32 results about "Right wrist" patented technology

The invention discloses a whole body attitude estimation method based on a sparse inertial sensor. The method comprises the following steps: 1, synthesizing acceleration data, direction data and angular velocity data through a finite difference method and a forward kinematics algorithm; 2, performing alignment processing on original acceleration data and original direction data acquired by three inertial sensors worn on a head joint, a left wrist joint and a right wrist joint of the user by rotating the transformation matrix; and 3, extracting depth features of an inertial motion data sample through an encoder combining Transform Encoder and a bidirectional long-short time memory network, designing a decoder based on a multilayer perceptron to calculate positions and relative rotation of joints, and sequentially estimating the relative rotation of the joints of different parts in a plurality of stages in combination with a human body kinematics model so as to realize whole body posture estimation. The method can effectively overcome the defect that sparse inertia input is used for whole body motion reconstruction in an existing attitude estimation method, and the robustness and prediction precision of the system are effectively improved.

The invention discloses an intelligent monitoring wrist strap for plateau adaptive sports and a system thereof. The intelligent monitoring wrist strap comprises a monitoring main body, a left wrist strap and a right wrist strap, one side of the monitoring main body is provided with a power supply lamp, a gait monitoring lamp and an osteoporosis early warning lamp, the other side of the monitoring main body is provided with a charging port, and the monitoring main body is internally provided with a micro-processing chip, an air pressure sensor, a temperature sensor, an ultraviolet sensor and an alarm microphone; an osteoporosis early warning module is arranged at the lower part of the monitoring main body, a display screen is arranged at the upper part of the monitoring main body, and an air pressure sensor, a temperature sensor, a blood oxygen detection module, a heart rate detection module, a gait monitoring module, an osteoporosis early warning module and a wireless transmission module are integrated on the micro-processing chip. According to the plateau environment characteristics and the skeletal system chronic disease risk, the motion state and health data of the wearer are dynamically monitored, and individualized motion guidance and early warning information is generated, so that the risk of plateau crowds in the motion process is reduced, and the individualized health management level is improved.

The invention relates to a sitting body forward bending action standard detection method, and belongs to the technical field of action standard detection, and the method comprises the steps: detecting left and right ankle coordinates, left and right knee coordinates, left and right hipbone coordinates, left and right shoulder coordinates, left and right elbow coordinates, left and right wrist coordinates, and hand tip coordinates of left and right hands of a person; when the 14 coordinates are detected, judging that the personnel has made preparation work, and starting to detect the forward bending action standard of the sitting body; 14 coordinates of each frame are recorded in the detection process; determining a completion score of each frame according to the hand tip coordinates of the left and right hands; judging whether the person completes the action according to the completion score of each frame, and obtaining a valid score or an invalid score; determining an upper limb termination score and a lower limb termination score of each frame, and determining a termination score of each frame according to the upper limb termination score and the lower limb termination score of each frame; and judging whether the action is illegal or not according to the termination score of each frame, and if the judgment result is that the action is illegal, terminating the assessment, and judging that the score is invalid.

The application discloses a method and system for body positioning in a face-to-face confrontation XR game, and relates to the technical field of spatial positioning in a confrontation XR game. In the face-to-face confrontation XR game, the glasses camera of an opponent player is used as an outward-inward sensor, and the world coordinates of key points such as the glasses center, left and right wrist, and left and right ankle of each player are calculated through triangulation in cooperation with the outward-inward 6DoF positioning of each pair of glasses. In the game, precise body positioning can be realized without wearing any additional sensors at the positions of the wrist, ankle and the like.

A wrist blood pressure monitor (100) includes a main body portion (10), a band-like member (20), a sensor cuff (22), and a pressure cuff (23). The band-like member (20) includes a first end portion and a second end portion positioned in a width direction. In a first state in which the band-like member (20) is wrapped around a left wrist, with the first end portion positioned on a finger side of a left hand, the second end portion positioned on an elbow side of the left hand, and the main body portion (10) disposed on a side surface (60c) of a left arm (60) on a thumb side of the left hand, the sensor cuff (22) is disposed so as to be capable of compressing a radial artery (63) of the left wrist from a front surface side (60d) of the left arm (60) on a palm side.In a second state in which the second end portion is positioned on a finger side of a right hand, the first end portion is positioned on an elbow side of the right hand, and the main body portion (10) is arranged on a side surface of a right arm on a thumb side of the right hand, the sensor cuff (22) is arranged to be capable of compressing a radial artery of a right wrist from a front surface side of the right arm on a palm side.

The invention relates to the field of intelligent identification, in particular to a complex maintenance scene-oriented virtual human intelligent motion control method, which comprises the following steps of: performing virtual human physical modeling, and establishing a virtual human model based on a GB10000 human body size standard and a human-machine ergonomics standard, wherein the kinematics architecture divides a virtual human into an upper body and a lower body, the upper body comprises eight joints including a spine, a neck, left / right shoulders, left / right elbows and left / right wrists, the lower body comprises six joints including left / right thigh roots, left / right knees and left / right ankles, and all the joints are abstracted into spherical hinge, hinge or universal joint kinematics mechanisms respectively. Joint angle constraints are set; the technical problem that a mode of designing animations in advance and combining prefabricated animations is adopted on the basis of action methods such as a state machine and a behavior tree, calculation and analysis generally face conventional maintainability tasks, and special and complex maintenance scenes are difficult to meet is solved.

The invention relates to the technical field of machine learning, in particular to a robot action generation method and device, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining a current visual state of a target robot and a corresponding task text instruction, inputting a preset target video generation model, and outputting a denoised submerged space feature; multi-step video generation diffusion sampling is avoided, the calculation amount is reduced, the real-time performance is improved, then current state features (current angle data of all joints) of the robot and left and right wrist images are obtained, and the current state features and the left and right wrist images are input into a preset action expert model together with submerged space features. By means of the multi-source information fusion input mode, the cross-modal fine-grained relation can be captured, understanding of complex instructions and environment information is enhanced, language semantic degradation can be avoided, modeling can be conducted on environment dynamic evolution, a reasonable action prediction result is finally output, and the actual application requirement of the robot is met.

1. The name of the design product: wrist protector skeleton (lower). 2. The use of the design product: for fixing and protecting the wrist. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view. 5. Other circumstances that need to be explained: this product is a left wrist protector skeleton, which is used with a right wrist protector skeleton; since the right wrist protector skeleton is symmetrical with the left wrist protector skeleton, all views of the right wrist protector skeleton are omitted.

The present invention discloses a method for decoding imagined movements based on tactile sensation calibration, comprising: (1) setting up a tactile stimulation device and applying tactile stimulation to the dorsal side of the left or right wrist of the subject; (2) setting up an EEG device to record EEG signals, with the original signals being digitally sampled at a frequency of 500 Hz and using a filter to filter the original signals; (3) using the tactile stimulation device and the EEG device to collect the pure imagined movement data of the subject, as well as the imagined movement data assisted by tactile sensation; (4) using the common spatial pattern algorithm to extract the EEG data features and training a classifier for classifying the EEG data features; wherein, the imagined movement data assisted by tactile sensation is used as the training set; (5) applying the trained classifier to pure imagined movement decoding. By using the present invention, EEG data with a higher signal-to-noise ratio can be obtained, and then a more robust and accurate model can be trained for movement decoding.

1. Name of the product in this design: Wristband. 2. Purpose of this design: Wrist brace for protecting the wrist joint. 3. The key design feature of this product is its shape. 4. Images or photos that best illustrate the design points: Refer to Figure 1 for the usage status of Kit 1. 5. Submitting the views is sufficient to express the appearance design; the top view of Suite 1, the bottom view of Suite 1, the view of Suite 2, and the bottom view of Suite 2 are omitted. 6. Other situations requiring explanation: Kit 1 is the left wrist guard, and Kit 2 is the right wrist guard.

The invention discloses a non-standing type body measurement method and device based on real-time key point detection. The method comprises the following steps: (1) collecting a non-standing type data set image; (2) marking joint key points: a left ear, a right ear, a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist, a right wrist, a left hip, a right hip, a left knee, a right knee, a left ankle and a right ankle; the labeling detection frame comprises a big arm, a small arm, a thigh, a shank, a body and a head; marking the longest edge key points of the local cross section: a big arm, a small arm, a thigh and a shank; (3) designing a composite network, merging all key points and detection frames, and sending the merged key points and detection frames into network training; and (4) the composite network supports three modes of video real-time detection, video uploading and picture uploading to obtain a body data result. The method has the advantages of being high in precision, low in delay and high in robustness, can be used for product function application such as body measurement of the physically disabled, assistance of rapid measurement of body data of healthy people and intelligent body measurement of clothing merchants, and has good commercialization prospects.

The utility model discloses a wrist joint movement trainer, and belongs to the technical field of medical instruments. The wrist joint training device solves the problem that in the prior art, when a training device is used by a patient who needs to do activity training on wrist joints of two hands, efficiency is low, the wrist joint training device comprises a left wrist joint training mechanism and a right wrist joint training mechanism which are arranged on a bearing mechanism, and the right wrist joint training mechanism comprises a base. A first rotating mechanism is arranged on the base, a second rotating mechanism is arranged on the first rotating mechanism, a palm model is arranged on the second rotating mechanism, a palm fixing mechanism is arranged on the palm model, and the left wrist joint training mechanism and the right wrist shutdown training mechanism are the same in structure. The palm model of the right wrist shutdown training mechanism is a left palm model, and the palm model of the left wrist shutdown training mechanism is a right palm model. Wrist joint movement training can be performed on the two hands of a patient at the same time, and the training efficiency is improved.

A blood pressure monitor main unit according to the present invention comprises a housing, a first measurement electrode, and a second measurement electrode. The housing includes a bottom surface, and a front surface, rear surface, first side surface, and second side surface each extending in a first direction intersecting the bottom surface. The front surface and the rear surface are positioned so as to be spaced apart in a second direction. The first side surface and the second side surface are positioned so as to be spaced apart in a third direction and are also positioned symmetrically with respect to a center line. The first side surface and the second side surface are each curved so as to protrude in the second direction and in a direction away from the center line. The first measurement electrode is provided on the first side surface, and the second measurement electrode is provided on the second side surface. The first measurement electrode and the second measurement electrode are each positioned closer to the front surface than to the rear surface. In a state in which the front surface faces a person to be measured, the first measurement electrode is configured to be capable of coming into contact with the wrist portion of the left hand of the person to be measured, and the second measurement electrode is configured to be capable of coming into contact with the wrist portion of the right hand of the person to be measured.

The invention relates to the technical field of industrial robots, in particular to a stacking robot wrist supporting structure and a rigidity calibration method. The structure comprises a forearm and a wrist, and the connecting end of the forearm and the connecting end of the wrist are each of a U-shaped structure. The small arm comprises a left small arm hinge lug and a right small arm hinge lug; the wrist comprises a left wrist hinge lug and a right wrist hinge lug; the left forearm hinge lug and the right forearm hinge lug are located on the inner side of the left wrist hinge lug and the inner side of the right wrist hinge lug respectively, the left forearm hinge lug and the left wrist hinge lug are hinged through a left short shaft assembly, and the right forearm hinge lug and the right wrist hinge lug are hinged through a right short shaft assembly. The supporting rigidity of the wrist is improved, the supporting rigidity can be adjusted while the axial relative position of the wrist and the forearm meets the bearing pre-pressing requirement, and the axial rigidity of the two hinge lugs of the wrist and the two hinge lugs of the forearm is improved.

The present invention relates to a three-dimensional dynamic gesture recognition method based on an improved dynamic time warping algorithm, belonging to the field of robot vision. The hardware system of the method includes a left camera, a right camera and a host computer that are parallel to each other; the specific recognition operation steps are as follows: (1) static gesture recognition, selecting the static gesture "one" of extending one finger as the recognition stop instruction, and the static gesture "five" of extending five fingers as the recognition start instruction; (2) eliminating redundant movements; (3) obtaining the three-dimensional motion trajectory sequence of the right wrist node and the three-dimensional motion trajectory sequence of the right elbow node; (4) completing the three-dimensional dynamic gesture recognition based on the established three-dimensional dynamic gesture classification template library. The three-dimensional dynamic gesture recognition method of the present invention enables the three-dimensional dynamic gesture recognition system to have a higher recognition accuracy rate for complex three-dimensional dynamic gestures.

The invention discloses a three-dimensional whole-body motion animation generation method and system based on three IMUs, and relates to the field of deep learning, and the method comprises the steps: obtaining original single-frame signals of the three IMUs worn on the head, the left wrist and the right wrist of a user, and determining an IMU signal sequence; inputting the IMU signal sequence and the initial global linear velocity into a pre-trained global velocity estimation module to obtain a global velocity sequence; inputting the IMU signal sequence, the initial attitude and the global speed sequence into a pre-trained time sequence attitude estimation module to obtain an original attitude sequence; inputting the original attitude sequence into a pre-trained vector quantization variational auto-encoder to determine the whole body attitude of the user again to obtain a reconstructed attitude sequence; fusing the original attitude sequence and the reconstructed attitude sequence to obtain a final attitude sequence; and generating a three-dimensional human body whole-body motion animation of the user based on the global displacement and the final posture sequence. According to the invention, the generation of the three-dimensional whole-body motion animation can be realized only by using three IMUs.

The utility model discloses a through folding storage wrist belt's mobile phone support relates to the protection shell design field, including wrist belt support and soft wrist belt, the upside of wrist belt support is shaped with wrist belt storage groove, and the middle part of wrist belt storage groove is shaped with the locating plate, and the locating plate divides wrist belt storage groove into two left and right symmetries, and the left and right wrist belt storage groove all integrative formation is provided with the stacking groove, and the both ends of soft wrist belt are one -to -one correspondence folding and place in the stacking groove, and the middle part of soft wrist belt is magnetically attracted and is pasted on the locating plate, the soft wrist belt of the utility model is when storage, and soft wrist belt can all be stored in the stacking groove through the mode of folding, and fixed through the mode of magnetic attraction, and it is convenient to carry, when unfolding soft wrist belt, can through the mode of manually pulling out soft wrist belt, let soft wrist belt separate the magnetic attraction part of locating plate, and continue to unfold can let the folding state of soft wrist belt unfold for straight -en state, realize the effect of opening soft wrist belt, be applicable to various mobile phones and tablet computer equipment.

The embodiment of the application discloses a pulse wave collecting device and method, the pulse wave collecting device comprises: a wristband main body, which is used for being worn on the left wrist or the right wrist of a human body; a first sensor group, which is arranged on the wristband main body and comprises a plurality of first pulse wave sensors arranged in sequence along the width direction of the wristband main body, the width direction of the wristband main body corresponds to the blood flow direction of the blood vessel of the human body; and a second sensor group, which is arranged on the wristband main body, the second sensor group and the first sensor are distributed along the circumferential direction of the wristband main body, the second sensor group comprises a plurality of second pulse wave sensors arranged in sequence along the width direction of the wristband main body, and the plurality of second pulse wave sensors correspond to the plurality of first pulse wave sensors one by one; wherein when the wristband main body is worn on the left wrist or the right wrist, one of the first sensor group and the second sensor group can collect the pulse wave of the corresponding wrist.

The utility model discloses a high-precision body fat scale which comprises a scale body, a weighing assembly, a first wrist strap, a second wrist strap, a first electrode assembly, a second electrode assembly, a third electrode assembly and a control panel. The weighing assembly is arranged on the scale body and is used for weighing a weight parameter of a user; the first wrist strap is worn on a left wrist of a user and is connected with the scale body; the second wrist strap is worn on the right wrist of the user and is connected with the scale body; the first electrode assembly is arranged on the scale body and used for measuring lower limb impedance of a user; the second electrode assembly is arranged on the first wrist strap and used for measuring the impedance of the left upper limb of the user; the third electrode assembly is arranged on the second wrist strap and used for measuring the right upper limb impedance of the user; the control panel is arranged on the scale body, is electrically connected with the weighing assembly, the first electrode assembly, the second electrode assembly and the third electrode assembly, and is used for calculating and outputting body fat parameters of a user; through the structure, the problems of compatibility of different crowds and testing difference deviation caused by holding posture change in multiple times of measurement of users are solved, and very good practicability is achieved.

The invention belongs to the technical field of image processing, and particularly relates to a real-time end-to-end human body behavior detection system based on deep spatial-temporal feature fusion and a detection method of the real-time end-to-end human body behavior detection system. The feature extraction module is connected with the target detection head and the human body posture key point detection head, the target detection head is connected with the ROI extraction module, the ROI extraction module is connected with the behavior recognition module, the human body posture key point detection head is connected with the ROI guided key point extraction module, and the behavior recognition module is connected with the behavior recognition module. The ROI-guided key point extraction module is connected with the behavior recognition module, the key point extraction module is further connected with the time sequence buffer, and the human body posture key point detection head is used for detecting key point positions of the head, the left shoulder, the right shoulder, the left elbow, the right elbow, the left wrist and the right wrist. The problem of invigilation of multiple examinees can be solved more efficiently and reliably, that is, the examination process of multiple examinees can be analyzed in real time at the same time.

The invention discloses a vision-based rope skipping rope-free empty jump detection method, which comprises the following steps of: arranging a camera above a rope skipping test area to acquire a rope skipping video, and acquiring 19 key point coordinates of a tester by a human body key point identification model based on YOLO framework training; calculating a wrist position score through the shoulder-wrist vector, and judging whether the wrist position is normal or not; constructing a human body center line by a shoulder and hip connecting line, and calculating left and right wrist symmetry scores; an arm posture plane is constructed through shoulder-elbow-wrist three points, and an upper limb posture score is calculated; the null jump score of each rope skipping action is calculated by integrating the wrist position, the symmetry, the upper limb postures and the time sequence shaking characteristics; and counting the number of suspected null jumps and the proportion, and when the number and the proportion exceed a preset threshold value, determining that cordless null jumps exist and outputting an alarm. The method can accurately identify the rope-free empty jump behavior in the rope skipping test, improves the fairness and accuracy of the sports test, and is suitable for the scenes of school sports examination, physical fitness test and the like.

Device consisting of wrist cuff (7), bandage (3) and thumb cuff (2) connected to form a base body, and a tension band (4), characterized in that the tension band (4) is placed ulno-palmarly around the thumb (1) just below the flexion fold (5) of the thumb in a left turn on the right hand and in a right turn on the left hand, running obliquely from the radial side to the proximal inner side of the hand in the area of ​​the flexion fold of the wrist in extension to the third ray (6), and can be released and tensioned.

A wrist sphygmomanometer (100) is provided with a main body (10), a band-shaped member (20), a sensing cuff (22), and a pressing cuff (23). The band-shaped member (20) has a first end portion and a second end portion located in the width direction. In a first state in which the band-shaped member (20) is wound around the left wrist such that the first end is positioned on the finger side of the left hand, the second end is positioned on the elbow side of the left hand, and the main body section (10) is disposed on the side surface (60c) on the thumb side of the left hand of the left arm (60), the sensing cuff (22) is disposed so as to be capable of pressing the radial artery (63) of the left wrist from the palm-side surface (60d) of the left arm (60). In a second state in which the second end portion is located on the finger side of the right hand, the first end portion is located on the elbow side of the right hand, and the main body portion (10) is disposed on the side surface (70c) of the right arm (70) on the thumb side of the right hand, the sensing cuff (22) is disposed so as to be able to compress the radial artery (73) of the right wrist from the surface (70d) of the palm side of the right arm (70).

The wrist-type body component measuring apparatus includes: a band configured to be worn on a wrist of a user; a first input electrode and a first output electrode disposed on an inside surface of the band and configured to be in contact with the wrist of the user; a second input electrode and a second output electrode disposed on an outside surface of the band; a measuring unit configured to apply a current to the first and second input electrodes and detect a voltage from the first and second output electrodes to measure a body impedance of the user; and an electrode converter configured to convert a disposition of the first and second input electrodes and the first and second output electrodes based on a determination of whether the band is worn on a left wrist or a right wrist of the user.

The utility model discloses a customized 3D printing wrist joint support for bone joint repair, and relates to the technical field of joint supports, the 3D printing wrist joint support comprises a soft plate and a movable plate, the two sides of the soft plate are respectively and fixedly provided with a left wrist support and a right wrist support, and the right wrist support is internally provided with a first fixing groove and a second fixing groove; the customized 3D printing wrist joint support for bone joint repair has the advantages that a binding band is pulled out, a spiral spring is tightened, a ratchet wheel rotates, a third sliding block is inserted into an inserting groove, a first fixing groove is formed in the right wrist support, and a winding groove is formed in the right wrist support and located between the first fixing groove and the second fixing groove. At the moment, one end of a ratchet wheel is clamped on one side of a second sliding block, a limiting plate is pressed down, the limiting plate is extruded towards the interior of a first fixing groove, the second sliding block is pressed downwards through an auxiliary plate, a spiral spring is reset, a bandage is tightened and limited, the length of the bandage can be adjusted according to the thickness of arms of different patients, and the comfort degree of the patients is improved.

1. The name of the design product: wrist protector skeleton (upper). 2. The use of the design product: for fixing and protecting the wrist. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view. 5. Other circumstances that need to be explained: this product is a left wrist protector skeleton, which is used with a right wrist protector skeleton; since the right wrist protector skeleton is symmetrical with the left wrist protector skeleton, all views of the right wrist protector skeleton are omitted.

The present invention is a transfer arm that moves a wafer inside a piece of equipment designed to manufacture electronic circuits. The transfer arm has a hand, used to securely hold the wafer using Bernoulli's Principle. The transfer arm has a left wrist and a right wrist connected to the hand, wherein the hand and the left wrist and the right wrist comprise sealed gears and sealed bearings. A left upper arm is connected by being threaded to the left wrist and a left elbow and a right upper arm is connected by being threaded to the right wrist and a right elbow. A left lower arm is connected by being threaded to the left elbow and the left shoulder and a right lower arm is connected by being threaded to the right elbow and the right shoulder.

The invention discloses a human body side-lying posture recognition method and device and a storage medium. The method comprises the steps that a depth camera is fixed to an opposite side-lying position human body for shooting; comprises: adjusting a shooting state of a depth camera; adjusting the position height of the depth camera; simultaneously shooting to obtain a standard color image and a registration depth image; the two-dimensional coordinates of the two-dimensional human body key points and the new key points are obtained; comprising the following steps: identifying a standard color image through an attitude estimation model to obtain two-dimensional body key point coordinates; comparing the abscissa values of the key points of the right wrist and the right elbow to determine the orientation of the side-lying human body; constructing new key points according to the identified key points, and calculating two-dimensional coordinates of the new key points; the three-dimensional coordinates of the key points are calculated to obtain a human skeleton; the three-dimensional coordinates of the key point and the new key point are obtained through the depth value of the key point measured in the depth map and the known two-dimensional coordinates. According to the invention, the influence of shielding on depth identification is avoided.

The application discloses a whole body posture estimation method based on a sparse inertial sensor. The application comprises the following steps: 1: synthesizing acceleration data, direction data and angular velocity data through a finite difference method and a forward kinematics algorithm; 2: performing alignment processing on original acceleration data and original direction data collected by three inertial sensors worn on the user's head joint, left wrist joint and right wrist joint through a rotation transformation matrix; 3: extracting deep features of inertial motion data samples by combining a Transformer Encoder and a bidirectional long short-term memory network encoder, designing a decoder based on a multilayer perceptron to calculate the positions and relative rotations of joints, and combining a human body kinematics model to estimate the relative rotations of joints in different parts in multiple stages to realize whole body posture estimation. The application can effectively overcome the defects of using sparse inertial input for whole body motion reconstruction in the existing posture estimation method, and effectively improve the robustness and prediction accuracy of the system.

The utility model provides a wrist rope hot cutting device which comprises a machine table, a hot cutting lower die and a hot cutting assembly located on the rear side of the hot cutting lower die are arranged on the machine table, the output end of the hot cutting assembly is located at the upper end of the hot cutting lower die, and the hot cutting lower die is composed of a wrist rope positioning part and a cutting positioning part. A wrist rope mounting groove in the left-right direction is formed in the middle of the upper end of the wrist rope positioning part, a hot cutter groove in the front-back direction is formed in the upper end of the cutting positioning part, and two single-rope adaptive arc grooves in the left-right direction are formed in the positions, corresponding to the wrist rope mounting grooves, of the hot cutter groove. And a hot cutting blade at the output end of the hot cutting assembly penetrates through the hot cutting knife groove to finish hot cutting of the wrist rope in the single-rope adaptive arc groove. The utility model relates to the technical field of wrist rope hot cutting.