Method for measuring human body data by integrating visual sensor on mobile terminal

By integrating vision sensors in mobile terminals, detecting hardware and environment, guiding users to wear and move, collecting data and reconstructing three-dimensional models, the problem of being unable to accurately measure human body data in the existing technology is solved, and the accurate trial-on effect of the online platform is achieved, and the user experience is improved.

CN120510289AInactive Publication Date: 2025-08-19DOT CLOUD INTELLIGENCE (SHENZHEN) TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510605240.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-12
Publication Date
2025-08-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art cannot effectively utilize mobile terminals to provide users with accurate three-dimensional human data measurement and simulated wearable effects online, resulting in inconsistent effects when purchasing clothing and affecting customer experience.

Method used

Through the mobile terminal, visual sensors are integrated to detect hardware and environment, guide users to wear and move, collect data, process and reconstruct three-dimensional models, display and upload data, use RGB and TOF sensors to generate high-precision human models, combine AI algorithms and texture maps.

Benefits of technology

It realizes that users measure three-dimensional human data by themselves and generate accurate three-dimensional models for online platforms and virtual fittings, improving the experience of purchasing clothing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120510289A_ABST
    Figure CN120510289A_ABST
Patent Text Reader

Abstract

The invention discloses a method for measuring human body data by integrating a visual sensor on a mobile terminal. Hardware and environment detection: detecting built-in hardware of the mobile terminal, and detecting whether light in a measurement environment meets a measurement condition or not; guiding measurement, informing the measured person of the wearing requirement during measurement, and detecting and prompting the position range and the motion amplitude of the measured person during shooting; data acquisition, including a dynamic mode and a static mode, and completing corresponding data acquisition in the corresponding dynamic mode and static mode; data processing and modeling, de-noising and filtering, and model reconstruction; and data display and data uploading: displaying the established 3D model through a mobile terminal, and uploading the data. According to the method for measuring the human body data by integrating the visual sensor on the mobile terminal, through the mode of the mobile terminal, a customer can conveniently scan the three-dimensional data of the customer by himself / herself, and therefore a corresponding three-dimensional model is generated for wearing simulation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of measuring human body data, and in particular to a method for measuring human body data by integrating a mobile terminal with a visual sensor. Background Art

[0002] Currently, when people buy clothes online, they cannot try them on and can only judge the effect on the upper body by looking at the model wearing the product. However, everyone's height, weight, measurements and other data are different. As a result, after purchase, the effect of different users wearing the clothes on themselves will be inconsistent with the model's display, resulting in problems such as returns and exchanges, affecting the customer's purchasing experience.

[0003] Currently, some online platforms allow customers to manually input their height, weight, measurements and other data into the platform, and recommend suitable clothing based on the customer's data. However, the data entered by the customer is only partial data, and it is impossible to accurately produce the corresponding three-dimensional model for wearing simulation, which also results in the inability to effectively show the customer the simulated effect of wearing the upper body. Therefore, there is a need for a method that can facilitate customers to provide accurate three-dimensional data themselves, so as to perform wearing simulation based on the three-dimensional data and provide a better purchasing experience. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for measuring human body data by integrating a mobile terminal with a visual sensor, which allows customers to scan their own three-dimensional data through a mobile terminal, thereby generating a corresponding three-dimensional model for wear simulation.

[0005] The technical solution adopted by the method for measuring human body data by integrating a mobile terminal with a visual sensor disclosed in the present invention is:

[0006] A method for measuring human body data by integrating a mobile terminal with a visual sensor comprises the following steps:

[0007] Hardware and environment testing: testing the built-in hardware of the mobile terminal to determine whether it is equipped with the required visual sensors, and testing whether the light in the measurement environment meets the measurement conditions;

[0008] Measurement guidance: informing the subject of the clothing requirements during measurement, detecting and prompting the subject's position range and movement range during photography;

[0009] Data collection, including dynamic mode and static mode, obtains mobile terminal sensor information as described above and automatically switches to the corresponding collection mode according to the sensor type in the information. In dynamic mode, the subject needs to rotate to capture full-body data; in static mode, the subject needs to pose in a specified position and take one or more photos to complete the corresponding data collection;

[0010] Data processing and modeling, denoising and filtering: Remove sensor noise or outliers through methods such as Gaussian filtering and statistical filtering; Model reconstruction: Human body modeling based on visual sensors uses color / texture information or depth data, combined with parametric human body models or 3D reconstruction technology to generate high-precision meshes and optimize physical consistency;

[0011] Data display and data upload: the established 3D model will be displayed through the mobile terminal, and the circumference data of each key part will be displayed synchronously; after the subject confirms that it is correct, the data will be uploaded.

[0012] As a preferred solution, the visual sensor includes one or more combinations of RGB sensors and TOF sensors. After hardware testing, if the mobile terminal is integrated with an RGB sensor, the subject is required to make a specified action and take one or more photos to complete the corresponding data collection; if the mobile terminal is integrated with a TOF sensor, the data collection modes include pulse wave modulation, continuous wave modulation, multi-point scanning, and dynamic timing.

[0013] As a preferred solution, the hardware detection method of the mobile terminal includes: the Android system calls the Sensor API for hardware detection; the iOS system calls ARKit for hardware detection; the lighting conditions are: when the ToF sensor is iToF, the ambient light is >5000lux, and the software prompts the user to change the measurement environment; when it is dToF, the ambient light is >20000lux, and the subject is prompted to change the measurement environment.

[0014] As a preferred option, the subject needs to wear a non-reflective tights, and during the measurement process, the subject's position is detected in real time to ensure that it is within the shooting range. If it is out of range or moves too fast during the measurement, a warning reminder will be issued.

[0015] As a preferred option, the body circumference measurement process:

[0016] Positioning key points: Using AI algorithms to detect key points for measuring human circumference, such as the acromion point, anterior superior iliac spine, chest height point, waistline greater trochanter point, etc. 3D model slicing: On the 3D model, a horizontal plane is cut along each key point in the vertical direction;

[0017] Calculate perimeter: calculate the cross-section perimeter of each key point;

[0018] Correct clothing error: Integrate the total length along the edge contour line of the cutting section and automatically deduct the influence of clothing thickness.

[0019] As a preferred solution, texture mapping is also included when building the model: the TOF depth map is integrated with the color photos taken by the mobile phone to add skin texture details to the model, so that the virtual human body presents real skin color folds.

[0020] As a preferred solution, when uploading data, Laplace noise is used and an encryption algorithm is used for encrypted upload.

[0021] The beneficial effect of the method of measuring human body data by integrating a mobile terminal with a visual sensor disclosed in the present invention is: by integrating active three-dimensional perception hardware into the mobile terminal, users can measure their own or others' body circumference data such as height and three-dimensional height. After the user measures these data, a corresponding 3D model is generated, and after confirmation, the corresponding 3D model data is uploaded to the e-commerce platform or the virtual fitting equipment of each offline store to generate a three-dimensional model of the human body. Therefore, when purchasing clothes, the user can use his own three-dimensional human body model to simulate the upper body effect for accurate trying on of wearable products. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of a method for measuring human body data by integrating a mobile terminal with a visual sensor according to the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described and explained below in conjunction with specific embodiments and accompanying drawings:

[0024] Please refer to Figure 1 ,A method for measuring human body data by integrating a mobile terminal with a visual sensor, comprising the following steps;

[0025] Hardware and environment detection: detect the built-in hardware of the mobile terminal to determine whether it is equipped with the required visual sensors. Visual sensors include one or more combinations of RGB sensors and TOF sensors.

[0026] The hardware detection method of the mobile terminal includes: Android system calls Sensor API for hardware detection; iOS system calls ARKit for hardware detection; the light conditions are: when the ToF sensor is iToF, the ambient light is greater than 5000 lux, the software prompts the user to change the measurement environment; when it is dToF, the ambient light is greater than 20000 lux, the user is prompted to change the measurement environment;

[0027] The measured person is guided on the clothing requirements, the position range and body movements during measurement. The measured person needs to wear non-reflective tights, and it is best not to wear silk materials or metal accessories, as reflections are likely to occur and affect the measurement data. During the measurement process, the measured person's position is detected in real time to ensure that it is within the shooting range. When the range is exceeded or the movement speed is fast during the measurement process, the mobile terminal will not be able to effectively capture the measured person during shooting and measurement, resulting in data errors, and timely warning reminders are required.

[0028] Data collection includes dynamic mode and static mode. By obtaining the mobile terminal sensor information as described above, it automatically switches to the corresponding collection mode according to the sensor type in the information, or prompts the photographer to switch to the corresponding data collection mode. In dynamic mode, the subject needs to rotate to capture full-body data; in static mode, the subject needs to pose in a specified posture and take one or more photos to complete the corresponding data collection.

[0029] If the mobile terminal is integrated with an RGB sensor, the subject is required to make a specified gesture and take one or more photos to complete the corresponding data collection; if the mobile terminal is integrated with a TOF sensor, the data collection modes include pulse wave modulation, continuous wave modulation, multi-point scanning, and dynamic timing.

[0030] The postures of the subjects in the static mode include T-Pose and A-Pose, that is, the subjects stand with both feet and raise their arms horizontally or above the head.

[0031] The process of measuring body circumference after collecting data:

[0032] Positioning key points: Using AI algorithms to detect key points for measuring human circumference, such as the acromion point, anterior superior iliac spine, chest height point, waistline greater trochanter point, etc. 3D model slicing: On the 3D model, a horizontal plane is cut along each key point in the vertical direction;

[0033] Calculate perimeter: calculate the cross-section perimeter of each key point;

[0034] Correct clothing error: Integrate the total length along the edge contour line of the cutting section and automatically deduct the influence of clothing thickness.

[0035] Data processing and modeling, point cloud denoising: The system automatically filters out isolated points floating in the air, such as dust and hair ends, retaining the continuous point cloud of the human body surface. For the trailing areas caused by motion blur, such as when swinging the arms or turning, time series analysis is used to eliminate abnormal points; model establishment: By calling the background API, multiple discrete points are connected into a triangular mesh, and the surface smoothing algorithm is used to eliminate sharp corners to generate a smooth human body model. The model is scaled proportionally according to the size of the calibration disk to ensure that the virtual human body is completely consistent with the actual size.

[0036] Texture mapping is also included when the model is built: the TOF depth map is integrated with the color photos taken by the mobile phone to add skin texture details to the model, so that the virtual human body presents real skin color folds.

[0037] Data display and data upload: the established 3D model will be displayed through the mobile terminal, and the circumference data of each key part, such as hip circumference, chest circumference, shoulder width, waist circumference, etc. will be displayed synchronously; after the subject confirms that it is correct, Laplace noise is used and the encryption algorithm is used for encryption and upload.

[0038] The present invention provides a method for measuring human body data by integrating a visual sensor in a mobile terminal. By integrating active three-dimensional perception hardware into the mobile terminal, users can measure their own or others' body circumference data such as height and three-dimensional height. After the user obtains these data, a corresponding 3D model is generated. After confirmation, the corresponding 3D model data is uploaded to an e-commerce platform or a virtual fitting device in each offline store to generate a three-dimensional model of the human body. Therefore, when purchasing clothing, the user can use the three-dimensional model of the human body to simulate the upper body effect for accurate fitting of wearable products.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A method for measuring human body data by integrating a mobile terminal with a visual sensor, characterized in that: The following steps are included: Hardware and environment testing: testing the built-in hardware of the mobile terminal to determine whether it is equipped with the required visual sensors, and testing whether the light in the measurement environment meets the measurement conditions; Measurement guidance: informing the subject of the clothing requirements during measurement, detecting and prompting the subject's position range and movement range during photography; Data collection, including dynamic mode and static mode, obtains mobile terminal sensor information as described above and automatically switches to the corresponding collection mode according to the sensor type in the information. In dynamic mode, the subject needs to rotate to capture full-body data; in static mode, the subject needs to pose in a specified position and take one or more photos to complete the corresponding data collection; Data processing and modeling, denoising and filtering: Remove sensor noise or outliers through methods such as Gaussian filtering and statistical filtering; Model reconstruction: Human body modeling based on visual sensors uses color / texture information or depth data, combined with parametric human body models or 3D reconstruction technology to generate high-precision meshes and optimize physical consistency; Data display and data upload: the established 3D model will be displayed through the mobile terminal, and the circumference data of each key part will be displayed synchronously; after the subject confirms that it is correct, the data will be uploaded.

2. The method for measuring human body data by integrating a mobile terminal with a visual sensor according to claim 1, wherein: Visual sensors include one or more combinations of RGB sensors and TOF sensors. After hardware testing, if the mobile terminal is integrated with an RGB sensor, the subject is required to make a specified action and take one or more photos to complete the corresponding data collection. If the mobile terminal is integrated with a TOF sensor, the data collection modes include pulse wave modulation, continuous wave modulation, multi-point scanning, and dynamic timing.

3. The method for measuring human body data by integrating a mobile terminal with a visual sensor as claimed in claim 2, wherein: The hardware detection methods for mobile terminals include: the Android system calls the Sensor API for hardware detection; the iOS system calls ARKit for hardware detection; the lighting conditions are: when the ToF sensor is iToF, the ambient light is >5000lux, and the software prompts the user to change the measurement environment; when it is dToF, the ambient light is >20000lux, and the subject is prompted to change the measurement environment.

4. The method for measuring human body data by integrating a mobile terminal with a visual sensor according to claim 1, wherein: The person being measured needs to wear a non-reflective tights, and during the measurement process, the position of the person being measured is detected in real time to ensure that it is within the shooting range. If it is out of range or moves too fast during the measurement, a warning reminder will be issued.

5. The method for measuring human body data by integrating a mobile terminal with a visual sensor according to claim 1, wherein: Body circumference measurement process: Positioning key points: Using AI algorithms to detect key points for measuring human circumference, such as the acromion point, anterior superior iliac spine, chest height point, waistline greater trochanter point, etc. 3D model slicing: On the 3D model, a horizontal plane is cut along each key point in the vertical direction; Calculate perimeter: calculate the cross-section perimeter of each key point; Correct clothing error: Integrate the total length along the edge contour line of the cutting section and automatically deduct the influence of clothing thickness.

6. The method for measuring human body data by integrating a mobile terminal with a visual sensor according to claim 1, wherein: Texture mapping is also included when the model is built: the TOF depth map is integrated with the color photos taken by the mobile phone to add skin texture details to the model, so that the virtual human body presents real skin color folds.

7. The method for measuring human body data by integrating a mobile terminal with a visual sensor according to claim 1, wherein: When uploading data, Laplace noise is used and encryption algorithm is used for encryption upload.