60 results about "Joint point" patented technology

The invention relates to a human body posture capture-based disabled assisting robot planning method and system, and the method comprises the following steps: S1, a patient is fixed to a system main body through a flexible fixing device, so that the posture capture precision is ensured, and accidental sliding is prevented; s2, a high-definition RGB camera and a depth sensor are used, real-time posture joint point data of the patient are obtained based on a human body posture estimation algorithm, and the real-time posture joint point data comprise the head position, the limb position and the trunk position; s3, resolving the captured data in real time, and referring to a posture database to generate a most suitable initial rehabilitation posture; s4, collecting visual, voice and physiological signals by using a camera, a microphone and other sensors, and performing feature extraction and fusion by using a convolutional neural network to improve the recognition accuracy; s5, judging the satisfaction degree of the patient to the current posture through an emotion recognition technology in combination with voice emotion analysis, and adjusting the system according to the satisfaction degree of the patient; the motion parameters of rehabilitation training of the patient are obtained quickly, the effectiveness and rehabilitation efficiency of rehabilitation training are improved, and the participation degree and enthusiasm of the patient are increased.

The invention provides a human body key point detection mechanical palm synchronous control method and system based on vision, and belongs to the technical field of robot control and human-computer interaction. The gesture recognition technology is used for conducting gesture estimation on the target arm, and key point data are captured and extracted. The key point data comprises joint position information of the arm and the hand, necessary input is provided for subsequent control, the data are processed, and the joint position information is converted into steering engine corner information capable of driving all joints of the mechanical arm. According to the invention, the Kalman filtering algorithm is adopted to filter the joint angle data, and then the filtered steering engine rotation angle information is transmitted to each joint point of the mechanical arm through the serial port communication technology, so that the precise control of the mechanical arm is realized, the stability and real-time performance of data transmission are ensured, and the reliability of the mechanical arm is improved. And the mechanical arm can quickly respond to the gesture change of a person.

The invention discloses a mechanical arm control method and device based on human body posture recognition and a storage medium, and relates to the technical field of robots. The mechanical arm control method comprises the steps that human body skeleton joint point coordinate information, collected by a sensor arranged on a robot, of an operator is obtained; on the basis of a preset action recognition model, action type recognition is conducted on the human skeleton joint point coordinate information, and the action type of the operator is obtained; determining the intention of the operator according to the scene information, the action type and the movement track of the operator; and determining a target task associated with the intention of the operator, and controlling the robot to execute the target task. In the invention, the robot can dynamically adjust the task execution strategy according to the real-time action and intention of the operator, so that the task execution efficiency and flexibility are improved.

The utility model relates to a parallel type multi-connecting-rod bionic frog robot which comprises a body unit, a rear leg unit and a driving unit, the rear leg unit is provided with three joint points, the rear leg unit is rotatably connected with the body unit through a first joint point and a second joint point at the same time, and the third joint point is used for making contact with the ground. The driving unit is arranged on the body unit and is in transmission connection with the rear leg unit to drive the rear leg unit to rotate around the first joint point and the second joint point at the same time, so that the third joint point is driven to move to enable the robot to jump up; in the rotating process of the rear leg unit, the first joint point, the second joint point and the third joint point are kept on the same straight line. Compared with the prior art, when the parallel type multi-connecting-rod bionic frog robot jumps, the first joint point, the second joint point and the third joint point of the rear leg unit are always kept on the same straight line, the stability of the pedaling angle is kept, the rotating tendency of the body unit is reduced during jumping, and the overturning possibility is remarkably reduced.

The invention relates to a user-defined gesture method and device based on a human hand three-dimensional joint point sequence. The invention mainly solves the problem of how to identify the custom gesture, and the main technical difficulty of the problem lies in that in order to ensure the fluency and convenience of interaction, the data of the custom gesture is less, and both online training and identification need to achieve real-time effect. According to the method, the representative static hand shape template is automatically generated through the unsupervised clustering model pre-trained on the large-scale label-free static hand shape data set, so that the problem of few samples in the training process is solved. According to the sequence template construction method provided by the invention, a sequence template and a wrist track template of a static hand shape are automatically generated, and an online real-time training effect is achieved; and an online real-time identification effect is achieved by using a regular matching algorithm and a P-based track matching algorithm. Practical use verifies that the method has the advantages of high automation degree, high precision and real-time performance, and can meet professional or popular application requirements.

The embodiment of the invention provides a method and device for judging upper limb compensatory movement, computer equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the following steps: collecting image data of a target object in a movement process; converting the image data into joint point space coordinate data; generating an upper limb skeleton coordinate sequence according to the node space coordinate data; calculating to obtain a shoulder inclination angle theta and the relative displacement of the horizontal axes of the shoulders, judging whether shoulder lifting type compensation movement exists or not, calculating to obtain a spine inclination angle alpha, and judging whether trunk bending type compensation movement exists or not; if the shoulder raising type compensation exercise and / or the trunk bending type compensation exercise exist, the upper limb compensation exercise exists, and prompt information for prompting the target object to change the exercise mode is output. According to the scheme, video shooting is carried out on the training process of the target object, whether the target object has upper limb compensatory motion or not is judged, the target object is reminded, and therefore the upper limb compensatory motion is effectively restrained.

The present invention relates to the technical field of tunnel deformation monitoring. Specifically, it is a tunnel deformation support control safety monitoring and early warning system, including: a data acquisition module, a deformation classification module, a support identification module, a cross-section generation module, and a safety matching module; by identifying the stress field and support joint points of the target tunnel according to the opposite direction and relative deviation of the target tunnel, obtaining the displacement and support deformation amounts of each support joint point under the opposite direction and relative deviation; and identifying the deformation types of each support joint point, dividing the relative deformation regions of each support joint point in the internal downward direction; predicting the change trend of the displacement and support deformation amounts of the current support structure under the relative deformation region; at the same time, generating multiple force-bearing cross-sections according to the change trend, and setting a vector analysis coefficient according to the displacement vector and deformation vector on the force-bearing cross-section; performing a safety matching calculation on the force-disturbed position according to the vector analysis coefficient; improving the safety of tunnel construction and operation.

The invention provides a synchronous driving method of a VR virtual character and VR equipment, which are used for optimizing network delay and improving a driving effect. Comprising the steps that based on received multiple poses, sent by second VR equipment, of all target articulation points of a second user within a specified duration, the poses of all the target articulation points at other moments within the specified duration are predicted, multiple predicted poses of all the target articulation points are obtained, and the number of the target articulation points is smaller than the preset number of all the articulation points; for any moment, determining a to-be-predicted joint point of a second user at any moment by utilizing the distance between the first virtual character and the second virtual character obtained according to the pose of the specified joint point of the first user at the moment and the pose of the specified joint point of the second user at the moment; and predicting the pose of the to-be-predicted joint point by using each pose of the target joint point to obtain the pose of the to-be-predicted joint point, and driving the second virtual character by using the pose of each joint point.

The present application provides a posture correction training method and device for human-centered intelligent manufacturing. The method provided by the present application includes: obtaining target joint point coordinates, inputting the target joint point coordinates into a human digital model to obtain the correspondence between the target joint point coordinates and human joints; the human digital model is used to match the target joint point coordinates and the real posture data of the human body; calculating according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and joint torsion angle of the target joint point coordinates; determining a target human risk score based on the correspondence, the inter-joint angle and the joint torsion angle; the target human risk score includes an expert evaluation score; when the target human risk score exceeds a preset risk threshold, a posture correction notification is sent using a composite message; wherein, the composite message sends reminders simultaneously based on multiple senses. The posture correction training method and device for human-centered intelligent manufacturing provided by the present application are used to accurately and reliably correct the posture of the human body.

The invention relates to a hip joint diagnosis index automatic quantitative calculation method based on three-dimensional equation expression. The method comprises the following steps: step 1, processing a CT image through a boundary-based contour line extraction method to obtain a three-dimensional hip joint point cloud; 2, establishing a three-dimensional equation expression of the hip joint, and calculating diagnosis indexes, namely an acetabulum index and a femoral head protrusion index; step 3, extracting a human body action sequence from the motion video by using a rapid monocular three-dimensional body action capture method; and 4, calculating five key points and the like through the three-dimensional coordinates of the pelvic bone center, the femoral head center, the femoral neck center and the lesser trochanter vertex. According to the method, an integrated auxiliary diagnosis motion model is constructed, the auxiliary diagnosis motion model avoids errors caused by distortion of muscles and skin in motion based on rigid characteristics of hip joint bones, two FAI auxiliary three-dimensional diagnosis indexes are provided based on morphological characteristics, errors caused by view angle changes in a CT image are avoided, and the accuracy of diagnosis is improved. And a reliable hip joint impact diagnosis basis is provided.

The present invention discloses a method for reconstructing hand posture based on multi-stage joint point enhancement. The method of the present invention proposes a multi-stage joint enhancement network, the first stage of which consists of a network that only trains the fingertip joint positions and the base of palm joint positions; the second stage combines the input image features obtained from the feature extractor and the 12 joint points output by the first stage, and performs joint reasoning through the Transformer module and the features extracted from the image to enhance the accuracy of the prediction of the remaining 30 joint points. The present invention combines visual modalities and geometric modalities, and improves the model's prediction ability for the remaining 30 joint points through multimodal fusion, thereby enhancing the accuracy of joint point prediction.

The utility model discloses a uterus lifting fixator which comprises a fixing frame, and the fixing frame comprises a left side support, a right side support and a cross beam piece connected with the left side support and the right side support. The left support comprises two left supporting rods, the right support comprises a right supporting rod, the beam piece comprises two beam rods arranged in parallel, and the two ends of each beam rod are correspondingly connected with the top ends of the left supporting rods and the top ends of the right supporting rods. The middle portions of the two left supporting rods are connected through a left spring, the middle portions of the two right supporting rods are connected through a right spring, the rotating connecting point of the right support is located at the upper position of the middle portion of the right supporting rod, and the left spring and the right spring are in a pre-pressing state in a normal state so that the two cross beam rods can get close to each other. During operation, the fixing frame can be erected right above an operation part, the uterus body is pulled and lifted upwards, the purpose of continuously and stably lifting and fixing the uterus body is achieved, the part to be sutured at the lower end of the uterus can be conveniently exposed, and the success rate of the uterus suturing operation can be improved.

The invention discloses a static sign language recognition method based on skeleton angle features, and belongs to the field of sign language recognition, and the method comprises the steps: obtaining human hand skeleton joint point coordinate data in a historical data set based on a Medipe method; performing data preprocessing on the human hand skeleton joint point coordinate data to obtain a preprocessed data set; constructing a long-short-term memory network model, and training the long-short-term memory network model based on the preprocessed data set to obtain a sign language recognition model; and recognizing the static sign language based on the sign language recognition model. According to the scheme provided by the invention, hand positioning, cutting and hand image adjustment do not need to be carried out, the requirement for a training data set is not higher than that of a traditional scheme, and only a researcher needs to provide a clear hand image.

The utility model discloses a ligament lifting, supporting and fixing device, which relates to the field of face lifting and comprises a ligament lifting line, a plurality of lifting discs arranged in the middle of the ligament lifting line, a fixing block arranged at the bottom of each lifting disc, a supporting block arranged at the top of each lifting disc and matched with the fixing block, and a placing hole formed in the middle of each fixing block. Extension grooves are formed in the two ends of the containing hole, a plurality of supporting holes are formed in the outer side of the circumference of the containing hole, assembling blocks are arranged on the two sides of the fixing block, an attaching plate is arranged at the bottom of the fixing block, the containing hole is connected with the lifting disc, and the ligament lifting line is matched with the extension grooves. According to the utility model, the ligament lifting line is arranged, the lifting disc is matched with the fixing block, so that the fixing block is conveniently mounted on the facial joint point, and the ligament lifting line is contracted after mounting, so that the lifting disc drives the fixing block to move, and the stretching exercise of the facial ligament is realized.

The invention discloses a video-based omni-directional remote rehabilitation training system, a video-based omni-directional remote rehabilitation training method and a medium, which are characterized in that a digital standardized training video library classified according to four stages of PT physical therapy is established, and more than 700 digital standardized training videos such as joint activity, balance training, gait correction and the like are covered; it is ensured that the training content is scientific and covers the whole period and all directions of rehabilitation training; rehabilitators generate personalized training schemes in combination with rehabilitation scene types (hospitalization / home / community / old-age care institutions) and clinical data and in combination with remote video evaluation of the rehabilitators, and training requirements in different environments are met. By capturing actions of limb joint angles, joint point motion trails and muscle force changes, a training action deviation rate is calculated and is fed back and output to a rehabilitation teacher in a grading manner, so that the training standardability is remarkably improved; rehabilitators can manage multiple patients online at the same time, remotely check training percentage data, adjust schemes and generate rehabilitation notes, and efficient, accurate and personalized rehabilitation guidance services are provided for the patients.

A squatted movement standardization evaluation method and device based on multiple regression, comprising the following steps: marking joint points matched with the squatted movement data of a tested person and establishing the coordinates of standardized joint points; setting action evaluation parameter thresholds and evaluating a single squatted movement in the squatted movement data based on the spatial coordinates to generate a determination parameter vector including multiple determination parameters for the single squatted movement; and making a determination on the determination parameter vector to determine whether the corresponding squatted movement meets the standard. The present invention can accurately analyze the movement details of each squat, and obtain a standard counting result according to the measurement standard of the standard squatted movement; moreover, action evaluation parameter thresholds can be set according to action requirements, and the thresholds can be modified according to scene requirements and the conditions of the tested person, with high detection accuracy, strong anti-interference ability, and being more accurate and scientific.

The application provides a clamp for a clasp spring type pin shaft, and relates to the technical field of circuit breaker assembly tools.The clamp for the clasp spring type pin shaft comprises a first jaw body, a second jaw body and a connecting rod assembly, the first jaw body and the second jaw body are cross arranged and hinged at a joint point, the first jaw body and the second jaw body are both divided into a front section and a rear section by the joint point as a boundary point, the front section of the first jaw body is provided with a positioning structure, the connecting rod assembly has a fixed end and a moving end, the fixed end is rotationally connected with the front section of the second jaw body, the moving end is slidingly connected with the front end of the first jaw body, and the fixed end is provided with a fixing structure for fixing the clasp spring, and when the front end of the first jaw body and the front section of the second jaw body are rotated towards each other, the moving end of the connecting rod assembly slides towards the positioning structure.In the case that the rear sections of the first jaw body and the second jaw body are pinched to the limit state, the clasp spring is pushed into a clasp spring limiting groove on the shaft pin to complete the connection with the shaft pin, the assembly is simple, the working strength and the working difficulty are small, and it is very safe.

The utility model relates to cable joint protection and positioning technical field, specifically is a kind of cable joint positioning fixture with guide slot.The device adopts concrete shell, both sides are provided with sealing cover and sealing rubber ring are provided with positioner simultaneously, cable passes through sealing rubber ring and passes through positioner, prevent displacement caused by vibration or external force.Sealing cover adopts detachable design, it is convenient to install and maintain.The utility model has reasonable structure, easy installation, convenient maintenance, effectively improves the protection performance and positioning stability of cable joint point, and is applicable to electric power, communication and industrial automation etc.

The invention discloses a monitoring system and method for dance movement correction, and relates to the technical field of data monitoring. Comprising the steps that actions of dancers at different standing positions are collected through a wearable device, and each action comprises a plurality of joint points and the three-dimensional space position of each joint point; different standing dancers are divided into different classes according to the three-dimensional space positions, and dancers of the same class execute the same dance action; curve fitting is carried out based on the joint point three-dimensional space position corresponding to the same joint of the dancer of the same kind, the space position of each joint point is corrected according to a curve fitting result, and a standard dancing action is obtained; actual dance actions are collected through the wearable device, and action offset is obtained by comparing the standard dance actions with the actual actions; and outputting an action correction result at the time T according to the action offset.

The invention relates to a punching tool for punching stacked workpieces to form a joint point, characterized in that the punching tool has a punch system with a punch, and a die system with a cavity, the punch having at least two punch parts, the punch portions can be moved into or out of the cavity in a first direction, and the punch portions can be moved in a second direction transverse to the first direction between an open state further away from each other and a closed state closer to each other, in which the punch portions can be moved into the cavity, and in which the punch portions can be moved out of the cavity in a second direction transverse to the first direction. The punch portions are movable in the cavity from a closed state away from each other into an open state, in which the punch portions, on a section thereof capable of entering the cavity, have a protrusion protruding over an outer circumferential surface of the section in a second direction. The invention also relates to a method for producing a joint point of a composite part by means of a stamping tool and to a composite part.

This will result in a pallet with improved beam strength compared to conventional models. [Solution] The pallet (1) comprises a girder section (20) in which at least one of the plurality of girder sections (20) includes a girder wall section (200) that forms the outer circumference of the girder section (20), and a first rib (30) and a second rib (31) that extend inward from the girder wall section (200) that forms the corner of the girder section (20). The first rib (30) and the second rib (31) have an interior angle of less than 90 degrees formed at a joint point P1 where one end of each imaginary line extending the first rib (30) and the second rib (31) in a straight line joins, and the other end of each of the imaginary lines (V1, V2) is provided at a position that intersects with the fork insertion direction of the fork inserted into the fork insertion section 11.

The invention relates to an orbital welding process in which two joining partners (152, 154) that are tubular in at least one joining area (150) are arranged relative to each other, in particular in a lap joint, and in which a chain (211) of joining points (210) extending circumferentially to the joining partners (152, 154) is generated in the joining area (150), which connects the joining partners (152, 154) by a material bond, wherein an arc burns between a welding electrode (126) and at least one of the joining partners (152, 154) to generate the chain (211) of joining points (210), wherein the arc is operated with a current characteristic curve that has a sequence of welding cycles with at least one high-current phase and one low-current phase, wherein the welding energies (Esz) of the individual welding cycles are in the range of 30–240 J, preferably 35 - 220 J, particularly 40 - 195 J.The invention further relates to an orbital welding device (100, 101) and a system (700) with such an orbital welding device (100, 101).

The invention discloses a sliding turnover massage mechanism of a chair, which is characterized in that the sliding turnover massage mechanism comprises a seat and a backrest, the seat is provided with a cavity at the waist of a human body, and the backrest is arranged in the cavity; one side of the backrest is provided with a massage face used for massaging the waist of a human body, the other side of the backrest is provided with a leaning face used for leaning for long-term use, positioning pins at the two ends of the backrest are in pin joint in the cavity, and the backrest rotates on the seat around pin joint points of the positioning pins. The chair has the beneficial effects that the backrest with the massage surface and the leaning surface is arranged on the seat and can rotate in the cavity around the positioning pin, so that the backrest can be adjusted according to the requirements of a user, the problem that the chair with the massage function is inconvenient to sit frequently is solved, and when the massage surface and the leaning surface are switched, the massage surface and the leaning surface are switched, so that the user can conveniently sit on the chair. Adjustment can be completed only by pulling the backrest to rotate and turn over in the cavity, and use is convenient and fast.

The invention discloses a novel truss structure with node rings. The novel truss structure comprises an upper truss structure and a double-row column supporting structure. The upper truss structure comprises an upper chord member, a lower chord member, inclined legs, transverse pull rods, web members and node rings; the inclined legs are located between the upper chords and the lower chords, one ends of the inclined legs are connected to the joints of the lower chords and the stand columns, and the other ends of the inclined legs are connected to one fourth or three quarters of the upper chords on the same side; the transverse pull rod is located between the upper chord and the lower chord, the upper end is connected to the joint of the upper chord and the inclined leg, and the lower end is connected to the middle top of the lower chord; the three node rings are respectively arranged at the joint points of the upper chord, the inclined legs, the transverse pull rods and the web members on the left side and the right side of the upper truss structure in a surrounding manner and the joint points of the transverse pull rods, the web members and the lower chord members in the middle of the upper truss structure in a surrounding manner. A traditional steel structure factory building beam is replaced by the novel truss with the node ring, and the problems that a traditional beam is insufficient in bearing capacity and large in deformation can be effectively solved.

The present invention discloses a method for constructing a three-dimensional hand posture model and a three-dimensional hand posture estimation method, which belongs to the field of three-dimensional posture estimation technology. The method comprises the following steps: cropping an RGB image carrying interactive hand information, setting evenly distributed three-dimensional anchor points on the cropped image, and obtaining three-dimensional coordinate information of each three-dimensional anchor point; inputting the image after setting the three-dimensional anchor points into a feature enhancement model to obtain three-dimensional offsets and weights of each three-dimensional anchor point to all corresponding estimated joint points; fusing the three-dimensional offsets and weights with the three-dimensional coordinate information to obtain the three-dimensional coordinates of the hand joint points, and then determining a loss function; and using the loss function to train a three-dimensional hand posture estimation network to obtain a target three-dimensional hand posture model. The present invention constructs interactivity between local three-dimensional anchor points, giving them global spatial and contextual perception, thereby better capturing the joint information of the joint points to be estimated and reducing the self-occlusion and mutual occlusion problems of the interactive hands.

The present invention provides a multi-scale motion rehabilitation assessment method, system, computer device, and storage medium. The method includes the following steps: collecting limb rehabilitation exercise videos during the rehabilitation training of the object to be evaluated; for each frame image in the limb rehabilitation exercise videos, extracting feature information of the limb parts, including equivalent shape information, vector information, and joint point information; performing feature encoding on each limb part to generate weights corresponding to each limb part and action sequence encoding; based on the feature encoding results, constructing an assessment model, which is a sequential model for establishing the internal connection of actions, and outputting the assessment result of the rehabilitation training of the object to be evaluated. The present invention can comprehensively evaluate the training actions by integrating the body part information, limb vector features, and joint point features in the actions, so as to more accurately evaluate the training actions.

A method for recognizing a hand gesture is disclosed. Image data is acquired, wherein the image data represents a two-dimensional image of a user's hand (1). Feature points (2, 3, 4, 5, 6) are determined in the two-dimensional image of the hand (1), wherein the feature points (2, 3, 4, 5, 6) comprise a wrist point (2) and, for each finger of the hand (1), finger joint points (3, 4, 5) and a fingertip point (6), wherein the finger joint points (3, 4, 5) for each finger comprise an MCP joint point (3), a PIP joint point (4), and a DIP joint point (5). A hand position is determined based on the relative positions of the feature points (2, 3, 4, 5, 6) to each other in the two-dimensional image of the hand (1).

The present invention belongs to the technical field of human motion recognition. A motion recognition method based on human skeletal joint points is as follows: When a human body is in motion, an image acquisition device is used to collect images of the actions of human skeletal joint points, and action images of skeletal joint points can be obtained; The action images of skeletal joint points are frame-divided, and the data in each frame image is extracted to find the positions of human skeletal joint points in each frame image, analyze the changes in the positions of human skeletal joint points in consecutive images in different frames, and analyze the actual movement distances of human skeletal joint points according to the changes in the positions of human skeletal joint points; The present invention collects and stores action feature data in various motion states, and then uses these data to construct a database, and further can accurately judge and analyze the motion states of different users according to their action feature data.

The finger tendon rehabilitation device comprises a palm supporting plate and a finger supporting plate, the palm supporting plate and the finger supporting plate are rotationally connected through a first damping rotating shaft, the finger supporting plate comprises a set of connecting plates, a plurality of sets of first bent plates and a plurality of sets of second bent plates, one end of each connecting plate is connected with the first damping rotating shaft, and the other end of each connecting plate is connected with the second damping rotating shaft. The other end of the connecting plate is rotationally connected with one group of first bending plates through a second damping rotating shaft, the first bending plates are rotationally connected with the second bending plates through second damping rotating shafts, a first fixing belt is arranged on the palm supporting plate, and a second fixing belt is arranged on the finger supporting plate; the first damping rotating shafts between the palm supporting plate and the finger supporting plate form joints, the multi-joint structure of the finger supporting plate is composed of multiple sets of second damping rotating shafts, multiple sets of joint points correspond to the joint positions of the hand, and rehabilitation training of finger tendons is achieved in the process that the hand overcomes damping force to be bent.

The invention relates to a method for detecting a hand gesture. Image data are captured, the image data representing a two-dimensional image of a hand (1) of a user. Feature points (2, 3, 4, 5, 6) are determined in the two-dimensional image of the hand (1), the feature points (2, 3, 4, 5, 6) comprising a wrist point (2) and finger joint points (3, 4, 5) and a fingertip point (6) for the fingers of the hand (1), the finger joint points (3, 4, 5) each comprising an MCP joint point (3), a PIP joint point (4) and a DIP joint point (5) for a finger. A hand posture is determined on the basis of relative positional relationships of the feature points (2, 3, 4, 5, 6) to one another in the two-dimensional image of the hand (1).