31 results about "Visual tracking system" patented technology

A method for adjusting camera intrinsic parameters of a single camera visual tracking device is described. In one aspect, a method includes accessing a temperature of a camera of the visual tracking system, detecting that the temperature of the camera exceeds a threshold, in response identifying one or more feature points that are located in a central region of an initial image, generating a graphical user interface element that instructs a user of the visual tracking system to move the visual tracking system towards a border region of the initial image, and determining intrinsic parameters of the camera based on matching pairs of the one or more detected feature points in the border region and one or more projected feature points in the border region.

A method of providing anonymized data for facilitating reidentification in a visual tracking system, the method comprising: detecting, in images obtained from a plurality of image sources, subareas which each contain a tracking target; computing, for each subarea, a feature vector which represents a visual appearance of the tracking target therein; for a first / second subgroup of the image sources, providing first / second reidentification data items by anonymizing each feature vector using a predefined one-way function modified by a first / second tracking-rights token, and disclosing the first / second reidentification data items annotated with locations of the respective subareas to a first / second tracking client, wherein the second tracking-rights token is distinct from the first tracking-rights token; and preventing access to the feature vectors.

The invention provides a visual tracking system and method for agricultural products, and the method comprises the steps: extracting the basic tracking information of the agricultural products from a tracking information label through analyzing the tracking information label on the outer package of the agricultural products; the basic tracking information comprises a unique identity label of the agricultural product and a first visual gradient feature, and judging whether the first visual gradient feature in the tracking information label is matched with the picture of the agricultural product; when the first visual gradient feature in the tracking information label is matched with the picture of the agricultural product, acquiring complete tracking information of the agricultural product from an agricultural product tracking server based on the unique identity label of the agricultural product, and the complete tracking information of the agricultural products is visually presented in combination with the pictures of the agricultural products, so that the loopholes of the existing anti-counterfeiting means can be effectively filled, and the agricultural products which are not strictly detected are prevented from flowing into the market.

The invention relates to the technical field of medical surgical navigation, and discloses an intraoperative instrument position real-time visual tracking system which comprises a preoperative three-dimensional reconstruction unit, an intraoperative positioning unit, a coordinate matching unit, an error compensation unit and a visual display unit which are in bidirectional communication through a data bus. According to the intraoperative instrument position real-time visual tracking system and method, the problem of electromagnetic interference is solved through a magnetoelectric fusion positioning engine and a dynamic magnetic field calibration module, and the magnetoelectric fusion positioning engine receives a gradient magnetic field signal generated by an electromagnet array and an electric field signal of a body surface reference electrode; the dynamic magnetic field calibration module is combined with the frequency division multiplexing technology to separate double-frequency signals, then space-time registration is carried out through the magnetoelectric conversion matrix, alignment of a magnetic sensor and a magnetic beacon coordinate system is not needed, magnetic field distortion caused by a metal instrument can be counteracted, angle calculation errors can be reduced through bimodal signal complementation even if the posture of the instrument changes, and the precision of the instrument is improved. And positioning accuracy is improved.

This application provides a visual tracking method and computing device, relating to the field of computer technology, and applied to a visual tracking system. The visual tracking system includes a camera and a display screen. The method includes: determining a first plane and a second plane based on images captured by the camera, wherein the first plane is a plane corresponding to a background image in the image, and the second plane is a plane corresponding to a face in the image; determining the homography matrix of the face in the second plane relative to the first plane based on a first image and a second image captured by the camera in chronological order; determining a rotation matrix and a translation vector of the face based on the homography matrix; and determining the physical coordinates of the user's gaze on the display screen based on the rotation matrix and the translation vector. The technical solution provided by this application can solve the technical problems of insufficient tracking accuracy and poor stability in related technologies based on monocular cameras.

The invention discloses a fracture reduction robot control system and method, and the system comprises two mechanical arms which are in rigid connection with two parts of a to-be-reduced bone respectively, and the tail ends of the two mechanical arms are provided with mark points visible on a perspective image; the perspective equipment is used for carrying out multi-view perspective shooting on the to-be-reset bone; the visual tracking system is used for identifying the pose of the perspective equipment; and the upper computer is used for establishing a mapping relation between the perspective images and the visual tracking system according to the poses of the perspective equipment at the perspective moment, determining the amount of motion of the two parts of the bone to be reset according to the reset key features marked on the perspective images, and controlling the corresponding mechanical arms to move. A large amount of X-ray fluoroscopy is not needed, the radiation hidden danger of a doctor is reduced, the iatrogenic risk is effectively reduced, and high reduction precision and reduction efficiency are achieved.

A method of providing anonymized data for facilitating reidentification in a visual tracking system, the method comprising: detecting, in images obtained from a plurality of image sources, subareas which each contain a tracking target; computing, for each subarea, a feature vector which represents a visual appearance of the tracking target therein; for a first / second subgroup of the image sources, providing first / second reidentification data items by anonymizing each feature vector using a predefined one-way function modified by a first / second tracking-rights token, and disclosing the first / second reidentification data items annotated with locations of the respective subareas to a first / second tracking client, wherein the second tracking-rights token is distinct from the first tracking-rights token; and preventing access to the feature vectors.

The invention discloses a power grid reactive dynamic compensation real-time visual tracking system based on optical flow field analysis, and relates to the technical field of power grid compensation visualization, and a multi-module cooperative system including image acquisition, electric power parameter acquisition, optical flow field calculation, comprehensive analysis, dynamic compensation control and visual interaction is constructed. Accurate recognition and response control of dynamic changes of reactive power of a power grid are achieved, the system intelligently discriminates a disturbance area by fusing optical flow vectors and electric power parameter characteristics, compensation equipment is guided to adjust in real time, and meanwhile the operation state of the power grid is displayed in a graphical mode. The accuracy and real-time performance of reactive compensation and the stability of system operation are effectively improved.

The present invention belongs to the field of automatic measurement and marking of complex castings. It discloses a high-precision calibration and online optimization method for dual robots. Based on hand-eye calibration and four-point calibration, the casting-measurement-marking system components are calibrated separately when the system is deployed to obtain high-precision initial values ​​of system parameters. Calibration data is collected online during the measurement-analysis-marking process based on a visual tracking system to achieve online optimization of multi-robot system parameters. The optimized robot paths are fed back to a data control center to ensure high-precision and stable operation of the robot marking.

This invention relates to direct scale level selection for multi-level feature tracking. A method for mitigating motion blur in a visual-inertial tracking system is described. In one aspect, the method includes: accessing a first image generated by an optical sensor of the visual tracking system; accessing a second image generated by the optical sensor of the visual tracking system, the second image following the first image; determining a first motion blur level of the first image; determining a second motion blur level of the second image; identifying a scale change between the first and second images; determining a first optimal scale level for the first image based on the first motion blur level and the scale change; and determining a second optimal scale level for the second image based on the second motion blur level and the scale change.

The utility model relates to the technical field of fan volute welding, and discloses an automatic welding device based on laser scanning and 3D camera recognition, which comprises a control mechanism, a Y-axis guide rail and a fan volute, the top of the Y-axis guide rail is movably provided with a supporting mechanism, the top of the supporting mechanism is fixedly provided with a longitudinal X-axis guide rail, and the X-axis guide rail is fixedly provided with a vertical Y-axis guide rail. A transverse mounting plate is mounted on the X-axis guide rail, a welding machine is fixedly mounted at the left end of the mounting plate, a welding manipulator is fixedly mounted at the right end of the mounting plate, a welding gun is fixedly mounted on the right side of the welding manipulator, and a laser scanning and 3D camera recognition system is fixedly mounted at the bottom of the welding gun. The teaching programming operation is simple, the fault-tolerant rate of the space position of the welding seam is high, the position of the welding seam is positioned and guided on line through the laser visual tracking system, intelligent automatic welding is achieved, a large number of welding locating tools and clamps are reduced, efficiency is improved, and manufacturing cost is reduced.

The invention relates to the technical field of automobile part manufacturing, in particular to a trailing arm stamping and welding process, which comprises the following steps of: uncoiling by using a servo drive uncoiling machine matched with a four-roller precision leveling machine, leveling a coiled material for multiple times, and blanking by using a numerical control plate shearing machine to obtain a plate blank; drawing the left / right trailing arm blank into the basic shape of the trailing arm on a drawing die, and trimming and punching by using a high-precision punching machine and a hydraulic machine; then, a vertical flanging die and a floating type side shaping die are used for flanging and side shaping, and the workpiece is rolled into a closed pipe shape; then, double-wire welding is adopted on a special clamp to conduct high-speed welding on a welding seam of the workpiece; 3D laser cutting equipment is used, a visual tracking system is arranged, the variable cross-section pipe is precisely cut, the size precision and the shape precision of the left trailing arm and the right trailing arm are effectively guaranteed, and the problems that in the prior art, precision control is difficult, efficiency and cost are contradictory, and process compatibility is poor are solved.

The invention discloses a method and a device for anonymizing re-identification data in a visual tracking system. The method comprises: detecting (210) sub-regions each containing a tracking target in an image obtained from a plurality of image sources; calculating (211), for each sub-region, a feature vector representing a visual appearance of the tracked target therein; providing (212.1 / 212.2) first / second reidentification data items for a first / second subset of image sources by anonymizing each feature vector using a predefined one-way function modified by a first / second tracking permission token, and disclosing (213.1 / 213.2) the first / second re-identification data item tagged with the location of the corresponding sub-region to the first / second tracking client, where the second tracking permission token is different from the first tracking permission token; and preventing (214) access to the feature vector.

The invention belongs to the technical field of vehicle control, and particularly relates to a four-quadrant identification dynamic visual tracking system based on feature tracking. Comprising an image data acquisition module, a four-quadrant target detection module, an optical flow tracking module, a trajectory prediction module and a steady-state target management module. The image data acquisition module is responsible for acquiring video stream data containing the surrounding environment of the four-quadrant mark and transmitting the data to the four-quadrant mark detection module frame by frame; the four-quadrant identifier detection module is responsible for performing real-time processing on an input source image and converting the input source image into an ROT region matched with a four-quadrant identifier in the source image; the optical flow tracking module is used for converting a source image transmitted by the image data acquisition module into a grayscale image to realize inter-frame tracking of four-quadrant identification feature points; the steady-state target management module is used for judging how to recover and predict a lost target position after tracking loss; and the track prediction module predicts the position of the next frame of source image through the motion model. Compared with the prior art, the technical scheme has the advantages that the tracking robustness is enhanced, the stability recovery speed is high, and the scene adaptability is high.

The invention belongs to the technical field of target visual tracking, and particularly relates to a high-performance weak and small target visual tracking system for an open complex environment, and the system comprises a heavy rotary table which is used for providing stable mechanical support for high-precision equipment in the system; the orientation and pitching control and driving module is used for driving the heavy rotary table and ensuring stable rotation, so that horizontal and pitching operation of the heavy rotary table is realized; the visible light imaging device is used for providing target identification and tracking with high resolution and rich details; the infrared thermal imaging device is used for providing target detection and tracking in an all-weather and low-visibility environment; and the information processor is used for performing data interaction with the outside. According to the invention, all-weather, full-coverage, high-precision and high-robustness multi-dimensional detection and tracking tasks can be carried out in a specific complex environment area, and the method has a good market application prospect.

A visual tracking system for tracking and identifying persons within a monitored location, comprising a plurality of cameras and a visual processing unit, each camera produces a sequence of video frames depicting one or more of the persons, the visual processing unit is adapted to maintain a coherent track identity for each person across the plurality of cameras using a combination of motion data and visual featurization data, and further determine demographic data and sentiment data using the visual featurization data, the visual tracking system further having a recommendation module adapted to identify a customer need for each person using the sentiment data of the person in addition to context data, and generate an action recommendation for addressing the customer need, the visual tracking system is operably connected to a customer-oriented device configured to perform a customer-oriented action in accordance with the action recommendation.

The application discloses a visual tracking system based on a modularized holder, relates to the technical field of visual dynamic tracking, and comprises the following: a modularized holder, which is used for erecting a visual collection module; the visual collection module, which is used for acquiring image data in real time; a data processing module, which is used for processing the obtained image data and determining an image key frame according to a processing result; a visual analysis module, which is used for determining a target feature to be tracked in the image key frame; and a visual tracking module, which is used for generating a cooperative intelligent control strategy according to the moving track of the target feature; through feature priority division and dynamic key frame demarcation range adjustment, full-range demarcation is adopted to focus on a core target when there is a high-priority feature, and a default range is adopted when there is no highest-priority feature, so that redundant data processing is effectively reduced, the computing power is inclined to high-value core features, and the accuracy and real-time performance of tracking are improved.

The utility model provides a drainage balance system which comprises an outer drainage device, a drainage support, a dropping bottle support, a dropping bottle, a drainage pipeline and a liquid drainage pipeline, the dropping bottle support is installed on the drainage support, and the drainage pipeline and the liquid drainage pipeline are both connected with the dropping bottle; the drainage monitoring unit comprises a plurality of preset sensors, and the preset sensors are used for monitoring the state of drainage liquid in the drainage pipeline and the state of drainage liquid at an outlet respectively; the visual tracking system is used for shooting an image of a region of interest on the target object and obtaining position information of a mark point on the region of interest according to the image of the region of interest; the drainage adjusting device is connected with the outer drainage device, and the outer drainage device can move and swing up and down relative to the drainage adjusting device. Accurate and comprehensive monitoring of the drainage process can be realized.

A method for adjusting camera intrinsic parameters of a multi-camera visual tracking device is described. In one aspect, a method for calibrating the multi-camera visual tracking system includes disabling a first camera of the multi-camera visual tracking system while a second camera of the multi-camera visual tracking system is enabled, detecting a first set of features in a first image generated by the first camera after detecting that the temperature of the first camera is within the threshold of the factory calibration temperature of the first camera, and accessing and correcting intrinsic parameters of the second camera based on the projection of the first set of features in the second image and a second set of features in the second image.

A visual tracking system for tracking and identifying persons within a monitored location, comprising a plurality of cameras and a visual processing unit, each camera produces a sequence of video frames depicting one or more of the persons, the visual processing unit is adapted to maintain a coherent track identity for each person across the plurality of cameras using a combination of motion data and visual featurization data, and further determine demographic data and sentiment data using the visual featurization data, the visual tracking system further having a recommendation module adapted to identify a customer need for each person using the sentiment data of the person in addition to context data, and generate an action recommendation for addressing the customer need, the visual tracking system is operably connected to a customer-oriented device configured to perform a customer-oriented action in accordance with the action recommendation.

This invention discloses an adjustable fundus fixation training visual tracking system suitable for different patients, belonging to the field of medical device technology. The system includes: a patient parameter acquisition module, an adaptive control center, a multimodal stimulus presentation module, an eye-tracking and quantitative assessment module, and an immersive interactive feedback module. This invention aims to solve the problems of fixed training parameters, lack of personalized adaptation, and inability to provide real-time quantitative feedback. By acquiring the patient's interpupillary distance, visual acuity, and tolerance parameters and mapping them to personalized training control parameters, it dynamically generates and adjusts visual stimuli. Simultaneously, it tracks and quantifies eye-tracking performance in real time, transforming the quantification results into multisensory interactive feedback. This achieves adaptive matching between training difficulty and patient ability, improving the personalization, accuracy, and patient compliance of the training.

A method for limiting motion blur in a visual tracking system is described. In one aspect, the method includes accessing a first image generated by an optical sensor of the visual tracking system, identifying camera operating parameters of the optical sensor for the first image, determining a motion of the optical sensor for the first image, determining a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, and adjusting the camera operating parameters of the optical sensor based on the motion blur level.

A visual tracking system helps to detect or locate an active object (such as an active sound source) in a live video or recorded video, and provides a way to help a user who views the live video or recorded video to focus on the active object, without easily being disturbed or distracted by other objects that are present with the active object. The visual tracking system may further track the active object, or detect a new active object when the live video or recorded video is played.

Methods for mitigating motion blur in a visual inertial tracking system are described. In an aspect, the method includes accessing a first image generated by an optical sensor of a visual tracking system, accessing a second image generated by the optical sensor of the visual tracking system, the second image being subsequent to the first image, determining a first motion blur level of the first image, determining a second motion blur level of the second image, identifying a scale change between the first image and the second image, determining a first optimal scale level for the first image based on the first motion blur level and the scale change, and determining a second optimal scale level for the second image based on the second motion blur level and the scale change.

The application discloses a multi-agent cooperative control system based on a multi-modal brain-computer interface-visual tracking, which comprises the following modules: a signal acquisition and processing module, which adopts an 8-lead electroencephalogram cap to collect electroencephalogram original data, selects a part of an occipital region (PO7, PO8, P3, P4, Pz, O1, O2 and Oz) as an electroencephalogram data acquisition area, and collects EEG data; a feature extraction and classification module, which uses a space-time convolution network to extract SSVEP signal features, combines an integrated learning strategy to optimize classification accuracy, extracts EOG signals based on a Transformer model, integrates an LMS adaptive filter to combine a wavelet transform to denoise EEG signals, expands the frequency tracking range of the adaptive filter, and minimizes signal loss; a cooperative control strategy design module, which maps electroencephalogram signals into control instructions of different agents, and realizes cooperative control of unmanned aerial vehicles and trolleys; and a target detection and tracking module, which optimizes an unmanned aerial vehicle visual tracking system based on a PP-YOLOE model, and realizes accurate tracking and automatic adjustment of the trolley.

The invention relates to the technical field of automobile parts, in particular to a manufacturing process of a cross beam of a torsion beam assembly. The method comprises the steps that a servo drive uncoiler is adopted to process coil stock, multiple times of reciprocating leveling are conducted through a four-roller precision leveling machine, a numerical control plate shearing machine is adopted, and blanking is conducted according to the optimal drawing plate size; a drawing die with special surface treatment is adopted; trimming and punching by using a high-precision punching machine and a hydraulic machine; a flanging die is adopted for flanging operation; a floating type side shaping die is adopted for side shaping to gradually form a closed pipe shape; double-wire welding is adopted for welding; a 3D laser cutting machine is used, a visual tracking system is arranged, and the variable cross-section pipe is accurately cut, so that the size precision and the shape precision of the cross beam are effectively guaranteed, and the welding precision and the consistency of the whole torsion beam assembly are greatly improved.

The invention relates to the technical field of ultrasonic contrast, in particular to a visual tracking system and method for dynamic distribution of an ultrasonic contrast agent, and the method comprises the steps: obtaining sound pressure and microbubble breakage data of ultrasonic contrast, analyzing the influence of the sound pressure on microbubble breakage, and obtaining a breakage influence coefficient; sound pressure and microbubble movement data of ultrasonic contrast are obtained, the influence of the sound pressure on microbubble movement is analyzed, and a movement influence coefficient is obtained; according to the breaking influence coefficient and the movement influence coefficient, the sound pressure is dynamically regulated and controlled, and regulated and controlled sound pressure is obtained; analyzing the vulnerability coefficient of the current microbubble according to the damage influence of sound waves on the microbubble within the scanning time; the regulation and control sound pressure is corrected through the vulnerability coefficient of the current microbubble, and optimized regulation and control sound pressure is obtained; adjusting the tracking area according to the current microbubble fracture rate and the vulnerability coefficient of the current microbubble; according to the method, the service life of the microbubbles is prolonged, stable development is maintained, non-specific rupture is reduced, biological risks are reduced, and the stability of a tracking area is effectively guaranteed.

This invention discloses an intelligent tooth preparation system, belonging to the field of medical device technology. It utilizes a visual tracking system to monitor the position of a marker in real time, thereby completing hand-eye calibration of the robotic arm, drill tip calibration, and intraoral registration. During tooth preparation, the position of the intraoral marker is monitored in real time. Based on the positional changes of the intraoral marker and its relative positional relationship with the target tooth, the real-time position of the target tooth is obtained. The motion scheme of the robotic arm's end effector is adjusted according to the real-time positional changes of the target tooth. Compared with existing technologies, this application can reduce the manual dependence of tooth preparation, achieving precise, efficient, minimally invasive, and safe tooth preparation through automation and intelligence, thus ensuring the quality of tooth preparation.

A method for limiting motion blur in a visual tracking system is described. In one aspect, the method includes accessing a first image generated by an optical sensor of the visual tracking system, identifying camera operating parameters of the optical sensor for the first image, determining a motion of the optical sensor for the first image, determining a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, and adjusting the camera operating parameters of the optical sensor based on the motion blur level.

A method for adjusting camera intrinsic parameters of a multi-camera visual tracking device is described. In one aspect, a method for calibrating the multi-camera visual tracking system includes disabling a first camera of the multi-camera visual tracking system while a second camera of the multi-camera visual tracking system is enabled, detecting a first set of features in a first image generated by the first camera after detecting that the temperature of the first camera is within the threshold of the factory calibration temperature of the first camera, and accessing and correcting intrinsic parameters of the second camera based on the projection of the first set of features in the second image and a second set of features in the second image.