52 results about "Body joints" patented technology

A real-time badminton action detection system, consisting of: a video recording module configured to continuously record video images at a frame rate of at least thirty frames per second; a pose estimation processing unit configured to detect and output two-dimensional skeletal landmark coordinates for a variety of body joints, including at least wrists, elbows, shoulders, hips, knees and ankles, from each video frame; a Motion Bidirectional Encoder Representation Transformer (Motion-BERT) configured to receive sequential skeleton landmark coordinates over a defined time window and encode motion trajectories using multi-head self-attention mechanisms across past and future frames; and a classification controller module operationally coupled to the Motion-BERT, wherein the classification controller module comprises a dense neural network with a softmax output layer configured to generate real-time probability distributions over a variety of badminton-specific action classes, the end-to-end system being configured to produce recognition results with a processing latency of less than 100 milliseconds; and wherein the video recording module comprises a high-speed digital camera with a wide-angle lens positioned at a point on the perimeter of the court, the camera being calibrated with intrinsic and extrinsic parameters for perspective correction, and wherein the system includes a calibration routine that aligns detected skeletal landmarks with a reference badminton court coordinate system.

A method for pose and gait classification and motion prediction using spatio-temporal relationships between body joints includes capturing a sequence of images or video frames of a subject; applying a neural network-based pose estimation algorithm to the sequence of images or video frames to detect landmark positions of anatomical joints; constructing a spatio-temporal graph from the detected landmark positions of the one or more anatomical joints, wherein nodes of the spatio-temporal graph correspond to the anatomical joints and the landmark positions, spatial edges of the spatio-temporal graph represent anatomical connections between the anatomical joints within a single image or frame, and temporal edges connect the one or more anatomical joints across successive images or frames of the sequence of images or video frames; and inputting the constructed spatio-temporal graph into a spatio-temporal graph convolutional network (ST-GCN) to classify pose and gait patterns and predict motion or stability states.

The invention relates to the technical field of rehabilitation instruments, in particular to a whole-body joint rehabilitation training device and a control method thereof. The method comprises the following steps: acquiring joint angles, IMU data and electromyographic signals when a user executes a plurality of standard actions; according to the joint angle, determining a joint motion range risk level of the target joint; according to the joint angle, the IMU data and the electromyographic signal, determining a compensatory behavior risk level and a cooperative efficiency score of a target joint; determining a training mode according to the risk level of the compensatory behavior, wherein the training mode at least comprises a general mode and a mode for the compensatory behavior; determining training parameters according to the joint motion range risk level, wherein the training parameters comprise resistance; adjusting the training parameters according to the collaborative efficiency score; and outputting the training mode and the adjusted training parameters. According to the method, the rehabilitation efficiency can be improved, and compensatory behaviors during training are reduced.

A system for acquiring, standardizing and evaluating biomechanical kinematics data of a joint includes a device for acquiring biomechanical kinematics of the joint and processing it in a computer-readable manner. A display device displays visual output to a user. A control unit processes the kinematics and determines a progression of kinematics parameters of the joint with respect to a first joint element with a first joint coordinate system and with respect to a second joint element with a second joint coordinate system. A standardization unit determines, via a predetermined target optimization, a transformation for adjusting an orientation and / or position of the first and / or second joint coordinate system to carry out a standardization, and output an evaluation via the display device. A method is used to acquire, standardize and evaluate biomechanical kinematics data of a joint, and can be executed by a computer with a computer-readable storage medium.

A method of operating a robot includes operating a robot that includes a body assembly that includes a frame formed of at least one body joint assembly, and at least one pair of joint linear actuators that form the at least one body joint. The method further includes controlling the at least one pair of joint linear actuators to operate in combination to adjust the at least one body joint assembly in two degrees of freedom through differential linear actuation.

The invention discloses a rehabilitation training action difficulty grading analysis and scheme recommendation method and system. The method comprises the following steps: defining a geometric center of a key virtual joint point; calculating a human joint mass center and a moving limb mass center; joint kinematics parameter meters are calculated, wherein the joint kinematics parameter meters comprise angles, angular velocities and angular accelerations; based on the mass center of the moving limb, the body weight ratio and the kinematics parameters, calculating torque in combination with a mechanics principle; based on prime mover muscle analysis of a human body posture, combining a joint angle and an angular velocity direction, and performing work division according to functions of prime mover muscles in human anatomy; evaluating an action difficulty grade; and comparing the actual functional state of the patient with the training standard corresponding to the current difficulty weight. The recognition precision is remarkably improved.

The invention discloses an analysis method, device and system suitable for an abnormal behavior of a judge. The method comprises the following steps: collecting a video stream of an area where the judge is located in real time through a plurality of cameras; identifying and analyzing the acquired video stream; acquiring a face image of a character object in the video image and joint point coordinate information of a body; obtaining an attitude feature information matrix S1; extracting a human face region by using MTCNN, and representing the human face region as K1; fusing the human body expression information K1 and the human body posture information S1, and representing a feature matrix S2; enabling the fused feature matrix to pass through an abnormal behavior recognition model of a residual network with noise robustness to obtain a final behavior recognition result of the human body posture; the method comprises the steps of extracting audio information in a video stream, performing text conversion and keyword extraction on the audio information to obtain an audio keyword set, and predicting an abnormal behavior to obtain an abnormal behavior prediction result. The method is accurate in monitoring and can deal with various scenes.

The present application relates to floor joint structure technical field, specifically a kind of floor anti-cracking joint structure, including floor body and positioning plate, the positioning plate both sides are provided with side along, the floor body is clamped in the inside of side along;The present application is positioned and installed first by positioning plate, then the floor body is clamped in the inside of side along on the both sides of positioning plate, engages mechanism cooperation engaging groove and engages, locking block is fixed in the through slot of positioning plate, and stably resist the end of push block, make push block and stable and catch engaging block, engaging block cooperation engaging groove stably and catch together, while filling sealant in locking block, continue to limit the activity of push block using the thermal expansion and contraction principle of sealant, so that floor body and positioning plate will be more closely engaged as temperature rises, so as to prevent the effect that floor body joint cracks, solve the problem that the existing floor joint mode is poor in rigidity and has cracking risk.

A system and method for mapping a user's gestural interactions (positional interactions and pointing interactions) from their environment to that of their avatar's environment. The system and method provide a multi-objective optimization (MO) process with the primary objective being to minimize the positional error between the end effector and goal target and the secondary objective being to preserve the original body pose while redirecting the end effector to the goal target. The primary and second objectives are addressed with a dynamic weight allocation approach that optimizes between the objectives of body joint redirection and preserving the body pose of the original interaction.

The utility model provides a connector assembly and a hair care appliance. The connector assembly comprises a handle connector and a body connector. The main body joint and the handle joint are matched with each other and can be rotationally fixed with each other, so that the main body part can keep a fixed posture at a first angle relative to the handle part; wherein the handle joint is connected with a handle part of the hair care appliance and keeps gas communication with the handle part, the main body joint is connected with a main body part of the hair care appliance and keeps gas communication with the main body part, and gas communication from the handle part to the main body part can be kept through the joint assembly.

A semantic-driven immersive telepresence system for bandwidth-efficient transmission of three-dimensional human representations. The system extracts compact semantic details from captured image data instead of transmitting complete raw 3D content. Color semantics are derived by estimating scene lighting characteristics using a lightweight model, combined with pre-captured base skin and clothing color. Motion semantics are extracted via keypoint detection of body joints, facial features, and hand positions. A regression-based method using keypoint-anchored vertices (KAVs) maps sparse keypoints to parametric human model parameters in real-time. The system transmits compressed semantic information over networks and reconstructs human representations at receiving devices. A multi-stage neural rendering pipeline with patch-based processing generates photo-realistic visual output. The approach significantly reduces bandwidth requirements compared to traditional bit-by-bit transmission of point clouds or meshes while maintaining low latency, real-time performance, and high visual quality suitable for interactive telepresence applications.

The utility model provides a detachable cycling garment which comprises an upper garment body and a lower trouser body which can be separated from each other, the bottom of the upper garment body extends downwards to form an outer-layer elastic waist tube, and the inner wall of the outer-layer elastic waist tube is provided with a buckling groove body. The top of the lower body extends upwards to form an inner-layer elastic waist opening which can be covered by the outer-layer elastic waist cylinder, and the outer wall of the inner-layer elastic waist opening is provided with a buckling strip body which can be clamped and matched with the buckling groove body; the buckle strip body and the buckle groove body are both magnetic, the buckle strip body is provided with a first limiting part and a second limiting part which are perpendicular to each other, the buckle groove body is provided with a first protruding part and a second protruding part, and the first protruding part and the second protruding part are arranged on the groove bottom wall and the groove side wall which are perpendicular to each other on the buckle groove body respectively; when the buckle strip body is clamped and matched with the buckle groove body, the first limiting part abuts against the first protruding part, and the second limiting part abuts against the second protruding part. The utility model solves the problems that the one-piece riding clothes are inconvenient to wear and take off, and the aerodynamic performance is influenced by the split scheme.

1. The name of the design product: physiotherapy instrument. 2. The use of the design product: physiotherapy instrument main machine for body joint and muscle massage health care. 3. The design points of the design product: in shape. 4. The picture or photo that can best show the design points: perspective drawing.

The application discloses a pedestrian abnormal behavior detection method based on a bidirectional trajectory prediction network, wherein a bidirectional trajectory prediction network is used to output the skeleton position of a pedestrian in each frame of a video, a loss function based on a body joint and posture is designed to train and optimize the bidirectional trajectory prediction network, and the skeleton position error between a predicted posture of the pedestrian and an actual posture is taken as an index to distinguish normal and abnormal events. The application identifies pedestrian abnormal events by evaluating the expectation of the pedestrian abnormal events in the video, outputs an abnormal score detected in each frame of the video, and supports visualization of a prediction result.

The present application relates to the technical field of rehabilitation equipment, and particularly relates to a whole-body joint rehabilitation training device and a control method thereof. The method of the present application comprises: collecting joint angles, IMU data and electromyographic signals when a user performs a plurality of standard actions; determining a joint range of motion risk level of a target joint according to the joint angles; determining a compensatory behavior risk level and a synergy efficiency score of the target joint according to the joint angles, the IMU data and the electromyographic signals; determining a training mode according to the compensatory behavior risk level, wherein the training mode at least comprises a general mode and a mode for compensatory behavior; determining a training parameter according to the joint range of motion risk level, wherein the training parameter comprises resistance; adjusting the training parameter according to the synergy efficiency score; and outputting the training mode and the adjusted training parameter. The method of the present application can improve rehabilitation efficiency and reduce compensatory behavior during training.

A method for detecting inflammation in a body joint of a subject, including: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature of the at least one body joint; marking at least one region of interest (ROI) in the at least one thermal image, wherein the marked ROI is a region in the at least one thermal image which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image; extracting values of one or more parameters of distribution of the temperature indications in the at least marked ROI; detecting inflammation in the body joint based on the extracted values.

The robot (100) comprises a body assembly (101) including a frame formed from at least one body joint assembly (104-110, 113, 115), and at least one pair of articulated linear actuators (202, 204, 206, 208, 210) forming the at least one body joint, the at least one pair of articulated linear actuators operating in combination and configured to adjust the at least one body joint assembly (104-110, 113, 115) in two degrees of freedom through differential linear actuation.

The utility model belongs to the technical field of bridge assembly, and provides a correction device for beam surface wet joint steel bar welding, which comprises annular ribs, a pinch bar, a lifting bar and a support rod, the annular ribs are arranged in a beam body joint, and the annular ribs are divided into low annular ribs and high annular ribs; the pry bar extends into a beam body joint in the longitudinal direction, the pry bar extends outwards in the radial direction to form a protruding block, the protruding block is arranged close to the lower end of the pry bar, the part, above the pry bar, of the pry bar is divided into a power arm through the protruding block, the part, below the protruding block, of the pry bar is divided into a resisting arm through the protruding block, and the side portion of the resisting arm is tightly attached to an upper transverse rib of a low annular rib; the lifting rod is transversely arranged on the side portion of the lower end of the resisting arm, the lifting rod and the protruding block are arranged in a staggered mode, and the length direction of the lifting rod is consistent with the length direction of the beam body joint. Annular ribs with different heights are corrected according to the lever principle, due to the fact that the arrangement positions of fulcrums are different, the corners of the end face of a cantilever of a beam body cannot be damaged while labor is saved, and the using effect is excellent.

The disclosure includes a computer-implemented method (100) for determining a 3D body joint position (20) of an object (70) comprising the following steps: - generating (102) a first 2D body joint position (12) for at least one body joint point (10) of the object (70) based on a body joint position data set (30) which contains at least one image from a plurality of camera perspectives; - Manually annotating (104) a second 2D body joint position (14) based on the body joint position data set (30) to determine an error deviation of the second 2D body joint position (14) from the generated first 2D body joint position (12); - determining (106) an error model (50) by estimating a statistical error value indicating a deviation (55) of the first 2D body joint position (12) from the second 2D body joint position data (14); - Determining (108) the 3D body joint position (20) for the at least one body joint point (10) on the basis of the first 2D body joint position (12) and the determined error model (50) by applying a statistical method.

The application provides an intelligent video teaching method and system for action recognition, comprising: obtaining historical learning information of a learner; obtaining and playing a learning video based on the historical learning information of the learner; wherein, in the process of playing the learning video, the position of a body joint of the learner is obtained in real time, the body action of the learner is judged, the playing progress of the learning video is controlled based on the body action of the learner; meanwhile, a face color image of the learner is obtained, the face key points in the face color image are identified based on the face color image of the learner, the mean value of left and right eye closure and the mouth opening angle are calculated based on the face key points, the head rotation angle is calculated based on the face color image, and the video playing content is updated based on the mean value of left and right eye closure, the mouth opening angle and the head rotation angle. The body control of the playing progress and the autonomous update of the playing content in online education are realized.

This disclosure describes systems, methods, and devices related to generating a three-dimensional full-body reconstruction using image data from a single camera. A method may include receiving first point cloud data from the camera, the point cloud data representing a person; identifying a first human body template, the first human body template representing body joints; generating, based on a comparison of the first human body template to the first point cloud data, parameters associated with the body joints; and generating, based on the parameters, a second human body template representing the person.

To provide an underpants type absorbent article having a crotch elastic member in which a front side waistline member hardly falls down and fitting performance in the hip is enhanced.SOLUTION: There is provided an underpants type absorbent article (1) having an absorbent body (10), a front side waistline member (20), a back side waistline member (30), and a crotch elastic member (17) stretchable in a longitudinal direction. In a longitudinal direction in an expanded and stretched state, the length (L2) from a central position to a back side end of the absorbent body is greater than the length (L1) from the central position to a front side end of the absorbent body. The length (SH2) from the central position to a back side end of the crotch elastic member is greater than the length (SH1) from the central position to a front side end of the crotch elastic member. The length (HMA2) of a back side body joined part is greater than the length (HMA1) of a front side body joined part. The length (GA2) from the central position to a front side end of an extension part is smaller than the length (GA1) from the central position to the back side end of the front side waistline member.SELECTED DRAWING: Figure 4

A system and method for mapping a user's gestural interactions (positional interactions and pointing interactions) from their environment to that of their avatar's environment. The system and method provide a multi-objective optimization (MO) process with the primary objective being to minimize the positional error between the end effector and goal target and the secondary objective being to preserve the original body pose while redirecting the end effector to the goal target. The primary and second objectives are addressed with a dynamic weight allocation approach that optimizes between the objectives of body joint redirection and preserving the body pose of the original interaction.

The embodiment of the invention provides a robot and an operation method and device thereof, a storage medium and a program product, and the method comprises the steps: based on a joint dynamic model of the robot, a whole-body Jacobian matrix and at least one moment limiting condition, taking the joint moment of the whole-body joints as an optimization variable, determining priorities, task parameters and constraint parameters of a plurality of subtasks of the hierarchical quadratic programming task; according to the sequence of the priorities of the sub-tasks from high to low, the optimal joint torque of each sub-task is solved layer by layer by utilizing the accumulated null space of the sub-task of the upper layer; and based on the optimal joint torque obtained through final solving, whole-body joints of the robot are driven so as to control operation of the robot. According to the method, strict priority control and whole-body moment limitation are taken into consideration, by means of hierarchical solution of an accumulated null space, it is guaranteed that a low-priority task does not interfere with a high-priority task, and the stability and predictability when multiple tasks are parallel are remarkably improved.

1. Name of the designed product: Massage apparatus (three rows) 2. Use of the designed product: The designed product is used for massaging body joints. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

The application discloses a kind of whole body teleoperation methods of humanoid robot based on joint matching and intention recognition, comprising: collecting the first attitude data of operator upper body joint and the second attitude data of lower limb joint;First attitude data is mapped to each corresponding upper body joint of robot;Based on second attitude data, motion intention is extracted by hybrid hierarchical logic, and lower limb intention instruction is obtained;Based on lower limb intention instruction, the course reinforcement learning framework based on logarithmic attenuation mechanism is used as control strategy, and the control torque of each lower limb joint of robot is generated, to realize the lower limb teleoperation control of robot.The application is applied to the field of robot control, not only can completely liberate the hands and waist of operator, so that it obtains more teleoperation degrees of freedom, but also can make robot stable in actual teleoperation, avoid instability when facing large amplitude and rapid arm swing and other violent upper body inertia disturbance.

The invention provides a remote emotion interaction robot system based on real-time pose projection, and relates to the technical field of robots. Limb actions, facial micro-expressions and voice information of a user are captured in real time through a multi-sensor fusion technology (a camera, a somatosensory glove, a pressure sensor and the like), 468 facial key points and 33 body joint points are extracted in combination with a MediaPipe model, and low-delay and high-precision action smooth mapping is realized by adopting Kalman filtering and an exponential weighted moving average (EMA) algorithm. Modularized bionic design is adopted for the robot, the bionic arms, the head and the breathing and heartbeat bionic module driven by flexible steering engines are arranged, the action rigidity, speed and contact strength can be dynamically adjusted, and human natural body languages and vital signs are simulated. A real-time communication link is constructed through a TCP / IP protocol, dual-mode interaction of real-time projection and a preset action library is supported, and the system is suitable for scenes such as remote nursing accompanying, parent-child interaction and psychotherapy healing.

The invention discloses a full-dimensional defect detection method and related equipment for a humanoid robot, and the method comprises the steps: obtaining the posture data of the robot, and carrying out the whole-body joint cooperative control of the humanoid robot according to the posture data of the robot, so as to obtain the thermal imaging data, image data and three-dimensional point cloud data of target equipment; performing abnormal region identification on the thermal imaging data to obtain a middle defect region; performing feature extraction on the image data and the three-dimensional point cloud data according to the middle defect area to obtain image features of the image data and point cloud features of the three-dimensional point cloud data; according to the image features, performing single-dimensional feature fusion on the point cloud features to obtain a single-dimensional fusion result; and according to the robot attitude data, performing full-dimensional updating on the single-dimensional fusion result to obtain a full-dimensional defect detection result of the target equipment. According to the method, the accuracy and robustness of defect detection on the industrial equipment can be improved. The invention relates to the technical field of defect detection.