221 results about "Movement tracking" patented technology

Provided in the present invention are an exoskeleton shared control method, system and device based on AI co-driving, and a storage medium. The exoskeleton shared control method based on AI co-driving comprises: acquiring real-time pose data of an exoskeleton wearer; on the basis of the pose data, performing switching between a local trajectory correction mode and a hybrid long-short-term motion optimization mode in real time, wherein the local trajectory correction mode is completed on the basis of an AI co-driving policy network model; and performing multi-task tracking on the direction of a three-dimensional motion of an exoskeleton and a walking trajectory thereof, so as to achieve motion tracking control over the exoskeleton. By using the method provided in the present application, when encountering a sudden obstacle, an initial path can be corrected to an optimal path in combination with pose data and target point image feature data, thereby helping an exoskeleton to realize omnidirectional walking in a three-dimensional complex environment.

The invention discloses an endoscope monocular dynamic scene reconstruction method based on dynamic Gaussian splashing and motion tracking, and the method comprises the steps: firstly obtaining a dynamic scene image, obtaining an initial three-dimensional track through introducing auxiliary prior information, and then obtaining three-dimensional Gaussian; based on the auxiliary prior information, generating a group of compact Sim3 motion bases, and obtaining each three-dimensional Gaussian transformation function in the dynamic scene image by using the weighted combination of the Sim3 motion bases, the parameters of the three-dimensional Gaussian transformation function including the transformation of the position and the shape along with the time; and performing three-dimensional Gaussian transformation to each frame of image of the dynamic scene according to the three-dimensional Gaussian transformation function, and performing image rendering on each frame to obtain a rendered image. According to the method, monocular depth and dense displacement field prior are combined, and the problem of monocular scale drift is solved by utilizing depth relative sequence stability. According to the method, real-time rendering is ensured, and meanwhile, the dynamic scene reconstruction precision is remarkably improved.

The invention relates to the technical field of dynamic visual target motion tracking control, in particular to a dynamic visual target motion tracking control method and system based on deep learning, and the method comprises the steps: synchronously collecting continuous multi-frame target scene image data through a visual multi-frame collection module; and performing time sequence association and memory fusion on target features in continuous multi-frame target scene image data through a cross-frame feature memory fusion module, and constructing a target feature model. According to the invention, the current and historical stable features are dynamically fused through the cross-frame feature memory fusion module, time sequence association is realized in combination with the long and short-term memory network, and the problem of slow feature model updating under target deformation and shielding is solved; the deformation-shielding bimodal recognition module accurately recognizes a scene state, provides a basis for the multi-branch Kalman filtering prediction module, enables the multi-branch Kalman filtering prediction module to call a corresponding branch, corrects a prediction equation through a compensation factor, and improves the position prediction accuracy.

The invention relates to the technical field of image processing, and discloses a three-dimensional reconstruction method, device and equipment of a moving object and a readable storage medium, and the three-dimensional reconstruction method of the moving object comprises the steps: obtaining a plurality of fringe images of a measured moving object at continuous moments, selecting one frame as a reference frame, and obtaining a plurality of fringe images of the measured moving object at continuous moments; constructing an image set together with adjacent image frames; inputting the image set into a deep learning network for pixel-level motion tracking to obtain motion position information; based on the motion information and the intensity information, constructing a phase calculation equation set to obtain a relative phase value; performing phase unwrapping processing on the relative phase value to obtain absolute phase information; and performing phase height mapping by combining system calibration parameters to obtain dynamic three-dimensional shape data. According to the method, phase distortion caused by motion interference is remarkably eliminated, the three-dimensional reconstruction precision and real-time performance in a dynamic scene are improved, and a reliable guarantee is provided for industrial detection and high-speed target measurement.

The invention discloses an automatic tracking method for an intelligent video monitoring terminal based on target detection, particularly relates to the field of automatic tracking of video monitoring, and comprises an image intelligent analysis and processing module and a monitoring terminal. According to the method, firstly, the relative distance of a target is measured and calculated through a target distance measurement and calculation module, a moving track prediction module and a target behavior detection module, the moving track of the target is recorded and predicted, the moving behavior of the target is detected, and a key target is analyzed in combination with an image intelligent analysis and processing module; automatic switching of key targets is achieved through the target movement tracking module according to changes of the targets, the shooting orientation angle and the focal length of the camera are sequentially controlled through the execution module, the key targets are located in the optimal state of a video picture, key target tracking, recording and shooting are achieved, and it is guaranteed that key monitoring objects on a working site are clearly visible; and abnormal conditions caused by human negligence are avoided.

The invention relates to the technical field of metallurgical continuous casting production, in particular to a continuous casting blank movement tracking method, which comprises the following steps of: calculating the thermal deformation of each section of a casting blank according to the section temperature of the casting blank along the length direction in combination with the material thermal expansion coefficient and the section length at the corresponding section temperature, and generating the real-time correction position of the casting blank after a physical correction track is generated; on the basis of the real-time correction position, a preset casting blank benchmark reference position, the real-time pulling speed, the real-time cooling water amount, respective preset benchmarks and motion inertia deviations calculated on the basis of material physical properties and the real-time pulling speed, track prediction adjustment factors are generated; generating a compensation amount for the reference disturbance compensation amount by combining the matching degree of the visual solidification front edge and the model prediction, obtaining a position compensation value, superposing the position compensation value to the original trajectory, obtaining a final tracking trajectory, converting the final tracking trajectory into a servo control instruction, and dynamically correcting the casting blank tracking position. According to the invention, the precision, the dynamic performance and the intelligent performance of the continuous casting blank movement tracking are realized.

Automated systems and methods are presented for determining the physiological response of human or suitable animal subjects to physical exertion. The methods and systems can include monitoring sensors that capture the motion of the subject along with corresponding physiological data, and can track such motion for the duration of a period of physical exertion. The system is able to acquire an initial stream of physiological data from the subject during a range of physical exertion activities that are representative of the events intended to be monitored with the proposed method and system, enabling a corresponding dynamic physiological response model to be created. The motion tracking system and physiological response model can then be used to predict the physiological response to physical exertion events under a prescribed framework, including applications during real-time event monitoring.

Example methods, apparatuses, and computer-readable media are provided. Example methods include generating a virtual environment including a first shape and a second shape in a virtual viewpoint, the first shape in front of the second shape. The second shape adjusts as the virtual viewpoint adjusts, and is offset from the first shape along a test axis. The first shape is affixed to the virtual viewpoint. The virtual viewpoint is configured to adjust in response to movement of a HMD. The method includes moving a position of the virtual viewpoint with respect to the second shape in response to the movement. The method includes recording reference data associated with moving of the position of the virtual viewpoint. The method includes generating a positional displacement vector by comparing reference data of the second shape with reference data of the first shape, and determining a HMD movement tracking error based on the vector.

The invention discloses an upper limb rehabilitation training system and method for a stroke patient. Relates to the technical field of medical rehabilitation. According to the stroke upper limb rehabilitation training system and method, the limbs are driven by a machine to do repeated movement, a nervous system for controlling limb movement is stimulated and reconstructed, and therefore the movement function of the limbs is recovered, and the rehabilitation training effect of the limbs is improved. On the basis of an existing motion tracking and feedback technology, the system and the method are improved, real-time data analysis is carried out based on a sensor, a brain-computer interface technology and a cloud platform, influences of operation environment information and motion performance are considered in individualized requirements of patients, individual differences and environment variables are comprehensively considered in the rehabilitation process, and the rehabilitation effect is improved. A patient can perform rehabilitation training at any place, a rehabilitation physician, the patient and family members can check the rehabilitation condition of the patient at any time, and the precise training system and method suitable for various environments and changeable rehabilitation requirements are provided.

A method and system for motion tracking that integrates pose estimation and segmentation. The method includes accessing a first set of keypoints generated by processing at least one image of a body area of a person. The first set of keypoints can be generated via pose estimation. The method further includes processing the at least one image to generate a body mask subsequently filtered to identify a second set of body contour keypoints, executing a predetermined function to identify a new keypoint based on the first set of keypoint and the second set of keypoints, generating a third set of keypoints based on the first set of keypoints and the new keypoint, and tracking the third set of keypoints to generate motion tracking data. The method generates feedback for the person based on the motion tracking data. The new keypoint and / or feedback can be generated based on a physical activity.

A user's accommodative spasm can be evaluated and mitigated via a virtual reality (VR) system, which can include a VR headset in electronic communication with a computing device. The computing device causes virtual environments, which can include objects, optotypes, various lighting conditions, and various weather conditions, to be displayed on the VR headset. Using varying combinations of eye-tracking sensors, eye-tracking cameras, motion-tracking sensors, handheld devices, and microphones, the VR headset collects data about the user as she focuses on various objects placed at different distances away from her in the virtual environments. Optionally, advanced algorithms in the computing device dynamically alter the virtual environments and the visual tasks and analyze the user's responses to evaluate the user's accommodative spasm.

A wearable device integrating a network of interactive sensors is disclosed, wherein said sensors are configured to detect, monitor, and transmit real-time spatial position data to a central control unit. The central control unit comprises a processing module that computes the relative positioning and orientation of each sensor within a predefined reference frame, enabling continuous user movement tracking. Upon reaching a predefined spatial condition, the system generates a feedback signal, triggering a responsive sensory output via a haptic, auditory, or visual feedback mechanism. The device employs multiple positioning technologies, including inertial measurement units (IMUs), accelerometers, gyroscopes, magnetometers, radio frequency identification (RFID), Bluetooth Low Energy (BLE), ultra-wideband (UWB), and infrared tracking to ensure high-precision spatial awareness. The system is designed for applications in sports performance optimization, medical rehabilitation, virtual and augmented reality (VR / AR), occupational safety, and industrial hazard detection.

The invention discloses a distributed electric vehicle motion planning method and system considering surrounding vehicle interactive perception, and relates to the technical field of electric vehicle motion planning. The method comprises the following steps: constructing a distributed electrically-driven automobile nonlinear dynamic model, and designing a motion tracking controller by adopting a feedback linearization method; based on the constructed vehicle closed-loop dynamics system, a regional polyhedron approximation method is adopted to carry out modeling and characterization on a safety forward reachable set of the vehicle; and in combination with a probability distribution model of interaction behaviors of surrounding vehicles, introducing a conditional value-at-risk constraint mechanism, converting an automobile motion planning problem into a trajectory optimization problem, and solving and outputting a final motion planning trajectory. According to the method, the advantage that four wheels of a distributed electric drive automobile are independent and controllable is fully utilized, the control freedom degree of the method is remarkably improved compared with centralized drive, a conditional value-at-risk constraint mechanism is introduced to be combined with a surrounding automobile interaction behavior probability distribution model, and safety and agility balance in an uncertain environment is guaranteed.

Embodiments described herein relate to systems, devices, and methods for use in the implementation of a brain-computer interface that integrates real-time eye-movement tracking with brain activity tracking to present and update a user interface that is strategically designed for high speed and accuracy of human—machine interaction. Embodiments described herein also relate to the implementation of a hardware agnostic brain-computer interface with specific user interface adaptations to enable high-speed, intuitive, and accurate user manipulation of applications and / or machines.

Vision safety protocols in workplaces (e.g., a construction site, factory, or hospital) can be evaluated via a virtual reality (VR) system, which can include a VR headset in electronic communication with a computing device. The computing device causes virtual environments with virtual hazards to be displayed on the VR headset. The computing device can prompt the user to complete a task in the virtual environment while adhering to a set of vision safety protocols. Using varying combinations of eye-tracking sensors, eye-tracking cameras, motion-tracking sensors, handheld devices, and microphones, the VR headset collects data about the user as she completes the task. Optionally, algorithms in the computing device can assess the efficacy of the vision safety protocols based on the user's performance of the task and recommend changes to the vision safety protocols that increase workplace safety and efficiency. Optionally, the computing device can cause the virtual hazards to be changed.

A user's visual disorders can be treated via a virtual reality (VR) system, which can include a VR headset in electronic communication with a computing device. The computing device causes vision tests to be displayed on the VR headset. Using varying combinations of eye-tracking sensors, eye-tracking cameras, motion-tracking sensors, handheld devices, and microphones, the VR headset can collect data about the user as she completes the vision tests. Using the data collected by the VR headset, the computing device can evaluate the user for various visual disorders and develop a personalized vision therapy plan for the user. Optionally, advanced algorithms in the computing device dynamically alter the vision therapy plan based on the user's performance and the progression of her visual disorders.

Apparatus is provided to detect motion of a target reflecting one or more pure tone signals, comprising transmission of one or more pure tone acoustic signals, reception of the signal reflected by a target ensonified by the transmitted signal, and motion detection of the ensonified target from analysis of the Discrete Fourier Transform (DFT) of the received signal, in particular values of the time-variance of energy within adjacent frequency bins in the signal DFT, where the emitted tone has a frequency at the boundary between the two adjacent frequency bins.

The technology disclosed relates to coordinating motion-capture of a hand by a network of motion-capture sensors having overlapping fields of view. In particular, it relates to designating a first sensor among three or more motion-capture sensors as having a master frame of reference, observing motion of a hand as it passes through overlapping fields of view of the respective motion-capture sensors, synchronizing capture of images of the hand within the overlapping fields of view by pairs of the motion-capture devices, and using the pairs of the hand images captured by the synchronized motion-capture devices to automatically calibrate the motion-capture sensors to the master frame of reference frame.

The invention discloses a respiratory movement tracking method and system, computer equipment and a medium thereof, which are applied to the technical field of medical treatment, and the method comprises the following steps: inputting a CT image sequence into a network model pre-constructed based on a conditional diffusion model, identifying the morphological change of a target area along with respiration, and generating a sequential deformation field changing along with respiration; selecting representative tracking points such as organ edge special position points and focus area center points from a target area, tracing position information at different moments according to a time sequence deformation field, calculating displacement and forming a displacement track; irrelevant frequency interference in displacement track data is filtered out through a band-pass filtering technology, breathing movement related signals are highlighted, phase information is extracted through Hilbert transform, a breathing movement curve is drawn, visual presentation and tracking of breathing movement are achieved, doctors can be helped to more accurately grasp the breathing law of a patient, and the accuracy of breathing movement tracking is improved. Errors caused by respiratory movement are avoided in advance in surgical planning.

A moving body tracking device obtains the position of a tracking object 55, and generates a signal for permitting irradiation of a target 50 with radiation when it is determined that the tracking object 55 exists inside a gate range. In the moving body tracking device, the gate range varies between timing when the tracking object 55 enters the inside from the outside of the gate range and timing when the tracking object exits from the inside to the outside. Accordingly, provided are a moving body tracking device and a radiation irradiation system with which it is possible to suppress a change in the dose distribution and a decrease in irradiation efficiency due to the influence of latency.

Motion tracking accuracy is an important feature to an immersive augmented or virtual reality experience. Motion tracking may be computed based on data from an inertial measurement unit of a device. This data may include errors that can vary with temperature. The disclosure describes a calibration process to reduce or eliminate these errors. The calibration process does not require special equipment and can be performed while the device is in use (i.e., online).

An apparatus for configuring a wearable device for exercise tracking includes a data storage unit for storing sensor data generated by a sensor arrangement in the wearable device based on sensed movement of the wearable device and optical movement data including representations of an individual obtained from an image-based monitoring system; and a processing unit configured to: execute a movement tracker model on the sensor data to determine a first exercise activity and an associated first confidence indicator; execute an optical tracker model on the optical movement data to determine a second exercise activity and an associated second confidence indicator; process the movement tracker model based on the first confidence indicator and the second confidence indicator.

The present invention discloses a textile sensor for robust joint motion tracking that can be flexibly placed. The textile sensor is composed of a standard textile elbow pad and a sparse network of six flexible stretch sensors, including a preparation process of the textile sensor: winding silk fibers around yarn. The present invention is directed to existing methods that mainly classify specific movements rather than accurately reconstructing human body movements using flexible sensors, and generally cannot compensate for large displacements. Some methods do not support sensor rotation. Due to the deformable characteristics of flexible sensors, it is more difficult to achieve robust motion tracking when the sensor has a position offset. In contrast, the method of the present invention can not only robustly track human joint movements, but also be robust to large annular and lateral device displacements. In addition, since the predictor of the present invention can compensate for displacements through a robust algorithm, the method of the present invention does not require calibration.

A system for generating synthesized sound or speech includes at least one sensor positioned on the tongue of a user to generate position data and orientation data associated with a position and orientation of the tongue. The generated position data and orientation data from the sensor is used to generate, via an articulation conversion model, synthesizable sound or speech data using the generated position data and orientation data, which can be output as audio of synthesized voice or speech or a textual representation of the synthesizable sound or speech data.

The invention discloses a digital photo frame angle adjusting method and system based on human body movement tracking, and the method comprises the steps: obtaining gravity center distribution data in the movement process of a user, processing the gravity center distribution data, and obtaining a gravity center distribution data set; generating an initial data set, and determining gravity center distribution characteristics; the intermittent static duration in the user moving process is analyzed, segmented labeling is carried out, and boundary point data are obtained; extracting moving intermittent features in the intermittent feature time sequence, and generating fluctuation mode distribution information; a segmented adjustment mechanism is adopted to generate an initial angle adjustment scheme; tracking the dynamic posture of the user in real time to obtain a dynamic posture estimation result; determining a final angle adjusting path; determining an angle adjustment opportunity based on the final angle adjustment path; and adjusting the pitch angle of the digital photo frame. According to the method, the pitching angle of the photo frame can be accurately adjusted in time at a proper adjusting time.

The invention discloses a bicycle driving risk early warning method and system based on visual identification, and relates to the technical field of visual identification. The method comprises the following steps: acquiring driving sensing data through a sensing module carried on a bicycle body; identifying a plurality of dynamic traffic participants based on the visual perception data, and predicting future behavior intentions and motion trails; carrying out risk assessment by fusing the predicted behavior intention, the motion trail and the running state data of the bicycle, and constructing a risk perception grid which comprises a traffic event, a participant, a risk level and a movement tracking state; and based on the risk perception grid, identifying the traffic event with the risk level or the mobile tracking state reaching an early warning threshold value and the positioning space, and generating early warning feedback information. The technical problems of insufficient bicycle driving risk identification and untimely early warning in the prior art are solved, and the technical effects of driving risk active perception and timely early warning based on visual prediction are achieved.

Methods and systems for performing computer-assisted surgery, including robot-assisted image-guided surgery. Embodiments include marker devices for an image guided surgery system, marker systems and arrays for tracking a robotic arm using a motion tracking system, and image guided surgery methods and systems using optical sensors.

A method, system, and computer readable medium for switching between motion tracking mode. The method includes detecting a significant change in confidence level for motion tracking. A change from a first tracking mode to a second tracking mode is initiated when a significant change in confidence level is detected and the change is paused until a saccade or blink is detected. by eye tracking device. After a saccade or blink is detected the tracking mode switches from the first tracking mode to the second tracking mode.

The application provides a human motion tracking method and system based on regional saliency analysis in the technical field of motion tracking, and the method comprises the following steps: step S10, creating a gating network model and a plurality of expert models based on a convolutional neural network, and training each gating network model and expert model; step S20, acquiring human posture data and monitoring data of a flexible sensor; step S30, inputting the human posture data into the gating network model to obtain weight coefficients of each expert model; step S40, inputting the monitoring data into each expert model to obtain posture prediction results, obtaining the human posture of a current frame based on the weight coefficients and the posture prediction results, and then completing human motion tracking. The application has the advantage that the accuracy of human motion tracking is greatly improved.