240 results about "Human body structure" patented technology

The present invention discloses a parallelized human body behavior identification method. According to the method, skeleton data of Kinect is used as input; a distributed behavior identification algorithm is implemented based on a Spark computing framework; and a complete parallel identifying process is formed. Acquisition of the skeleton data of a human body is based on scene depth acquisition capacity of Kinect and the data is preprocessed to ensure invariability of displacement and scale of characteristics; and a human body structural vector, joint included angle information and skeleton weight bias are respectively selected for static behavior characteristics and a dynamic behavior searching algorithm for a structural similarity is provided. On the identification algorithm, a neural network algorithm is parallelized on Spark; a quasi-newton method L-BFGS is adopted to optimize a network weight updating process; and the training speed is obviously increased. According to an identification platform, a Hadoop distributed file system HDFS is used as a behavior data storage layer; Spark is applied to a universal resource manager YARN; the parallel neural network algorithm is used as an upper application; and the integral system architecture has excellent extendibility.

The invention discloses a public-oriented method and system for medical treatment guide-type self-help triage registering, belonging to the field of medical information processing and network application. According to symptoms provided by a user, diseases relevant to the symptoms are searched from a preset disease library, and the diseases are arranged according to degressive correlation degree or suspected probability; according to the suspected disease chosen by the user, a medical department and hospital analysis are carried out; and registering operation is carried out by connecting the online registration or appointment system of a hospital chosen by the user. The system comprises a logic calling management and service interface, a human body structure and symptom management module, a relevant symptom reasoning module, a suspected disease reasoning module, a department reasoning module, a registering interface calling module, a knowledge node positioning module, a knowledge node association module and the like. The method and the device are used for solving triage shunting and preventing diseases from broadcasting and crossing because patients with communicable diseases blindly go to the hospital. By utilizing the method and the device, a one-stop service function of automatic triage and registering is realized, and the informationization level is improved, thereby bringing convenience for pushing combination of medical networks.

The invention discloses a behavior identification method based on a recurrent neural network and human skeleton movement sequences. The method comprises the following steps of normalizing node coordinates of extracted human skeleton posture sequences to eliminate influence of absolute space positions, where a human body is located, on an identification process; filtering the skeleton node coordinates through a simple smoothing filter to improve the signal to noise ratio; sending the smoothed data into the hierarchic bidirectional recurrent neural network for deep characteristic extraction and identification. Meanwhile, the invention provides a hierarchic unidirectional recurrent neural network model for coping with practical real-time online analysis requirements. The behavior identification method based on the recurrent neural network and the human skeleton movement sequences has the advantages of designing an end-to-end analyzing mode according to the structural characteristics and the motion relativity of human body, achieving high-precision identification and meanwhile avoiding complex computation, thereby being applicable to practical application. The behavior identification method based on the recurrent neural network and the human skeleton movement sequence is significant to the fields of intelligent video monitoring based on the depth camera technology, intelligent traffic management, smart city and the like.

The invention discloses a method for designing and forming a stiffness-controllable bone tumor defect repair implant. The method comprises the following steps of acquiring and preprocessing image data; performing reverse image fusion and registration, and constructing an accurate curve surface materialized repair body model; carrying out parallel finite element analysis and optimization on a porous design scheme by a microscopic porous scheme design; and importing the model into a 3D printing system for printing forming. According to the method, a personalized porous structure, mechanical optimization design and 3D printing forming of a post-bone tumor excision defect area reconstruction repair body are realized in combination with digital modeling, finite element analysis and medical 3D printing technologies according to a symmetric characteristic of a human body structure morphology, so that the reconstruction effect of an individualized anatomic morphology and the design forming efficiency of the repair body are improved, the time and material costs are reduced, the mechanical properties and the bone integration microenvironment after reconstruction are better optimized, and the bone growth repair of a bone defect area is facilitated.

The invention discloses a human body behavior identification method based on a depth sequence. The human body behavior identification method comprises the following steps: adopting a LBP (Local Binary Patterns) operator based on normal information; adopting a combined LBP operator of a spatial pyramid form; carrying out the sparse representation of the combined LBP operator; and carrying out the segmentation and the alignment of a behavior sequence. In order to obtain surface features which reflect different human body behavior surfaces in a depth map and further improve the robustness of human body behavior identification, a LBP description operator of normal information in the depth map is defined according to the similarity and the associated information of a human body structure in the depth map, wherein the operator keeps the geometric characteristics of a human body behavior surface on an aspect of details, extracts the local features of the surface on a local space, and expresses the local features as the human body behavior local features in the depth map. On the whole, detail information is integrated by a coding method based on dictionary learning, the local spatial structure relationship of a human body surface is kept by the pooling processing of an adaptive space-time pyramid and a thinning coefficient, and the detail and integral feature description of three-dimensional human body behaviors is realized.

The invention provides a lower limb rehabilitation robot gait planning method based on lower limb walking characteristics. Firstly, parameterized modeling is performed based on the lower limb walking characteristics, wherein parameterized mathematic models of the lower limb hips, knees and ankle turn angles of the human body are established, and the forms of function curves of the models and required parameter number are determined; secondly, a mathematic inverse solution equation set of curve parameters is established; thirdly, the linear and nonlinear mapping relation of human body structure parameters and characteristic key point positions is found; finally, human body structure parameters are measured, the characteristic key points of a patient are found according to the mapping relation between the human body structure parameters and the characteristic key points, the curve parameters are inversely solved to obtain a specific curve expression, kinematic positions and corresponding lower angles of a robot are solved according to the specific structure and configuration of the lower limb rehabilitation robot to generate a joint movement instruction corresponding to the robot. The lower limb rehabilitation robot gait planning method conforms to a human body lower limb movement rule and can also reveal the mechanism of human body lower limb movements.

The invention discloses a humanoid intelligent robot and a working method thereof. A working process of the humanoid intelligent robot is similar to a process that people completes a concrete task, and the humanoid intelligent robot can reliably and conveniently assist daily life of the people. The humanoid intelligent robot comprises eyes, ears, a mouth, hands, front arms, upper arms, feet and legs, corresponding to a structure of a human body, wherein a camera vision module is installed at each eye part; a microphone auditory module is installed at each ear part; and a horn module is installed at the mouth part. The working method comprises the following steps of (1) receiving a command; (2) the step of searching and recognizing; (3) the step of finishing a functional task command; and (4) the step of finishing the task.

The invention relates to a digital tool applicable to medical research, clinic consultation, teaching in schools and personal somatosensory, in particular to a system for digital analysis of human body and pathology. The system mainly comprises a three-dimension human body model processor module, a pathology document storage module, a pathology data search and analysis module, a multimedia server, video output equipment (such as projectors, displays or touch screens) and the like. A windows Chinese operating system or an android operating system is taken as a main running platform of the system, data of skin, muscles, tissues, organs, bones, acupoints and the like of the human body are recorded into the system by means of a virtual digital technique, and accordingly, a user can do analysis, research and study on detailed structure of the human body comprehensively at 360 degrees through a human-computer interaction technique; as various pathology data of different portions of the human body are recorded into the system, the user can do comparison visually and finally realize study, research and judgment and analysis of pathology.

The invention provides a method for designing the pant suit pattern and the pant suit modeling structure. Based on studying the human body structure and pant suit structure, and pant suit modeling structural characteristics and rules, the method for designing the pant suit pattern and the pant suit structure is obtained through a large number of experiments and practical applications. The method has the advantages of simpleness, easy learning, intuition, easy understanding and strong maneuverability, gives full play to advantages of convenient understanding and operation of the equant graphics, and overcomes the defects that the prior pant suit structure pattern has complicated formula calculation, multiple sizes, uncertainty, hard memory and small design changing space. The method can also better reflect the relation between the human body and the pant suit structure and has flexible and accurate modeling structural changes. The designed pant suit modeling has steady and unique style pattern, and the design efficiency is greatly improved. The method not only deepens the theoretical study of the pant suit structure, but also further expands the thought and the method of the pant suit structural design, has good practicability and economic value potential, and has the practical significance of promoting the raiment culture development and improving the production efficiency of the clothing industry.

The invention discloses a dynamic space-time coupling processing method for noise and missing data processing in the optical human motion capture data, comprising the establishment of a dynamic pulse noise model of the noise data and the missing data in the originally-gathered motion data based on a standby semantic chunk, which is characterized in that: the invention comprises the following steps of: generating the standby semantic chunk based on a matched rigid structure, establishing a human topology model based on semantic nodes, generating an optimal human body structure based on the spatial semantic constraint, establishing a pulse noise model based on the position of the semantic chunk and the dynamic time sequence based on the attitude attribute, filtering noise data and reconstructing missing data. The processing method of the inventive embodiment is applicable for processing the motion data which meet any feature point arrangement of the local rigidity structure with good practicability and robustness.

The invention provides a queue length automatic detection method and a queue length control method. The queue length automatic detection method comprises the following steps: detecting pedestrians based on a human body structure model algorithm; tracking the pedestrians through a feature online selection lifting algorithm; fitting out a queue shape of pedestrians through an RANSAC-based least square polynomial curve fitting method according to the detected pedestrians, and estimating the length of the queue; converting an image coordinate system into a world coordinate system through image calibration, and calculating the actual queue length; and calculating the length of the curve through curve fitting, and calculating the number of people in the queue according to the queue length and the distance between adjacent people in the queue. Through the queue length automatic detection method and the queue length control method of the invention, the length of a pedestrian queue in a monitoring scene can be detected quickly and accurately, the problem of target loss is avoided, and no pedestrian is missed in detection. Through real-time queue monitoring, passengers can move to a handling window with a shorter queue in a timely manner. Therefore, the problem of waiting in a queue is solved, and passengers can be better served.

The invention discloses a fine-grained action detection method of a convolutional neural network based on multistage condition influence. The method comprises the steps of: establishing a convolutional neural network influenced by multistage conditions; fusing the explicit knowledge added in the visual scene with the multi-level visual features; enabling the multi-level conditional influence convolutional neural network MLCNet to take a conditional influence multi-branch convolutional neural network structure as a main trunk, generating multi-level visual features, encoding additional spatialsemantic information of human body structure and object context information as a condition, dynamically influencing feature extraction of a CNN through affine transformation and an attention mechanism, and finally fusing and modulating multi-mode features to distinguish various interactive actions; and carrying out model training on the convolutional neural network influenced by the multi-level condition, and outputting a fine-grained action detection result by the obtained model. According to the method, the proposed method is evaluated on the basis of two most common references, namely HICO-DET and V-COCO, and experimental results show that the method is superior to the existing method.

The invention relates to a gesture identification method and device in a depth image. The method comprises the following steps of extracting a human body three dimension profile form the depth image; calculating local features of the three dimension profile; inputting the local features of the three dimension profile into a preset human body structure model to obtain the absolute space distribution and condition space distribution of human body joint points; calculating the positions of the human body joint points in a three dimension space according to the absolute space distribution and the condition space distribution of the human body joint points to obtain a human body gesture identification result. On the basis of the original random sen, gesture identification is performed by the preset human body structure model, the method has low feature dimension and strong description capability, human body gestures are uniformly learned aiming at the bodies of different heights by the human body structure model, the learning ability is reduced, and the practicability and accurate rate of an algorithm are improved; compared with the original probabilistic graphical model, the method is faster in gesture reasoning and is suitable for a real-time gesture capturing system.

The invention provides a three-degree-of-freedom parallel mechanism ankle joint recovery device, and belongs to the technical field of recovery engineering. The three-degree-of-freedom parallel mechanism ankle joint recovery device comprises a pedal, an L-shaped connection plate, a U-shaped connection plate, a supporting rod, a slide block, a guide rail, a support, a supporting seat, a bottom plate and three branched chains. Rotation pairs are formed between the pedal and the L-shaped connection plate, between the L-shaped connection plate and the U-shaped connection plate as well as between the U-shaped connection plate and the support. The first branched chain and the second branched chain are connected with the pedal through spherical hinges, and connected with the bottom plate throughhooke joints; the third branched chain is connected with the U-shaped connection plate through one rotation pair, and connected with the bottom plate through another rotation pair. The first branchedchain, the second branched chain and the third branched chain form a spatial parallel mechanism which has three rotation degrees of freedom. The three-degree-of-freedom parallel mechanism ankle jointrecovery device is good in rigidity and high in bearing capability, can achieve adjustment of altitude and angles, conforms to the human body structure, can meet the movement requirements of the anklejoint, and has important effects on recovery of the ankle joint.

The invention discloses an intelligent immersed teaching system and device used for nasogastric tube operating training. A virtual human body structure is constructed through a virtual reality modeling technology, students complete a nasogastric tube manual placing step on the system and achieve cognition training. The process achieves visualization, and physiological response of a patient is simulated for students through touch sense feedback and stereo sound effects. Action of a student during the whole nasogastric tube manual placing process is subjected to quantitative evaluation, which helps the student to raise clinic operation skills. Autonomic and high-efficiency training of students is achieved, sensory cognition and clinic communication skills of learners are raised, and data support is provided for teaching planning.

The invention discloses a plating method for suit sleeve strip matching and check matching. By means of the proportion of the chest circumference to the front cross to the front shoulder projection width, the armhole arc line overall length and other parameters, a sleeve top point is controlled to shift backwards, and a back height line transversely passing through the armhole and multiple horizontal-direction auxiliary lines such as a prolonging line, a sleeve length upper flat line and a sleeve top depth auxiliary line of the back height line are added, a crossed point produced by sleeve top and sleeve bottom arc line horizontal lines transversely shifts so as to adjust the sleeve capacity, the fabric grain inclination degree of a sleeve seam is increased by moving a cuff front slanting sleeve point forwards, the sleeve pulling difficulty is lowered, the operation difficulty is lowered, the check matching effect is improved, the sleeve model incurvation is more natural and accords with the human body structure, and the overall attractiveness of a sleeve model is improved.

The invention relates to the field of impact wave therapy, in particular to an erectile dysfunction impact wave therapeutic instrument. The erectile dysfunction impact wave therapeutic instrument comprises a main machine generating high voltage pulses and a therapy head connected with an electric tube cable of the main machine. The therapy head comprises an electromagnetic wire array type impact wave generator connected with the electric tube cable of the main machine. A liquid bag is further arranged on the electromagnetic wire array type impact wave generator. The electromagnetic wire array type impact wave generator generates impact waves in a wire array type region under the effect of the high voltage pulses. According to the instrument, the electromagnetic wire array type impact wave generator generates the impact waves in the wire array type therapy region, the low-energy impact waves are used for treating the corpus cavernosum and the penis root, the nitric oxide content and activity of the corpus cavernosum and the penis root can be improved, the inflammatory cytokine level is reduced, inflammation is resisted, angiogenesis and blood capillary regeneration are stimulated, microcirculation is facilitated, the blood flow in the therapy region is increased, plenty of blood of the cavernosum is obtained, so that the ED therapy purpose is achieved, the shape of the liquid bag can be changed, and the liquid bag can be suitable for different human body structures.

The invention provides a human body posture estimation method and a human body posture estimation system. The method includes the following steps: A, building a human body structuralized model, and combining with information of a sensor to calculate posture of human body motion and position information in a geodetic coordinate system; B, building a Bayesian network model of human body motion, combining with the posture of human body motion and the position information in the geodetic coordinate system to solve the geodetic coordinate system, and predicting human body posture of a later frame by a belief propagation algorithm in the Bayesian network model through human body posture data of a former frame. The human body posture estimation method and the human body posture estimation system have the advantages that human body posture can be predicted, operation efficiency of the whole system is improved remarkably, and predicting instantaneity of the system is guaranteed.

The invention provides a human body body hip modeling and simulation method based on muscle groups, and relates to the human body hip modeling and simulation method based on the muscle groups. The object of the method is to solve the problem that existing human hip models cannot take into account refined human body structures and finite element simulation implementing, and the human body hip modeling and simulation method based on the muscle groups is provided. The method comprises the steps of first, acquiring human hip image data; second, conducting geometric modeling on human hip, which includes geometric three-dimensional reconstruction of hip bone (cortical bone and cancellous bone), thigh bone (cortical bone and cancellous bone), articular cartilage, sartorius muscle, musculi quadriceps femoris, biceps femoris, semitendinosus, semimembranosus, gracilis, phalanges, long adductors, short adductors, adductor muscles, gluteus maximus, gluteus medius, gluteus maximus and entire hip; third, establishing muscle group models, conducting model assembly on the hip bone, the thigh bone, the articular cartilage, the muscle groups and the whole hip, establishing a fat and skin model, andadding tendon; fourth, determining meshing parameters, determining inter-tissue contact relationship, and implementing the meshing of the geometric models; fifth, attaching materials to the structureof each part of the human hip model, and determining the material parameters; sixth, achieving mechanical simulation of the human hip model. The method is used in the field of biomedical engineering.

The invention relates to an inflatable collar capable of being used as a headrest. The collar is changed into the headrest by air inflation in rooms or vehicles and during travelling or field activities, so that people can have a rest at anytime and anywhere. The inflatable collar is positioned on the upper part of a coat and is provided with an accommodating neck and collar sharps positioned on both sides of an opening of the accommodating neck; the collar is formed by sewing a surface fabric and a bottom fabric; an inflating air bag is arranged between the surface fabric and the bottom fabric; and an inflating nozzle of the inflating air bag is positioned at one of the collar sharps. When people need to have a rest, the collar is turned over, the air bag in the collar is inflated from the inflating nozzle by mouths, and the inflating nozzle is sealed by a sealing plug on the inflating nozzle, so that the collar is changed into the headrest around the neck. The headrest is positioned in the positive backside of a head, clings to the head neck and is in a collar annular shape, so the headrest corresponds to a human body structure, and can fulfill the aims of resting conveniently and protecting the head necks effectively while keeping the attractive appearance of the collar and increase the functionality and additional value of clothing.

The invention discloses an intelligent nursing robot and belongs to the technical field of machine manufacturing and automation thereof. The technical aim that a virus spreading route is cut off from an infection source is achieved. The intelligent nursing robot is shaped like a human body structure and comprises a head part, a neck part, a trunk and foot parts, wherein the head part is connected with the trunk through the neck part; the trunk is fixedly connected with the foot parts. The intelligent nursing robot replaces nurses to complete related work, direct contact between the nurses and patients is avoided, and disease spreading is blocked off from the source and controlled effectively.

The embodiment of the invention provides a head and neck lymph node and drainage area automatic sketching method based on deep learning. The method utilizes the symmetry of a human body structure to divide a head area into a left part and a right part for training and prediction, thereby indirectly increasing the data volume of model training, and reducing the scale of a deep learning model at thesame time. According to the method, a step-by-step processing optimized sketching strategy is used, the lymphatic drainage area easy to segment is achieved through the deep learning model, then the lymphatic drainage area is optimized and lymph nodes are segmented through the multi-task deep learning model, the relevance between the lymphatic drainage area and the lymph nodes is fully utilized, and the segmentation accuracy of the lymphatic drainage area and the lymph nodes is improved. According to the invention, an AI (artificial intelligence)-assisted contour sketching method is implemented in a radiotherapy plan work flow, so that the sketching consistency of the work efficiency of medical workers can be effectively improved, and the head and neck tumor radiotherapy precision is improved.

The invention discloses a multi-mode human behavior recognition method based on sports biomechanics. On the basis of the exercise biomechanics, the human body structure is converted into a human bodyskeleton action model with exercise characteristic parameters, action description parameters are determined, and then the biomechanics characteristics are calculated. Describing human body action postures by using the characteristic parameters, and establishing a relation model between the parameters and the action modes; The human body action posture description method based on biomechanics comprises the following steps: analyzing the characteristics of human body action time sequence data, performing boundary detection on continuous actions in multiple modes by using a key frame extraction method based on combination of a curve simplification algorithm and a frame subtraction algorithm, and realizing segmentation and automatic labeling of basic actions and transition actions; And analyzing characteristics of the basic action mode and the transition action mode, and establishing an identification model of the basic action mode and the transition action mode by adopting a multi-model idea to realize identification of multi-mode behaviors.