338results about How to "Realize real-time tracking" patented technology

The invention belongs to the technical field of computer application, and provides a method and a system for tracking, three-dimensionally superposing and interacting a target object without a special mark. The method comprises the following steps of: firstly, segmenting the target object from an image shot by a camera, and creating a characteristic template of the target object automatically; next, directly identifying the target object by utilizing the characteristics of the target object, and calculating three-dimensional information (relative to the camera) of the target object; and finally, superposing a virtual object or an animated picture in a three-dimensional coordinate system in a realistic space through a graphics engine in real time. According to the method disclosed by the invention, video images and template images are subjected to characteristic matching via a surf algorithm so as to finish the calibration on the camera, so that real-time tracking and real-time three-dimensional superposing of the target object without the special mark are realized; for each frame of video image, three-dimensional coordinate information of the target is calculated in real time, so that interaction of a person or an object in reality with a virtual person or a virtual object is realized; and therefore, the method and the system disclosed by the invention are relatively high in degree of automation and have relatively popularization and application values.

The invention relates to one intelligent trace system and discloses one system to focus its upper load camera machine onto one or more aim objects through main infrared positioning in level and vertical dimensional angel to judge aim object and system distance. The invention identifies the different aim objects through infrared emission machines codes to compute cameral lens level and forward and focus parameters to drive relative servo work.

The invention relates to a video monitoring system and method for target detection and tracking. The system comprises a video collection device, a target detection device, an information processing device, an information transmission device and an image collection device, wherein the image collection device is composed of a front end image collection device and a video decoding device and is usedfor obtaining a real-time video stream of a target object; the target detection device analyzes the position and the size of the target object in a video image; the information processing device performs real-time processing on related information of the target object within a continuous time to obtain a moving speed, a trajectory and direction information of the target object, and judges the number, the location and the size information of the target object in advance; the information transmission device sends the related information of the target object to the image collection device; and the image collection device controls the target object to always locate in a middle area of the screen and tracks the target object in real time. According to the video monitoring system and method, thetracking of numerous small targets is facilitated according to the deep neural network with multiple features, the recognition rate is improved, and it is beneficial to the good running of the tracking algorithm, and real-time tracking of the target object is achieved.

The invention discloses a control method for a robot automatic spraying system. The control method of the robot automatic spraying system comprises the following steps of (1) acquiring feature data of a workpiece to be sprayed; (2) processing acquired data by using an image processing system; (3) automatically generating a track; (4) simulating; (5) controlling a user interface; (6) determining a spraying parameter; and (7) performing spraying. The control method of the robot automatic spraying system has the advantages of high automation degree, high machining precision, wide application range and the like. Different workpiece spraying tracks can be generated automatically, the operation difficulty of a user is reduced, the traditional manual programming on single different-model workpieces to be sprayed is replaced, consumed time on spraying is shortened, and the production efficiency is improved.

The invention discloses a laser visual tracking system, which mainly comprises an industrial personal computer, wherein a COM 1 (Component Object Model) port of the industrial personal computer is connected with an X axis motor and a Z axis motor through a motor control and drive circuit; output ends of the X-axis motor and the Z-axis motor are connected with a welding torque; the controller of the welding torque and a welding machine control circuit are connected with the industrial personal computer; the industrial personal computer is also connected with a laser sensor for acquiring information on the welding torque and a workpiece in real time and delivering the acquired information to the industrial personal computer; the laser sensor is a visual sensing module and mainly comprises a camera and a laser diode; the camera is vertically aligned with the workpiece; a laser is slantwise arranged and forms an angle of 30 degrees with the laser; laser emitted by the laser irradiates the workpiece to form a narrow light strip; after the light strip is reflected or refracted by the workpiece, the light strip enters the camera to image, and the image is transferred to the industrial personal computer for processing; after the image is analyzed and processed by the industrial personal computer, an action command is emitted to the welding torque, the X-axis motor and the Z-axis motor.

The invention relates to a method and a device for detecting and tracking a target image, belonging to the technical field of video monitoring. The method comprises the following steps of: detecting a target in a video image frame, and establishing an initial histogram model of the target according to an area in which the detected target is located; carrying out area detection on a subsequent video image frame, and establishing ta tracking histogram model of the target according to the detected area; according to the similarity of the initial histogram model of the target and the tracking histogram model of the target, determining the dimension of the target image at the current time and the central position of the located area, and judging whether the initial histogram model of the target is updated or not; according to the central position of the video image of the current time and the central position of the located area of the target of the current time, adjusting the rotating direction and the speed of a camera head, and adjusting the focus of the camera head according to the dimension of the target image. The invention can be used for detecting and tracking the target in a big scene so as to improve the effect of detecting and tracking the target in the big scene.

The invention discloses a video target real-time tracking method based on sending Hash features. The method includes the steps of 1) reading a first frame of a video sequence to be tracked, 2) drawing a rectangular box properly enclosing a target in the image as a target box, 3) conducting gray-scale treatment for a video frame image, 4) extracting partial Hash features of the target box, computing the partial Hash features, 5) reading the next frame of the video and conducting gray-scale treatment for the video frame image as in step 3), 6) obtaining candidate boxes in the current frame at the same position of the target in the previous frame through an inverted pyramid candidate box searching method, 7) extracting partial Hash features of all candidate box as in the step 4), 8) calculating the similarity of all candidate boxes and the target box in the previous frame, selecting the candidate box with the highest similarity as a new target box, and repeating the step 5) to 7) until the end of the video.

The invention discloses a method for debugging and positioning an embedded system in real time and a device thereof. The method comprises the following steps: A. querying a user command input by a user by a terminal; B. analyzing the user command and obtaining the corresponding function instruction by searching a prearranged symbol table; C. executing the function instruction; D. returning the prompting information concerning the result of execution to the terminal. The method and the device of the invention solve the problems in the real-time trace and debugging, and bring convenience to the application module of the embedded system for inputting a debug command and outputting debug information.

The invention discloses a device and method for simulating low gravity. The device for simulating low gravity mainly comprises multiple constant-tension control systems and a movable and rotary three-degree-of-freedom comprehensive platform, a control subsystem, a main hanging structure and a multi-hanging-point combined control system, wherein the constant-tension control systems are used for controlling the tension of hanging ropes within the range of the vertical operating stroke according to a command, the multiple constant-tension control systems are connected to the lower portion of the movable and rotary three-degree-of-freedom comprehensive platform and are connected with a simulated low-gravity object through the hanging ropes, the posture parameter of the multiple constant-tension control systems serve as the control information of the movable and rotary three-degree-of-freedom comprehensive platform after being coupled, the main hanging structure is arranged on a servo comprehensive platform, and the multi-hanging-point combined control system calculates the current hanging force values of all hanging points and guarantees that the hanging force meets the set gravity requirement according to the position posture of the simulated low-gravity object, and the hanging force passes through the center of mass of the simulated low-gravity object. According to the low-gravity simulating device, the stress condition of all movable parts of moving mechanisms and the stress condition of the positions where the movable parts are connected can be represented truly so that the device can be adapted to the real-time change of the center of mass.

The invention discloses an automatic roll call system. The system comprises a teacher machine, a face detection module and face identification server. The face detection module comprises a camera device and a face obtaining unit; the camera device is configured to receive control signals from the teacher machine, collect video frames and input the video frames to the face obtaining unit; and the face obtaining unit pre-processes the input video frames, extracts face biological features and non-face Haar features from the video frames, uses a trained classifier to classify the video frames, obtains face information, extracts the face edge according to the typical face length and width proportions, and transmits an obtained face picture to the teacher machine. The teacher machine receives the face picture and transmits the face picture to the face identification server for face identification. Face detection is implemented based on the face biological features and the typical face length and width proportions, an educational administration information management system is connected to carry out face identification of specific library, complex faces can be rapidly and effectively identified, the identification rate is improved, and effective management is realized.

The invention belongs to the technical field of radar multi-target tracking and discloses a self-adaptation variable-sliding-window multi-target tracking method. The self-adaptation variable-sliding-window multi-target tracking method includes the following steps that firstly, distance-time data or distance-Doppler data are obtained; secondly, an initial detection window of a jth target is set, and corresponding N frame data are stored into the initial detection window of the jth target; thirdly, a detection result of the jth target in the current detection window is obtained according to the N frame data of the jth target in the current detection window; fourthly, if a detection result of the jth target in a previous detection window exists, the fifth step is executed, and if not, the sixth step is executed; fifthly, track fusion is performed according to the detection result of the jth target in the previous detection window and the detection result of the jth target in the current detection window; sixthly, when a radar receives new frame data, the current detection window of the jth target is updated, and then the third step is executed.

The invention relates to a surgical navigation simulation method based on an electromagnetic positioning technology and intraoperative image guidance. The surgical navigation simulation method comprises the steps that 1, a preoperatively shot CT image of a patient is obtained; 2, the preoperatively shot CT image of the patient is reconstructed into a three-dimensional CT model; 3, registration andvisualization of surgical instruments are achieved; 4, the electromagnetic positioning technology is utilized to achieve real-time tracing of the surgical instruments under an image coordinate system; 5, an ultrasonic probe is calibrated, an ultrasonic image is obtained during operation in real time, and preliminary fusion between the three-dimensional CT model and the ultrasonic image is achieved; 6, by utilizing grey information and characteristic information of the ultrasonic image and adopting a mutual information method and an automatic SIFT characteristic extraction method, real-time registering of the preoperative three-dimensional CT model and the intraoperative ultrasonic image in the surgical process is performed; 7, simulation control of surgical robot movements is achieved. Compared with the prior art, the surgical navigation simulation method has the advantages of high navigation precision, low calculation complexity, good stability and reliability, convenient achievement, low cost, good clinic applicability and the like.

The invention discloses a method and a device for real-time online game, a method and a device for game watching, and a system. The method and the device for the real-time online game, the method and the device for the game watching, and the system have the advantages that by sending game sponsoring information to a server, the range of game participators of an online game project is widened, and the limitation of contact persons on a self directory of a mobile device is broken, so the different-place matching game of a plurality of users on a network is realized; the starting and finishing of the game are controlled by the server, and the real-time game information corresponding to each game participator is received by the server, so the real-time tracking of the competitive state of each game participator in the game process is realized, and the game result is automatically received the first time after the game is finished; by utilizing a network device, the game information is found in real time, and the encouraging information is sent to the corresponding game participator; the different-place real-time game is realized, the real-time property of the game result is high, and the interesting and activity of all people participating in the sports are favorably improved.

The invention provides a flexible sweat sensor. The flexible sweat sensor comprises a flexible substrate as well as a glucose working electrode, a lactic acid working electrode and a reference electrode which are arranged on the surface of the flexible substrate. Glucose oxidase (or lactate oxidase) on the electrode is utilized for oxidizing glucose (or lactic acid) in sweat to generate hydrogen peroxide; hydrogen peroxide can directly perform reduction reaction on the electrode; reduction current is detected through an electrochemical workstation and then the concentrations of the glucose andlactic acid in the sweat can be obtained according to the current magnitude and a standard curve. According to the preparation method disclosed by the invention, the response current level is improved by utilizing a Prussian blue layer to speed up the decomposition of hydrogen peroxide; the sensor disclosed by the invention has high sensitivity; the minimum detection limit for the glucose reaches10nM and the minimum detection limit for lactic acid reaches 1mu M.

The embodiment of the invention discloses an industrial robot visual servo system and a servo method and device. The industrial robot visual servo system comprises a six-axis robot, a weld joint tacker, a calibration object, a wireless handheld demonstrator, a USB wireless receiver, an infrared laser positioning base station, a robot control cabinet, a welding machine power supply control cabinet,an upper computer control cabinet and an automatic wire feeding system. Rapid demonstration without programming is achieved, non-uniform workpiece incoming is avoided, and real-time tracking of welding thermal deformation is achieved; the working process of a traditional welding automatic system is improved, and an operator does not need to use the demonstrator to carry out complex demonstrationprogramming; as the recognition technology based on deep learning is adopted for weld joint tracking, the universality of welding automation is greatly improved; and in addition, welding path planning, demonstration, system calibration and welding real-time tracking are completely integrated in the same upper computer interface, and therefore the process operation and management can be conveniently carried out by the operator.

The invention relates to a multi-target tracking method based on a DSP. The method comprises the following steps in order: a monitor area and a blind area are artificially designated in a gun machine monitor background, and a ball machine is placed in the blind area; the gun machine and the ball machine carry out real-time coding on an acquired video monitor image and transmit a video stream to the digital signal processor (DSP) through a network; the digital signal processor (DSP) carries out decoding and processing on the video stream, controls the ball machine to carry out real-time tracking on a moving object and displays a result to a user. The invention also discloses a multi-target tracking system. According to the method and the system, the digital signal processor (DSP) is taken as a core of the system, a monitored video monitor image is subjected to decoding and processing, the ball machine is controlled to carry out real-time tracking on the moving object, real-time multi-target tracking is realized, and cost of the whole multi-target tracking system can be reduced.

The invention provides a target tracking method and a device for space-based surveillance scene. The method provided by the invention, includes obtaining the video to be tracked of the target object in real time, extracting a first frame and a second frame, clipping a first frame to obtain a first region of interest image, clipping the second frame to obtain a target template image and a second region of inter image, inputting a target template image and a first region of inter image to an appearance tracker network, inputting the first region of interest image and the second region of interest image into the motion tracker network to obtain the motion tracking position, finally, inputting the appearance tracking position and the motion tracking position into the depth fusion network to obtain the final tracking position. The target tracking method provided by the invention utilizes the appearance and motion information of the target object to carry out positioning tracking through themethod of parallel connection of two tracker networks, and then fuses the two positioning information, thereby realizing real-time tracking of the target object.

The invention discloses an intersection pedestrian and motor vehicle collision prediction method based on video detection. The track information and the speed information of the motor vehicles and thepedestrians at the intersection can be rapidly extracted through combination of the image processing technology, and the probability of motor vehicle and pedestrian collision can be predicted by establishing an appropriate probability model so as to provide the appropriate data support for intersection safety assessment.

The invention discloses a tracking method and system. The tracking method is implemented in a server, wherein the server stores map information of a set region. The tracking method specifically comprises the steps of receiving a vehicle license plate number, identification information of passengers in the corresponding vehicle and location information of the current road section access where the vehicle is located which are transmitted by information acquisition devices at each access of each road section in real time, wherein the identification information of the passengers is mobile phone information of the passengers or face information of the passengers; performing associative storage on the license plate number, the location information of the road section access where the license plate number is located and the identification information of the passengers in the vehicle corresponding to the license plate number; and marking the location of the vehicle corresponding to the license plate number in the map information stored in the server according to the location information of a road section or access where the license plate number appears in real time, forming a traveling track of the vehicle corresponding to the license plate number and outputting the traveling track so as to realize real-time tracking for the vehicle and the passengers inside the vehicle.

The invention discloses a zero correction method and a device of a torque sensor. The method comprises static zero learning and dynamic zero correction, and mutually checks and conforms according to a certain time sequence and an algorithm, so as to filter off disturbance and guarantee the control accuracy, and can dynamically track zero deviation in real time during the using process of a user. The method limits the control algorithm within a limiting range of the torque sensor, seriously guarantees the safety of zero correction, ensures that a steering system is always symmetrical and balanced during the driving process of the user, and even if zero correction range is exceeded to a certain degree, a controller can immediately cut off power assisting output and light up a fault light, provides driving comfort and safety for the user to the maximum degrees, ensures that the electric power assisting steering system is optimally matched, and prolongs the service life of products.

The invention discloses a bar-code-based material dynamic tracking warehousing data processing system and method. The system includes a database which is connected with a WEB server, wherein the WEB server is connected with a switch through a network, the switch is connected with a plurality of clients, and each client is connected with a handheld terminal in a wired or a wireless manner; a database DB used for storing system data; a data adapter JPA used for mapping data in the relational database into object-oriented data which can be identified by a java language; a data acquisition layer EAO used for packaging sentences for addition, deletion, modification and check operations on the database; an entity object Bean used for a table in a database corresponding to each entity object bean; a service logic layer Service used for packing the EAO layer according to the demand of an mvc controller; and an affair management module TM used for ensuring the integrity of operations on the database. The bar-code-based material dynamic tracking warehousing data processing system and method ensure information authenticity, reliability and undeniability and realize combination of warehouse management, material life cycle management and bar-code management.

The invention relates to a scheduling method of vehicles in electric power overhaul. The scheduling method comprises steps as follows: geographical location information of the vehicles is acquired; the geographical location information, identity recognition information and scheduling state information of the vehicles are packaged and sent to a scheduling state processing server; the scheduling state processing server acquires an electronic map of an area where the vehicles are located through a GIS (geographic information system) server, and positions of all idle vehicles are marked in the electronic map; the scheduling state processing server receives a scheduling request from a scheduling terminal; the scheduling state processing server marks vehicle scheduling destinations in the electronic map according to the scheduling request; paths between current positions and scheduling destinations of all the idle vehicles are automatically generated; and paths of the vehicles are compared, the optimal path is selected, and a scheduling instruction is sent to a corresponding vehicle. Compared with the prior art, the scheduling method greatly improves flexibility of vehicle scheduling and optimizes the scheduling process.

The invention discloses a dynamic target tracking system and a dynamic target tracking method based on an electronic map and a video surveillance, which relate to the field of the electronic map and the video surveillance. For solving defects of the existing video surveillance assisted public security mode, the system comprises a control center module, a target setting module, an electronic map module, a surveillance calling module, an image analysis module and a commanding module; the control center module dynamically generates and regulates more than three tracking circles, judges and tracks a target motion path, calls and manages the rest modules, and realizes functions of each module; the electronic map module is used for automatically drawing the tracking circles according to position of a tracking target and radius of the tracking circles, and drawing a tracking target motion path on the map; and the surveillance calling module is used for reading information of all surveillance lenses within a selected tracking circle range, and displaying lens symbols on the electronic map. By taking full use of the electronic map, a surveillance video and an image analysis technology, real-time tracking for the tracking target can be realized, and working efficiency of maintaining public security is improved.

The invention belongs to the technical field of radar and sonar, and mainly relates to a method for achieving CJML-IMM-PDA, in particular to a method for achieving initialization and maintenance of multi-weak-target trajectories under a dense clutter condition based on a GPD architecture. The trajectories of the multiple excited weak targets under the conditions of the low signal to noise ratio and the high clutter can be quickly initialized and the successfully-initialized trajectories can be kept in a tracking state on a Visual studio of a software integrated development platform provided by Microsoft.

The invention relates to a method for adjusting a super real-time coincidence time sequence based on transient power angle stability margin, which belongs to the technical field of power system stabilization and control. When the alternating current power transmission line has a malfunction, online identification is carried out on an admittance parameter by using a least square method according to the practically measured data such as electromagnetic power and a power angle after breaker tripping caused by the malfunction provided by a wide area measurement system (WAMS); the identified admittance array is modified to simulate head end coincidence and tail end coincidence of the power transmission line respectively; a system change track in two coincidence time sequences is predicted by using a predictor-corrector method and is subjected to quantitative evaluation by using an extended equal area criterion (EEAC) to obtain a transient power angle stability margin index; and the coincidence time sequence with larger transient power angle stability margin is selected as an optimized coincidence scheme. The method has high prediction accuracy, and can solve the problem that the operation mode of the coincidence time sequence scheme obtained by using the traditional ''offline calculation, online matching'' method is mismatched with the malfunction position, and the like.

The invention provides a moving target tracking system and tracking method based on random medium surface diffusion light to solve the technical problem of narrow application scope of a conventional moving target tracking system and tracking method. The tracking system comprises a laser, a beam expander, rotary ground glass, a random medium, an aperture diaphragm and a detector array, wherein the light emitted by the laser forms pseudothermal light after passing the beam expander and the rotary ground glass and irradiates on a moving target to be tracked, light carrying target information is irradiated onto the scattering surface of the random medium at an acute angle, the diffusion light, of which the stray light is filtered by the aperture diaphragm, is received and acquired by the detector array, and the tracking method is used to calculate the acquired images to obtain the actual displacement of the moving target to be tracked. Target tracking is realized through diffusion light on the surface of a random medium, and the application scope is wide. The system and the method also have the advantages of simple algorithm, high tracking precision and simple system structure, and are applicable to the fields of biomedicine and earth observation.

The invention discloses a solar light chasing device. The solar light chasing device comprises a supporting base and a solar panel fixing frame, wherein the solar light chasing device also comprises an azimuth adjustment device and an elevation angle adjustment device; the azimuth adjustment device is supported on the supporting base; the elevation angle adjustment device is supported on an output shaft of the azimuth adjustment device through a bracket; an output end of the elevation angle adjustment device is hinged to the solar panel fixing frame to drive a solar panel to realize elevation angle swinging; an encoder used for detecting angle change is arranged on an output shaft of the azimuth adjustment device; an encoder for detecting the angle change is arranged on a rotating shaft of the solar panel fixing frame or a hinge shaft which is hinged to the azimuth adjustment device. According to the solar light chasing device, an elevation angle drive device and an azimuth drive device are arranged, so that the position of the solar panel can be adjusted according to an incidence angle of solar rays; therefore, solar energy can be fully absorbed, the absorption rate is improved, and the application of solar heat is improved.

The invention relates to the field of communication, and provides a signaling trace method, a WEB client, a service end and a signaling trace system, wherein the signaling trace method comprises the following steps: packaging an information protocol in advance, wherein a request information body from the WEB client to the service end and a response information body from the service end to the WEB client are packaged in the information protocol; in the process of signaling trace, according to the operation step of signaling trace, adopting an asynchronous mode by the WEB client to send request information to the service end and receive returned response information after the service end carries out corresponding processing, and displaying the result of signaling trace on a user interface. Multi-user multi-condition real-time trace is realized, a user can access the WEB client by using a browser at all times and places, and a web page is unnecessary to refresh when the data of the result of signaling trace traced by the WEB client is displayed, and the display is easier and more smooth; moreover, three interface display manners are further provided, and the usability is strengthened.

The invention discloses an installation method for an energy-saving fin keel of a ship. The installation method comprises following steps: actually measuring the contour line of an outer plate of a stern tube shaft in an installation region of an energy-saving fin, utilizing the actually measured line shape and an installation angle of the fin keel to find a primary installation position line of the fin keel on the stern contour of a tube shaft, utilizing the line shape to cut off the remaining amount of the fin keel in advance, compiling control program of deviation of the fin plate, correlating three-dimensional coordinates of a fin keel point measured by a total-station instrument to the positioning deviation of the fin keel for real-time tracking and positional guiding of the fin keel, reinforcing the fin keel prior to welding and formulating reasonable program of welding process, utilizing positioning deviation of the fin plate to control program so that welding influence upon installation of the fin keel is adjusted within the controllable range. The installation method for the energy-saving fin keel of the ship is capable of shortening time spent on positioning and installing the energy-saving fin keel in the dock phase and effectively reducing period of newly constructing a dock of the ship and dock-repair period of repairing the ship so that construction or cost of the ship or dock repair can be effectively saved.

The invention discloses a case tracking interaction system comprising a background management server and a client connected with the background management server. The background management server comprises a data storage module, a patent distribution module, a patent tracking module, a patent reminding module, and an interface management module. The invention further discloses a case tracking interaction method. Compared with the related technology, the invention provides a case tracking interaction system which enables customers to check the progress of a patent and make modification in a timely manner.