31 results about "Human Modelling" patented technology

The invention discloses an evolutionary algorithm for surface fitting in human body modeling, belonging to the technical field of computer application. Based on a principle of being a burgeoning searching optimizing technology, the evolutionary algorithm has the beneficial effect of providing a general framework for solving complicated systems. According to the invention, B spline surface fitting based on the evolutionary algorithm is applied to the human body modeling; a curve boundary line is determined first by the B spline surface fitting method of the evolutionary algorithm so as to obtain a basal plane; surface control points are obtained through reverse engineering according to the basis principle of the surface fitting; and then optimization selection is carried out on the judgment on the fitness of the control points according to the evolutionary algorithm, so that the surface fitting in the human body modeling is realized finally. According to the invention, the calculation speed and efficiency are improved by virtue of the robustness of the evolutionary algorithm, the solving process is simplified, errors generated in the fitting process are reduced, and further the advantages of the evolutionary algorithm is proved.

The invention provides a human body modeling technique conforming to a customized human body size and is applied to the field of three-dimensional test systems and computer-aided design garments. The method mainly comprises three steps of 1, extracting 26 human body measurement dimensions from an instance model to form a dimension set, performing statistical analysis of the relationship between the dimensions, and dividing the instance model into 16 rigid parts; and 2, performing block analysis of statistical information of human body shapes, wherein the linear regression method is used in the statistical analysis of the mapping relation between the human body shape to the dimension data and a new method for accurately generating a customized model is used, and leaning the linear mapping relation between the local deformation parameter and the semantic parameter of each human body part; and 3, performing human body modeling according to an input dimension, and finely tuning an initial model to enable it to conform to the input dimension parameter after a new human body model is obtained. The method can accurately generate a customized human body model for virtual fitting with less distortion.

The invention discloses a method for improving virtual human modeling accuracy in 3D clothing fitting software. The method includes 1, selecting 11 figure modeling parameters affecting surface greatly to serve as BP neural network output parameters; 2, figuring out 36 figure feature parameters to serve as BP neural network input parameters; 3, establishing an initial model of a BP network in Matlab environment, acquiring an optimal network structure by means of network training, and establishing a nonlinear mapping relationship of the figure feature parameters and figure adjusting parameters; 4, analyzing the encoding manner of human parameter modeling interface files in the 3D clothing fitting software, and generating a customized virtual human based on a customized figure and human size. The method has the advantages that the personalized and customized human modeling requirements for clothing fitting evaluation can be met, efficient personalized human body generation from the figure feature parameters can be implemented, and the method can be widely applied to clothing customization platforms.

The invention discloses a network fitting system. The system is characterized by comprising the steps that a purchaser logs in the fitting system via a terminal; size information of the purchaser is added to a human body size chart and can be stored in a customized manner; a human body model can be established in a human body modeling method according to the input size information; the human body model is finally obtained via correction and rendering by virtual technology; clothes selected by the purchaser is tried on the human body model; the clothes is ordered if the size of the clothes is consistent to the size of the purchaser; and otherwise, the purchaser can check whether a manufacturer of the clothes provides customized service, or the purchaser can choose a bigger or smaller size for fitting again, and the clothes is ordered until the purchaser is satisfied with the clothes. The system can simulate practical fitting effect of the purchaser, effectively helps the purchaser in selecting a suitable clothes, and reduces occurrence of returning and exchanging.

The invention discloses a virtual fitting method. The method comprises the following steps: making a three-dimensional model of a garment according to a two-dimensional image of the garment; fitting the three-dimensional clothing model to the three-dimensional standard human body model; obtaining a two-dimensional image of a target human body; inputting the obtained three-dimensional human body parameters into a standard human body model for fitting; matching the clothing three-dimensional model to the three-dimensional human body model; and the three-dimensional human body model is basically consistent with the target human body posture. The invention provides a method for obtaining accurate human body three-dimensional model parameters by analyzing a whole human body photo through a deep neural network, and human body modeling can be quickly performed only by one common photo; meanwhile, the three-dimensional garment model is obtained by processing the two-dimensional garment picture in advance, the user does not need to participate in the background work and only needs to select the garment style which the user wants to virtually try on, the system can automatically match the corresponding garment model, and the authenticity and the reduction degree are kept through a series of methods.

The invention discloses an exoskeleton function detection system. The exoskeleton function detection system comprises a sky rail suspension module, a plantar pressure detection and analysis module, athree-dimensional motion capture module, a multi-physiological-parameter monitoring module and a human body modeling and simulation module. The human body modeling simulation module performs modelinganalysis according to data obtained by the pressure analysis module, the three-dimensional motion capture module and the multi-physiological-parameter monitoring module to obtain kinematics, dynamicsand physiology data of the exoskeleton. According to the exoskeleton function detection system, the human body modeling simulation module performs the modeling analysis by combining the obtained gaitanalysis data, the motion and motion trail of the whole exoskeleton and the physiological parameter data of the human body wearing exoskeleton; the kinematics, dynamics and physiology data of the exoskeleton can be obtained, the performance of the exoskeleton can be comprehensively detected through various data analyses, and therefore data support can be provided for formulating schemes of optimaldesign and complete functions of the exoskeleton.

The invention discloses a 3D virtual fitting method and system and a storage medium, and the method comprises the steps: receiving modeling data provided by a user, and carrying out the 3D human body modeling, and obtaining a 3D human body model; performing 3D clothing modeling according to the clothing picture data to obtain a clothing model; and rendering the clothing model and the 3D human body model, and displaying the fitting effect of the 3D human body model. According to the 3D virtual fitting method, a new technical path is created, 3D virtual fitting is achieved through 3D human body modeling and 3D clothes modeling, the fitting effect of a user is truly displayed, more direct reference is provided for the user to purchase clothes, and for offline stores, by installing a program corresponding to the 3D virtual fitting method in the embodiment, the tedious fitting process of the user can be saved, and clothes can be purchased more simply and efficiently.

The invention discloses a human body modeling method for virtual fitting. According to the method, a specially made garment where small square pasters are pasted is used, the specially made garment is put on a model, then photo taking is conducted, the deformation and the size of the pasters in photos are analyzed so as to determine human body position information of the points where the pasters are located, and through a large amount of collected information, modeling data can be obtained. The method is easy to implement, good in effect and wide in application value.

The embodiment of the invention provides a three-dimensional human body modeling method and device, electronic equipment and a storage medium. The method comprises the steps: determining a point clouddata frame sequence to be modeled; determining a point cloud data frame sequence to be modeled; determining a nearest point pair between point cloud data of each pair of adjacent frames in the pointcloud data frame sequence; taking the minimum sum of distance errors of all nearest point pairs in the point cloud data frame sequence as a target, and adjusting all the nearest point pairs to obtainregistered point cloud data; and establishing a three-dimensional human body model based on the registration point cloud data. According to the method and device, the electronic equipment and the storage medium provided by the embodiment of the invention, global registration is carried out on the point cloud data frame sequence, so that accumulated errors between the point cloud data are reduced,tight closing between the initial frame and the end frame of the point cloud data is achieved, and the modeling precision of a three-dimensional human body model is improved.

The invention discloses a safety control software system of an intelligent collaborative robot. The safety control software system of the intelligent collaborative robot comprises a sensor system anda robot motion control system; the sensor system collects real-time position information of a human body and the robot in real time and sends the information to the motion control system; a sensor information fusion function package of the motion control system carries out real-time human body modeling, a robot real-time model is established according to the joint position of the robot, a "collision" detection function package carries out "collision" detection according to real-time human body expansion model data and a robot real-time state model, when it is detected that a person is outsidea working space, the system adopts an autonomous motion mode; when the person enters the working space, a safe motion mode is adopted, and a motion planning function package carries out real-time planning, so that an operator is avoided while existing task execution is guaranteed; and when "collision" cannot be avoided, the robot enters a shutdown waiting mode, and the robot continues to execute the original task after the person evacuates. According to a method of realizing the safety control software system of the intelligent collaborative robot, the safety of personnel can be ensured afterthe personnel intentionally or unintentionally enter the working space of the robot.

Embodiments of the present invention disclose a human body modeling method and apparatus. The method according to the embodiment of the present invention comprises the steps of: extracting key points in a human body model; connecting the key points into smooth curves, and deriving a curved surface and a body from the smooth curves, to obtain a geometric human body model; meshing the geometric human body model, to obtain a human body mesh model; applying a voltage to the human body mesh model, and performing finite element solution, to obtain an electric shock simulation result. The present invention can better simulate real human electric shock cases.

The invention provides a three-dimensional human modeling method by using cartographical sketching, comprising the following steps of: 1. analyzing a sketch: decomposing a human sketch into a skeleton stroke set Ss, an outline stroke set Sp and a thread stroke set Sc; 2. extracting the model characters: extracting a human skeleton structure on a predefined human mesh model MH; 3. recovering the depth: identifying a thread determination result on the thread stroke set according to the skeleton structure and calculating the three-dimensional posture according to the human skeleton structure based on the two-dimensional human posture; and 4. reconstructing three dimension: deforming the section outline characteristics of four limbs and a trunk mesh model. By using the cartographical sketching to draw human front elevation skeleton and outline and directly generating the three-dimensional mesh model, the invention accords with the plane drawing habit of an animation role designer, simplifies the human modeling flow and greatly reduces the time for users to construct human models.

The invention provides a method and a system for measuring human body modeling dimensions. The method comprises the steps of obtaining a target human body image, and extracting a body surface contourof the target human body image; establishing a human body three-dimensional model according to the body surface contour; and according to the human body three-dimensional model and the actual height of a target figure, performing calculation for obtaining human body dimension data of the target figure. The method and the system settle problems of low convenience and high cost in existing human body modeling, and further has advantages of improving convenience in human body modeling and improving accuracy in human body dimension measurement.

The invention discloses an aircraft assembly path optimization method based on human body biological characteristics, and belongs to the technical field of aircraft assembly. The optimization method comprises the following steps: establishing an assembly model; constructing a virtual human body model; establishing a fuzzy comprehensive evaluation model based on the time task based on a fuzzy comprehensive evaluation algorithm; establishing a state balance equation according to the overall stress condition of the assembly worker; carrying out dynamic modeling on upper limbs of aircraft assemblers; carrying out dynamic modeling on the lower limbs of aircraft assemblers; and integrating the models to obtain an optimized assembly path. On the basis of aircraft digital assembly, the postures ofworkers, human body biological characteristics and the like in the assembly process are studied and analyzed through virtual human body modeling, the aircraft assembly path is optimized, and the purposes of improving the aircraft assembly efficiency and protecting the health of the workers are achieved.

The invention discloses a human body three-dimensional modeling system based on a hand-drawn sketch, and the system comprises an input sketch module which is used for obtaining a sketch image inputtedby a user; a deformation-based human body model generation module which is used for extracting morphological characteristics from the sketch image through a neural network and deforming the human body standard template model based on the target morphological characteristics to obtain a deformed human body three-dimensional model; and a parameterized model optimization module which is used for predicting human body posture parameters and human body shape parameters according to the deformed human body three-dimensional model and the human body standard template model so as to optimize the deformed human body three-dimensional model. According to the system, the high-quality human body three-dimensional model of the corresponding posture can be obtained through simple lines edited by a useror drawn by hand, high-precision and complex sketch input is not needed, and the system can be widely applied to various human body modeling software.

The embodiment of the invention provides a human body modeling model acquisition method and device, electronic equipment and a storage medium. The key point loss of the true value key point information and the predicted key point information is calculated, and the loss of the deep learning model is calculated and obtained in combination with the key point loss and the human body mask loss, therebyreversely adjusting the parameters of the deep learning model according to the loss of the deep learning model. When the loss of the deep learning model is calculated, key point loss is added, the influence of key points on parameter adjustment can be effectively improved, and therefore the performance of the deep learning model is improved. When the loss of the deep learning model is calculated,the human body masking loss is added, and the area where the human body is located, the human body shape and the like can be restrained.

The invention belongs to the technical field of human body posture correction, and particularly relates to a posture correction system and method based on human body posture recognition. Aiming at solving the problem that defects exist in online search video follow-up training or face-to-face training, the posture correction system comprises a human body modeling unit, a posture analysis unit, a training unit and a supervision unit, the human body modeling unit is used for scanning and modeling postures, the posture analysis unit is used for analyzing scanned posture modeling, the training unit is used for training and correcting postures of a user, the monitoring unit is used for reminding and monitoring daily sitting postures, walking postures, training arrangement and the like of the user, the human body modeling unit is connected with the posture analysis unit, the posture analysis unit is connected with the training unit, and the training unit is connected with the human body modeling unit and the supervision unit. The system and the method provided by the invention have good robustness, and can provide professional virtual private tutoring by accurately identifying own conditions without limitation of time and places.

The invention discloses a simple and high-efficient three-dimensional human body reconstruction method based on a single Kinect. The three-dimensional human body reconstruction method comprises the following steps of 1) acquiring point cloud; 2) carrying out point cloud pretreatment; 3) carrying out local aligning; 4) carrying out global aligning; and 5) carrying out surface reconstruction. A user can easily realize three-dimensional human body modeling in a narrow space, such as a home room or an office room, and only a personal computer and a Kinect are needed. In order to make the human body modeling become rapid, accurate and convenient, the invention provides an effective whole body scanning data acquisition strategy. Through six angles, three frame scanning is performed for each angle so that the human body can be completely covered. Point cloud data processing captured by the Kinect includes two steps of the local aligning and the global aligning. The new three dimensional human body modeling method can be suitable for most of applications, such as digital measurement, a product design and on-line shopping.

The invention discloses a three-dimensional human body modeling method based on OpenGL and deep learning. The method comprises the following steps: extracting a human body image in a two-dimensional image through a deep learning model Mask R-CNN, and reconstructing a personalized three-dimensional human body model through the combination of OpenGL and a standard 3D human body model. The method comprises the following steps: firstly, segmenting a human body image in a two-dimensional image by adopting a Mask R-CNN deep learning model; and then extracting main features of the human body contourobtained after segmentation, finally mapping the features of the human body contour image to a three-dimensional standard human body model established by 3d-max by using OpenGL, and quickly constructing a three-dimensional human body model in the OpenGL. The method is fast in image processing and high in model generation efficiency.

The invention discloses a method for optimizing an aircraft assembly path based on human biological characteristics, and belongs to the technical field of aircraft assembly. The optimization method includes establishing an assembly model; constructing a virtual human body model; establishing a fuzzy comprehensive evaluation model based on a time task based on a fuzzy comprehensive evaluation algorithm; establishing a state balance equation according to the overall force of the assembly worker; Dynamics modeling of lower limbs of aircraft assembly workers; synthesis of various models to obtain an optimized assembly path. Based on aircraft digital assembly, the invention optimizes aircraft assembly path through virtual human body modeling to study worker's posture and human biological characteristics in the assembly process, so as to improve aircraft assembly efficiency and protect workers' health.

The invention discloses a finite element human body modeling method oriented to human body communications, belonging to the technical field of human body communications. The method comprises the following steps: (1) performing geometrical abstraction to every part of a human body according to the shape properties of every part of the human body; (2) defining an inner geometrical structure of everypart of the human body; (3) setting electromagnetic property parameters of stratum mediums in every part of the human body; (4) connecting every part of the human body to form a completed finite element model of human body. The finite element human body modeling method oriented to human body communications provided in the invention can form a finite element human body software model with the geometrical property and electromagnetic property which are similar to an authentic human body, and the finite element human body software model has significance to the study and application of the humanbody communication technology.

The invention discloses a method for improving virtual human modeling accuracy in 3D clothing fitting software. The method includes 1, selecting 11 figure modeling parameters affecting surface greatly to serve as BP neural network output parameters; 2, figuring out 36 figure feature parameters to serve as BP neural network input parameters; 3, establishing an initial model of a BP network in Matlab environment, acquiring an optimal network structure by means of network training, and establishing a nonlinear mapping relationship of the figure feature parameters and figure adjusting parameters; 4, analyzing the encoding manner of human parameter modeling interface files in the 3D clothing fitting software, and generating a customized virtual human based on a customized figure and human size. The method has the advantages that the personalized and customized human modeling requirements for clothing fitting evaluation can be met, efficient personalized human body generation from the figure feature parameters can be implemented, and the method can be widely applied to clothing customization platforms.

The invention discloses an unmanned aerial vehicle for three-dimensional modeling of a human body and an application thereof, and relates to the field of modeling of an unmanned aerial vehicle. The device includes a main body. The camera device is arranged on the main body. The camera control device controls the camera device to take pictures. The signal receiving device is connected with the camera control device. The control device controls the flight of the drone. and a distance measuring device that measures the distance between the drone and the human body to be modeled. The invention also discloses a three-dimensional human body modeling system for an unmanned aerial vehicle and a modeling method using the system. The system includes an unmanned aerial vehicle, a signal transmitting device connected with a signal receiving device, and a circular motion track, and the circular motion track includes several camera points evenly distributed along the circumference. The UAV in the present invention has strong mobility when modeling the human body and is not limited by the working environment, while the modeling method using the system in the present invention can model static or dynamic human bodies from multiple angles and in all directions.

The present invention provides a method and system for dimension measurement of human body modeling, the method comprising: acquiring a target human body image, and extracting the body surface contour of the target human body image; establishing a human body three-dimensional model according to the body surface contour; according to the The three-dimensional model of the human body and the actual height of the target person are calculated to obtain the human body dimension data of the target person. The invention solves the problems of insufficient convenience and high cost in existing human body modeling, can improve the convenience of human body modeling, and improve the accuracy of human body dimension measurement.

The invention relates to the technical field of human body modeling, in particular to a human body 3D modeling method. Comprising the following steps of 1, taking a picture by taking a size background picture as a background before a person stands on the size background picture, obtaining a front picture and a side picture of a human body, and obtaining a corresponding positive contour line and a corresponding side contour line through picture processing; 2, establishing a plurality of card-shaped marking lines H, obtaining a part perimeter contour line, corresponding to the card-shaped marking lines H, of the human body, taking the size background picture as a background picture to photograph the part perimeter contour line, and obtaining a part contour line after picture processing; 3, marking intersection points generated by the card type marking line H and the front contour line and the side contour line as anchor points; 4, determining an anchor point of the part contour line based on the card type marking line H; and 5, synthesizing a human body basic model by taking the anchor points of the determined part contour lines as base points, and carrying out human body 3D modeling. The invention provides a human body 3D modeling method which is convenient to operate and can improve the accuracy of modeling data.

The invention discloses a three-dimensional human body modeling method based on OpenGL and deep learning. The deep learning model Mask R-CNN is used to extract a human body image in a two-dimensional image, and OpenGL and a standard 3D human body model are combined to reconstruct a personalized human body model. Methods for 3D Human Body Models. First, the Mask R‑CNN deep learning model is used to segment the human body image in the two-dimensional image, and then the main features of the human body contour obtained after segmentation are extracted. 3D standard human body model, and quickly build a 3D human body model in OpenGL. The invention not only has fast image processing, but also has high model generation efficiency.

The invention discloses a human body model special for a short-track speed skating project for a wind tunnel test, a construction method and a construction system, and relates to the field of human body modeling. The robot comprises a trunk part sub-area, a hip part sub-area, a left arm part sub-area, a right arm part sub-area, a left leg part sub-area and a right leg part sub-area. The hip part sub-area, the left arm part sub-area and the right arm part sub-area are all buckled with the trunk part sub-area through pins; the left leg part sub-area and the right leg part sub-area are both buckled with the hip part sub-area through pins. The method can be applied to short-track speed skating item training, competition suit design and research and development, equipment appearance structure design and research and development and performance evaluation.

The present invention provides a 3D shaping buttock pad design method oriented to personalization and customization. Firstly, the 3D point cloud data of the whole body of the human body is collected and preprocessed; Preliminary construction, and then design the structural line on the body-fitting layer and shaping layer; finally, compound the body-fitting layer and shaping layer, and set the body-fitting layer inside the shaping layer to obtain a personalized 3D shaping buttock pad. Based on reverse engineering and parametric human body modeling technology, the present invention carries out the 3D design of the shaping buttock pad through hybrid modeling, and uses 3D virtual reality and virtual try-on technology to carry out the fitting and shaping effect of the 3D shaping buttock pad Comprehensive evaluation, the design process has a strong visual sense, and the design results are highly reliable, which is conducive to the collaborative innovation design of buttock pads to meet the personalized and diversified needs of consumers, and is economical and convenient, which is conducive to shortening the design and development cycle . At the same time, this method can also be used in the development of the buttock pad mold.