803 results about "Body type" patented technology

The invention discloses a virtual garment customization method based on 3D modeling, and relates to the technical field of garment customization, and the method comprises the steps: collecting image video data corresponding to the body data of a user, and carrying out the preprocessing of the collected data, and obtaining the basic three-dimensional point cloud data of a human body; carrying out primary human body modeling according to the human body basic three-dimensional point cloud data, then adjusting the model shape based on key parameters input by a user, and carrying out body type matching to realize parameterized human body modeling; secondly, modeling the clothes, predicting clothes deformation by adopting machine learning, simulating cloth dynamics by adopting a physical engine, performing collaborative tracking and matching on clothes and human body dynamic characteristics according to a clothes template selected by a user, and realizing virtual try-on through an AR (Augmented Reality) technology; the customized order confirmation information of the user is obtained, the 2D garment pattern graph is generated and sent to the customized production server, it can be ensured that the user can obtain a high-quality 3D modeling result under different devices and environments, and the user experience can be enhanced through AR try-on.

The invention discloses an intelligent wearable exoskeleton self-adaptive auxiliary regulation and control method and an intelligent wearable exoskeleton system.The intelligent wearable exoskeleton self-adaptive auxiliary regulation and control method comprises the steps that a motion data sample of human walking is obtained, and a human motion model is constructed based on a man-machine closed-chain motion model according to the motion data sample; collecting multi-modal data of the target user when the target user wears the exoskeleton in real time; calling a human body motion model and a man-machine closed-chain motion model, and generating an exoskeleton control instruction of man-machine motion cooperation according to the multi-modal data; and dynamically adjusting motion control parameters of the exoskeleton according to the control instruction. According to the method, the precise human body motion model is constructed based on the man-machine closed-chain motion model, the man-machine motion cooperative exoskeleton control instruction is generated in combination with the model, the exoskeleton motion control parameters are dynamically adjusted according to the instruction, the body type difference, the muscle strength level and the motion habit of different users can be precisely matched, and the wearing comfort and safety are effectively improved.

The invention provides a personalized garment matching recommendation and display method and system based on deep learning, and relates to the technical field of intelligent garment recommendation, and the method comprises the steps: obtaining target scene information and body type parameters of a user, screening candidate garments conforming to a scene, extracting garment feature data, and generating a matching recommendation score in combination with the wearing preference of the user, and generating a human body simulation model, calculating a garment deformation parameter and a material performance parameter, and outputting a virtual fitting effect.

The invention provides a virtual fitting recommendation method based on an artificial intelligence technology, and the method comprises the steps: firstly, obtaining the body type data of a user through a three-dimensional scanning device, marking key points through a deep learning network, and inputting body type features and clothing preference labels; thirdly, in combination with the dynamic fitting relation between the clothes and the human body, virtual fitting verification nodes are set, and spatial topology optimization is carried out to generate a virtual fitting mapping layout; then, user data and mapping layout are called from the clothing simulation layer, dynamic deformation simulation is carried out based on the action posture sequence, visual fitting data are extracted, the fitting matching degree is calculated, and a fitting degree evaluation matrix is formed; and then, the interaction feedback layer collects real-time interaction behavior data of the user, performs action calibration, and generates a recommendation correction instruction through comparative analysis. And finally, an optimization decision-making layer optimizes a recommendation strategy and deformation parameters based on historical data, and generates a personalized try-on quality report. According to the invention, the fidelity of virtual fitting, the user experience and the recommendation accuracy can be improved.

The invention discloses a garment customization design system and method based on AI body shape data analysis, and relates to the technical field of data processing, user customization circumference basic evaluation is carried out based on user circumference body shape data, and garment design schemes of all parts of a user in all scenes are generated according to user customization circumference basic evaluation results; adjusting and evaluating the costume design scheme based on the muscle change condition data of each part and the activity condition data of each part; and judging whether the costume design scheme needs to be adjusted based on the costume design scheme adjustment evaluation result, outputting each part, needing to be adjusted, of the user in each scene according to the costume design scheme adjustment evaluation judgment result of each part of the user in each scene, and performing costume customization design according to different conditions of each part of the user in each scene. Different scenes and requirements are met, a user can show the personal style, meanwhile, it can be ensured that the clothes cannot limit movement, and the wearing comfort and the long-term use experience of the user are improved.

The invention provides a massage control method, a massage chair and a controller applied to the massage chair, the massage chair at least comprises the controller, a massage chair main body, an image acquisition device and at least one massage arm.The method comprises the steps that if it is detected that a user sits stably, the image acquisition device is controlled to acquire a current image of the user; identifying a body model of the user according to the current image; and according to the body type model and the current massage mode, determining an action track sequence of each massage arm, and according to the action track sequence of each massage arm, controlling each massage arm to execute massage. The massage process can cover a wider massage area, the personalized massage path can be automatically generated according to the body shape of the user, the massage fitting degree and comfort degree are improved, the whole body surface of the user is massaged, meanwhile, the personalized adaptation capacity of the massage process is improved, and the user experience is improved. The massage experience of the user in the massage process is enhanced, and the personification of the massage process is improved.

The invention relates to an intelligent clothing recommendation system based on image recognition and a recommendation method thereof, and the system obtains a human body image through a multi-modal data collection module, constructs a three-dimensional body model in combination with a deep learning algorithm, and achieves the precise measurement of key parameters such as shoulder breadth and chest circumference. And customized recommendation schemes are generated based on body types such as apple types and pear types. The clothing recommendation module integrates fashion trend analysis and a scene adaptation algorithm, provides style screening, single article combination and dynamic AR fitting functions, and supports 360-degree rotation observation and fabric texture simulation. The virtual fitting module generates dynamic wrinkles of clothes through motion capture, and the error is controlled within 150ms. The system integrates an e-commerce platform and a social sharing function, supports user preference learning and intelligent reminding, improves the accuracy of body type measurement, and improves the recommendation matching degree. Through three-dimensional body shape analysis, dynamic physical simulation and multi-mode interaction, the garment fitting precision and the user experience are remarkably improved.

The invention provides a reloading pedestrian re-identification method based on a decoupling network. The method comprises the following steps: acquiring appearance information and semantic body type information of a pedestrian to be detected; inputting appearance information and body type information of a pedestrian to be detected into the constructed re-identification model to obtain final features; the re-recognition model comprises a multi-scale information fusion decoupling module, a median driving channel attention and human body shape enhancement module and a clothes mixing module. According to the method, the identity-related features and the clothes features are effectively decoupled, the characterization of the identity-related features is enhanced, and the negative influence of the clothes change on the model performance is reduced by mixing the clothes features.

The invention discloses an intelligent guiding method based on a 3D virtual garment customization process, and relates to the technical field of garment customization, and the method comprises the steps: obtaining the basic information of a user through a user interaction interface, and generating a 3D virtual human body model matched with the body type of the user through 3D scanning equipment; performing intelligent matching through a machine learning algorithm according to the basic information of the user and the style information in the costume design database, and displaying a matching recommendation result on a user interface in a visual form for the user to select and preview; dynamically adapting the 3D model of the clothes selected by the user to the 3D virtual human body model, and providing an intelligent adjustment option and an intelligent algorithm to generate an adjustment suggestion; according to the method and the device, fitting simulation, comfort evaluation and visual effect evaluation feedback are performed, user design is optimized, and a customization scheme containing a 3D model file and a production drawing is generated according to a design scheme finally confirmed by a user, so that the operation of a virtual garment customization process is simpler, the auxiliary decision-making experience degree is higher, and the customization efficiency is improved.

The utility model relates to medical rehabilitation training equipment, in particular to a modularized flexible lower limb exoskeleton robot. Comprising a control part, a driving part, a transmission part, a hip joint body part and an ankle joint body part, the driving part communicates with the control part, the driving part is connected with the hip joint body part and the ankle joint body part through the transmission part, and the hip joint body part is arranged at the hip joint of the human body. The ankle joint body part is arranged at the ankle joint of the human body, and the driving part controls the hip joint body part and the ankle joint body part through the transmission part to assist lower limb movement. The power assisting device is compact in structure, small and exquisite, easy to wear, light in weight, portable, adjustable in height and suitable for being worn by people with different body types, a separated modular design principle is adopted, and a power assisting mode can be configured according to specific requirements so as to meet the use requirements of different users in different environments.

The utility model discloses a comfortable chair suitable for multiple usage postures. An overturnable desk board is arranged on a chair backrest, and a desk board adjustment mechanism can fix the angle of the desk board and support the desk board. The chair is provided with overturnable chair armrests, and armrest angle adjustment mechanisms can adjust the angle of the armrests, so as to provide users with various usage postures, realizing high flexibility and practicality. Embedded armrests are also arranged on the chair armrests and can be equipped with matching small desk boards. With embedded armrest adjustment mechanisms, the embedded armrests can be adjusted in both height and forward / backward position, so as to cater to users of different body types and heights.

The invention discloses a remote 3D clothing intelligent customization system based on virtual reality, which comprises a customization primary selection module, a try-on experience simulation analysis module and a try-on experience simulation module, and is characterized in that the customization primary selection module is used for primarily selecting and screening customized clothing styles and categories according to the body type of a customer and customer selection; the try-on experience simulation analysis module is used for analyzing the stress condition of the body parts of the customer after try-on, and the try-on experience simulation module is used for simulating the garment wearing experience feelings under different body postures after real try-on according to the analysis result of the try-on experience simulation analysis module. The customization primary selection module is electrically connected with the try-on experience simulation analysis module, the try-on experience simulation analysis module is electrically connected with the try-on experience simulation module, and the system has the characteristics of real try-on experience and personalized optimization design.

The invention relates to a Gaussian model-based three-dimensional garment generation method, which comprises the following steps of: analyzing data of human body shape parameters, garment types and human body textures from text cues, and initializing and decoupling a garment three-dimensional Gaussian model by using the data; human body shape parameters, clothing types and human body texture data serve as point cloud input, a single three-dimensional Gaussian model is constructed, and the model comprises a clothing vertex set and a body vertex set; inputting the clothing vertex set and the body vertex set into a differentiable renderer, and respectively outputting color rendering graphs and depth rendering graphs of the clothing and the human body; and inputting the text cue word and the rendering graph into the optimized single three-dimensional Gaussian model to generate three-dimensional clothes. Compared with the prior art, the method has the advantages that decoupling of the clothes and the body is achieved, the quality of the produced three-dimensional clothes is higher, and the visual impression is more fidelity.

A water floating device is provided, which is provided with a floating element and a leaning element, they are detachably connected by a fastener. The fastener includes a fixed seat and an insertion end, the water floating device can be stored without releasing air after use. A height of the leaning element can also be adjusted by the fastener to achieve an effect of adjusting an appropriate height of the seating space for people of different body types. The present application provides multiple solutions for fastening the fastener, which can be connected by a rope body or fastened by a buckle. The axis of the fixed seat and the insertion end are locked; thus, they are both kept in a non-movable and in a rotatable state, which has advantages of quick installation / disassembly, good fastening effect, convenient adjustment, easy storage, and storage without releasing air.

The invention provides a method and a system for generating a skeleton by matching animation data, and belongs to the technical field of animation character construction. Comprising the following steps that S1, biological skeletons of a role are established, and the biological skeletons at different positions have unique codes and the same initial length but are not completely the same in shape; s2, constructing a complete skeleton model; s3, adjusting the length of each biological skeleton according to the height of the role and whether the next section of adjacent biological skeleton exists or not; and S4, according to the pose matrix of the corresponding biological skeleton in each frame of character animation data, the animation data uses the same coding mode as the biological skeleton, the corresponding biological skeleton in the skeleton model is adjusted to the corresponding position, and a biological skeleton image of each frame is generated. According to the method, a certain number of biological skeletons are preset and sequentially coded, the number and the positions of the biological skeletons are adjusted according to the body type, the biological skeleton combination structure conforming to the character image is constructed, and the skeleton animation file of the character is further obtained.

The invention discloses a safety belt grading type pre-tightening and force limiting method and system based on passenger signs, and the method comprises the steps: obtaining a passenger image, and measuring the weight information of a passenger, so as to calculate the gender, age, upper trunk height, sitting posture angle and weight of the passenger; the height of the safety belt is adjusted according to the upper trunk height and the sitting posture angle; pre-tightening force and a force limiting table are preset according to the gender, the age and the weight of the passenger, different safety belt pre-tightening and safety belt force limiting are matched for the gender, the age and the weight of different passengers, and safety belt pre-tightening is divided into safety belt first-level pre-tightening and safety belt second-level pre-tightening according to the emergency degree. According to the main technical scheme and the main effects, passengers are classified through sign recognition, so that the pre-tightening force and the force limiting value of the safety belt can be dynamically adjusted according to the body weight, the age and other characteristics, and the adaptability of the safety belt system to the passengers with different body types is remarkably improved.

The novel multifunctional dumbbell stool comprises a mounting seat, the left side of the mounting seat is rotationally connected with a seat cushion, the right side of the mounting seat is rotationally connected with a back cushion, the left side of the mounting seat is fixedly connected with supporting legs, the right side of the mounting seat is fixedly connected with a supporting frame, and the right end of the supporting frame is fixedly connected with a U-shaped frame; the left side of the supporting leg is rotationally connected with a frame body, and a handle and a leg limiting roller are fixedly installed on the left side of the frame body. The multifunctional dumbbell stool has the advantage of multiple functions, and the problems that an existing dumbbell stool is single in function in the using process, the angles of a seat cushion, a back cushion and a leg limiting structure are inconvenient to adjust, the exercise requirements of users with different body types are difficult to meet, an elastic band is difficult to fix, and multiple training modes of the users are affected are solved.

A skeleton point extraction unit (102) that extracts skeleton points of an occupant based on an image capture, a correct sitting determination unit (104) that determines whether a state of a posture of the occupant is a correct sitting state based on status information about a status of the vehicle or the occupant, a feature calculation unit (105) that determines whether the skeleton points of the occupant extracted by the skeleton point extraction unit (102) are correct sitting skeleton points extracted based on the image capture in which the occupant was recorded in the correct sitting state, and in a case that the skeleton points of the occupant extracted by the skeleton point extraction unit (102) are correct sitting skeleton points, calculates a body structure determination feature based on the information about the correct sitting skeleton points,and a body type determination unit (107) is provided which judges the body type of the occupant based on the body type determination feature.,

The invention discloses an intelligent typesetting and cutting method for garment customization based on special body shape data, and aims to improve the automatic generation efficiency of garment customization, reduce the waste of cloth and improve the efficiency of the whole customization process. Comprising the following steps: S1: data input and processing: receiving and inputting body size data of a user, receiving suit style data selected by the user, and inputting cloth information including width, texture direction and elasticity modulus; s2, automatically generating a parameterized model: based on a preset parameterized model library, taking the body size and style data of the user as input parameters, and automatically generating a set of digital models, completely matched with the user, of all cut pieces of the western-style clothes; the parameterized model defines a mathematical relationship between each size and the shape of the garment piece, and ensures that the generated garment piece is fit and conforms to style aesthetics; s3, performing intelligent optimization typesetting; and S4, a cutting path planning and output module.

The utility model provides a safety belt connecting mechanism which comprises a safety belt connecting device and a connecting part. The connecting part is arranged on the seat or the safety cushion, the safety belt connecting device installed on the safety belt is connected with the connecting part, and the safety belt located on the belly when the safety belt is tied according to the existing technical specifications is pulled and fixed to the connecting part through the safety belt connecting device. Discomfort caused by pressing the abdomen of a passenger when the safety belt contracts can be avoided; according to the safety belt connecting mechanism, the plurality of inserting holes matched with the inserting ends and the locking pieces are arranged on the connecting part, so that proper positions can be selected for connection and fixation according to the body types of passengers, the safety belt connecting mechanism can be suitable for the passengers with different body types, and the use comfort is improved. According to the safety belt connecting device, the locking piece is arranged in a non-gear locking mode or a buckle matching mode, so that the safety belt connecting device can be stably connected with a connecting part on a seat or a safety cushion, and the safety belt connecting device is easy to operate and convenient to disassemble.

The invention discloses an intelligent human body modeling method and system based on a three-dimensional dot matrix, and relates to the field of intelligent modeling, and the method comprises the steps: carrying out the structural analysis of the semantic level of an original three-dimensional point cloud, and predicting a space displacement field pointing from the surface of observed clothes to the surface of an internal real human body under the semantic guidance. By applying the displacement field, double transformation of point cloud stripping and standardization is carried out on the point cloud, so that repeated fine tuning and optimization are carried out on the body type and posture parameters of the human body model in a standardized space, and finally a high-fidelity human body three-dimensional model is generated through driving. In this way, the complex clothes interference problem is deconstructed into a staged geometric mapping and parameter optimization process, and therefore the robustness and accuracy of human body three-dimensional reconstruction under the real wearing condition are effectively improved.

Eyewear providing an interactive augmented reality experience to allow a user of an eyewear device to display a 3D overlay image on a viewed person. The user can select the overlay image from a list of images, such as costumes, stored in memory or generated by the user. The images can be sorted in memory based on common attributes. Registration points of the person are continuously aligned with registration points of the overlay as the person moves such that the user appears to be wearing the 3D costume during movement. By aligning the registration points, the costume adapts to different body types and heights. The coloring of the costume can change based on the environment, such as the lighting, or to contrast with colors viewed in a viewfinder.

The invention discloses a dairy cow body shape and appearance judgment method based on key point detection and related equipment, and relates to the technical field of image processing. The method comprises the steps that each first image of a cow to be detected is acquired, and each first image comprises at least two continuous frames of images; inputting the first images into an appearance feature detection model, and obtaining key points output by the appearance feature detection model; correcting the key points in each first image to obtain a target key point based on an association relationship between the key points in each first image of at least two continuous frames; based on the pixel point distance between the target key points, determining the body shape and appearance of the to-be-detected dairy cow; wherein the appearance feature detection model is obtained by training a sample dairy cow image and a sample label, and the sample label is a pixel point corresponding to a key point representing the appearance feature of the dairy cow body type in the sample dairy cow image. By implementing the technical scheme provided by the invention, the problem of inaccurate key point positioning caused by the posture change of the dairy cow can be effectively solved, so that the accuracy of evaluating the body shape and appearance of the dairy cow is improved.

The utility model provides a clamping groove locking type safety belt connecting mechanism. The clamping groove locking type safety belt connecting mechanism comprises a safety belt connecting device and a connecting part. The connecting part is arranged on the seat or the safety cushion, the safety belt connecting device installed on the safety belt is connected with the connecting part, and the safety belt located on the belly when the safety belt is tied according to the existing technical specifications is pulled and fixed to the connecting part through the safety belt connecting device. Discomfort caused by pressing the abdomen of a passenger when the safety belt contracts can be avoided; the sliding groove matched with the connecting rod of the second connecting end and the limiting grooves matched with the connecting bases are formed in the connecting part, the connecting rod can move in the sliding groove, the appropriate limiting grooves are selected for connection and fixation according to the body types of passengers, the passenger seat can be suitable for the passengers of different body types, and the use comfort is improved. The safety belt connecting device and the connecting part are both made of high-strength materials, enough support and protection can be provided for passengers, and the safety performance is improved.

The invention relates to the technical field of costume design, in particular to an intelligent display system and method for costume design, and the method comprises the following steps: receiving a costume design sketch, employing a convolutional neural network to extract contour features, and generating a structured 3D costume model containing a layout topological relation and fabric physical parameters; obtaining user body type scanning data, and constructing a parameterized virtual human body with an anatomical level and soft tissue dynamic response capability; dynamic fitting of the garment model and a virtual human body is achieved through a physical simulation engine, and garment deformation behaviors changing along with actions are calculated; and analyzing the scene semantic tag input by the user, matching illumination, accessories and background elements in a preset material library, and generating an interactive 3D display scene with physical interaction and light and shadow effects. According to the method, the costume design modeling efficiency and simulation precision can be improved, intelligent matching of the costume style and scene semantics is realized, and the immersion of costume display and the user experience are enhanced.

The utility model discloses an orthopedic nursing traction support, which relates to the technical field of medical instruments, and comprises a bracket, an adjusting pad is arranged on one side of the bracket in a sliding and penetrating manner, the other side of the bracket is fixedly connected with a stand column, the bottom of the bracket is fixedly connected with an assembly block, and the lower end of the assembly block is provided with a first hydraulic oil cylinder. By means of the assembling block and the connecting shaft, the angle of the extension rods on the two sides is adjusted, the fixing device is suitable for patients of different body types, after the feet of the patients are fixed to the fixing base, the stability of the position of the fracture broken end can be maintained, shortening and displacement of the fracture broken end are overcome, fracture reduction is more accurate, and during follow-up rehabilitation training, the rehabilitation training efficiency is improved. The position of the sliding seat on the extension rod can be adjusted, the knee joint is driven to be bent in cooperation with rotation of the extension rod, and the provided traction force assists in functional exercise of limbs, promotes blood circulation, prevents amyotrophy and joint stiffness and accelerates recovery of limb functions.

The utility model discloses a landing buffering device of a single-body type hovercar and the single-body type hovercar, the single-body type hovercar is provided with an integrated power device, the integrated power device can be switched between a first position and a second position, and the landing buffering device is fixedly connected with the integrated power device. The landing buffer device comprises an undercarriage and damping wheels; wherein the damping wheels can be supported on the ground in a rolling mode when the integrated power device is located at the first position, and the landing buffering device and the ground can be arranged in a spaced mode when the integrated power device is located at the second position. Therefore, when the single-body type hovercar lands on the ground, the landing buffer device can reduce impact on the single-body type hovercar when the single-body type hovercar makes contact with the ground, and can prevent the integrated power device from colliding with the ground; the landing buffer device and the ground are arranged at an interval, so that the smoothness of the single-body type hovercar walking on the ground is guaranteed.

The invention discloses a self-adaptive waist tracking method, a computer readable storage medium and an intelligent seat, the self-adaptive waist tracking method is used for the intelligent seat, the intelligent seat is provided with a pressure sensor array and a waist support adjusting mechanism, and the method comprises the following steps: acquiring real-time pressure data of a current user collected by the pressure sensor array; extracting pressure characteristic parameters according to the real-time pressure data, and determining the body type category of the current user according to the pressure characteristic parameters by using a pre-trained body type recognition model; determining a current sitting posture type and an initial pressure threshold value of the current user according to the real-time pressure data by utilizing a pre-trained sitting posture recognition model; determining a target pressure threshold value according to the real-time pressure data, the body type category and the initial pressure threshold value; according to the target pressure threshold value, supporting parameters of a waist support adjusting mechanism are adjusted, so that the waist support is matched with the waist state of the user. According to the self-adaptive waist-following method, personalized waist-following adaptation of the user in multiple scenes is realized.

The invention discloses a wearable upper limb exoskeleton and a control method thereof. The wearable upper limb exoskeleton comprises a back support and two arm exoskeletons. Each arm exoskeleton comprises a plurality of translational connecting modules and a plurality of rotary connecting modules which are alternately connected, the back support is connected with one translational connecting module, each translational connecting module comprises a first sub-connecting part, a second sub-connecting part and a telescopic connecting rod joint, and the telescopic connecting rod joints are connected with the first sub-connecting parts and the second sub-connecting parts correspondingly; and the length of the translation connecting part is adjusted. According to the exoskeleton, the telescopic connecting rod joints are arranged in the multiple translation connecting modules and the multiple rotary connecting modules, the length of each translation connecting module can be adjusted, and the exoskeleton can adapt to the shoulder breadth and the large and small arm length of different users. The adjusted exoskeleton size can meet diversified body type requirements, the application range of the product is expanded, and the control method for automatically adjusting the exoskeleton model parameters improves the exoskeleton accurate control capacity.

The invention provides an athlete action evaluation method and system, and belongs to the technical field of data analysis, and the method comprises the steps: determining a target athlete category and a benchmark action sample corresponding to the target athlete category based on the target body type data of a target athlete, the benchmarking action sample comprises motion function parameters and action data of the benchmarking athlete; determining motion function difference data based on the target motion function parameters of the target athlete and the motion function parameters of the benchmarking athlete; adjusting the initial motion change rate threshold value based on the motion function difference data to obtain a target motion change rate threshold value; acquiring target action data of the target athlete, and calculating an action change rate based on the target action data; determining a target key frame based on a size relationship between the action change rate and a target action change rate threshold; and determining an action evaluation result based on the action parameter corresponding to the target key frame and the action data of the benchmarking athlete. The accuracy of athlete action assessment can be improved.