49results about How to "Accurately get the location" patented technology

The invention discloses a real-time gesture interaction method based on computer vision, which comprises the following steps: acquiring a digital image from an image input device; detecting hands by a statistical learning method; initializing a hand contour tracker according to the detecting result, and calculating a skin color model of a specific hand; tracking the hand contour by a combined method of a conditional probability density transmission algorithm and a heuristic search technology; analyzing the moving track of the hands by a Hidden Markov Model to obtain the gesture identifying result; and applying the gesture analyzing result to the interaction of various application programs. The real-time gesture interaction method of the invention expands the interactive mode of the traditional mouse and keyboard, realizes automatic hand detection, tracking and gesture identification by the computer vision and image processing techniques, has real-time performance, robustness and easy realization and operation, and can enable computer users to interact with the computer more naturally, visually and intelligently by hand gestures.

The invention relates to a traffic guiding system for assisting blind person to pass the intersection, as the prior sound hint system has bad guiding effect. The invention comprises a positioning device, a guide line, an electronic cane and a traffic light controller. Wherein the positioning device is arranged embedded to the ground adjacent to the outlet of the typhlosolis corresponding to the intersection. The guide line is arranged at the road between two positioning devices corresponding to the two sides of the road. The electronic cane and the positioning device establish optical communication with the opposite infrared light transmitting circuit and infrared light detection circuit through respective infrared light detection circuit and the infrared light transmitting circuit. The wireless communication circuit of the traffic light controller is connected with the wireless communication circuit signal of the electronic cane. The invention has simple technology and can obtain the position and direction of advance of blind persons, which is convenient for the traffic light controller to provide relative information and guarantee the safety of blind persons to the maximum.

The invention relates to a multifunctional intelligent vehicle networking terminal and a method for implementing the multifunctional intelligent vehicle networking terminal, aiming to solve the problem that the existing vehicle-mounted satellite communication products do not have the function of automatically diagnosing the vehicles. The multifunctional intelligent vehicle networking terminal comprises hardware and software; the hardware comprises an upper cover, a lower cover, a satellite positioning system module, a communication antenna, a satellite positioning antenna and the like; the software comprises an operation system layer, a driving layer and an application program layer; the operating system is an embedded real-time operating system and takes charge of the scheduling, management and communication of all tasks; the driving layer is mainly used for completing the configuration, reading, writing and starting of all modules; and the application program layer is used for filling different functions by calling the interface function of the driving layer. Combined with an e-line vehicle networking service system and an intelligent mobile phone, the multifunctional intelligent vehicle networking terminal can realize monitoring, dispatching, fuel consumption management, mileage management, fault diagnosis, a real-time road condition acquisition, incident detection, driving behavior optimization, automatic hibernation, remote upgrade and the like. The multifunctional intelligent vehicle networking terminal is convenient to install and easy to use and has small size and low cost.

The invention provides a browser testing method and a browser testing device. Screenshot of a control or area of a to-be-tested browser is packaged into a testing program, the screen image of equipment where the to-be-tested browser is located is read, and image matching is carried out on the read screen image and the acquired browser control or area image, so that the position of the to-be-tested control or area of the browser is accurately acquired, and automatic testing is carried out on the position, therefore the problem that the testing program cannot be in common use caused by difference of browsers in different operating systems and different platforms is solved, and the browser testing accuracy and efficiency are improved.

The invention relates to an intelligent ship path planning method based on a fast search genetic algorithm. The method comprises the steps of (S1) performing rasterization on a test site electronic chart, obtaining obstacle points for the rasterized chart, obtaining starting point coordinates and target port coordinates, presetting a maximum number G of iterations, an initial temperature T0, an ending temperature Tf and an attenuation value a, and obtaining an initial path set pop0 and an inflection point of an unmanned ship, (S2) obtaining the inflection point spacing sum D of each path in the initial path set pop0, and (S3) obtaining an updated path set popm through G times of iterations by using crossover, variation, proportional selection and annealing optimization operations accordingto the inflection point spacing sum D, a target temperature T and a preset attenuation value a, performing temperature updating according to an attenuation coefficient a, and selecting a shortest path in the updated path set popm as an optimal path when T is smaller than Tf. The planned path of the invention has a small steering angle, the trajectory is smooth, an obstacle is actively avoided, the method is close to actual navigation application, the convergence speed is fast, and the problem that a traditional genetic algorithm is easy to fall into a local extremum is overcome.

The invention discloses an intelligent firefighting rescue command and dispatch system. The intelligent firefighting rescue command and dispatch system comprises a main individual transmitter, a positive pressure air breathing apparatus, an intelligent firefighting bracelet, an audio and video helmet, a Mesh network repeater, an interphone, an emergency command box, a positioning module and a main positioning IPC (Industrial Personal Computer), wherein the main individual transmitter performs information exchange with each of the positive pressure air breathing apparatus, the intelligent firefighting bracelet, the audio and video helmet and the Mesh network repeater through the wireless network, the Bluetooth, signal lines and the Mesh network, so as to monitor the on-site rescue situation in real time; the emergency command box performs information exchange with the 119 command center through 4G; and the positioning module is connected with the main positioning IPC through a wireless serial port to realize the positioning of rescue workers. According to the intelligent firefighting rescue command and dispatch system, the seamless information integration of a plurality of departments is realized through the effective network convergence, and meanwhile the vital signs of rescue workers and the air pressure values in air bottles can be monitored in real time, an early warning is given to the rescue workers, and the expansibility is good due to reserved interfaces.

The invention discloses an automatic deviation correction laser navigation system, which comprises a moving trolley, photosensitive batteries, a rotary laser, a bracket, a laser controller, a laser wireless communication module, a vehicle-mounted wireless communication module and a vehicle-mounted controller, wherein the vehicle-mounted controller has two working modes; and when left-right deviation of the moving trolley is small, the vehicle-mounted controller is used for controlling the moving trolley to turn leftwards, turn rightwards or stop turning according to the positions of the photosensitive batteries at the front end of the trolley. When the moving trolley deviates the central line greatly, a rotation instruction is transmitted by the vehicle-mounted controller, a laser rotation device is controlled to rotate by the laser controller according to the rotation instruction, the moving trolley target is actively searched by the rotation laser, and a left-right turning judgment is made by the vehicle-mounted controller according to the photosensitive battery signal change condition around the moving trolley. The automatic deviation correction laser navigation system has the advantages of simple control model, high extensibility, wide application range, capability of automatically returning the moving trolley to a set path without manual control in case of large deviation and the like.

The invention discloses a single cell sorting device and method based on image processing and ink-jet printing. The single cell sorting device comprises a micro-fluidic chip, an image acquisition device, an image processing and control unit, a displacement actuator, a liquid container and a displacement table, Liquid containing cells flows in a pipeline in the micro-fluidic chip under the drive ofpressure, when the image acquisition device shoots and recognizes a target object needing to be screened, the control unit drives the displacement actuator to generate the action of knocking the chip, micro-droplets containing single cells are printed out from a nozzle of the micro-fluidic chip, and in combination with the displacement table, different target cells are divided into different droplets. The microfluidic cell printing technology provided by the invention is combined with an in-situ image detection technology, so that high-precision cell sorting can be realized.

The invention discloses a single-soldier emergency rescue intelligent wearable device, which comprises an indoor positioning module, a smart bracelet, a help-calling device, an audio and video helmet,a MESH host, a plurality of MESH repeaters, an MESH receiving host and an emergency command box, wherein the indoor positioning module sends a signal to the help-calling device through a first Bluetooth module; the smart bracelet sends a signal to the help-calling device through a second Bluetooth module; the help-calling device receives the signals sent by the indoor positioning module and the smart bracelet through a Bluetooth main control module and sends the signals to the emergency command box through a radio frequency module or a first wireless communication module; the video and audiohelmet is connected with the MESH host; the MESH host sends the signals to the MESH receiving host through the MESH repeaters, or sends the signals to the base station through a second 4G / 5G module;the server of the emergency command box receives the signals sent by the help-calling device and the MESH host, and sends the received signals to a command center through a third wireless communication module. The single-soldier emergency rescue intelligent wearable device in the invention realizes multifunctional, high-reliability, wide-protection and light-weight emergency rescue protection.

The invention belongs to the field of image processing and photoelectricity and particularly relates to a ship-based image-stabilizing method based on sea-sky boundary detecting. The method comprises the following steps that denoising and down-sampling processing are carried out on surveillance video image frames; longitudinal projection vectors of down-sampling images are established, the changing rate vectors of the longitudinal projection vectors are obtained, the changing rate highest point is extracted as a sea-sky boundary reference position; a zone comprising the sea-sky boundary reference position is intercepted at a certain height in an initial image; edge extracting and Hough converting are carried out on the zone in sequence, the maximum value in a Hough zone is a straight line parameter of the sea-sky boundary; the initial image is subjected to horizontal moving and rotating converting according to the straight line parameter of the sea-sky boundary, and converting results are used as an image-stabilizing result image to be output. According to the method, influence caused by noise of a sea surface and sky can be effectively removed, the position of the sea-sky boundary in the image can be accurately acquired, and an image-stabilizing function is achieved.

The invention discloses a shared bicycle parking detection method based on video progressive area extraction, which comprises the following steps of: carrying out attention area extraction processingon a video image to obtain a background image; clustering the length and width of a target object in a training set image; according to the clustering results, adjusting the regional generatgion network parameters of a regional convolutional neural network, and extracting the candidate regions of the target object by the regional convolutional neural network. In the process of adopting the targetdetection technology, the invention utilizes the existing well-deployed monitoring video system to adjust the region generation network parameters of the region convolution neural network of the clustering result of the target object by using a clustering method, so that the position and classification of the target object can be accurately obtained, and the management standard of the target object can be facilitated. The shared bicycle parking detection method and system based on the video progressive region extraction of the invention can be widely applied in the field of image processing.

The invention provides a cable well environment monitoring method based on the Internet of Things, comprising the following steps: based on the position information of a cable well, paving a temperature sensing cable in the cable well, and paving a temperature measuring optical fiber along the temperature sensing cable; monitoring temperature data information of the temperature sensing cable in real time; monitoring temperature and humidity data information of the cable well; obtaining an abnormal temperature point and an abnormal temperature and humidity point of the cable well; obtaining mapposition information of the abnormal points of the cable well, and transmitting the cable well map information of the abnormal points to a mobile communication terminal of a monitoring contact through a communication module; and triggering a physical alarm of cable well abnormality. The invention further provides a cable well environment monitoring system and device based on the Internet of Things. According to the cable well environment monitoring method, system and device based on the Internet of Things provided by the invention, the system platform issues alarm information in the form of aphysical alarm mode, and a user is notified by an APP or a short message, thereby effectively realizing double insurance and guaranteeing the safe production of a power company.

The invention provides a failure point positioning method and a chip failure analysis method. Specifically, a chip comprises a substrate and a device located at the substrate. The positioning method includes: conducting thinning treatment on the back of the chip to a state close to the device; carrying out ion beam bombardment on the back of the chip subjected to thinning treatment so as to make an ion beam pass through the device; and performing electron-beam scanning on the front of the chip subjected to ion beam bombardment so as to position the location of a failure point in the chip. By means of ion beam bombardment on the back of the chip subjected to thinning treatment, the method provided by the invention makes the ion beam pass through the device and generates a breakdown area in the device, so that when a to-be-detected surface of the chip is scanned by electron beam, the surface charge generated on the to-be-detected surface can be released along the breakdown area on the device surface, the influence of surface charge on the device surface potential can be reduced, and then the position of the failure point in the device can be acquired accurately.

The invention discloses an artificial intelligence information management system based on multi-sensor fusion. The system comprises a fire-fighting acquisition and positioning terminal, a mobile terminal acquisition module, a data fusion processing module, a fire behavior simulation analysis module, a spreading trend prediction module and a fire behavior tracking calibration module. According to the artificial intelligence information management system based on multi-sensor fusion provided by the invention, data analysis and fusion processing are carried out on the collected fire parameter information so that the fire combustion danger levels in the detection areas where fire-fighting detection units are located are analyzed, the escape emergency danger coefficient of the personnel in each detection area is judged according to the number of mobile terminals in the detection area, data collected by multiple sensors are fused and displayed, the system has the characteristic of intelligent information management, a reliable escape route is provided for guiding the personnel to escape in the later period, and the safety of the personnel is improved.

The invention belongs to the technical field of uranium ore geology research and uranium resource region evaluation, and particularly relates to a geological drilling spatial trajectory restoration method. The method comprises the following steps of performing three-dimensional conversion of a generalized geological map; performing spatial locating of a prospecting line profile map, performing three-dimensional conversion on a prospecting line planar projection map by utilizing two-point coordinate conversion to obtain a converted prospecting line planar projection map, and performing three-dimensional conversion on a prospecting line longitudinal projection map by utilizing the two-point coordinate conversion to obtain a converted prospecting line longitudinal projection map; and restoring a drilling trajectory. According to the method, a spatial form of drilling can be obtained; a stratigraphical position and an ore discovery position can be accurately obtained; and exploration engineering deployment can be restored to the maximum extent.

The invention provides a dam interior inertial navigation monitoring device automatic traction system comprising a traction device. The traction device is internally provided with winding devices which are driven to rotate by a driving device. A traction rope is wound on the winding devices and is connected with a monitoring device which walks along a flexible test tube. The dam interior inertial navigation monitoring device automatic traction system also comprises rotatable first guiding wheels. The traction rope is wound on the first guiding wheels. A wrap angle guiding wheel is arranged at the front and back parts of the first guiding wheels so as to increase the wrap angle of the traction rope on the first guiding wheels. An absolute value photoelectric encoder is arranged on the first guiding wheels or the winding devices. According to the dam interior inertial navigation monitoring device automatic traction system, the position of the monitoring device in the flexible detection tube and walking speed can be accurately acquired by the arranged absolute value photoelectric encoders with cooperation of a PLC or a single-chip microcomputer.

The invention brings forward a moving target tracking method based on a matrix low-rank representation theory in the framework of a particle filter theory. A moving target observation matrix composed of image sequences is decomposed into a low rank matrix representing a moving target and a sparse matrix representing shields; the low order matrix is used as a moving target model, and the sparse matrix is used as a target shielding model; a target observation probability optimization equation is established by using the moving target model and the target shielding model; the moving target model and the target shielding model are solved separately by using an optimization algorithm; and the moving target model and the target shielding model are substituted into the target observation probability optimization equation to calculate a moving target observation probability required by target tracking so as to achieve the tracking of a moving target. According to the invention, a problem of tracking drift and even target losing after the moving target is shielded is solved, thereby improving the anti-shielding ability of the moving target tracking. The moving target tracking method of the invention has high robustness.

The invention provides a building high-altitude parabolic point blind-vision quantitative evidence obtaining method and a building high-altitude parabolic point blind-vision quantitative evidence obtaining system. A first camera and a second camera are arranged at the right corner and the left corner of the top of a building respectively to shoot parabolic videos, and the positions of parabolic points are determined in the modes of video frame-by-frame point tracing superposition, parabolic point imaging included angle calibration, wall-attached imaging surface parabolic point calculation andactual parabolic point calculation. According to the blind quantitative evidence obtaining method and system for the high-altitude parabolic point of the building, the first camera and the second camera are deployed at the crossed visual angle, the imaging range is adjusted to be close to the floor, it is ensured that the private space of all owners is shielded in an imaging blind area, and therefore various disputes and litigation caused by privacy leakage are avoided; according to the invention, through frame-by-frame point-tracing superposition, calibration and analysis processing of the parabolic video, the parabolic trajectory is reconstructed, the position of the parabolic point can be accurately obtained, and evidence obtaining quantification is achieved.

A wearable intelligent sensing blind guiding system disclosed by the present invention comprises an MCU main control unit, a binocular camera, a voice broadcast module, a GPS positioning module, a local memory, a 4G / 5G communication interface and an antenna, the binocular camera is connected with the MCU main control unit through a USB interface, the GPS positioning module is connected with the MCU main control unit through a UART interface. The local memory is connected with the MCU main control unit through a bus interface, the 4G / 5G communication interface is connected with the MCU main control unit through a DTU interface, the 4G / 5G communication interface is connected with an antenna, and the voice broadcast module is connected with the MCU main control unit through a UART interface; the binocular camera collects environment information, and the MCU uses a CNN deep learning neural network model to detect various obstacles on a walking channel of the visually impaired person, determine distances and orientations of the obstacles, reasonably plan a walking route, identify zebra crossings and traffic lights at a traffic intersection, and prompt the visually impaired person to walk through voice.

The invention discloses an infrared thermal image-based fire early warning and early elimination system, wherein a thermal infrared imager is used for acquiring an infrared thermal image of monitored equipment; an image analysis controller is used for analyzing the infrared thermal image and generating an analysis result; and a fire alarm and linkage controller is used for generating a control signal according to the analysis result of the image analysis controller. By acquiring the infrared thermal image of the equipment, analyzing the temperature field distribution and changing to prevent a fire disaster, the probability of the fire disaster of the equipment is reduced; and linkage with a fixed-point fire extinguishing device can be realized to perform early fire elimination, and the timeliness of fire handling is improved. The infrared thermal image-based fire early warning and early elimination system has the characteristics of high control accuracy and low rate of false alarm.

The invention discloses a device for accurately positioning tray holes on the basis of machine vision. The device comprises a framework, an image acquisition device, a conveying device, a positioningdevice and a control system. The conveying device is mounted on the framework, and the image acquisition device is used for acquiring images of trays; the positioning device comprises a fixed barrier,an adaptive barrier, pressure plates and photoelectric sensors for detecting the locations of the trays; the trays, the conveying device and the positioning device have different colors; the controlsystem is mounted on the framework, signals transmitted by the photoelectric sensors can be received by the control system, the image acquisition device can work under the control of the control system, and the acquired images can be processed by an image processing module of the control system, so that the tray holes can be positioned. The device has the advantage that the problems of poor tray hole positioning adaptability, low operation efficiency and positioning precision and the like of industrial seedling growing at present can be solved by the aid of the device.

The invention discloses an object identification method, which comprises the following steps: detecting an object, acquiring a related data set, calibrating an image of a target object data set by using an image marking tool for the acquired data set, performing data enhancement on the acquired data set, extracting a detected target object, and performing category classification, to classify the categories of target objects into a large category and a small category; and performing relation processing on the target data set to form a relation hierarchical graph, constructing large category and small category matching weight matrixes through the relation hierarchical graph and cosine similarity, and determining the category of an object and the object through an object identification network and the matching weight matrixes. The object identification method is accurate in identification, and can identify a plurality of objects of uncertain categories.

The invention provides a silk screen printing device. The device comprises a rotary disc, wherein a positioning station and a printing station are sequentially arranged in the circumferential direction of the rotary disc; at least one printing table which is arranged on the rotary disc, wherein when the rotary disc rotates, the printing table is driven to rotate to the positioning station and theprinting station; a positioning system which is located at the positioning station and comprises an infrared light source and an alignment camera, wherein when the printing table rotates to the alignment station, the infrared light source and the alignment camera are both located above the printing table; and a printing system which is located at the printing station and is in communication connection with the positioning system. According to the silk screen printing device, the infrared light source emits infrared light to the back surface of a silicon wafer, and the alignment camera capturesreflected light of the infrared light on the back surface of the silicon wafer to form an image, so that the position of a positioning pattern can be accurately obtained, and back surface grid linescan be accurately printed; and the width of the back grid line is reduced to 140 microns, so that the double-sided efficiency of the double-sided cell is improved.

The invention belongs to the technical field of glass defect detection, and particularly relates to a device and method for detecting and identifying glass defects and particularly Pt flashing pointsin glass. The device comprises a sample carrier unit, defect detecting unit and a defect distinguishing unit, the optical system structure of the detecting device is reasonable, and the device can beexclusively used in detecting the Pt flashing points in the glass; the device effectively solves the problem of the macroscopic optical quality detection of large-size glass, and the device completelyavoids a detection drawback of only detecting a small part of to-be-detected sample to judge whether or not the Pt flashing points exist in the large-size glass. The device not only can detect the Ptflashing points in the glass, but also can detect stones and bubbles in the glass, the device is multifunctional, and the device has low manufacturing cost; a defect position in the glass is firstlydetermined by the defect detecting unit during use, and then the defect distinguishing unit is started to identify a defect type in the glass, scan detection is carried out on the glass layer by layer, the defect position and type in the large-size glass can be accurately obtained, and the operational method is easy.

The invention provides a failure point positioning method and a chip failure analysis method. Specifically, a chip comprises a substrate and a device located at the substrate. The positioning method includes: conducting thinning treatment on the back of the chip to a state close to the device; carrying out ion beam bombardment on the back of the chip subjected to thinning treatment so as to make an ion beam pass through the device; and performing electron-beam scanning on the front of the chip subjected to ion beam bombardment so as to position the location of a failure point in the chip. By means of ion beam bombardment on the back of the chip subjected to thinning treatment, the method provided by the invention makes the ion beam pass through the device and generates a breakdown area in the device, so that when a to-be-detected surface of the chip is scanned by electron beam, the surface charge generated on the to-be-detected surface can be released along the breakdown area on the device surface, the influence of surface charge on the device surface potential can be reduced, and then the position of the failure point in the device can be acquired accurately.

The invention discloses a machine vision technology based leather detection device. The device includes a support, an industrial camera, an LED lamp and a control device; the industrial camera can take pictures of leather on a conveyor belt; the LED lamp can illuminate the leather on the conveyor belt; and the control device can obtain the area and position information of the leather by taking pictures of the leather on the conveyor belt through the industrial camera, and control a nozzle to perform spraying on the leather on a corresponding position or with a corresponding area on the conveyor belt when the leather is conveyed to a spraying chamber by the conveyor belt. A leather detection method is also disclosed. The method includes the following steps: 1, performing camera calibrationon the industrial camera, and determining the position of a spray gun and the speed of the conveyor belt being V; 2, obtaining the area of the leather or the position information of the leather on theconveyor belt; and 3, controlling, by the control device, the spray gun to perform spraying on the leather on the corresponding position or with the corresponding area. Thus, the positions of the leather can be accurately detected and measured; the scope of detecting and measuring the positions of the leather is large; and the device and method are stable and reliable in operation.

The invention relates to a radar signal phase encoding law recognition method and device. The method includes the following steps that: radar pulse signals are acquired; wavelet filtering processing is performed on the collected radar pulse signals, so that filtered radar pulse signals can be obtained; the abrupt change points of the filtered radar pulse signals and the corresponding positions ofthe abrupt change points are determined; and intervals between every two adjacent abrupt change points are calculated, and the intervals are sequentially recorded; and the encoding law of the radar signals is recognized according to the sequentially recorded intervals. The method of the invention has the advantages of simplicity, high reliability and high radar number recognition accuracy.

Therefore, the real-time traffic risk AI prediction method and system based on the driving path provided by the invention are characterized in that the method comprises the following steps: S1, establishing an urban road model; s2, establishing a traffic risk level model based on real-time computer simulation or vehicle positioning information; s3, performing real-time traffic risk prediction by using the established traffic risk model to obtain prediction data; or the method comprises the steps of S1 to S3, and further comprises the steps: and S4, according to the continuously accumulated prediction data, executing any one or a combination of the work of enhancing traffic supervision, improving road construction, optimizing a safe driving scheme of a driver and establishing a relation model between weather and the prediction data. According to the invention, real-time monitoring of urban road risks is realized, and big data support is provided for traffic construction, current and historical driving records of search vehicles and local weather conditions.

The invention provides a central control system of an electric scooter. The central control system comprises a scooter central controller and a position server; the scooter central controller comprises a GPS positioning module, a CPU, a WIFI module and an MCU module. The scooter central controller communicates with the cellular network module through the asynchronous transceiver to achieve communication with the Internet and is in communication connection with the position server through the communication module, and a WIFI module of the scooter central controller is set to be in an STA mode;the scooter central controller finds a corresponding position server through an IP address on the Internet; in the position server, GPS coordinates, MAC addresses and floor information of AP hotspotsand RSSI attenuation signal values of the AP hotspots on different floors are stored. The invention further discloses an electric scooter positioning method. The central control system of the electricscooter allows a user of the service to accurately obtain the position of the scooter and enables the user to park the scooter in any area where the scooter is allowed to be parked.