A method and system for generating adaptive fixed protective gear

By obtaining user video information, building three-dimensional models and setting adaptive solutions, optimizing materials with comfort requirements, and generating personalized fixed protective gear, the problem that traditional protective gear cannot adapt to personalized needs is solved, and efficient adaptability and Comfort effect.

CN118557349BActive Publication Date: 2024-11-15JIAXING BOJI MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410607083.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-15
Estimated Expiration
2044-05-16

AI Technical Summary

Technical Problem

Traditional fixed protective gear cannot adapt to the personalized needs and physiological characteristics of different users, resulting in poor fixation effects and uncomfortable wear.

Method used

By obtaining the video information of the target user, analyzing and building a three-dimensional model, setting an adaptive scheme based on the user's characteristic information, performing protective gear generation simulation, optimizing material selection in combination with comfort requirements, and generating personalized adaptive fixed protective gear.

Benefits of technology

The efficient adaptability and comfort of the protective gear is achieved, ensuring that the protective gear can fit the target part perfectly, providing sufficient protection and ensuring comfort and convenience during wear.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118557349B_ABST
    Figure CN118557349B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of fixed protective gear, and provides a method and system for generating an adaptive fixed protective gear. The method comprises: obtaining a target video, recording the video information of the target part of the target user based on a predetermined shooting plan; analyzing the video to obtain multiple part images, and constructing a target three-dimensional model; setting an adaptive plan according to predetermined characteristic indicators; using the adaptive plan as a constraint simulation to generate a fixed protective gear structure; obtaining the comfort requirements of the target user, analyzing the protective gear material database to obtain the target protective gear material; combining the protective gear structure and the protective gear material to generate an adaptive fixed protective gear for the target user. The present application solves the technical problem that traditional fixed protective gear cannot adapt to the personalized needs and physiological characteristics of different users, resulting in poor fixing effect of the protective gear and uncomfortable wearing, and realizes obtaining the protective gear structure and protective gear material according to the part characteristics and comfort requirements of the target user, thereby improving the adaptability and comfort of the protective gear.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical engineering technology, specifically to the field of fixed brace technology, and in particular to a method and system for generating an adaptive fixed brace. Background Art

[0002] With the growing demand for medical health, sports rehabilitation and personal protection, fixed protective gear plays an increasingly important role in protecting the human body from injury and promoting rehabilitation. However, with the diversification of application scenarios and the increase in personalized needs, traditional fixed protective gear has gradually revealed its limitations. Traditional fixed protective gear often relies on pre-designed templates or standardized sizes, and cannot fully take into account the unique physiological characteristics, exercise habits and comfort needs of each user. This leads to deficiencies in the adaptability, comfort and functionality of fixed protective gear, which makes it difficult to meet the requirements of modern medical and personal protection fields for efficiency, precision and personalization. Summary of the invention

[0003] The present application provides a method and system for generating an adaptive fixed protective gear, aiming to solve the technical problem that traditional fixed protective gear cannot adapt to the personalized needs and physiological characteristics of different users, resulting in poor fixing effect of the protective gear and uncomfortable wearing.

[0004] In view of the above problems, the present application provides a method and system for generating an adaptive fixed protective gear.

[0005] In a first aspect disclosed in the present application, a method for generating an adaptive fixed protective gear is provided, the method comprising: obtaining a target video, the target video referring to video information of a target part of a target user collected based on a predetermined shooting scheme; analyzing the target video to obtain a target image set, the target image set including a plurality of part images; constructing a target three-dimensional model of the target part based on a point cloud data set of the plurality of part images; setting a target adaptive scheme according to target feature information of the target user collected based on predetermined feature indicators; performing a fixed protective gear generation simulation on the target three-dimensional model with the target adaptive scheme as a simulation constraint to obtain a target protective gear structure; obtaining a target comfort requirement of the target user, and performing an optimization analysis on a protective gear material database with the target comfort requirement as a constraint to obtain a target protective gear material; and generating a target adaptive fixed protective gear for the target user by combining the target protective gear structure with the target protective gear material.

[0006] Another aspect disclosed in the present application provides an adaptive fixed brace generation system, the system comprising: a video information acquisition module, the video information acquisition module is used to obtain a target video, the target video refers to the video information of the target part of the target user acquired based on a predetermined shooting plan; a target video analysis module, the target video analysis module is used to analyze the target video to obtain a target image set, the target image set includes multiple part images; a three-dimensional model construction module, the three-dimensional model construction module is used to construct a target three-dimensional model of the target part based on a point cloud data set of the multiple part images; a plan setting module, the plan setting module is used to The target feature information of the target user collected by the predetermined feature index sets a target adaptive scheme; a protective gear simulation module, the protective gear simulation module is used to perform fixed protective gear generation simulation on the target three-dimensional model with the target adaptive scheme as a simulation constraint to obtain a target protective gear structure; an optimization analysis module, the optimization analysis module is used to obtain the target comfort requirement of the target user, and perform optimization analysis on the protective gear material database with the target comfort requirement as a constraint to obtain the target protective gear material; an adaptive protective gear generation module, the adaptive protective gear generation module is used to combine the target protective gear structure with the target protective gear material to generate the target adaptive fixed protective gear for the target user.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The above-mentioned adaptive fixed protective gear generation method obtains video information of a specific part of a target user through a predetermined shooting scheme, and this video will serve as the basis for subsequent analysis and modeling. Subsequently, these videos are analyzed to extract multiple images of key parts. A three-dimensional model of the target part is then constructed based on the images of multiple key parts, and this model can very accurately reflect the shape and size of the user's part. After that, an adaptive protective gear design scheme is formulated according to pre-set characteristic indicators. This scheme will ensure that the protective gear can perfectly fit the target part while providing necessary protection. Based on this adaptive scheme, simulation is performed on the three-dimensional model to simulate the generation process of the protective gear. Through this simulation, a preliminary designed protective gear structure can be obtained. Then, the comfort requirements of the target user are obtained, and then these requirements information are used to search and optimize the protective gear material database to find the most suitable protective gear material for the target user. Finally, the obtained protective gear structure and the selected protective gear material are combined to generate an adaptive fixed protective gear that fully adapts to the target user. This protective gear can not only provide sufficient protection, but also ensure the comfort and convenience of the user when wearing it.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 The figure is a flow chart of a method for generating an adaptive fixed protective gear in one embodiment.

[0012] Figure 2 A system architecture diagram is generated for an adaptive brace in one embodiment.

[0013] Explanation of the accompanying drawings: video information acquisition module 1, target video analysis module 2, three-dimensional model construction module 3, solution setting module 4, protective gear simulation module 5, optimization analysis module 6, adaptive protective gear generation module 7. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a method and system for generating an adaptive fixed protective gear to solve the technical problem that traditional fixed protective gear cannot adapt to the personalized needs and physiological characteristics of different users, resulting in poor fixing effect of the protective gear and uncomfortable wearing.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0017] Embodiment 1

[0018] like Figure 1As shown, the present application provides a method for generating an adaptive fixed brace, the method comprising:

[0019] A target video is obtained, where the target video refers to video information of a target part of a target user collected based on a predetermined shooting plan.

[0020] With the rapid development of modern society, people's demands for health, safety and personalization are growing. In sports competition, rehabilitation training, industrial production and daily life, fixed protective gear is widely used as an important auxiliary tool to protect the body from injury and promote rehabilitation.

[0021] In an embodiment of the present application, when obtaining video information of the target part of the target user, the system terminal collects video information according to a predetermined shooting scheme. This predetermined shooting scheme includes two core elements, namely shooting distance and shooting angle. This shooting distance is determined according to the size, shape and degree of detail of the target part to be captured. An appropriate shooting distance can ensure that the system terminal can clearly observe the overall morphology of the target part while capturing key detail information, providing an accurate data basis for subsequent three-dimensional modeling and protective gear design. The shooting angle is determined according to the characteristics of the target part and the angle to be displayed. By adjusting the shooting angle, the target part can be observed from multiple perspectives to obtain more comprehensive information. This is crucial for subsequent three-dimensional model construction and fixed protective gear design because it can ensure that the protective gear achieves the best results in terms of adaptability and functionality. In summary, through a predetermined shooting scheme, high-quality target video information can be obtained, providing strong support for subsequent adaptive fixed protective gear generation.

[0022] The target video is analyzed to obtain a target image set, wherein the target image set includes a plurality of part images.

[0023] In one embodiment, the system terminal compresses the video, analyzes it frame by frame, extracts two adjacent images for feature value deviation analysis, and compares them with a predetermined deviation threshold. Subsequently, based on the comparison result, it is determined whether the compressed video needs to be segmented to obtain multiple segmented video segments. After that, each segmented video segment is offset registered to obtain a target image set. This target image set includes multiple part images, providing reliable data support for subsequent three-dimensional model construction and protective gear design.

[0024] Further, the present application provides analyzing the target video to obtain a target image set, including:

[0025] The target video is compressed to obtain a target compressed video; a first image and a second image in the target compressed video are extracted in sequence, wherein the first image and the second image are adjacent images; and it is determined whether the image feature value deviation between the first image and the second image meets a predetermined deviation threshold.

[0026] Preferably, in order to efficiently obtain the target image set, the system terminal compresses the original target video to obtain a compressed version, namely the target compressed video. During the compression process, redundant information in the video will be removed as much as possible, while maintaining the integrity and recognizability of the video content. Subsequently, two adjacent images, namely the first image and the second image, are extracted from the target compressed video in sequence. The two images are continuous in time, reflecting the dynamic changes of the target part in a short period of time. Afterwards, the system terminal analyzes the texture features of the first image and the second image through the discrete cosine transform principle to obtain two eigenvalues. The two eigenvalues ​​correspond one to one with the first image and the second image. Then, based on the two eigenvalues ​​obtained, the system terminal calculates the image eigenvalue deviation, that is, the degree of difference between them. Finally, the system terminal determines whether this deviation value meets the predetermined deviation threshold, and determines whether to perform subsequent video segmentation operations based on the judgment result.

[0027] If it does not match, the target compressed video is segmented with the first image and the second image as the boundary to obtain a target segmentation result; multiple frames of images in the first segmented video segment are offset and aligned to obtain a first part image, wherein the first segmented video segment refers to any segmented fragment in the target segmentation result; and the target image set is established based on the first part image.

[0028] Preferably, when it is analyzed that the characteristic value deviation between the first image and the second image exceeds a predetermined threshold, the system terminal will segment the target compressed video according to the two images. This segmentation process is to divide the video into different segments based on the two images to generate a target segmentation result. Subsequently, the system terminal selects a segmented segment in the target segmentation result, namely the first segmented video segment, and extracts key feature points from each frame image of the first segmented video segment. After that, the extracted feature points are converted into feature vectors of fixed length using the scale-invariant feature transform (SIFT) method, so that similar feature points in different images can be represented in the same format. Then, the angle between the two feature vectors is calculated by cosine similarity to quantify the degree of difference between the two feature vectors, thereby evaluating the similarity between the two feature points. After calculating the similarity between all feature points, the system terminal determines the best matching pair. Further, the system terminal calculates the transformation parameters between the images in the first segmented video segment based on the matched feature points, including parameters of geometric transformations such as translation, rotation, and scaling. Subsequently, each frame image in the first segmented video segment is transformed using the calculated transformation parameters to align it with the first frame. When necessary, the system terminal performs interpolation operations to ensure that the transformed image remains smooth and continuous. For example, pixel-level misalignment caused by rotation. Afterwards, the system terminal merges all transformed frame images into a continuous sequence and performs appropriate cropping to remove unnecessary parts. This sequence is offset-registered, that is, each frame in it is consistent with the first frame in position. Then, the system terminal extracts a clear and representative frame from the registered sequence as the first part image. This image can accurately reflect the morphology and characteristics of the target part in the video segment. Finally, the system terminal adds the first part image to the target image set. The target image set is a set of multiple key images used for subsequent three-dimensional model construction and protective gear design. By continuously extracting and adding part images from each segmented video segment, a complete and accurate target image set can be gradually constructed, providing strong support for subsequent work.

[0029] Furthermore, the present application provides a method for determining whether a deviation of image feature values ​​between the first image and the second image meets a predetermined deviation threshold, the method further comprising:

[0030] Based on the discrete cosine transform principle, a first discrete cosine transform coefficient of the first image is obtained; and a first AC coefficient in the first discrete cosine transform coefficient is standardized to obtain a first eigenvalue.

[0031] Optionally, in order to extract texture features related to the part structure from the first image, the system terminal adopts the discrete cosine transform (DCT) principle. Discrete cosine transform is a mathematical tool used for image processing and signal processing, which can convert image signals from the spatial domain to the frequency domain, thereby facilitating analysis and processing. First, the system terminal divides the first image into multiple 8x8 sub-blocks. This is because discrete cosine transform is more effective when applied to smaller data blocks. A one-dimensional discrete cosine transform is applied to each sub-block, and a discrete cosine transform is performed on each row, and then the result is used as input to perform a discrete cosine transform on each column. After that, the system terminal outputs the discrete cosine transform result, and the transform result is a coefficient matrix of the same size as the original sub-block. The elements in this matrix are discrete cosine transform coefficients. In this coefficient matrix, the element in the upper left corner, that is, the first element, is a direct current (DC) coefficient, which represents the average brightness of the entire sub-block. All coefficients except the DC coefficient are alternating current (AC) coefficients, which contain texture and structural information of the image. Then, the system terminal extracts the AC coefficients in the first discrete cosine transform coefficients because they are directly related to the texture features of the image. In order to eliminate the differences between different images due to factors such as brightness and contrast, these AC coefficients are standardized. Standardization includes subtracting the mean and dividing by the standard deviation, so that the texture features between different images can be compared on a unified scale. After standardization, the first eigenvalues ​​of the first image are obtained. These eigenvalues ​​take into account the texture features in the image, that is, the structural information of the part. These eigenvalues ​​will serve as the basis for subsequent analysis, comparison or recognition, helping the system terminal to understand and process image data more accurately.

[0032] Acquire a second eigenvalue of the second image; and use an absolute value of a difference between the first eigenvalue and the second eigenvalue as the image eigenvalue deviation.

[0033] Optionally, the system terminal performs a discrete cosine transform on the second image to obtain the second eigenvalue using the same method as the above method for obtaining the first eigenvalue. Subsequently, the system terminal calculates the difference between the first eigenvalue and the second eigenvalue, takes their absolute values, and uses this absolute value as the image eigenvalue deviation. The image eigenvalue deviation measures the degree of difference between the two images in specific features. If the deviation value is very small, it means that the two images are very similar in features; conversely, if the deviation value is very large, it means that there are significant differences in features between the two images.

[0034] A target three-dimensional model of the target part is constructed based on the point cloud data set of the multiple part images.

[0035] In one embodiment, the system terminal extracts point cloud data from multiple part images. The point cloud data contains the three-dimensional coordinates, reflection intensity and color information of the target part, and is the basis for building a three-dimensional model. Subsequently, these point cloud data are used to build a three-dimensional model that can more accurately represent the three-dimensional structure of the target part. This process involves multiple steps, including building a part registration fusion model, generating a consistent point set, and building a target three-dimensional model. In summary, building a three-dimensional model of the target part based on a point cloud data set of multiple part images is a complex but important process. It involves multiple steps, and the final model can more accurately represent the three-dimensional structure and features of the target part, providing important support for subsequent fixed brace simulation.

[0036] Furthermore, the present application provides a method for constructing a target three-dimensional model of the target part based on the point cloud data set of the plurality of part images, and the method further includes:

[0037] A part registration fusion model is constructed using the principle of random sampling consistency algorithm; the part registration fusion model randomly samples from the point cloud data set to obtain a first sample set, and obtains a first estimated parameter of a first model based on the first sample set; the first sample set is removed from the point cloud data set to obtain a first non-sample set, wherein the first non-sample set includes multiple non-sample point cloud data.

[0038] Preferably, the system terminal builds a model framework, which is the basic structure for building the part registration fusion model. It defines the overall workflow of the model, the input and output interfaces, and the basic process of data processing. Subsequently, a random sampling consensus (RANSAC) algorithm is integrated into this model framework to form a part registration fusion model. Through the random sampling consensus algorithm, the part registration fusion model can randomly sample a part of the data points from the point cloud data set to form a first sample set, and this first sample set will be used to preliminarily estimate the parameters of the three-dimensional model. After that, based on the first sample set, the part registration fusion model will generate an initial registration hypothesis model, i.e., the first model. This hypothesis describes how to align or fuse multiple point cloud data of the target part, and this hypothesis is a rigid transformation, including rotation and translation, used to describe the relative position relationship between point clouds. After generating the initial hypothesis, the part registration fusion model will estimate the parameters in this hypothesis based on the first sample set, i.e., the first estimated parameters of the first model. These parameters define how to transform a point cloud to a position aligned with another point cloud. After obtaining the first estimated parameters, the system terminal removes the first sample set from the original point cloud data set, leaving the unselected data points, namely the first non-sample set. The first non-sample set contains multiple non-sample point cloud data that were not used to estimate the model parameters in the previous steps, but they are still important information required to build a complete 3D model.

[0039] The distances from the plurality of non-sample point cloud data to the first model are calculated in sequence, and the plurality of non-sample point cloud data are screened in combination with a preset distance threshold to obtain a first consistency point set.

[0040] Preferably, the system terminal initializes a variable to store the shortest distance to the first model point set and a variable to store the corresponding nearest point for each point in the non-sample point cloud data. The initial shortest distance is infinite and the initial nearest point is empty data. Subsequently, each point in the first model point set is traversed again. For the current point in the non-sample point cloud data, the distance between this point and the current point in the first model point set is calculated by Euclidean distance. If the calculated distance is less than the previously stored nearest distance, the values ​​of the nearest distance and the nearest point are updated. After traversing all points in the first model point set, the system terminal obtains the nearest distance and the corresponding nearest point from the current point in the non-sample point cloud data to the first model point set. After that, the above process is repeated for each point in the non-sample point cloud data until the nearest distance and the nearest point of all points to the first model point set are calculated. Then, according to the preset distance threshold, points whose distance is less than or equal to the threshold are screened out to form a first consistency point set. The preset distance threshold is determined based on actual needs and data characteristics, and is used to determine which points are consistent with the first model. The first consistent point set includes all points close to the first model and is used for subsequent analysis and comparison.

[0041] Calculate the first data volume in the first consistency point set, and determine whether the first data volume meets a preset quantity threshold; if the first data volume does not meet the preset quantity threshold, obtain a first re-estimation instruction; according to the first re-estimation instruction, obtain the second estimated parameters of the first model based on the first consistency point set.

[0042] Preferably, after obtaining a first consistency point set close to the first model, the system terminal calculates the number of points in this point set, i.e., the first data volume. This number represents how many points are judged to be consistent with the model. Subsequently, the system terminal compares this first data volume with a preset quantity threshold. This quantity threshold is pre-set according to actual needs, and it represents the minimum number of points required to accurately estimate the model parameters. If the first data volume does not meet the preset quantity threshold, i.e., the size of the point set is not large enough, the system terminal determines that the current model estimation is not accurate enough and requires further evaluation and adjustment, and generates a first re-estimation instruction, which instructs the system terminal to re-estimate the parameters of the first model based on the existing first consistency point set. After obtaining the first re-estimation instruction, the system terminal uses the same method as above to re-estimate the parameters of the first model based on the first consistency point set, and obtains a new set of model parameters, i.e., the second estimated parameters, which can better reflect the characteristics of the first consistency point set, thereby improving the accuracy of the subsequent construction of the target three-dimensional model.

[0043] The first estimation parameters are replaced by the second estimation parameters as target estimation parameters; and the target three-dimensional model is constructed based on the target estimation parameters.

[0044] Preferably, the system terminal uses the obtained second estimated parameters to replace the initially obtained first estimated parameters as target estimated parameters for constructing the target three-dimensional model. This process involves creating a basic framework of the target three-dimensional model using basic geometric bodies based on three-dimensional reconstruction technology, then applying the previously obtained target estimated parameters to the basic framework, and adjusting the corresponding parts of the basic framework according to the parameters to ensure that the constructed target three-dimensional model meets actual needs.

[0045] Furthermore, the present application provides that the first data volume satisfies the preset quantity threshold, and the method further includes:

[0046] If the first data volume meets the preset quantity threshold, the first estimation parameter is used as the target estimation parameter.

[0047] Optionally, if the first data volume meets a preset quantity threshold, then it means that the current first estimated parameter has sufficiently accurately reflected the characteristics of the model. In this case, the system terminal does not need to perform subsequent re-estimation operations, but directly uses the first estimated parameter as the target estimated parameter for constructing the target three-dimensional model.

[0048] A target adaptation scheme is set according to the target feature information of the target user collected based on predetermined feature indicators.

[0049] In one embodiment, the system terminal collects the target feature information of the target user according to the predetermined feature index to set the target adaptive scheme, which is a process of personalized setting for the specific needs of the user. Among them, the predetermined feature index refers to the target user's demand for the effectiveness of the fixed protective gear. For example, the comfort of the protective gear, the range of the protective gear, etc. By collecting these target feature information of the target user, the system terminal sets a target adaptive scheme, which aims to provide a configuration of fixed protective gear that meets the personalized needs of the user. When setting the target adaptive scheme, the system terminal will also analyze some feature information in addition to the basic predetermined feature indicators such as comfort and protective gear range, including the user's activity habits, injured parts, etc. The comprehensive analysis of this information can help the system terminal predict the needs of the user more accurately and customize a personalized adaptive scheme accordingly. For example, if the target user is an athlete who often performs high-intensity sports, the target adaptive scheme formulated by the system terminal will tend to have a higher protective gear strength and protective gear range to meet the target user's needs to reduce the risk of injury. Through this process, the system formulates a fixed protective gear configuration that can provide more in line with user needs, thereby improving the satisfaction and user experience of the target user.

[0050] Furthermore, the present application provides a predetermined characteristic indicator, and the method further includes:

[0051] The predetermined characteristic indicators include protective gear strength requirements and protective gear range requirements.

[0052] Preferably, the predetermined characteristic indicators set by the system terminal include the protective gear strength requirement and the protective gear range requirement. Specifically, the protective gear strength requirement reflects the target user's requirements for the strength of the protective gear to provide support and protection. For example, some users may need high-strength protective gear to stabilize joints or prevent injuries, while some users may prefer moderate or lightweight protective gear to maintain flexibility. The protective gear range requirement refers to the user's expectation of the size or range of the body part covered by the protective gear, which depends on the user's injured part, activity type, and personal comfort preference. Through these predetermined characteristic indicators, the system terminal can more accurately understand the user's personalized needs, thereby customizing a more suitable protective gear adaptive solution for the target user. Such a solution can not only meet the user's actual use needs, but also improve the user's overall satisfaction and comfort.

[0053] The target adaptive scheme is used as a simulation constraint to perform fixed protective gear generation simulation on the target three-dimensional model to obtain a target protective gear structure.

[0054] In one embodiment, after determining the target adaptive scheme, the system terminal uses this scheme as a constraint condition for the simulation, and simulates the generation of fixed protective gear for the previously constructed target three-dimensional model. The purpose of this simulation is to simulate the structure of fixed protective gear suitable for the user based on the personalized needs of the user. Specifically, the simulation process will consider various parameters in the target adaptive scheme, such as the strength requirements of the protective gear and the range requirements of the protective gear, to ensure that the generated protective gear structure can fully meet the specific needs of the user. Through simulation, various situations of the protective gear in actual use, such as wearing comfort, support effect, etc., can be simulated, so as to continuously optimize the structural design of the protective gear. Finally, through this process, the system terminal obtains a target protective gear structure that meets the personalized needs of the user. This structure can not only meet the basic functional requirements of the user for the protective gear, but also ensure that the user obtains the best comfort and support effect during use.

[0055] The target comfort requirement of the target user is obtained, and the protective gear material database is optimized and analyzed with the target comfort requirement as a constraint to obtain the target protective gear material.

[0056] In one embodiment, in the process of generating the target protective gear structure, in addition to considering the mechanical properties and coverage of the protective gear, the comfort requirements of the target user also need to be considered. In order to meet this demand, the system terminal clarifies the target user's specific expectations and requirements for the comfort of the protective gear, which includes considerations of the material, weight, breathability, and other aspects of the protective gear. Once the target comfort requirements of the target user are obtained, the system terminal uses this requirement as a constraint condition to perform an optimization analysis on the pre-established protective gear material database. This database usually contains various protective gear materials and corresponding performance parameters, such as lightness, breathability, strength, etc., which directly affect the comfort and service life of the protective gear. Through optimization analysis, the system terminal selects materials in the database that can meet both the mechanical performance requirements of the protective gear and the comfort requirements of the user. This process involves comparing the materials in the protective gear material database in pairs until the material with the highest comfort is selected under the constraint of the target comfort requirements of the target user. This material is the most suitable protective gear material for the target user, that is, the target protective gear material. In summary, by optimizing the protective gear material database and finding the most suitable protective gear material for the user, we can ensure that the generated protective gear not only meets the functional needs of the target user, but also has a high degree of comfort to meet the user's personalized needs.

[0057] Furthermore, the present application provides a method for obtaining the target comfort requirement of the target user, and performing an optimization analysis on a protective gear material database with the target comfort requirement as a constraint to obtain the target protective gear material, and the method further includes:

[0058] The target comfort requirement includes the target user's requirement for lightweight protective gear and a lightweight requirement weight, breathability requirement and a breathability requirement weight, strength requirement and a strength requirement weight, thermal resistance requirement and a thermal resistance requirement weight; extracting a first data group of a first protective gear material from the protective gear material database.

[0059] Preferably, the target comfort requirement determined by the system terminal is the target user's expectations and attention to the protective gear in multiple key aspects, including the lightweight, breathability, strength and thermal resistance of the protective gear. These requirements not only reflect the target user's basic performance requirements for the protective gear, but also reflect the target user's personalized preferences and usage scenarios. At the same time, the system terminal is assigned a corresponding weight to each requirement, which helps to more accurately balance the trade-offs between various performances in the subsequent material selection process. These weights are determined according to the actual application scenarios of the target user. Subsequently, the system terminal randomly extracts a protective gear material from a pre-established protective gear material database as the first protective gear material, and extracts the corresponding performance parameters as the first data group. Among them, the protective gear material database contains a variety of protective gear materials, such as plaster, plastic brackets, metal brackets, bandages and other wearable devices, and each material has a set of corresponding performance parameters in the database. These parameters describe the specific performance of the material in terms of lightweight, breathability, strength, thermal resistance, etc., and are the key basis for evaluating whether the material is suitable for the needs of the target user.

[0060] The first data group is analyzed in combination with the target comfort requirement to obtain a first comfort of the first protective gear material; the first comfort is compared with a second comfort of a second protective gear material obtained in the protective gear material database to obtain a comparison result; and the target protective gear material is determined according to the comparison result.

[0061] Preferably, the system terminal performs weighted processing on the performance parameters in the first data group according to the comfort requirements and weights of the target user to calculate the first comfort of the first protective gear material. This comfort represents the performance of the material in meeting the user's comfort requirements. Subsequently, the system terminal repeats the same method as the above-mentioned extraction of the first data group to obtain the second data group of the second protective gear material, and then performs the same analysis on the second protective gear material to obtain the second comfort of the second protective gear material. After obtaining the first comfort and the second comfort, the system terminal compares the two comforts to obtain a comparison result. This comparison result retains the material with the highest comfort and the corresponding comfort of the two materials. After that, the system terminal extracts a protective gear material from the protective gear material database again, repeats the above process, and compares the calculated comfort with the comfort in the comparison result. If it is greater than the comfort in the comparison result, the system terminal replaces the content in the comparison result with the newly extracted protective gear material and the corresponding comfort. If it is less than the comfort in the comparison result, the system terminal repeats the extraction operation until all the protective gear materials in the protective gear material database are compared for comfort. Then, the system terminal determines the most suitable protective gear material for the target user based on the final comparison results, namely the target protective gear material. This selection process comprehensively considers the target user's multiple comfort needs and their weights, ensuring that the final selected protective gear material can meet the user's expectations in many aspects.

[0062] The target protective gear structure and the target protective gear material are combined to generate a target adaptive fixed protective gear for the target user.

[0063] In one embodiment, after determining the target protective gear structure and target protective gear material, the system terminal generates the target adaptive fixed protective gear required by the target user based on this information. Specifically, the system terminal first uses 3D printing technology to build the skeleton and shape of the protective gear according to the design requirements of the target protective gear structure to ensure that it can accurately cover and protect the user's injured part or the area that needs support. At the same time, according to the performance parameters of the target protective gear material, the corresponding materials are selected to manufacture the various parts of the protective gear to ensure that the protective gear has good comfort, air permeability and thermal resistance while providing sufficient support. The target adaptive fixed protective gear finally generated is a highly customized product that fully meets the personalized needs of users. It can not only meet the needs of users in terms of function, but also meet the expectations of users in terms of comfort and user experience, thereby providing users with better protection and user experience.

[0064] In summary, the embodiments of the present application have at least the following technical effects:

[0065] The embodiment of the present application collects video information of the target part of the target user, extracts key frame images through video compression and image processing technology, and then constructs a three-dimensional model of the target part. Subsequently, based on the specific needs and physical characteristics of the user, a target adaptive scheme is set, and this scheme is used as a simulation constraint to simulate the generation of fixed protective gear for the three-dimensional model, and simulate the protective gear structure that meets the user's needs. In terms of material selection, the user's comfort needs, such as lightness, breathability, strength and thermal resistance, are deeply considered, and the target protective gear material that best suits the target user is determined by optimizing the protective gear material database. Afterwards, the target protective gear structure and the target protective gear material are combined to generate a target adaptive fixed protective gear that meets the personalized needs of the user. These technical effects jointly solve the technical problems that traditional fixed protective gear cannot adapt to the personalized needs and physiological characteristics of different users, resulting in poor protective gear fixing effect and uncomfortable wearing, and realize the effect of obtaining protective gear structure and protective gear material according to the position characteristics and comfort needs of the target user, and improving the adaptability and comfort of the protective gear.

[0066] Embodiment 2

[0067] Based on the same inventive concept as the method for generating an adaptive fixed protective gear in the aforementioned embodiment, Figure 2 As shown, the present application provides an adaptive fixed brace generation system, the system comprising:

[0068] Video information acquisition module 1: the video information acquisition module 1 is used to acquire a target video, wherein the target video refers to video information of a target part of a target user acquired based on a predetermined shooting scheme;

[0069] Target video analysis module 2: the target video analysis module 2 is used to analyze the target video to obtain a target image set, and the target image set includes multiple part images;

[0070] Three-dimensional model construction module 3: the three-dimensional model construction module 3 is used to construct a target three-dimensional model of the target part based on the point cloud data set of the multiple part images;

[0071] Solution setting module 4: the solution setting module 4 is used to set a target adaptive solution according to the target feature information of the target user collected based on the predetermined feature index;

[0072] Protective gear simulation module 5: the protective gear simulation module 5 is used to perform fixed protective gear generation simulation on the target three-dimensional model with the target adaptive scheme as a simulation constraint to obtain a target protective gear structure;

[0073] Optimization analysis module 6: the optimization analysis module 6 is used to obtain the target comfort requirements of the target user, and perform optimization analysis on the protective gear material database with the target comfort requirements as constraints to obtain the target protective gear material;

[0074] Adaptive protective gear generation module 7: The adaptive protective gear generation module 7 is used to combine the target protective gear structure and the target protective gear material to generate the target adaptive fixed protective gear of the target user.

[0075] Furthermore, the target video analysis module 2 is also used to perform the following method:

[0076] Compressing the target video to obtain a target compressed video;

[0077] Sequentially extracting a first image and a second image from the target compressed video, wherein the first image and the second image are adjacent images;

[0078] Determining whether a deviation between the image feature values ​​of the first image and the second image meets a predetermined deviation threshold;

[0079] If not, segmenting the target compressed video using the first image and the second image as a boundary to obtain a target segmentation result;

[0080] Performing offset registration on multiple frames of images in a first segmented video segment to obtain a first part image, wherein the first segmented video segment refers to any segmented segment in the target segmentation result;

[0081] The target image set is constructed based on the first part image.

[0082] Furthermore, the target video analysis module 2 is also used to perform the following method:

[0083] Acquire a first discrete cosine transform coefficient of the first image based on a discrete cosine transform principle;

[0084] performing normalization processing on the first AC coefficient in the first discrete cosine transform coefficient to obtain a first eigenvalue;

[0085] Acquire a second eigenvalue of the second image;

[0086] The absolute value of the difference between the first eigenvalue and the second eigenvalue is used as the image eigenvalue deviation.

[0087] Furthermore, the three-dimensional model building module 3 is also used to execute the following method:

[0088] The part registration fusion model is constructed using the principle of random sampling consistency algorithm;

[0089] The part registration fusion model randomly samples from the point cloud data set to obtain a first sample set, and obtains a first estimated parameter of a first model based on the first sample set;

[0090] Eliminate the first sample set from the point cloud data set to obtain a first non-sample set, wherein the first non-sample set includes a plurality of non-sample point cloud data;

[0091] sequentially calculating the distances from the plurality of non-sample point cloud data to the first model, and screening the plurality of non-sample point cloud data in combination with a preset distance threshold to obtain a first consistency point set;

[0092] Calculating a first data volume in the first consistency point set, and determining whether the first data volume meets a preset quantity threshold;

[0093] If the first data amount does not meet the preset quantity threshold, obtaining a first re-evaluation instruction;

[0094] According to the first re-estimation instruction, obtaining second estimated parameters of the first model based on the first consistency point set;

[0095] replacing the first estimated parameter with the second estimated parameter as a target estimated parameter;

[0096] The target three-dimensional model is constructed based on the target estimation parameters.

[0097] Furthermore, the three-dimensional model building module 3 is also used to execute the following method:

[0098] If the first data volume meets the preset quantity threshold, the first estimation parameter is used as the target estimation parameter.

[0099] Furthermore, the scheme setting module 4 is also used to execute the following method:

[0100] The predetermined characteristic indicators include protective gear strength requirements and protective gear range requirements.

[0101] Furthermore, the optimization analysis module 6 is also used to perform the following method:

[0102] The target comfort requirements include the target user's requirements for lightness of protective gear and the weight of lightness requirement, breathability requirement and the weight of breathability requirement, strength requirement and the weight of strength requirement, thermal resistance requirement and the weight of thermal resistance requirement;

[0103] Extracting a first data group of a first protective gear material from the protective gear material database;

[0104] Analyzing the first data group in combination with the target comfort requirement to obtain a first comfort of the first protective gear material;

[0105] Comparing the first comfort with the second comfort of the second protective gear material obtained in the protective gear material database to obtain a comparison result;

[0106] The target protective gear material is determined according to the comparison result.

[0107] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0109] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for generating an adaptive fixed protective gear, characterized in that: The method comprises: Acquire a target video, where the target video refers to video information of a target part of a target user collected based on a predetermined shooting plan; Analyze the target video to obtain a target image set, wherein the target image set includes a plurality of part images; Constructing a target three-dimensional model of the target part based on the point cloud data set of the plurality of part images; Setting a target adaptation scheme according to target feature information of the target user collected based on predetermined feature indicators; Using the target adaptive scheme as a simulation constraint, a fixed protective gear generation simulation is performed on the target three-dimensional model to obtain a target protective gear structure; Obtaining the target comfort requirement of the target user, and performing optimization analysis on the protective gear material database with the target comfort requirement as a constraint to obtain the target protective gear material; Combining the target protective gear structure with the target protective gear material to generate a target adaptive fixed protective gear for the target user; The target comfort requirement of the target user is obtained, and the target comfort requirement is used as a constraint to perform optimization analysis on the protective gear material database to obtain the target protective gear material, including: The target comfort requirements include the target user's requirements for lightness of protective gear and the weight of lightness requirement, breathability requirement and the weight of breathability requirement, strength requirement and the weight of strength requirement, thermal resistance requirement and the weight of thermal resistance requirement; Extracting a first data group of a first protective gear material from the protective gear material database; Analyzing the first data group in combination with the target comfort requirement to obtain a first comfort of the first protective gear material; Comparing the first comfort with the second comfort of the second protective gear material obtained in the protective gear material database to obtain a comparison result; The target protective gear material is determined according to the comparison result.

2. The method according to claim 1, characterized in that: Analyzing the target video to obtain a target image set also includes: Compressing the target video to obtain a target compressed video; Sequentially extracting a first image and a second image from the target compressed video, wherein the first image and the second image are adjacent images; Determining whether a deviation between the image feature values ​​of the first image and the second image meets a predetermined deviation threshold; If not, segmenting the target compressed video using the first image and the second image as a boundary to obtain a target segmentation result; Performing offset registration on multiple frames of images in a first segmented video segment to obtain a first part image, wherein the first segmented video segment refers to any segmented segment in the target segmentation result; The target image set is constructed based on the first part image.

3. The method according to claim 2, characterized in that: Determining whether a deviation of image feature values ​​between the first image and the second image meets a predetermined deviation threshold includes: Acquire a first discrete cosine transform coefficient of the first image based on a discrete cosine transform principle; performing normalization processing on the first AC coefficient in the first discrete cosine transform coefficient to obtain a first eigenvalue; Acquire a second eigenvalue of the second image; The absolute value of the difference between the first eigenvalue and the second eigenvalue is used as the image eigenvalue deviation.

4. The method according to claim 1, characterized in that: Constructing a target three-dimensional model of the target part based on the point cloud data set of the plurality of part images includes: The part registration fusion model is constructed using the principle of random sampling consistency algorithm; The part registration fusion model randomly samples from the point cloud data set to obtain a first sample set, and obtains a first estimated parameter of a first model based on the first sample set; Eliminate the first sample set from the point cloud data set to obtain a first non-sample set, wherein the first non-sample set includes a plurality of non-sample point cloud data; sequentially calculating the distances from the plurality of non-sample point cloud data to the first model, and screening the plurality of non-sample point cloud data in combination with a preset distance threshold to obtain a first consistency point set; Calculating a first data volume in the first consistency point set, and determining whether the first data volume meets a preset quantity threshold; If the first data amount does not meet the preset quantity threshold, obtaining a first re-evaluation instruction; According to the first re-estimation instruction, obtaining second estimated parameters of the first model based on the first consistency point set; replacing the first estimated parameter with the second estimated parameter as a target estimated parameter; The target three-dimensional model is constructed based on the target estimation parameters.

5. The method according to claim 4, characterized in that: If the first data volume meets the preset quantity threshold, the first estimation parameter is used as the target estimation parameter.

6. The method according to claim 1, characterized in that: The predetermined characteristic indicators include protective gear strength requirements and protective gear range requirements.

7. An adaptive fixed protective gear generation system, characterized in that: The steps for implementing the method for generating an adaptive brace according to any one of claims 1 to 6 include: Video information acquisition module: acquiring a target video, wherein the target video refers to video information of a target part of a target user acquired based on a predetermined shooting plan; Target video analysis module: analyzing the target video to obtain a target image set, wherein the target image set includes a plurality of part images; A three-dimensional model building module: building a target three-dimensional model of the target part based on the point cloud data set of the plurality of part images; Solution setting module: setting a target adaptive solution according to the target feature information of the target user collected based on the predetermined feature index; Protective gear simulation module: using the target adaptive scheme as a simulation constraint to perform fixed protective gear generation simulation on the target three-dimensional model to obtain a target protective gear structure; Optimization analysis module: obtaining the target comfort requirements of the target user, and performing optimization analysis on the protective gear material database with the target comfort requirements as constraints to obtain the target protective gear material; An adaptive protective gear generation module is used to generate a target adaptive fixed protective gear for the target user by combining the target protective gear structure and the target protective gear material.