124results about How to "Real-time judgment" patented technology

The invention discloses an image identification-based intelligent transformation substation state monitoring system, which is characterized in that: a camera is used for monitoring the states of a circuit breaker indicator, a pressure plate, a knob switch and the like on a switch cabinet in an intelligent transformer substation, the image of an area where a monitoring device is arranged is acquired, the states of each indicating lamp, the pressure plate and the switch are obtained by using an image identifying technology, and relevant identified states are transmitted to a background monitoring system through a 61850 protocol, so that automatic management of the running situation of the intelligent transformer substation is realized.

The invention belongs to the field of automobile audio technology and particularly relates to a system and a method for automatically adjusting a sound effect mode of a vehicular audio system in an automobile. In order to solve the problem that through a traditional audio system, a user only can manually adjust different sound effect modes, the system for automatically adjusting the sound effect mode of the vehicular audio system comprises a passenger distribution recognition unit and an audio processing unit, wherein the passenger distribution recognition unit is used for recognizing position distribution information of passengers in the automobile; the audio processing unit can adjust the sound effect mode of the vehicular audio system according to the position distribution information of the passengers in the automobile; and the audio processing unit pre-establishes a corresponding relation between the sound effect mode of the vehicular audio system and the position distribution information of the passengers in the automobile. Through the technical scheme, the sound effect mode of the vehicular audio system is adjusted according to the position distribution information of the passengers in the automobile, the passengers in the automobile can hear an optimal sound effect without the need for manual adjustment by the user, and therefore user experience is greatly improved.

The invention discloses a wiring judgement control machine for a wiring simulation system for verification on a power transformer. The wiring judgement control machine is composed of a drive output module, an acquisition input module, a polarity and signal discrimination module, an RS232 transceiver, an MCU (microprogrammed control unit) module, a power supply unit, etc; the MCU module is in one-way connection with the drive output module, the acquisition input module, and the polarity and signal discrimination module, and is in two-way connection with the RS232 transceiver; and the whole controller adopts a digital integrated circuit, and is used for rapidly judging the wiring relationships of 48 connecting wires under the management of embedded software, and uploading the result to an upper PC (personal computer) continuously and in real time, so as to perform further processing such as a judgement about right or wrong. Via the wiring judgement control machine disclosed by the invention, an effective solution is provided for a wiring judgement for the conductor terminal of each simulator in the wiring simulation system for verification on the power transformer.

The invention combines RFID dedicated read / write device with handset including SIM card. Characters of the invention are as following: RFID read / write chip capable of reading / writing RFID electronic label and external antenna connected to the said RFID read / write chip are setup on card body of SIM card; RFID read / write chip is connected to IC chip in SIM card. The invention makes general handset implement function for reading and writing RFID electronic label so as to constitute handset with RFID reader / writer built in.

The invention relates to a lower limb movement pose quick predicting system based on fusion of a plurality of sensors. The lower limb movement pose quick predicting system comprises surface myoelectricity sensors, inertial sensors, a pose responding module, a pose resolving module and an external auxiliary device, wherein the external auxiliary device is worn to the waist and the lower limbs of awearer; the surface myoelectricity sensors are used for obtaining muscle surface myoelectricity signals of the lower limbs of the wearer in a real-time manner; the inertial sensors are fixed to the external auxiliary device; the pose responding module is used for determining the motion state corresponding to the current muscle surface myoelectricity signal of the lower limbs according to the collected sequencing of each muscle surface myoelectricity signal; and the pose resolving module is used for performing short time dynamic weighting data fusion on each joint movement angle collected by the inertial sensors and the joint movement angle estimated by resolving, so that the lower limb movement posture and the position coordinates of the joints of the wearer are obtained in a real-time manner. The invention further provides a lower limb movement pose quick predicting method. Through the adoption of the lower limb movement pose quick predicting system and method disclosed by the invention, the movement pose of the lower limbs of the human body can be quickly predicted, and besides, the estimating accuracy of the continuous movement amount is improved.

The invention provides an identification method for judging home invasion in real time, belonging to the security field of video surveillance. The method comprises the steps of: collecting a real-time surveillance video or image and preprocessing the video or the image; and identifying the invasion time, number, body figures and threatening degree of the invaders in the surveillance region by zoning and segmentation processing. According to the method, the problems that the current video or image surveillance system is only used for static forensics and cannot identify a warning condition or give an alarm without the assistance of other sensors are solved; and specific information of the warning condition such as the number, body height, body width and threatening degree of the invaders can be analyzed by the method according to the surveillance video or image, and the surveillance effect and the alarming effect for the surveillance region can be greatly improved.

The invention discloses an online power transmission tower monitoring method and system of the power system. The monitoring method comprises the steps of data collection, data transmission, data display and analysis and early warning. The monitoring system comprises an onsite data collector, a data transmission module, a database, a data display module and an analysis and early warning module, wherein the onsite data collector synchronously collect four parameters including the wind speed and the wind direction of the wind-field environment of a power transmission tower as well as the vibration acceleration of the power transmission tower and the rod member strain of the power transmission tower, the data transmission module transmits received data to the data display module, the data display module displays the received data via a display interface, and transmits the received data to the analysis and early warning module, and the analysis and early warning compares the wind speed and the wind direction of the wind field environment, the vibration acceleration of the power transmission tower and the rod member strain of the power transmission tower with preset alarm values in the analysis and early warning module, emits alarm signals when the alarm values are exceeded, and thus, prevents the tower from falling off and prevents wires from being broken.

The invention relates to a dual-camera face living-body detection method based on thermal-imaging effect. The method is characterized by using the thermal-imaging effect as living-body features of a living-body face, and thus distinguishing between the living-body face and a non-living-body face through detecting whether a face region simultaneously meets three criteria of the thermal-imaging effect. The method comprises the following specific steps: collecting a photograph by a visible-light camera for face detection; locating a face position of the visible-light photograph, and collecting the face position in the photograph by a low-resolution thermal-imaging camera; carrying out image morphology processing and convex-hull detection on a face position of a thermal-imaging image; and judging whether the face position of the thermal-imaging image meets the three criteria of the thermal-imaging effect, determining the same as the living-body face if the three criteria are simultaneouslymet, and otherwise, determining the same as the non-living-body face. The method is suitable for use in face recognition and living-body authentication systems of access control attendance, site monitoring and the like, and has capability of preventing malicious cheating of photographs or videos on the systems.

The invention relates to a sensory evaluation method for predicting fermented yogurt based on a BP neural network, having the following benefits: adopting a computer system with objective mechanical measurement as input and subjective sensory evaluation as output and realizing prediction via the accurate value measured by the instrument, thus not only reducing human input and lowering the evaluation cost, but also rapidly and accurately determining sensory evaluation result of fermented yogurt in real time. The method realizes that physicochemical index measurement replaces sensory evaluation detection and follows the development direction of the food industry. The method of the invention is simple and convenient, low in realization cost, easy for operation and result analysis, suitable for predicting preference sensory evaluation of various food after adaptability modification and wide in application field.

The invention discloses an intelligent landslide catastrophe monitoring method based on L-type liquid metal antennas. The intelligent landslide catastrophe monitoring method based on the L-type liquid metal antennas includes the following steps that first, a certain number of L-type liquid metal antennas are arranged in a landslide body to be monitored; second, the natural frequency of the L-type liquid metal antennas is measured; third, data of the natural frequency of the L-type liquid metal antennas are transmitted; fourth, the data are analyzed and a landslide alarm is given out. The intelligent landslide catastrophe monitoring method based on the L-type liquid metal antennas has the advantages that the anti-interference capacity of a circuit, the automation degree and the measurement precision are high, and the changes of the state of the landslide can be remotely monitored in real time.

The invention discloses an intelligent power grid fault positioning method and device. The method and the device monitor the operation temperature of distribution lines of the intelligent power grid system in real time, determine the normal operating state or abnormal fault operating state, warn about the area where the fault occurred, automatically estimate the location of the high-risk distribution network rack prone to occur fault and make an early warning mark, transmit the information through a communication function to a power grid base station and push it to the power grid operation andmaintenance personnel, so that faults can be processed more timely, and the influence caused by faults on the operation of the power grid is reduced. Measures can be taken in time for potential safety hazards to reduce the occurrence of operational faults. The distribution lines of each remote area are monitored in real time, so that the fault points can be intelligently judged, positioned in time and alarm can be timely raised when the remote areas occur an emergency situation, such as damage and fault of the distribution lines, so as to improve the operation and maintenance efficiency of the power grid.

The invention relates to a method for judging a laser cleaning effect according to a time-resolved spectrum. The method includes the steps that a detection wavelength is selected; a laser irradiates the surface of an object to be cleaned, and a plasma spectral line is acquired; a time-resolved spectrum signal of the selected wavelength is acquired; the cleaning effect is judged according to the time-variation characteristic of the acquired signal. According to the method, the cleaning effect is judged according to the time-resolved spectrum, which is a new judgment method. Real-time, fast and accurate judgment of a high repetition frequency laser cleaning effect can be carried out, the method lays a foundation for closed-loop control, the damage risk of a metal substrate is greatly reduced, a purpose of efficiently cleaning is achieved, and the method has the advantages of being high in efficiency and low in cost.

The present application provides a collision detection method, device and apparatus based on unmanned vehicle and a storage medium, wherein, the method includes: acquiring first point cloud data of each obstacle on each area around the unmanned vehicle, the first point cloud data characterizing coordinate information of the obstacle, and the first point cloud data being based on a world coordinatesystem; converting the first point cloud data of each obstacle into a second point cloud data based on a relative coordinate system, wherein the origin of the relative coordinate system is a point ofan unmanned vehicle; determining the likelihood of a collision of an unmanned vehicle based on the second point cloud data for each obstacle in all areas. The method does not depend on the world coordinate system, and provides a way to detect collision without relying on more modules and subsystems based on the parameters of the world coordinate system, so as to improve the reliability and stability of collision detection. When the positioning system of the unmanned vehicle fails, the collision detection can be completed by using this scheme.

The present invention discloses a deep learning-based signal lamp duration detection method and belongs to the field of image processing and pattern recognition. According to the technical scheme of the invention, a vehicle-mounted camera system is adopted to collect the image of a signal lamp. The image of the signal lamp is subjected to size normalization, and the digital of the signal lamp is centered, wherein the size of the image is fixed to be 32 * 32 pixels. A fast feature-implanted convolution structure is adopted to train samples in a training set, so that a training model is obtained. Based on the weight file of the well trained training model, the image of the signal lamp, collected by the vehicle-mounted camera system, is subjected to signal lamp duration detection. Therefore, the detection accuracy of the signal lamp is greatly improved, and the duration of the signal lamp can be detected in real time. In this way, the information of the signal lamp at an intersection can be timely obtained.

The invention discloses a bus signal triggering priority determination method based on virtual electronic fence. The method includes the following steps: 1. arranging a virtual electronic fence on an electronic map and acquiring coordinate information of the virtual electronic fence, on the basis of the driving direction of the roads that are fenced by the virtual electronic fence, arranging an entrance strategy, wherein the virtual electronic fence includes a terminal yard terminal electronic fence, bus stop electronic fences, road section electronic fences and intersection electronic fences. The virtual electronic map forms a multilateral electronic triggering region; 2. determining the relationship between the current position of a bus and the electronic triggering region; 3. If the current position point of the bus is within the electronic triggering region, determining the current driving behavior of the bus; and 4. on the basis of the current driving behavior of the bus, determining whether to trigger a bus priority signal. The method uses the information acquired by using the electronic map and an onboard positioning navigation terminal, and real-time determines whether to trigger a bus priority signal.

The invention discloses an indoor positioning and tracking system based on grating matrix technology, comprising an indoor grating arrangement and a monitoring system. The indoor grating arrangement refers to a grating matrix system arranged horizontally or vertically in a room. The monitoring system comprises a data generating transmitting module and a background data processing system. The datagenerating transmitting module is integrated with the grating receiving tube, and transmits the state information data of the grating receiving tube to the background data processing system in real time. The background data processing system automatically marks and connects the coordinate positions of the continuously moving persons or objects according to the related information to obtain a real-time moving track of persons or objects, and performs the identification confirmation with the identity registration condition of persons or objects entering the room. According to the indoor positioning and tracking system based on grating matrix technology, the grating matrix of the system is simple to construct, small in investment, accurate in positioning and good in popularization prospect.

The invention provides a vehicle steering judgment method based on image ambiguity comparison. The method includes the steps of collecting driving images of a vehicle at all moments in real time through a camera shooting device, receiving the driving images and dividing the driving images into a plurality of sub-images, extracting the sub-images sensitive to gray level and color gradation changes to form ROI areas, symmetrically dividing each ROI area into a left area and a right area, calculating the image ambiguity degree of each area, counting the difference values between the image ambiguity degrees of the left areas and the right areas of the ROI areas composed of 300 or more driving images corresponding to different speeds, calculating mean values and variances of all the difference values at the corresponding speeds, and judging whether the vehicle is in the turning state or not and judging the steering direction of the vehicle according to the difference value between the image ambiguity degrees of the left area and the right area of the corresponding ROI area at the current speed of the vehicle. The method is small in calculation amount, the turning state of the vehicle can be rapidly judged in real time without being limited by day or night conditions, and the method is particularly suitable for back-mounted portable navigation products.

The invention relates to a method and a system for scheduling vehicles. The method comprises the following steps of: A, acquiring vehicle information, wherein the vehicle information comprises a vehicle serial number, a vehicle state and a relative position; B, placing a vehicle icon corresponding to the vehicle serial number at a corresponding position of a virtual line scheduling graph according to the vehicle state and the relative position, wherein the virtual line scheduling graph comprises a line list which consists of a plurality of independent lines; each line comprises an uplink line, a downlink line, line description and the vehicle icon; and each vehicle icon corresponds to a vehicle with a specific serial number; and C, displaying the virtual line scheduling graph updated in the step B. The invention also discloses the system for scheduling the vehicles. The system comprises a vehicle information acquisition unit, a vehicle state judgment and processing unit, a display unit and a scheduling unit. The system realizes convenient, rapid and accurate monitoring and scheduling by the method for scheduling the vehicles visually by utilizing the virtual line scheduling graph.

The invention is suitable for the field of highway bridge detection. If a bridge support or a stretching device is damaged, under the excitation action of dynamic loads, the stretching device or a beam body can generate longitudinal shock vibrations. The invention discloses a method for evaluating the longitudinal shock resistance of a highway bridge support and a stretching device quickly. According to the method, a vibration data acquisition module for acquiring a longitudinal acceleration response signal of an object to be evaluated, a longitudinal shock resistance evaluation model which defines calculating and grading methods of the longitudinal shock resistance and the shock resistance deterioration rate, and a deterioration process database for storing the evaluation results of the longitudinal shock resistance and the shock resistance deterioration rate in all detection periods, tracking and monitoring the change of the shock resistance deterioration rate, and diagnosing and identifying the early deterioration and damage of the shock resistance are included. According to the method, the detection efficiency is improved, and the reliability of checking and evaluation is improved.

A method for judging the residual film on a sample by optical measurement, the sample includes a first metal film and an insulating film, the change of the reflectance of the first metal film depends on the wavelength of the measurement light, and the insulating film is on the first metal film Formed above, the residual film is a second metal film above the insulating film, the method includes: irradiating the sample with measuring light, so as to measure the change of the intensity of light reflected from the sample as the wavelength of the measuring light changes, thereby obtaining a reflectance spectrum curve ; and dividing the reflectance spectral curve into several wavelength regions, so as to judge whether there is a second metal film above the insulating film according to the waveform in each spectral region of the reflectance spectral curve.

The invention discloses a fault detecting method of a subway video monitoring system. In the method, video sources, transmission networks, servers and display terminals in the subway video monitoring system are regarded as testing objects, the system is provided with a video monitoring testing module which is connected to an automatic detecting module through the network; videos transmitted in the network are acquired by the video monitoring testing module, after the characteristics of the video data are analyzed, the characteristic data of the relevant acquired data is transmitted to the automatic detecting module through the network; the automatic detecting module collects the video data corresponding to the testing objects and the network characteristic data, and the link where the monitoring video generates faults is judged according to the characteristics of each testing object data and the difference among data of the different testing objects. Through the method, the equipment and the region resulting in monitoring video faults can be effectively identified, so that the operator and the maintenance personnel can conveniently locate them and the subway video monitoring system is recovered for normal operation.

The invention provides a voice following method capable of feeding back loud-reading progress of a user in real time. The voice following method capable of feeding back the loud-reading progress of the user in real time includes the following steps: (1) inputting text to be tracked; (2) setting up tracking decoding networks according to the text and transmitting the tracking decoding networks and an acoustic model to a decoder; (3) collecting acoustic feature sequences in real time and transmitting the acoustic feature sequences to the decoder in real time; (4) judging the loud-reading progress of the user in real time by the decoder, and meanwhile detecting whether the user reads contents irrelevant to the text or not loudly by the decoder or not; (5) displaying the tracking progress in real time. The voice following method capable of feeding back the loud-reading progress of the user in real time solves the problem that normal tracking is not achieved because the user does not read in order abnormally, improves ability of anti-interference of environmental noise of the system, and ensures that the function of voice loud-reading tracking really achieves practical levels.

The invention discloses an electronic rearview mirror system and a vehicle. The electronic rearview mirror system comprises a plurality of cameras, a display screen and an image integration processingmodule. The image integrated processing module comprises an image acquisition module, an image processing module and an image display module; the image processing module selects to-be-displayed imagedata based on the image data acquired by the image acquisition module and an actual vehicle signal, recombines the to-be-displayed images and splices the to-be-displayed images to form a whole-screensingle-picture image, or cuts the to-be-displayed images into a plurality of continuously arranged sub-images in the transverse direction or the radial direction according to a preset proportion. According to the invention, images obtained by the plurality of cameras are spliced or segmented and thus the plurality of cameras correspond to one display picture; the driver can accurately and quicklyobserve and judge the visual fields of multiple visual angles in real time, and change and display of a display picture along with the running state condition of the vehicle are realized through control, so that distortion of image display is avoided, and the running safety is greatly improved.

The invention discloses a prompting method and system of a waterlogging road condition. The method includes the following steps: S1: connecting a plurality of bulbs in parallel and marking a vertical distance of each bulb with the ground on each bulb; S2: a humidity sensor sending signals to an embedded gateway when detecting that the humidity of the air exceeds a preset value, and then the embedded gateway controlling the plurality of bulbs to light up at the same time; S3: pressure sensors arranged on the same horizontal plane with the bulbs sending signals to the embedded gateway when detecting that the water pressure is larger than a set threshold, then the embedded gateway sending a lighting-off command to an execution node and then the execution node lighting off bulbs which are on the same horizontal plane with the pressure sensor. The humidity sensor is used to sense the humidity of the air so as to judge whether it is raining so as to control on-off of an intelligent light system and through the pressure sensors, the depth of the rain of a waterlogging pool is sensed to control on-off the bulbs so that the heights of light-up bulbs are heights not reached by the waterlogging and thus it is convenient for drivers to judge accurately and rapidly the condition of the waterlogging in a rainy day.

The invention discloses an intelligent range hood. The intelligent range hood comprises a check valve capacitor unit, an information processing unit, a main control unit and a motor driving unit, wherein the check valve capacitor unit, the information processing unit, the main control unit and the motor driving unit are connected in sequence; the check valve capacitor unit generates different capacitance according to the opening and closing states of a check valve; the information processing unit collects the generated capacitance and converting the capacitance into a rectangular wave; the main control unit collects the frequency of the rectangular wave and the running state of the current range hood, judges the opening and closing states of the current check valve in real time according to the frequency size and the running state of the rectangular wave and generates different control signals according to different opening and closing states; and the motor driving unit drives a motorto operate at different gears according to different control signals so as to automatically adjust the opening and closing states of the check valve when the opening and closing states of the check valve is detected to be abnormal. According to the scheme, the intelligent range hood has the advantages that the opening and closing states of check valve blades can be accurately detected, the workingstate of the range hood can be accurately judged in real time, and the automatic respiratory function of the range hood can be achieved.

The invention discloses a method for detecting the stereo degree of an autostereoscopic display by using random dot stereopsis. The method comprises the following steps: (1) designing random dot stereogram groups to compose the random dot stereopsis; (2) constructing a geometric model of binocular disparity to calculate a theoretical stereo depth value S obtained by both eyes; (3) observing the random dot stereopsis by eyes through the autostereoscopic display to obtain the actual stereo depth value; and (4) comparing the theoretical stereo depth value with the actual stereo depth value, calculating the error percentage epsilon of the actual stereo depth value in relative to the theoretical stereo depth value, and determining the stereo degree of the autostereoscopic display according to the error percentage. The method is visual, convenient, accurate and real-time in detecting the stereo degree. The random dot stereogram has controllable disparity, and the method can determine the stereo degree of the autostereoscopic display by observing the random dot stereopsis composed by random dot stereograms with different disparities, and comparing the actual stereo intensity with the theoretical value.

The invention discloses a Chinese character text line writing quality automatic evaluation method and system based on time sequence point set calculation. The method comprises the specific steps of obtaining point set data of a handwriting Chinese character text line writing track of a user; performing line division according to the obtained point set data; performing word segmentation by adoptingan image processing method according to the line division result to obtain a line axis; calculating user handwritten text line index characteristics by using the line axis description; performing quality evaluation scoring according to indexes in the handwritten text line of the user. The method can be used for judging whether the handwritten Chinese character text line of the user is neat or notand conforms to the general aesthetic principle or not, can be applied to chapter training in hard-tipped pen writing teaching, can also be used for text line personalized writing guidance and the like, and has important practical significance.

The invention relates to the field of vibration detection, in particular to a portable crystallizer vibration amplitude and horizontal oscillation measuring system of a continuous caster, providing reliable evidences for technicians to regulate and maintain a crystallizer. The system at least comprises vertical displacement sensors, horizontal displacement sensors and a processing and analyzing unit and is characterized in that the vertical displacement sensors and the horizontal displacement sensors are distributed on a crystallizer vibrating platform; the crystallizer vibrating platform of the continuous caster vibrates at a frequency of 0.35-6Hz and the processing and analyzing unit synchronously acquires vertical vibration quantity and horizontal oscillating quantity signals of each distributed vertical displacement sensor and horizontal displacement sensor at the adoption rate being bigger than the vibration frequency of the crystallizer vibrating platform, and the processing and analyzing unit obtains the casting blank quality and the relation between the vibration amplitude and the frequency influence of the crystallizer vibrating platform of the continuous caster through processing and analyzing the vertical vibration quantity and the horizontal oscillating quantity. The system is beneficial to carrying out real-time reconstruction, record, analysis and judgment on the crystallizer vibration amplitude and horizontal oscillation, thereby providing the reliable evidences for the technicians to regulate and maintain the crystallizer.

The invention discloses an automatic real-time solar radio burst detection method based on image processing. According to the method, the detection of solar radio burst is regarded as moving object detection for a solar radio spectrum image, the idea of a Gaussian mixture model is adopted to detect the moving region of the solar radio spectrum, accurate quantization is performed on the detected burst region, the burst strength, burst bandwidth and duration are extracted, and two parts, namely the automatic detection of solar radio burst and the extrication of parameter values of the solar radio burst are included. According to the invention, the parameter values of the solar radio burst are extracted automatically, the detection work of solar radio burst, which is completed manually and wholly, is completed automatically through an image processing method, so that efficiency and accuracy of parameter extraction are improved; the solar radio burst detected in real time and extracted burst parameters are provided as data for early warning of severe space weather in real time; before the severe space weather, the modern equipment system is adjusted, so that the influence brought by severe space weather is reduced as far as possible.

The application provides a simulation test device and a simulation test method for cement sheath micro annulus space. The device comprises an inner cylinder and an outer cylinder, wherein an annular space is formed between the inner cylinder and the outer cylinder; the inner cylinder and the outer cylinder are both installed on a pedestal; a port of the inner cylinder is enclosed by an inner cylinder upper cover; a port of the outer cylinder is enclosed by an outer cylinder upper cover; the inner cylinder upper cover is provided with a through hole; a high pressure oil pipe is embedded in the through hole; the outer cylinder upper cover is provided with a small hole; the pedestal is provided with a small hole; gas can be injected in the annular space through the small hole in the pedestal; the injected gas can be discharged through the small hole in the outer cylinder upper cover; two ultrasonic imagers are installed at two sides of the outer cylinder so as to scan the outer cylinder and the inner cylinder. The simulation test device and simulation test method for cement sheath micro annulus space of the application can determine in real time whether or not micro annular space generates and obtain the cementation condition of cement and cylinder walls in a visualized mode.