. The tank signal is processes by a plurality of processes, each process being adapted to determine a process variable in a specific region of the tank, each specific region corresponding to a predefined propagation distance range. Such multi-processing of the received tank signal has the advantage that each process can be optimized to that particular region of the tank. More specifically, a process concerned with a particular region of tank only needs to treat a portion of the tank signal.

The invention relates to a method for generating a real-time gait path of a biped robot. The method includes steps of forming an oscillator network by means of omni-directionally coupling four oscillator neural units, designing mapping functions and generating sole paths of the biped robot in an online manner; forming a gravity center path generator by three oscillator neural units and generating three-dimensional gravity center paths of the robot in an online manner; enabling sensors to detect environmental information, creating a feedback circuit, and adjusting the sole paths and the gravity center paths in real time to obtain the gait paths with environmental adaptability; and optimizing parameters of a control system by a multi-objective evolutionary algorithm to obtain the optimal gait path. The oscillator network can output four channels of oscillator signals with adjustable phase relations. Compared with the prior art, the method has the advantages that abundant dynamic characteristics and the characteristic of capabilities of coupling walking environments and feeding information of the oscillator neural network are sufficiently utilized, so that the gait path generated in an online manner is adaptable to the walking environments to a certain degree.

The invention provides a combined type measurement and three-dimensional reconstruction method combing a Kinect device and an articulated arm measuring instrument. Firstly, quickly obtaining point cloud data of an object through the Kinect, performing secondary measuring on feature information which cannot be obtained by the Kinect and on features with high accuracy requirements through the articulated arm, completing fusion of different data source information by means of point cloud registration technology, and reconstructing a three-dimensional model of the object. According to the combined type measurement and three-dimensional reconstruction method combing the Kinect device and the articulated arm measuring instrument, non-contact measurement and contact type measurement are combined together, not only the problem of low accuracy of the non-contact measurement can be solved, but also point cloud data with lost boundaries and concave holes and the like can be effectively repaired, meanwhile, measuring efficiency can be improved, and novel technology and means are provided for data acquisition.

The invention discloses an indoor and outdoor separation method for a multi-dimension measurement report. The indoor and outdoor separation method is used for effectively compensating the limitation of an MR grid evaluation method. A multi-dimension indoor and outdoor MR separation method is formed based on an indoor source signal separation method, an outdoor test feature separation method and a user mobility separation method for distinguishing indoor and outdoor MR data, in order to form indoor and outdoor MR grids for evaluating the quality of wireless networks in residential buildings, office buildings, hotels and other indoor scenes and various outdoor road scenes.

The invention discloses a multi-assortment commodity price expectation data pre-processing method based on neural networks. The best order of magnitude of commodity price data which is obtained from websites is calculated by an improved radical basis function (RBF) neural networks and an improved back propagation (BP) artificial neural networks. The calculated best order of magnitude is used to preprocess normalized order of magnitude of the commodity price. Expectation accuracy of the RBF neural networks and the BP neural networks is improved. Generality of the RBF neural networks and the BP neural networks for expectation of different kinds of commodity prices is improved.

The invention relates to a bending and horizontal type reshaping method of a high-pressure bend, mainly comprising the following steps of: 1, feeding a tube blank with the outer diameter of D(1+delta) and same wall thickness as that of the bend; 2, heating a straight tube blank into a austenite structure, and then placing on a concave mould of a bending mould preheated to 200-300 DEG C, wherein aconvex mould downwards moves with a cross beam positioned on a press till the convex mould and the concave mould are closed for pressing bending deformation, after the bending mould is closed, the section of a cavity perpendicular to an axial line is in the shape of an ellipse, a long axis of the ellipse is 1.2 times of the nominal diameter of the bend, a short axis of the ellipse is 0.8 times ofthe nominal diameter of the bend, and the bending radius of the middle of the convex mould is set to be 1.5-2.0 times of the radius of the bend to prevent the contact area of the middle of the tube blank and the convex mould from collapses so that the tube blank is integrally bent and the section of the tube blank is changed into the shape of the ellipse at the same time; 3, horizontally placing the tube blank which is initially formed after being bent in a concave mould cavity of a reshaping mould preheated to 200-300 DEG C, wherein the motion direction of the long axis of the sectional ellipse of the tube blank is the same as that of a reshaping convex mould, the reshaping mould is combined vertically so that the tube blank undergoes circumferential compression, and the elliptical section of the tube blank is reshaped into a circular section. According to the invention, the production efficiency is greatly enhanced, and the designing and processing periods of a mould are shortened; in addition, the bending and the reshaping moulds are simple and are easy to operate, so that vast manpower and material resources are saved.

A method for determining a power-save mode of multimedia application, when a user operates a computer system through a peripheral input device, an image sensor retrieves a first image data corresponding to the user's facial feature. Next, the first image data is stored into the computer system. Then, the computer system confirms whether an input signal from the peripheral input device is received or not within a preset time. Once the preset time is reached, the image sensor is used to retrieve a second image data. Then, the computer system compares the second image data with the first image data, and if the matching rate between the second image data and the first image data falls out of a specific range, the computer system enters the power-save mode.

An authentication method comprises the following steps of transmitting at least one first shooting parameter to a terminal device when a service processing request sent from the terminal device is received, and controlling a shooting device to acquire a face image for an authentication user by the terminal device according to the first shooting parameter; receiving the face image sent from the terminal device, matching a second shooting parameter of the face image with the first shooting parameter, and simultaneously matching the face image with a preset face image; and determining whether the authentication of the user is passed or not according to a matching result. Further, the invention also provides an authentication device and system. With the above authentication method, device and system, the safety of the authentication based on face recognition can be improved.

The invention relates to the field of metal pressure moulding and provides an overlarge type ring rolling machine which has large rolling force, good rigidity, high processing precision, high processing efficiency and low processing cost and can be suitable for the manufacturing requirement on a large cylindrical section. A stand of the overlarge type ring rolling machine comprises a drive side stand and an operating side stand which are longitudinally and oppositely arranged, both ends of each roll are supported, and axes are horizontally arranged; a drive roll is arranged at the lower part of the stand, and a core roll is positioned on the drive roll; at least one of double axial directions of the core roll is set to be a drawing direction of the core roll, one end of the core roll points to the other end along the drawing direction, the starting point end is a suspending end, and the terminal point end is a drawing end; a drawing unit comprises the core roll and a drawing end core roll bearing seat thereof or the core roll and core roll bearing seats at both ends of the core roll; the overlarge type ring rolling machine is provided with a roll drawing mechanism for doing reciprocating motion along the drawing direction of the core roll; and the roll drawing mechanism is provided with a detachable type fixing structure of the drawing unit. The invention is suitable for producing a large cylindrical section with large axial size, weight and wall thickness in the fields of large nuclear power, petrochemical container, aerospace, and the like.

The invention discloses an accurate path tracking control method of an unmanned ship based on dual-guidance of speed and course. The accurate path tracking control method of the unmanned ship based onthe dual-guidance of the speed and the course includes the following steps of calculating a path tracking error dynamic state; designing a dual-guidance law of speed and course; designing a finite-time unknown observer; and designing a non-smooth controller based on the finite-time unknown observer. According to the accurate path tracking control method of the unmanned ship based on the dual-guidance of the speed and the course, the dual-guidance law which can simultaneously guide the speed and a course angle according to tracking errors is put forward, so that position errors of the unmannedship can be stabilized to zero in finite time, the operating burden of a rudder is reduced, and the operation flexibility and integrity of a guidance system are improved; the dual-guidance law of thespeed and the course is designed to improve the operation flexibility and integrity of the guidance system, the finite-time unknown observer accurately observes complex external disturbances and internal uncertainties, and compensation is carried out in the non-smooth speed controller and a course controller, and thus the tracking accuracy of a path tracking control system is greatly improved.

The invention discloses a method and system for controlling hover, reconnaissance and strike integrated aircraft. The control system comprises aircraft, airborne weapon systems, airborne detection systems and a ground monitoring station; belly suspending plates are installed on the aircraft of all states and weapons are installed on the belly suspending plates, electro-optical pods can be installed and the lifting height of the electro-optical pods can be adjusted to prevent the firing of the weapons from being interfered, and other weapons can be suspended outside under wings or on a fuselagewhile the belly suspending plates are installed. According to the designing scheme of the method and system for controlling the hover, reconnaissance and strike integrated aircraft, the problem of limited weapon firing angle is solved, by arranging the belly suspending plates, missiles arranged on the suspending plates are capable of keeping in the same pointing direction with an observing and sighting device at any time, but synchronously alignment is not necessary, the missiles only need to be capable of keeping in the same pointing direction with the observing and sighting device at any time, or capable of pointing at the same direction along with the observing and sighting device, and therefore firing conditions can be set up at any time to overcome defects in the prior art.

The invention provides a dimensionality-reducing HOG-MBLBP fusion feature based traffic sign recognition method based on PCA.. The method of the invention comprises the following steps of: training aclassifier model by using a training sample; constructing a training sample database; extracting a training sample image of the determined training set for graying, extracting HOG features and MBLBP features; serially connecting two eigenvectors of HOG and MBLBP to obtain a HOG-MBLBP fusion eigenvector; the obtained fusion eigenvector being dimensionally reduced by using a PCA algorithm; a linearsupport vector machine (SVM) algorithm being used to train the obtained dimension-reduced fusion eigenvector to obtain an SVM traffic sign classifier; obtaining a traffic sign image; traffic sign images being recognized by the classifier model. The technical proposal of the invention solves the problems that the traffic sign recognition method in the prior art has low recognition accuracy rate andlong operation time, and is difficult to meet the requirement of vehicle-mounted real-time performance.

The invention discloses a fire ventilation and smoke exhaust experimental simulation device based on an urban underground traffic linkage tunnel system. The fire ventilation and smoke exhaust experimental simulation device comprises a simulation fire source device, a tunnel longitudinal smoke exhaust control optimization device, a fire detection device, a multi-feature parameter measurement device and a tunnel slope adjustment device. The fire ventilation and smoke exhaust experimental simulation device consists of four single hole tunnels, the fire ventilation and smoke exhaust experimental simulation device is placed in directions of up-north, lower-south, left-west and right-east, and an underground parking garage is arranged in the center; the fire ventilation and smoke exhaust experimental simulation device is provided with an emergency escape door, model vehicles, an inlet jet blower, an outlet jet blower, axial flow fans, jet flow fans and smoke exhaust ports; a plurality of the axial flow fans and a plurality of the jet flow fans are respectively arranged on walls and upper ends of the tunnels of the simulation device; and the slope of the tunnel device can be adjusted. The fire ventilation and smoke exhaust experimental simulation device can simulate fire smoke characteristics and fire detection performance of the urban underground traffic linkage tunnels, and provides a research platform for acquiring reasonable fire smoke control schemes and smoke exhaust effect of the urban underground traffic linkage tunnels.

The invention discloses a nanometer microcrystalline cellulose reinforcing polylactic acid glycolic acid electrospun membrane, a preparation method thereof and application and relates to the field of biomedicine. Two natural organic polymer materials of PLGA and CNCs are composited, the method of preparing the electrospun film through electrospinning can effectively enhance the strength and the bioactivity of the materials, give full play to the biological nanometer effect and effectively compensate for the limitation of pure PLGA in biomedical application, and wound healing is well facilitated. In addition, the CNCs reinforcing PLGA electrospun membrane prepared through the method can also be used in fields of medicine controlled slow-release, repair of organs, such as skin, nerve and heart, tissue regeneration and the like.