84 results about "Human anatomy" patented technology

The invention provides a human behavior recognition method based on fusion of multi-modal data acquired by an unmanned aerial vehicle, and the method comprises the following steps: splicing a joint Tokens with a space CLS Tokens of the same frame after feature extraction is completed by using a space Transform, and obtaining a feature fusion module; performing structure coding on the joint point sequence based on a human anatomy structure, and constructing a human topological structure association module; the method comprises the following steps of: constructing a time sequence cross Transform module; the space Transform, the feature fusion module, the human body topological structure association module and the time sequence crossing Transform module are stacked to obtain a trunk feature extraction network; a 10-layer trunk feature extraction network is adopted to perform deep feature extraction on input early-stage fusion data and feature fusion data, and classification is performed by using a classification head; the features output by the backbone network are mapped to the dimensions with the same number as the behavior categories, a prediction score is output for each category, and a human body behavior recognition result is obtained according to the prediction scores. According to the method, the human body behavior in the multi-modal data acquired by the unmanned aerial vehicle can be effectively identified.

The invention belongs to the technical field of gait recognition, and particularly relates to a human gait recognition method and system in a complex scene. And sequentially performing illumination correction, human body posture angle alignment and shielding processing on the extracted human body gait data, and performing human body gait recognition based on the gait data obtained after illumination correction, human body posture angle alignment and shielding processing. According to the occlusion processing, a comprehensive and reliable occlusion area judgment standard is set based on the connection relation between skeleton nodes, the human anatomy reference distance, kinematics constraint and the time continuity requirement, and then a missing human body area is reconstructed through optical flow compensation or bilinear interpolation based on information of visible pixels around the occlusion area. The accuracy of gait recognition in a complex scene is improved, the problem of adaptability of the complex scene is solved in a breakthrough mode, high-precision gait identity recognition is achieved, and the security and protection monitoring requirement of a real scene is met.

Systems and methods for impingement analysis are disclosed herein. A method includes receiving a three-dimensional model of a human anatomy comprising a spinopelvic joint; receiving input related to a spinopelvic condition of a patient; determining at least one of a sacral slope or a lumbar lordosis of the patient based on the input; classifying the spinopelvic condition of the patient based on at least one of the sacral slope or the lumbar lordosis in a plurality of positions; modifying the three-dimensional model based on the spinopelvic condition and a placement of an implant; performing at least one simulation of one or more activities with the modified three-dimensional model; and displaying an impingement analysis on a display device based on the at least one simulation.

The invention relates to a multi-stage optimization and kinematics constraint-based thumb posture estimation method and computing equipment. The method comprises the following steps of: acquiring original hand data, preprocessing the original hand data, and initializing parameters; constructing a multi-objective optimization function with multiple constraints, obtaining an initial estimation thumb posture based on the preprocessed data, taking the initial estimation thumb posture as an initial value, and performing recursive calculation by using a kinematics chain to obtain an accurate angle of each joint of the thumb; integrating the accurate thumb joint angle to complete hand posture parameters and outputting the parameters; a computing device is implemented based on the method. Complete and accurate thumb kinematic chain recovery under incomplete input is achieved, it is guaranteed that all estimated thumb joint angles conform to the human anatomy activity range, and high-fidelity basic data are provided for downstream application; the generated thumb motion sequence is continuous and smooth in the time dimension, and the visual experience in real-time interaction application is greatly improved; in an interactive application, a more natural, accurate and jitter-free gesture control experience can be realized.

The utility model provides a multi-curvature ankle joint prosthesis which comprises a tibia prosthesis connected with a tibia, a talus prosthesis connected with a talus and a cushion block with one side connected with the tibia prosthesis, a joint contact surface is arranged on the other side of the cushion block, and a talus contact surface matched with the joint contact surface is arranged on one side of the talus prosthesis. The curvature of the sagittal plane Z in the talus contact face is reduced from front to back, and the instantaneous rotation center of the talus prosthesis on the joint contact face is in an arc shape. According to the multi-curvature ankle joint prosthesis, the talus contact face and the anatomical structure of the human body are high in consistency, the natural form and the motion mode of the ankle joint are accurately restored, the ankle joint prosthesis better conforms to biomechanics and kinematics in the motion process, the motion stability of the human body is improved, local friction stress of the ankle joint prosthesis is smaller, and the ankle joint prosthesis is more stable in motion. And the service life of the ankle joint prosthesis is prolonged, so that the durability of the ankle joint prosthesis is improved.

In one implementation, we describe the semantics of skeleton joints of the avatar to be animated as a mapping to a highly-detailed skeleton model containing most or all of the joints and bones of human anatomy (the "reference skeleton"). Such a reference skeleton (e.g., the "LOA-4" version of the Web3D humanoid skeleton model) features detailed models of the hand and foot phalanges and joints for every vertebra of the spine. Owing to the level of detail of the reference skeleton, each joint of a user-defined animation skeleton can be mapped to one of the joints of the reference skeleton. The identification and location of each joint in the user-defined skeleton on the human body is thereby accurately and unambiguously described. Such semantics can be used in implementing some features of a virtual world platform, for example, in automated action or gesture recognition.

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 relates to the technical field of medical image processing and computer-aided diagnosis, in particular to a liver blood vessel three-dimensional reconstruction method based on deep learning and image processing. The method comprises the following steps: 1) constructing a data set containing multiple liver blood vessel CT images for three-dimensional reconstruction; 2) screening out qualified CT images, and ensuring that the reconstruction result is accurate; 3) inputting the screened image into a three-dimensional reconstruction system, and preparing for further processing; 4) preprocessing the CT image by using an image processing technology to highlight the ROI of the liver blood vessel; 5) automatically identifying and segmenting a liver blood vessel structure in the CT image through a semantic segmentation algorithm embedded in the system; 6) performing enhancement processing on the segmented image, and constructing a three-dimensional form of the liver blood vessel from different directions by using a multi-view reconstruction technology; and 7) performing three-dimensional reconstruction on the segmented blood vessel image to generate an accurate liver blood vessel three-dimensional model. Doctors are helped to master the anatomical structure of the human body more clearly, so that the operation safety and the treatment effect are improved.

The invention relates to the technical field of artificial intelligence, and discloses a palm vein recognition method and device based on human anatomy, equipment and a medium, and the method comprises the steps: obtaining a palm vein image sequence of a user; carrying out anatomical key point positioning processing on the palm vein image sequence to obtain anatomical key point coordinates of the palm vein image sequence; according to the anatomical key point coordinates, carrying out geometric correction processing on an ROI region of the palm vein image sequence to obtain a standardized ROI region sequence; performing multi-modal feature extraction processing on the standardized ROI region sequence to obtain vein texture features and hemodynamic features; and performing cross-modal fusion processing on the vein texture features and the hemodynamic features to obtain palm vein fusion features. According to the invention, the recognition rate and safety of palm vein recognition can be improved.

An electromagnetic tomographic scanner, for use in imaging a live human body part, includes an imaging chamber, a plurality of antennas, a controller, a lid, and a quantity of matching media. The imaging chamber is supported on the base, defines an imaging domain in that receives the head, and has an open end. The antennas are supported by the imaging chamber and encircle the imaging domain. The controller controls one or more antenna. The lid is attachable to the open end and includes a hollow boundary model that mimics a part of human anatomy that is outside the imaging domain. The matching media fills the interior of the model while an empty field measurement is carried out. Various tensors may be produced.

The application discloses a kind of Chinese fifth percentile old male passenger injury bionical model with sign, also called biomechanical model, is the digital computing tool in the technical field of intelligent high-end detection equipment of automobile safety.This application is based on the fifth percentile male automobile passenger injury bionical model of thurstone, its each part is adjusted with age-related change to represent old male.The injury bionical model provided by the application meets the Chinese fifth percentile old male sign parameter;The model has detailed human anatomy structure characteristics.The Chinese fifth percentile old male passenger injury bionical model developed and constructed in the application not only provides a high-fidelity simulation tool for studying the injury mechanism of Chinese old passengers during the collision process, but also helps to deepen the understanding of the complex relationship between age change, body geometry and tissue mechanical properties and injury risk.

The invention relates to the production method of anthropomorphic head-neck phantom in heterogeneous structure and in a form suitable for human anatomy using 3D printer and molding technique.

The invention discloses an anatomy teaching system and method based on VR, relates to the technical field of VR anatomy teaching, solves the problem that in anatomy teaching based on the VR technology, it is difficult to observe human anatomy during movement and reveal the complex movement law of the human body, integrates a motion capture system, a computer system and a projector, and improves the teaching efficiency. Firstly, the system utilizes an infrared camera module, a tracking module and a high-precision motion capture device to accurately capture kinematics data of a human body, and anatomical positioning points are positioned one by one and projected according to human bony marker positioning points and anatomical picture resources needing to be displayed; the function not only improves the dynamic expressive force of teaching content, but also ensures the accuracy of anatomical structure display, avoids the limitation that a static model cannot display complex dynamic information in traditional teaching, and secondly, the system can realize projection following the human body position in movement.

This invention discloses a rare-earth magnetic graphene far-infrared spinal health pillow. Based on human anatomy and biomechanics, the pillow body is designed with seven independent functional zones. In the supine position, the neck support zone consists of, from top to bottom, a biomimetic curved support layer, a negative ion health function layer, a far-infrared emission source layer, a support filling layer, and a magnetic therapy composite array layer. Height-adjustable airbags are also provided within the zone. This invention uses graphene far-infrared light waves to physically excite the negative ion substrate to release negative ions, abandoning high-voltage ionization methods, resulting in no leakage, no radiation, and no harmful byproducts. The far-infrared rays are amplified through secondary excitation, achieving focused energy and deep therapy. The support layer features a soft upper layer and a hard lower layer, while the magnetic therapy layer uses rare-earth permanent magnets and soft magnetic topological arrangements to form a stable and uniform magnetic field. The product is suitable for various sleeping positions and body types, with a negative ion concentration of 1500-3000 ions / cm³ and a far-infrared emissivity of no less than 85%. It combines cervical spine alignment, calming and sleep aid, and microcirculation regulation functions. It is structurally stable, safe, durable, and offers outstanding health benefits.

The utility model relates to skill training device technical field, concretely, it is human anatomy model of peritoneal dialysis simulation training, including human body torso model body, the front of human body torso model body is provided with transparent observation cylinder, the front of human body torso model body is provided with abdominal wall simulation layer, abdominal wall simulation layer is located at the inside center position department of transparent observation cylinder, the inside of human body torso model body is provided with abdominal cavity cavity, is provided with internal organ model in abdominal cavity cavity, still be provided with peritoneal membrane simulation layer in abdominal cavity cavity, the outside of human body torso model body is provided with dialysis pipe, the inner wall one side of transparent observation cylinder is fixed and is installed with internal transparent board, is provided with a plurality of needle guide cylinder of guiding puncture needle and carries out puncture on internal transparent board, the utility model discloses build up the abdominal cavity environment of fitting human real anatomical structure, convenient for simulation operation, reach the effect of helping trainee to adapt to clinical actual operation quickly, reduce real operation risk.

This invention relates to the field of image feature recognition technology, specifically to a method and system for locating key surgical points in orthopedic surgery based on anatomical structure feature recognition. The method includes the following steps: constructing a prior skeletal topology map representing biomechanical connectivity based on human anatomical standards; utilizing a graph attention mechanism to perform semantic mapping and feature aggregation between the multi-scale anatomical feature map and the prior skeletal topology map to generate node-enhanced feature vectors; and performing spatial coordinate regression calculations based on these node-enhanced feature vectors to output the coordinates of the surgical key points. In this invention, by introducing prior anatomical topological knowledge as a global constraint for feature extraction, the information transmission mechanism of the graph structure effectively captures the geometric dependencies between key skeletal points. This solves the problem of local feature ambiguity caused by traditional methods in complex pathological scenarios such as fracture displacement, bone hyperplasia, or tissue occlusion, achieving high-precision and robust surgical key point localization.

The invention discloses a multi-modal fusion self-adaptive sign language digital character generation method and system. By extracting three-dimensional coordinates of hand joint points, contour masks and multi-modal features of an optical flow field, an interpolation strategy is dynamically selected by using a reinforcement learning model according to states such as the number of missing frames and gesture complexity, and hierarchical cross-modal attention fusion and biomechanical constraints of a hybrid neural network are combined, so that high-precision gesture completion is realized. And the system applies skeleton dynamics and muscle-skin coupling constraint to the complemented joint points to ensure that the actions conform to the human anatomy law, and finally drives the digital figure to generate smooth sign language actions. According to the method, joint point errors are effectively reduced in a shielding scene, and the precision and efficiency of sign language digitization can be improved.

The invention discloses a monocular picture 3D human body posture estimation method based on a space state module. The method comprises the following steps: firstly, extracting a 2D key point sequence from a monocular picture, splicing the 2D key point sequence with noise, inputting the spliced 2D key point sequence into a backbone network and a regression head, gradually denoising through repeated iteration, and outputting a 3D human body posture estimation result. The backbone network comprises a plurality of continuous space state modules, and each space state module comprises a joint pyramid pooling module and a bidirectional space-time scanning module; and the joint pyramid pooling module performs grouping average pooling on the input joint feature representation H according to a human anatomy structure to generate multi-scale feature mapping representing different semantic levels. The bidirectional space-time scanning module carries out reordering and bidirectional scanning on the feature sequence through a space state model, then modulates the feature sequence through a SiLU gating signal, and finally inputs the feature sequence to the next space state module. According to the method, higher attitude estimation precision and parameter efficiency are realized while the calculation complexity is remarkably reduced.

A medical apparatus and method of using the same allowing a user to capture a medical image and add a human anatomy diagram overlay on the medical image to specify each image's position on its own version of the diagram and display a small version of the diagram on the image, incorporated by reference in their entirety herein U.S. Pat. No. 8,924,864 and U.S. Pat. No. 10,638,089.

The invention relates to the technical field of dissecting operating tables for teaching, in particular to a lifting type human dissecting table for teaching. The technical problems that after an existing dissecting table inclines, a human body specimen is prone to slipping off from the dissecting table, liquid medicine flowing downwards along the dissecting table is inconvenient to block through the existing dissecting table, the liquid medicine is prone to dripping on the ground to pollute the teaching environment, and the using effect of the human body dissecting table is poor are solved. A lifting type human body dissecting table for teaching comprises supporting legs, lifting frames are connected to the two sides of the supporting legs in a sliding mode, and the two lifting frames are symmetrically arranged. After the dissecting table inclines, four limbs of human body specimens of different sizes are clamped and locked at the current position through the clamping pieces, and then the human body specimens of different sizes can be fixed when the dissecting table inclines, so that the human body specimens are not prone to sliding off from the dissecting table after the dissecting table inclines. Therefore, the use effect of the human body dissecting table is further enhanced.

The invention relates to an improved guide splint (1) for dental procedures in fully or partially edentulous patients, having a lower face (1a) with an anatomical shape designed to rest on a jaw of the patient and comprising at least one through hole (2) configured to serve as a reference for a dental procedure. The splint (1) of the invention also comprises at least one recess (3) on the lower face of same configured for snap-fit engagement with at least one lug (T) protruding from the gum.

The invention discloses a humanoid robot expression control method and system based on anatomy and a facial topological structure, relates to the technical field of bionic robots and voice interaction, and aims to solve the problems that the mouth shape and pronunciation of an existing robot are not matched, the expression is rigid, and no natural micro-expression exists in a non-pronunciation state. A facial topological structure model matched with a robot is constructed based on human anatomy, a lip-tooth-tongue time sequence synchronous linkage control instruction is generated in combination with a language pronunciation rule, facial expressions, micro expressions and eye movement data matched with pronunciation are synchronously generated, meanwhile, an independent expression control instruction can be generated in a non-pronunciation state, and the control precision is improved. And finally, full-scene full-face natural expression control of the robot is realized. The humanoid reality and man-machine interaction naturalness of the humanoid robot are greatly improved, and the method can be widely applied to various bionic service robots and virtual digital humans.

A method for producing a partial or total knee prosthesis suitable for human anatomy of an individual patient, the method comprising a design step of taking into account the patient's current and pre-lesion knee motion behavior, and further taking into account the patient's individual hip-knee-ankle joint (HKA) mechanical alignment, and utilizing these inputs, to produce a partial or total knee prosthesis suitable for human anatomy of the individual patient. A knee joint model as natural is recreated, where still the recreated natural knee joint model rather than the diseased knee joint model is used to create a prosthesis that recreates the natural knee joint.

The invention relates to a training method for generating an AI system (1) for estimating the position of an anatomical landmark (L) by means of text input, wherein the training method comprises the following steps: - Providing a context set (L) that includes a list of names of anatomical landmarks (L), - Providing a position list (P) that includes position tokens (P) which are expressions with respect to relative positioning, - Generating multiple question inputs (Q) that ask for the relative position of a landmark (L), using varying combinations of the landmarks (L) and position tokens (P) of the context set (L) and position list (P), - Generating a number of target landmarks (T) for each question input (Q) by inputting the question inputs (Q) into a Large Language model (12) with a basic understanding of human anatomy, parsing the response (A) for landmarks (L) and defining the found landmarks (L) as target landmarks (T), - Forming multiple training datasets (X), where each training dataset (X) includes the landmark (T), the position token (P) from a question input (Q), and the target landmark (T) from the answer (A) to that question input (Q), - Training the AI ​​system (1) with the training data set (X) and additional spatial coordinates (C) of a subset of the landmarks (L) of the context set (L). Furthermore, the invention describes an AI system and a training device.

In some aspects, a device comprising an implant configured for insertion into a portion of human anatomy, and at least one covering coupled to the implant is provided. According to some aspects, the implant comprises one or more protrusions configured to prevent leakage of material and / or to resist displacement of the implant. According to some aspects, the covering is configured to facilitate improved leakage and / or implant displacement prevention.

The invention discloses a movable type human body dissecting and storing dual-purpose dissecting table which comprises a storage assembly. The storage assembly comprises a storage box, the inner side wall of the storage box is fixedly connected with a shell, and the inner side wall of the shell is rotationally connected with a threaded rod through a rotating shaft; through the arrangement of the plate bodies, the two plate bodies are hinged to the bottom of the top cover through the independent hinges, single-side opening is supported, an operator can select to only open the lighting plate on the corresponding side and keep the other side closed according to the anatomical direction, the plate body on the opening side forms a physical barrier, hard light in a non-operation area is effectively prevented from directly irradiating eyes of the operator, glare interference is avoided, and the safety of the operator is improved. The lamp tubes embedded in the plate body project light at a 45-degree inclination angle, the light is focused on a corpse operation area, the side lamp tubes are turned on to form a crossed light source with the first illuminating lamp set and the second illuminating lamp set in the center of the top cover, illumination dead angles are compensated from different angles, and therefore shadows generated by instruments or hands of an operator are eliminated.

Disclosed are various embodiments for training physicians to perform surgeries or procedures. To do this, a display can render a three-dimensional model of human anatomy and a virtual surgical instrument in a virtual space. A computing device can receive movement input from an input device. Based on the movement input from the input device, the computing device can cause the virtual surgical instrument to move on the display. The computing device can detect a collision between the virtual surgical instrument and the three-dimensional model of human anatomy in the virtual space and, in response, the computing device can direct the input device to provide haptic feedback. Various other features are disclosed that further aid in the training of a surgeon to perform surgeries or procedures.

The invention relates to a portrait missing image completion method and system based on hybrid editing, and the method comprises the steps: expanding a canvas space of an input image, and reserving a blank completion region of a missing part in an expansion region; a limb contour and a face positioning line are drawn on the expanded canvas, and an intermediate image is generated; performing background filling according to color distribution characteristics of adjacent pixels in the missing area; inputting the image containing the structure reference and the background filling into the generative image completion model, and generating a preliminary completion image in combination with a cue word reversely deduced from the original image; and adjusting the human body posture of the complemented score in the preliminary complemented image and optimizing the marginal area until the complemented score and the original image are coordinated and consistent in posture and background, and outputting a final complemented image so as to achieve the purpose of efficiently completing high-quality complementation of the missing part of the portrait while keeping the accuracy of human anatomy.

The present application proposes a chest and abdominal respiration signal decoupling and reconstruction method based on millimeter wave radar. Using a millimeter wave multiple-input multiple-output radar device, the radar echo is first mapped to a three-dimensional space using 3D beamforming technology, mapping the one-dimensional time domain signal to a spatial energy heat map containing distance, azimuth, and elevation three-dimensional information. Then, through spatial filtering strategy, the physiological vibration source signal clusters of the subjects with coupling relationship are separated. When the physiological vibration source includes the chest reflection area of the first anatomical site and the abdominal reflection area of the second anatomical site, combined with the adaptive best point selection algorithm, according to the anatomical features of the human body, the chest reflection area and the abdominal reflection area are physically located and distinguished in the three-dimensional space, and the independent breathing waveform is extracted from the body surface reflection to perform high-precision spatial separation and anti-interference waveform extraction operation of chest and abdominal respiration movement. The present application can realize high-precision spatial separation and anti-interference waveform extraction of chest and abdominal respiration movement.

A method for producing a partial or total knee prosthesis suitable for human anatomy of an individual patient, the method comprising a design step of taking into account the patient's current and pre-lesion knee motion behavior, and further taking into account the patient's individual hip-knee-ankle joint (HKA) mechanical alignment, and utilizing these inputs, to produce a partial or total knee prosthesis suitable for human anatomy of the individual patient. A knee joint model as natural is recreated, where still the recreated natural knee joint model rather than the diseased knee joint model is used to create a prosthesis that recreates the natural knee joint.