2093results about How to "Improve tracking accuracy" patented technology

A tracking and navigation system is provided. The system includes an imaging or treatment device, a tracker device, and a fiducial marker. At least part of the imaging or treatment device is movable relative to a patient. The tracker device is mounted on the imaging or treatment device and is movable therewith relative to the patient. The fiducial marker may be fixed relative to the patient to define a patient coordinate system. The fiducial marker is detectable by the tracker device to substantially maintain registration between the tracker device and the patient coordinate system. A tracking and navigation kit including the tracker device and at least one fiducial marker may also be provided, for example, for retrofitting to existing imaging or treatment devices

The invention provides a pose estimation method based on RGB-D and IMU information fusion. The method comprises the following steps: S1, after time synchronization of RGB-D camera data and IMU data, the gray image and depth image acquired by the RGB-D camera and the acceleration and angular velocity information collected by the IMU are preprocessed to obtain the characteristics of adjacent frame matching in the world coordinate system. Point and IMU state increment; S2, a visual inertial device in a system is initialized according to system external parameters of a pose estimation system; S3,according to information of the intilized visual inertial device, feature points matching adjacent frames in a global corrdinate system, least squares optimization functions of an IMU state incrementconstruction system; an optimization method is used to iteratively solve the optimal solution of the least squares optimization function, and the optimal solution is used as the pose estimation statequantity; further, loop detection is performed to acquire globally-consistent pose estimation state quantity. Therefore, feature point depth estimation is more accurate, and positioning precision of the system is improved.

The present invention facilitates clock and data recovery (330,716 / 718) for serial data streams (317,715) by providing a mechanism that can be employed to maintain a fixed tracking capability of an interpolator based CDR circuit (300,700) at multiple data rates (e.g., 800). The present invention further provides a wide data rate range CDR circuit (300,700), yet uses an interpolator design optimized for a fixed frequency. The invention employs a rate programmable divider circuit (606,656,706) that operates over a wide range of clock and data rates (e.g., 800) to provide various phase correction step sizes (e.g., 800) at a fixed VCO clock frequency. The divider (606,656,706) and a finite state machine (FSM) (612,662,712) of the exemplary CDR circuit (600,650,700) are manually programmed based on the data rate (614,667). Alternately, the data rate may be detected from a recovered serial data stream (718) during CDR operations (on-the-fly) utilizing a frequency detection circuit (725) to automatically program the divider (706) and FSM (712) to provide CDR circuit operation at the nearest base clock rate (716).

The invention relates to a systematic calibration method of a welding robot guided by a line structured light vision sensor, which comprises the following steps: firstly, controlling a mechanical arm to change pose, obtaining a round target image through a camera, accomplishing the matching of the round target image and a world coordinate, and then obtaining an internal parameter matrix and an external parameter matrix RT of the camera; secondly, solving a line equation of a line laser bar by Hough transformation, and using the external parameter matrix RT obtained in the first step to obtain a plane equation of the plane of the line laser bar under a coordinate system of the camera; thirdly, calculating to obtain a transformation matrix of a tail end coordinate system of the mechanical arm and a base coordinate system of the mechanical arm by utilizing a quaternion method; and fourthly, calculating a coordinate value of a tail end point of a welding workpiece under the coordinate of the mechanical arm, and then calculating an offset value of the workpiece in the pose combined with the pose of the mechanical arm. The systematic calibration method of the welding robot guided by the line structured light vision sensor is flexible, simple and fast, and is high in precision and generality, good in stability and timeliness and small in calculation amount.

The cerebral operating robot system based on optical tracking and closed-loop control for receiving medical image information, detecting and determining disease focus position, assisting operation plan and performing operation guidance is one closed-loop pose measuring and real-time feedback controlling robot system comprising one computer, one five-freedom robot, one optical tracking device and one passive marker. The passive marker is mounted in the end of the five-freedom robot, and the five-freedom robot includes one mechanical arm and one mechanical arm controller. The operation plan assisting and operation guiding software includes a digital image inputting and pre-treating module, a disease focus extracting and 3D reconstructing module, an operation planning module, and an operation executing module. The present invention has the advantages of raised precision, low cost, simplified calibration process, etc.

The invention discloses a pedestrian tracking method based on HOG-LBP, comprising the following steps of, A1, sample establishment; A2, feature extraction; A3, SVM model establishment; A4, classifier training; A5, video capture and pretreatment; A6, video pedestrian examination; A7, video pedestrian tracking: applying a particle filtering tracking method based on an HOG-LBP feature to track the pedestrian examined in step A6. The method firstly learns an image pedestrian mode through a support vector machine, and then classifies a moving area in a video sequence and inputs the result to a particle filtering machine to update the particle status, and finally realizes continuous tracking to pedestrian movement in the scene. Because the method collects pedestrian feature by adopting HOG-LBP and uses the particle filtering to track movement, it has good adaptability and stability to movement interleave and sheltering phenomenon in a scene and non-linear feature presented by the movement.

An autonomous weapon system including weapon (9) and weapon mounting system (7, 8) operable to point the weapon (9) in accordance with input control signals. The weapon system includes a sensor (2) to acquire images and other data from a target zone and an image processor (3) to process acquired image data and identify potential targets (1) according to predetermined target identification criteria. Targeting system (4, 5) provides input control signals to the weapon mounting system (7, 8) to point the weapon (9) for firing at potential targets (1). A control system operates targeting system (4, 5) and fires the weapon (9) at selected targets (1) according to a predetermined of rules of engagement. The rules of engagement include combat, peacekeeping or policing scenarios. Remotely located operator (10) may amend the rules of engagement, or override the control system as required.

The invention discloses a method for tracing the track of a wheeled mobile robot based on a quantum-behaved particle swarm algorithm. The method sets a coordinate system within a motion range first, establishes a kinematic model of the wheeled robot, utilizes an inversion design method to decompose the kinematic model, obtains an error propagation equation of a reference pose and an actual pose through the track generated by path planning, takes the equation as a target function, utilizes the quantum-behaved particle swarm optimization algorithm to obtain parameters of a controller with quick speed and strong global solving capacity, designs the controller through the group of parameters, and further guarantees that the robot can be stably and quickly converged on the target track, namely the target function value is close to or less than an allowable value within a limited time period. The method solves the problems of high nonlinearity and non-integrity of track tracing of the wheeled mobile robot, and can quickly realize track tacing of the wheeled mobile robot and improve the tracing control effect of the mobile robot.

The invention relates to mobile tracking of vehicle targets in the communication and transportation field. A self-adapting interactive multiple model mobile target tracking method comprises the following steps of establishing mixed initialized input. including a covariance matrix of a mixed initial condition and a mixed initial state. of each model; establishing constant velocity (CV) and constant acceleration (CA) motion models; updating: calculating covariance matrix and innovation of an error according to a Kalman filter formulation; constructing a likelihood function of a target motion module by utilizing the innovation of a Kalman filter result, and calculating a Markov state transition probability matrix; carrying out estimation output after being fused by utilizing the Markov state transition probability matrix as weight of switch among each motion model. According to the self-adapting interacting multiple model mobile target tracking method disclosed by the invention, the problem that the error is increased or the tracking is failed caused by non-matching of a filter model and a target motion model due to the motion of a target in the traditional interactive multiple model algorithm is solved; the self-adapting interacting multiple model mobile target tracking method has the advantages of low calculation complexity and good tracking effect, and can be applied to target tracking of motor vehicles in the communication and transportation field.

The invention discloses a hand movement tracking system and a hand movement tracking method. The invention comprises an attitude and heading reference system based on an accelerometer, a gyroscope and a magnetic sensor, and a hand movement tracking method based on the attitude and heading reference system. The hand movement tracking method comprises the following steps: firstly, obtaining a triaxial acceleration measured by the accelerometer, a triaxial angular velocity measured by the gyroscope and a triaxial magnetic-field component measured by the magnetic sensor, performing error compensation on the magnetic sensor by adopting a least square method to establish an error model after an upper computer receives sensor data, eliminating high-frequency noise of the triaxial acceleration by virtue of a window low-pass filter, and establishing an error model for the gyroscope so as to perform error compensation on random drift of the gyroscope; secondly, effectively integrating the gyroscope, the accelerometer and the magnetic sensor by virtue of an improved adaptive complementary filtering algorithm to obtain an attitude angle and a path angle; and finally, performing gravity compensation and discrete digital integration on acceleration signals to obtain a velocity and a track of a hand movement. The tracking system and the tracking method disclosed by the invention can be applied to a man-machine interactive system, is convenient to operate, and is strong in experience feeling.

The invention discloses a heliostat tracking error correction method. Based on the characteristics that a heliostat tracking deviation angle has small variation in a short time and the tracking deviation angles at the same moment in the adjacent days have small variation, an image collecting and processing system is adopted to detect and obtain the tracking deviation angles of a certain heliostat at multiple moments in the whole day, or the tracking deviation angles obtained by the heliostat at multiple moments in one day or previous days are taken as the intraday tracking deviation angle; an intraday tracking deviation curve of the heliostat is obtained by the interpolation; according to the tracking deviation curve, the current angle of the heliostat is corrected to ensure that the facula of the heliostat can basically accurately be projected to a target position. The invention obtains the tracking deviation angles at multiple moments by detection of heliostat tracking error many days a year or many times a day; the everyday corresponding tracking deviation curve of each heliostat can be found by one-year or multiple-year tracking deviation angle data analysis treatment and curve fitting; and thus, the facula of the heliostat can be projected to the target position more accurately.

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 discloses a moving object detection and tracking method. The method comprises the following steps: firstly, obtaining a frame image from a video sequence, converting the image into a gray scale image, and filtering and denoising are performed; then, the moving target region is obtained by using three-frame difference method, and the hole in the difference image is filled by morphological filter closure operation; the pixel points with non-zero gray value in the image after morphological filter closure operation are calculated by optical flow calculation, and the moving target isextracted; then the Kalman filtering algorithm is used to predict the centroid position of the moving object in the current frame image, the predicted value is compared with the centroid position tracked by a Camshift algorithm, and the centroid coordinates of the moving object are determined by the comparison results, and the size and position of the search window are determined when searching the next frame image; the model is updated to get the next frame image, the whole tracking process is repeated, and finally target tracking is achieved. The invention reduces the error of moving targetdetection and tracking, and improves the accuracy.

Method, system and apparatus for calibrating an eye tracker comprising presenting a subject with a visual target. Detemiining a physical arrangement in space of the subject. Obtaining an eye measurement of the subject. Storing a record of the subject's physical arrangement in space and data derived from the eye measurement of the subject, associated with the visual target presented to the subject. Repeating for one or more further different visual targets.

The present invention relates to a solar heating and power generation combined supply system. Said system includes the following several components: rotating parabolic saucer condenser, rotating hyperbolic spectral control system, light-gathering photovoltaic group battery and hot-pipe type water heater. Said invention also provides the concrete structure of the above-mentioned every portion and the working principle of said system.

The invention discloses a pilotless automobile lateral control method based on turning curvature estimation. The pilotless automobile lateral control method based on the turning curvature estimation comprises setup of a preconceived track, collection of GPS-INS integrated positioning system data and steering wheel turning angle command signals send out by an autopilot, and especially is a method that a preview distance based on a road curvature is set firstly, and then a preview point A and a preview point B are reset according to the preview distance, later, longitudes and latitudes of the preview point A and the preview point B are converted into a vehicle coordinate system to work out an optimum turning curvature, and steering wheel turning angle controlled quantity is worked out according to the optimum turning curvature and is output to the autopilot to achieve lateral control of a pilotless automobile. According to the pilotless automobile lateral control method based on the turning curvature estimation, through actual measurement, the maximum tracking error is only 0.4m when the speed of the automobile is at 20km / h, the maximum tracking error is only 0.6m when the speed of direction change is 5km / h; both accurate tracking of various kinds of complex tracks is achieved, and steering wheel shaking caused by single-point preview feedback control is avoided, and the control quantity of the pilotless automobile is more smooth; the method can be widely used in pilotless driving control of the various kinds of vehicles.

The invention relates to a multi-target tracking system based on deep learning and an implementation method. The method comprises the following steps: getting the target position of a first frame through target detection, and adding multiple to-be-tracked targets to a tracking queue; inputting a next frame of image and traversing the tracking queue to get the position of the target in the next frame; after getting the position of the target in the next frame, judging whether the target is off the screen based on thresholds; if the target is not off the screen, invoking target detection every other fixed frame, and calculating the IOU (intersection over union) of the target detection result and the tracking result; if IOU<0.1, judging that a new target is added to the screen, and adding the target to the tracking queue; if IOU>0.5, replacing the tracking box with the target detection box to correct the position; and continuing target tracking. By carefully designing the network structure and improving the training method, under the condition of high tracking precision, the tracking speed is increased significantly, network redundancy is reduced, and the size of the model is reduced.

The invention relates to a flexible satellite locus linearization attitude control method based on a disturbance observer. The invention aims at solving problems that a single locus linearization control method is poor in capability of inhibiting interference, is poorer in robustness, and does not consider external interference and the impact from flexible accessories. The method comprises the steps: employing Euler angles for describing attitudes of a spacecraft, employing an idea of equivalent disturbance, and building a flexible spacecraft dynamics and kinetics equation; solving the pseudo-inverse of a controlled object under the condition of neglecting equivalent disturbance, designing a quasi-differentiator of a specific type, and obtaining the nominal control of an expected locus; and designing a linear time varying adjuster through proportion-integration control. The method gives consideration to the influence of equivalent disturbance, designs the disturbance observer, and guarantees the asymptotic convergence of a tracking error of a flexible spacecraft. The method improves the anti-interference capability of a system, and improves the robustness of the system. The method is used in the attitude control field of flexible satellites.

The invention provides a method for tracing the position and pose of a 3D human face in a video sequence. In the method, based on the principal component analysis, by using a deformable 3D grid model, minimizing the distance between a key point on the grid model and a corresponding key point on an input image, the model can fit the head figure of a user; the human face texture can be obtained by using the 3D model at an initial phase, so as to render human face images under different poses; the feature points can be selected in the rendered images, and a corresponding position can be searched on the input image; the matching faults can be removed by using a random sampling mode; then, mode pose changed parameters can be estimated according to the corresponding relationship between the feature points, so as to update a hypothetical state; finally, a distance between the rendered image and an actual image can be calculated by using the average normalized correlation algorithm, so as to calculate a hypothetical weight. Experiments show that the method can effectively trace the pose of the 3D head in the video.

The invention relates to a genetic-algorithm-based trajectory planning optimization method for a mobile mechanical arm. According to the technical scheme, the method comprises the following steps of first establishing a forward kinematic model and an inverse kinematic model of a multi-degree-of-freedom mobile mechanical arm; then fitting a joint trajectory by adopting a composite curve of a quartic polynomial mathematical model and a quintic polynomial mathematical model, and calculating solutions of the corresponding mathematical models according to a linear constraint equation; next selecting a trajectory optimization target according to the principles of shortest motion time, minimum spatial motion distance and less than or equal to maximum set joint torque of the mobile mechanical arm; and finally globally optimizing the optimization target by utilizing a genetic algorithm to obtain an optimal trajectory curve of an end actuator of the mechanical arm. According to the method, the trajectory planning efficiency and the tracking accuracy of the mechanical arm are improved, and the problems of real-time trajectory planning of the mobile mechanical arm and trajectory planning optimization and control of the mechanical arm in an uncertain environment are also solved; and the trajectory planning optimization method for the mobile mechanical arm is effective.

The invention provides a fuzzy sliding mode trajectory tracking control method for an SCARA robot with modified sliding mode surface and reaching law. The method has the advantages that no precision dynamical model is required, and robustness is high; a fast terminal sliding mode surface which is modified is adopted, so that convergence rate of a system is increased, and singularity of the traditional terminal sliding mode surface is eliminated; the fast reaching law is adopted, the exponential approach law features fast reaching when leaving the sliding mode surface, power reaching law features smooth reaching when reaching the sliding mode surface, and tracking speed is increased, and meanwhile trajectory tracking precision is guaranteed; a sign function is replaced with a hyperbolic tangent function, and accordingly, high frequency chattering of the system is eliminated effectively; exponential term coefficient of the reaching law is corrected with a fuzzy adaptive controller, and the problem of moment shock caused by large system initial error is improved.

The invention relates to an anti-overlap method for tracking a moving target based on mean shift and belongs to the image processing technology field. The method comprises the following steps: constructing a mean shift model and a Kalman filter model; pre-estimating by utilizing a Kalman filter to obtain the initial position of searching each frame mean shift; obtaining the outline of an object by an image difference method; and defining whether similar factors can shade the object or not. When the similar factors shade the object, the position of the object in current frame is predicted and serves as a starting point for predicting the next frame by attaching different weights to color information and movement information respectively, according to the difference of mobile status of the object. Accordingly, the linear prediction of target position replaces the function of Kalman filter. Experiments prove that the method can realize the tracking of a quickly moving object and has good robustness for shading.

The invention relates to a movement tracking device for man-machine interaction and a tracking method thereof. The invention comprises a movement tracking device and a target information processing device. The tracking method comprises the following steps of: (1) binding a micro inertial measurement unit and a specified-wavelength light source with a tested target; (2) transmitting target movement parameters to a target information processing system by the movement tracking device; (3) processing the acquired target movement information by the target information processing system; and (4) outputting accurate target movement information to a man-machine interaction interface through a target space coordinate and a movement posture information output interface. The invention provides the device and the tracking method thereof which can be applied to man-machine interaction, virtual reality, and enhancement of a real system and can effectively expand the movement tracking range.

The invention relates to a method of controlling a holder camera to automatically track a target. The method comprises the following steps. A tracking model is automatically chosen. A video frequency processing module automatically chooses an automatic tracking model and a global search model according to the tracking state of the target. The processing process of the automatic tracking model is that the video frequency processing module judges the state of the holder camera and after the tracked target is matched, control orders are sent according to the position and size of the target to regulate the position and the focal distance of the camera. The processing process of the global search model is that the video frequency processing module detects and matches the target through a taking turn manner in a plurality of search areas of a monitored area until the tracked target is found. The invention has reasonable design, realizes the automatic tracking function of the camera on the target, ensures that the position and size of the target are suitable for monitoring, has the advantages of high tracking precision, strong real-time property, low cost, flexible expansion and the like, facilitates the use of monitoring staff and improves the work efficiency of the monitoring staff.

The invention discloses an SINS / GPS super-compact integrated navigation system and an implementing method thereof. The method comprises the following steps: the doppler frequency assistance is provided for a GPS carrier loop by using the velocity information of a strapdown inertial navigation system, therefore, the loop equivalent bandwidth is increased, the influence of the carrier dynamic stateon the carrier loop is lowered, and the noise suppression capability is improved by reducing the bandwidth of a filter; meanwhile, in order to eliminate the correlation between the pseudo-range rate error and the inertial navigation error, a carrier loop tracking error model is obtained by establishing the relationship between the carrier tracking error and the inertial navigation speed error, andthe influence of the carrier tracking error is subduced in the measurement equation; and in addition, the carrier frequency is adjusted according to the output error estimation information, and the tracking accuracy of the carrier loop is enhanced. The invention can effectively enhance the noise suppression capability and the dynamic tracking performance of the tracking loop and enhance the tracking accuracy of a GPS receiver and the navigation accuracy of the integrated navigation system under strong interference and high dynamic circumstance.

A subject tracking apparatus which performs subject tracking based on the degree of correlation between a reference image and an input image is disclosed. The degree of correlation between each of a plurality of reference images based on images input at different times, and the input image is obtained. If the maximum degree of correlation between a reference image based on a first input image among the plurality of reference images and the input image is equal to or higher than a threshold, a region with a maximum degree of correlation with a first reference image is determined as a subject region. Otherwise, a region with a maximum degree of correlation with a reference image based on an image input later than the first input image is determined as a subject region.

The invention discloses a reentry aircraft finite time control method based on a disturbance observer and relates to the reentry aircraft finite time control method. The reentry aircraft finite time control method belongs to the field of aircraft control technology. The reentry aircraft finite time control method comprises the following steps: a first step, establishing a reentry aircraft dynamic model, presenting a finite time gesture tracking task; a second step, performing feedback linear processing on a model which is established in the first step; a third step, providing a finite time control law; a fourth step, providing a finite time disturbance observer for estimating system uncertainty and outer disturbance; and a fifth step, providing a finite time global sliding mode control method based on the disturbance observer, and effectively improving tracking precision of a gesture control system through substituting an estimated disturbance value into the control law. The reentry aircraft finite time control method has functions of improving system error convergence speed, preventing a singular problem and improving uncertainty of the controlled system to the parameter, global robustness of outer disturbance and tracking precision.

The invention discloses antenna beam tracking device and method of a moving communication satellite communication system. The antenna beam tracking device comprises a geographical position detection device, a carrier gesture detection unit, a signal intensity detection unit, a signal conditioning circuit and a master control computer, wherein the master control computer controls a servo driver; and the servo driver controls an azimuth and pitching motor. The antenna beam tracking method comprises the following steps of: 1, initially capturing a target satellite; 2, tracking: setting initial parameters, storing and updating the initial parameters in real time, generating simultaneous disturbance random vectors, driving disturbance, measuring the intensity of received signals, estimating gradient, determining tracking error signals, regulating antenna beam pointing directions, and judging the received signals; and 3, recapturing. The invention has the advantages of simple design, low cost, system implementation without changing the hardware structure of an original tracking system, easy operation, high tracking accuracy and fast tracking speed and overcomes the defects of inconvenient operation, complex tracking step, lower tracking accuracy and tracking speed, and the like of the traditional method.

The invention relates to a sun orientation automatic tracking method and a device used for photovoltaic power generation. The detection precision of the existing method and the device is lower. The method is a 24-hour 2D sun orientation automatic tracking method which uses a light intensity sensor to combine photoelectric tracking and sun motion trail tracking. The light intensity sensor detects climate and respectively adopts three different working modes to track the sun orientation in sunny days, cloudy days and rainy days, which solves the influences of climate changes and environment interference on the tracking stability to a certain extent, and simultaneously eliminates the accumulated errors through the closed loop control function of the photoelectric tracking mode, thus being capable of stably implementing sun orientation tracking in 24 hours. The device for realizing the method includes a wave-pass drum, the light intensity sensor, protective glass, a four-quadrant photoelectric detector, a signal processing circuit, a computer and an external clock chip. The invention improves the detection precision and solves the problem of unstable detection signal caused as the sunorientation detector is easy to be interfered by environmental light.