57results about How to "Troubleshoot tracking issues" patented technology

The invention belongs to the crossing field of computer vision and intelligent robot, and discloses a new multi-feature multi-sensor method for a mobile robot to track a moving body. The method comprises the following steps: 1, coarsely positioning a body carrying a passive tag around a radio frequency identification (RFID) system by using the RFID system; 2, initially positioning the body in an image by using an adaptive template matching algorithm based on head and shoulder features; 3, accurately positioning the body in the image by using a multi-feature-based mean-shift algorithm; 4, predicting the moving state of the body by using a extended Kalman filter algorithm; 5, screening the acquired target position information by using a double-layer collaboration positioning mechanism; and 6, controlling the robot to move along with the body by using a robot following control algorithm. By the method, bodies with different poses can be tracked, the problem that the tracking is influenced when a target suddenly turns and is shielded is solved, and the robot can accurately, stably and continuously track the moving body.

The invention relates to a low and slow small target tracking method based on a polar coordinate system. The technical feature is that the method comprises the following steps: step 1. establishing atemporary track by using measurement points scanned by a radar for the first time as track heads respectively; step 2. after the radar scans the measurement point for the second time, determining a relevant wave gate by using speed limit; step 3. after the radar scans the measurement point for the third time, for the temporary track with a trace point number of 2, determining the relevant wave gate through Kalman filtering of the polar coordinate system; step 4. moving the track with a trace point number of 3 in a temporary track set into a reliable track set; step 5. after the radar scans a new measurement point, firstly performing association updating with the reliable track set, and if non-associated measurement points still exist, performing association updating with the temporary track set; and step 6. traversing all tracks, if a certain track is not updated exceeding a certain time, performing track is extinction or extrapolation. By adoption of the low and slow small target tracking method provided by the invention, a decoupling problem and a conversion error are avoided, and meanwhile the calculated amount is reduced.

The invention relates to a forest fire detection platform based on satellite remote sensing images. The forest fire detection platform comprises a ground receiving station, a ground processing station and a fire alarm system. The ground receiving station is used for receiving and recording the satellite remote sensing images. The ground processing station is connected with the ground receiving station and used for processing the satellite remote sensing images and identifying flame images in the satellite remote sensing images. The fire alarm system is connected with the ground processing station and used for realizing forest fire alarms at different levels according to the areas of the flame images. Through the forest fire detection platform based on the satellite remote sensing images, the remote sensing images of all positions of a forest can be obtained in a satellite remote sensing mode, the flame images are identified by analyzing the obtained remote sensing images, and the hierarchical forest fire alarms are given according to the areas of the flame images.

The invention discloses a joint reasoning-based video multi-target tracking method in the technical field of video processing. The method comprises the following steps: firstly, reading a frame of image of a video file, carrying out image rasterization processing, and then calibrating a candidate position of a target by adopting an online detector and a KLT tracking algorithm as a tracker, respectively screening and then integrating the results; secondly, carrying out quantitative grading on the obtained candidate position result; finally, describing the target tracking condition by using a joint function, and taking the optimal solution based on the joint function as the position of the target in the frame, so as to achieve target tracking. By adopting the joint reasoning-based video multi-target tracking method, the processing of the treatment method combined with a detection tracking algorithm and multi-target relationship in the tracking technology under multi-target tracking can be achieved, and the multi-target relationship is described by using the joint function, so that not only is the result fusion of detection and tracking achieved, but also the relationship between the targets is integrated according to overall situation, so that a global optimal resolution is obtained.

The invention discloses a method and system for tracking targets in a video based on the PTZ. The method comprises the following steps: 100, utilizing a Gaussian mixture modeling method for setting up a background model for a video image obtained by a camera in a preset position scene, and detecting the motion targets in a monitored video image immediately obtained by the camera in the preset position scene; 200, calculating a grey level histogram of the motion targets of the monitored video image, recording template information of the motion targets, and updating parameter information of the motion targets according to the video image immediately obtained by the camera; 300, conducting judgment according to the parameter information and controlling the camera to conduct the corresponding adjustment according to the judged result. The method and system for tracking the targets in the video based on the PTZ can initially and accurately track the motion targets and accurately distinguish the motion targets of the video image.

The invention provides a method for dynamic position tracking of a train. The method comprises the following steps: starting to track the train position according to the train departure signal; searching the tracked position in the departure route locking zone up to the interval zone; assigning the train operation direction according to the departure route direction; when a station track is subject to voidance in the train station, deleting the train position information concerning the station track; tracking the train position according to the train operation direction, wherein the tracked position is the existing occupied zone, and obtaining the train position information from the left zone and the right zone of existing occupied zone; tracking the train position according to a train receiving signal, searching the tracked position according to the receiving route locking zone until the corresponding receiving station track in the next train station is found and deleting the train operation direction; and restarting the original tracking method the train continues to proceed. The method of the invention has the advantages of simple tracking logic, easy processing and control, high tracking efficiency and accurate and reliable tracking.

The invention discloses a method and a device for large-range and high-resolution atomic force micro detection for a large sample. By adopting a method combining the scanning of a piezoelectric ceramic probe and the large-range motion of a step motor and designing an open sample stage, the micro-nano detection of large-sized super-precise workpieces is realized. The device is provided with a large-range and high-resolution scanning probe system, an X-Y-axis step electric translation stage, an optical platform and a scan imaging and feedback control system, wherein the large-range and high-resolution scanning probe system consists of a laser, a light path tracking lens, piezoelectric ceramics, a micro cantilever probe and a photoelectric detection element; and the X-Y-axis step electric translation stage is used for moving large-sized samples in large range. The method and the device have the advantages of overcoming the limitation that a conventional AFM is only suitable for small-range detection of small samples, designing a simple and practical lens system to solve the light path tracking problem when the probe scans in the large range, and adopting the open sample stage and the two-dimensional step motor to realize large-range scanning and detection in any area for the large-sized super-precise workpiece samples under the condition of keeping the ultra-high resolution of the AFM.

The invention discloses a method for retrieving vehicles on the basis of sparse codes of features of vehicular ornaments. The method includes acquiring vehicle image data and detecting vehicle areas in images by the aid of gray co-occurrence matrix features and support vector machines; acquiring vehicular ornament area images in the vehicle images; creating over-complete dictionaries of the vehicular ornament area images; solving sparse vectors of the vehicular ornament area images corresponding to the to-be-inquired vehicles; reconstructing to-be-inquired vehicular ornament area images and computing Euclidean distances from reconstructed images to the to-be-inquired vehicular ornament area images; updating the sparse vectors of the to-be-inquired vehicular ornament area images, sorting elements of the sparse vectors according to the magnitude and setting thresholds to obtain retrieval results of the vehicular ornament area images. Compared with the prior art, the method has the advantages that the vehicles are retrieved on the basis of the features of the vehicular ornaments, accordingly, the retrieval precision and reliability can be greatly improved, and important bases can be provided for effectively solving problems in the aspect of illegal vehicle tracking.

The invention relates to a finite-time neural network control method of a motor-driven single-connection rod manipulator. The method comprises steps of (1) establishing a mathematical model of the motor-driven single-connection rod manipulator and an actuator nonlinear module with a dead zone and input saturation limitations; (2) determining a control target, wherein system output is capable of tracking reference output of the system within the infinite time, and the system output is kept in a limited range; (3) designing an infinite time neural network control law and achieving a control target; and (4) designing a barrier Lyapunov candidate function and analyzing stability of a closed loop system, and according to the stability analysis of the Lyapunov candidate function, determining control parameters of the designed control law. According to the invention, by considering limitation factors of input saturation limitations, the dead zone, output limitations and system indeterminancy,the control method can be well applied in an actual system. In addition, infinite-time track tracking can be achieved; tracking time is reduced; and robustness and control precision of the system areimproved.

The invention is applicable to the field of multi-sensor information fusion and provides a multi-target tracking method and system for flicker noise. The method comprises a prediction step, an updating step, a generation step and an extraction step. According to the technical scheme provided by the invention, while the real-time performance of data processing is guaranteed, a tracking problem of a nonlinear moving target under flashing noise is solved effectively.

The invention discloses a reliable and controllable vehicle electronic identity information acquisition device comprising an electronic identifier reading module, a satellite positioning module and a wireless communication module which are bound to one another, wherein the output end of the vehicle electronic identifier reading module and the output end of the satellite positioning module are connected with the wireless communication module. The device is used for acquiring vehicle electronic identity information, traveling track and vehicle running state information in real time and uploading the information automatically, so as to realize deep integration of the vehicle electronic identifier and the satellite positioning module, effectively prevent the problem of identity management chaos caused by satellite positioning terminal disassembly and replacement without permission and improve effective regulation of operating vehicles by the public security organ and the transportation department and the timeliness of information acquisition. The device can also be applied to vehicle-to-vehicle communication (v2v) identity authentication management of intelligent networked vehicles.

The invention is suitable for the field of multi-sensor information fusion and provides a multi-maneuver target tracking method and system suitable for flicker noise. Through a prediction step, an updating step, a fusion step, a generation step and an extraction step, t distributed model is performed on the flicker noise, a variational bayesian method is adopted to approximatively obtain covariances and target states of observation noise under different models and the joint probability density of the freedom degree, multi-maneuver target tracking under the flicker noise is effectively achieved, and the multi-maneuver target tracking precision is improved.

The invention discloses a pheromone prediction-based ant colony multi-cell tracking system. The system comprises four modules: a pheromone field prediction module, an ant decision module, a pheromonefield Gaussian fitting module and a state estimation module. Through analysis of the modules, multi-cell tracking is realized. After an original picture is input, based on a cell pheromone field Gaussian fitting result of a previous frame, pheromone field prediction is performed by utilizing a Gaussian mixture model; a pheromone field is constructed by utilizing a bell curve-based pheromone diffusion model in a pheromone gradient-based ant working mode; and through a K-mean clustering method, cell position estimation is performed after removal of a false target caused by clutters, and finallyassociation is performed by utilizing cell distance features to obtain cell motion tracks, thereby realizing the multi-cell tracking.

The invention relates to a high-power sealed alternating current contactor. The shell of the high-power sealed alternating current contactor is fixed on a pedestal, an input terminal and an auxiliary output terminal are fixed on the shell, a main output terminal is fixed on the pedestal, and a main output stationary contact is fixed at the inner end of the main output terminal; a suction type electromagnetic mechanism is fixed on the pedestal through a bracket and positioned at the middle part in the shell, and a rectifying part is arranged on the bracket; the upper part of the moving end of the suction type electromagnetic mechanism is connected with a pushing ring, the lower part is connected with a main output moving contact, and the main output moving contact is positioned over the main output stationary contact; a coil-controlled normally closed contact and an auxiliary output normally open contact are arranged above the suction type electromagnetic mechanism and controlled through the pushing ring; and the input terminal is connected with the rectifying part, the rectifying part is connected with the suction type electromagnetic mechanism, the coil-controlled normally closedcontact is connected with the control end of the suction type electromagnetic mechanism, and the auxiliary output normally open contact is connected with the auxiliary output terminal. The invention has the characteristic of compact structure, impact resistance, large loading capability and the like and is particularly suitable for switching circuits in ships and other high-power military equipment.

The present invention provides a method for tracking a turning maneuver target, wherein the method includes: a prediction step, an estimation step, an update step, a generation step and an output step. The invention also provides a system for tracking a turning maneuvering target. The technical solution provided by the invention effectively solves the tracking problem of the turning maneuvering target while ensuring the real-time performance of data processing.

The invention provides a multi-sensor maneuvering target tracking method based on the principle of maximum entropy. The method comprises the steps of establishing a multi-sensor measurement data set from the same target; calculating the degree of membership between data in the multi-sensor measurement data set, obtaining the class center of the measurement data set through clustering processing to complete the data merging of the multi-sensor measurement data set; performing filtering tracking treatment on the merged data by using the interactive multiple model to update the target; output target track data after update and processing. The method performs data clustering processing based on the principle of fuzzy maximum entropy when merging data of the same target from multiple sensors, and proposes the vector analysis method for decoupled solution of the degree of membership to solve the problems of conventional clustering algorithms that errors are caused because the calculation of the degree of membership is coupled with a clustering center and the initialization of a class center is improper. Thus, the method guarantees full utilization of data of multiple sensors and can realize accurate tracking of a maneuvering target based on the data and the interactive multiple model.

The invention discloses an electric bicycle obstacle avoiding method integrating sparse representation and particle filter. The method mainly comprises the steps of: synchronously collecting images ahead by two cameras at the front part of an electric bicycle, judging, detecting and ranging obstacles by an imaging processing module through using an image detection and particle filter tracing algorithm. The obstacle ahead and distance to the same are automatically detected; a central controller works out current controlling value of rotating speed of a hub motor in each wheel according to the distance from the electric bicycle to the obstacle sent by the image processing module (2), and if the current controlling value is lower than current actual speed, the central controller (3) reduces the rotating speed of the hub motor (4) to the current controlling value and meanwhile emits a warning sound. Consequently, the electric bicycle can automatically speed down or brake when the obstacle is within the dangerous distance ahead so as to ensure the life or property safety of the user or other people.

The invention discloses a multi-target tracking method based on coarse-to-fine occlusion processing, and the model construction comprises the following steps: adding an occlusion score prediction on the basis of a JDE model prediction head, thereby completing the complete processing of a non-occlusion target and the coarse processing of an occlusion target; on the basis, taking a pedestrian shielding area after mapping and cutting as a training set of the second-step model for training, and completing accurate detection and apparent feature vector extraction of the shielded pedestrians, thereby realizing the fine processing of the shielded target; integrating results output by the two-step model, and finishing pedestrian tracking by using a data association algorithm. According to the invention, the problem that pedestrians cannot be accurately tracked in a shielding scene in the prior art is solved, and the method can well adapt to public environments of various time periods and various pedestrian densities; the method has a better effect on tracking pedestrians.

The invention provides a mesoscale convection system identification and tracking method based on a stationary satellite infrared cloud atlas, which is characterized by comprising the following steps of: 1) identifying a mesoscale convection system boundary on the stationary satellite cloud atlas; 2) filling and numbering an area surrounded by the closed boundary; 3) repeating the steps 1) and 2) until all mesoscale convection systems are identified; 4) respectively calculating the cloud cluster attribute of each numbered mesoscale convection system; 5) determining a candidate cloud cluster ofthe mesoscale convection system to be tracked at the next moment by utilizing two continuous frames of cloud charts; 6) calculating a spatial correlation coefficient between the to-be-tracked mesoscale convection system and the candidate cloud cluster, and 7) completing the tracking of the mesoscale convection system through the comparison of the spatial correlation coefficient. The method can automatically complete the recognition and tracking process of the mesoscale convection system, and remarkably improves the calculation efficiency and accuracy.

The invention discloses an out-of-step oscillation center positioning system and method based on wide-area measurement impedance angle information. According to the system and the method, real-time oscillation direction information sent by a plurality of out-of-step solution substations deployed on the two sides of a power transmission section channel in a regional interconnected power grid in theout-of-step oscillation process is comprehensively utilized in a control main station, and the position of an oscillation center is accurately judged in real time. According to the method, a master station and a plurality of substations are included, and the substations communicate with the master station through 2M multiplexing optical fiber channels. The substation collects voltage and currentdata of a section channel line, calculates and measures an impedance phase angle in real time through the voltage and current data, judges the direction of an oscillation center in real time accordingto the size distribution of the phase angle in fixed time, and sends the direction of the oscillation center to the main station in real time. And the main station can judge the position of the oscillation center in real time according to the oscillation direction information sent by each substation and a preset logic strategy. The position of the oscillation center can be accurately judged in real time.

The invention relates to a load parameter identification device and method for an electric power system station terminal. The method comprises steps that 1), voltage and current signals of a power grid secondary loop are acquired in real time, after the acquired voltage and current signals are converted and filtered, discrete sampling is carried out to acquire original sampling values of the voltage and current signals; 2), the open state information of the power grid secondary loop is acquired in real time, after anti-shaking and discrimination of the acquired open state information are carried out, the information is converted into a digital signal, and the opening and closing state information of a line switch is acquired for man-machine interface display; 3), phasor calculation and load parameter identification are carried out according to the original sampling values of the voltage and current signals to acquire the phasor calculation result and the load parameter identification result; and 4), the opening and closing state information of the step 2) and the phasor data and the load model identification result acquired in the step 3) are displayed through a man-machine interface and are uploaded to a main scheduling station.

The invention discloses a method for tracking a moving source by using a single unmanned aerial vehicle. The method specifically comprises the following steps: step 1, acquiring the distance between the single unmanned aerial vehicle and a moving source in real time by a UWB sensor mounted on the single unmanned aerial vehicle; 2, when the moving source moves linearly at a constant speed according to a certain speed direction, calculating the relative speed of the moving source relative to the single unmanned aerial vehicle according to the distance collected by the UWB sensor in real time and a relative speed conversion method so as to estimate the speed direction of the moving source , and calculating the speed vs of the moving source according to the speed direction of the moving source; and step 3, calculating the relative speed of the single unmanned aerial vehicle relative to the moving source according to the speed of the moving source, and estimating the position of the moving source based on a multi-point data fusion strategy. The method is simple and effective in algorithm and clear in logic, and an accurate speed estimation algorithm and a rapid source position positioning method are provided for the moving source tracking problem.