A human body parameter detection method, device and storage medium thereof

Abstract

The present application relates to a human body parameter detection method, device and storage medium thereof, and relates to the human body detection technology field, which includes obtaining a first parameter data group of a human body to be tested collected by a parameter acquisition device; generating a human body contour line according to the first parameter data group of the human body to be tested, and sending the human body contour line to an interactive device so that the interactive device displays the human body contour line; sending the human body contour line to a movable detection device so that the movable detection device moves to a target detection position according to the human body contour line; obtaining information on several positioning points of the human body to be tested detected by the movable detection device at the target detection position; obtaining a second parameter data group of the human body to be tested according to the information on several positioning points of the human body to be tested; obtaining a human body parameter detection result according to the first parameter data group and the second parameter data group of the human body to be tested, and sending the human body parameter detection result to the interactive device. The present application has the effect of improving the accuracy of human body parameter detection.

Description

Technical Field

[0001] The present application relates to the technical field of human body detection, and in particular to a human body parameter detection method, device and storage medium thereof. Background Art

[0002] When conducting physical examinations, body shape and posture corrections, outfit recommendations, clothing customization, size recommendations, and clothing customization, it is usually necessary to measure human body parameters. Traditional human body parameter measurements are usually manual measurements, which are highly dependent on manual labor, inefficient, and have poor accuracy. At present, with the development of the intelligent era, some automatic detection equipment for human body parameters have also appeared on the market, but automatic detection equipment usually detects through positioning and identification of detection equipment. For users of different body types, the positions of the located human body parts may vary greatly, and if the user does not align with the detection range of the detection equipment during the detection process, it will also cause deviations in the positioning position. Therefore, in the process of detecting users of different body types, it is easy for the detection equipment to be inaccurately positioned, resulting in large errors in the detection results, thereby affecting the accuracy of human body parameter detection. Summary of the invention

[0003] The purpose of this application is to provide a human body parameter detection method, device and storage medium thereof, which help to improve the accuracy of human body parameter detection.

[0004] In the first aspect, a human body parameter detection method provided by the present application adopts the following technical solution:

[0005] A human body parameter detection method, comprising:

[0006] Acquire a first parameter data group of a human body to be measured collected by a parameter collection device, wherein the first parameter data group includes but is not limited to height data and weight data of the human body to be measured;

[0007] Generate a human body contour line according to the first parameter data group of the human body to be measured, and send the human body contour line to the interactive device so that the interactive device displays the human body contour line;

[0008] Sending the human body contour line to the movable detection device so that the movable detection device moves to the target detection position according to the human body contour line;

[0009] Obtaining information of several positioning points of a human body to be detected by a movable detection device at a target detection position;

[0010] Acquire a second parameter data group of the human body to be measured according to information of a plurality of positioning points of the human body to be measured;

[0011] A human body parameter detection result is obtained according to the first parameter data group and the second parameter data group of the human body to be detected, and the human body parameter detection result is sent to the interactive device.

[0012] By adopting the above technical solution, before controlling the detection device to detect human body parameters, the present application first obtains the approximate body shape data of the human body to be tested, that is, the first parameter data group, such as height data and weight data, and then generates a human body contour line based on the height data and weight data, and displays the human body contour line on the interactive device, so that the user can align the detection device according to the human body contour line to reduce the position deviation of the detection device caused by the user's misalignment of the detection device during the detection process. At the same time, the detection device of the present application is a movable detection device, so that the detection device can adjust its detection position according to the human body contour line of the human body to be tested before detection, further reducing the position deviation during the detection process, thereby reducing the error caused by inaccurate positioning of the detection device, which helps to improve the accuracy of human body parameter detection.

[0013] Furthermore, the step of generating a human body contour line according to the first parameter data set of the human body to be measured comprises:

[0014] Acquire several groups of first parameter data sample groups in the database, each group of first parameter data sample groups including but not limited to a height data sample and a corresponding weight data sample;

[0015] Obtaining human body contour line samples corresponding to a plurality of groups of first parameter data sample groups in a database;

[0016] Associating a plurality of first parameter data sample groups with corresponding human body contour line samples to construct a human body contour line prediction sample set;

[0017] Construct a neural network prediction model, input a human body contour prediction sample set to train and test the neural network prediction model, and obtain a human body contour prediction model;

[0018] The collected first parameter data group of the human body to be tested is input into the human body contour line prediction model to obtain the predicted human body contour line of the human body to be tested.

[0019] By adopting the above technical solution, the present application constructs a neural network prediction model, and uses the neural network prediction model to predict the height data and weight data of the human body to be tested to obtain a human body contour line that is closest to the human body to be tested, so that the user can align the movable detection device with the human body contour line to further improve the accuracy of human body parameter detection. Since the human body contour line is generated based on the first parameter data group of the human body to be tested, it can be more suitable for human body parameter detection for users of different body shapes compared to directly displaying a reference contour line.

[0020] Further, the step of obtaining a second parameter data set of the human body to be measured according to information of a plurality of positioning points of the human body to be measured specifically includes:

[0021] Perform denoising on the information of several positioning points of the human body to be measured;

[0022] Select key positioning point information from among the plurality of positioning point information after denoising;

[0023] A second parameter data group of the human body to be measured is obtained according to the key positioning point information.

[0024] By adopting the above-mentioned technical scheme, since during the detection process, the collected several positioning point information may contain certain noise information, that is, unnecessary positioning point information, the present application filters out the unnecessary positioning point information through denoising processing to obtain the required key positioning point information, and calculates more specific human body parameter data through the key positioning point information, thereby improving the accuracy of human body parameter detection.

[0025] Furthermore, in the process of selecting key positioning point information from the plurality of positioning point information after denoising, when all key positioning point information cannot be obtained, it also includes: predicting unobtained key positioning point information based on the key positioning point information already obtained on the human body to be measured.

[0026] By adopting the above technical solution, during the detection process, occlusion may occur, resulting in incomplete collection of positioning points, thereby causing the loss of key positioning points. However, since human body parameters are correlated to a certain extent, the key positioning point information that has not been obtained can be predicted based on the key positioning point information that has been obtained, making the key positioning point information more accurate.

[0027] Furthermore, the step of predicting the unobtained key positioning point information based on the acquired key positioning point information specifically includes:

[0028] Selecting a human body data sample that is identical to the first parameter data group of the human body to be tested from the database, and obtaining a key positioning point information sample set in the human body data sample;

[0029] Constructing a neural network prediction model, taking key positioning point information samples obtained in the key positioning point information sample set as input, taking key positioning point information samples not obtained in the key positioning point information sample set as output, training and testing the neural network prediction model, and obtaining a key positioning point information prediction model;

[0030] The key positioning point information acquired by the human body to be tested is input into the key positioning point information prediction model to obtain the prediction result of the key positioning point information not acquired by the human body to be tested.

[0031] By adopting the above-mentioned technical scheme, the present application constructs a neural network prediction model, takes the acquired key positioning point information samples as input, and takes the unacquired key positioning point information samples as output, thereby predicting the unacquired key positioning point information based on the acquired key positioning point information, and the sample set for training the model selects human body data samples that are the same as the first parameter data group of the human body to be tested, that is, human body data samples with an approximate body shape similar to the human body to be tested, thereby increasing the accuracy of the prediction results of the key positioning point information prediction model, thereby improving the accuracy of human body parameter detection.

[0032] Furthermore, the step of obtaining information of several positioning points of the human body to be detected by the movable detection device at the target detection position specifically includes: obtaining information of several positioning points of the human body to be detected by the movable detection device at the target detection position during 360° rotation.

[0033] By adopting the above technical solution, in order to increase the comprehensiveness of the positioning point information collection, it is necessary to collect information of several positioning points during the 360° rotation of the human body to be measured, so as to further improve the accuracy of human body parameter detection.

[0034] Furthermore, the process of obtaining information of several positioning points of the human body to be detected by the movable detection device at the target detection position also includes:

[0035] Preset the error range beyond the human body contour line during the rotation of the human body to be measured;

[0036] When receiving a signal from the movable detection device that the detected human body exceeds the error range of the human body contour line during rotation, a detection pause signal and an out-of-range prompt signal are generated;

[0037] Sending a detection suspension signal to the movable detection device to cause the movable detection device to suspend detection;

[0038] An out-of-range prompt signal is sent to the interactive device so that the interactive device displays an out-of-range prompt.

[0039] By adopting the above-mentioned technical solution, since the detection errors may occur due to movement of the human body to be measured during the 360° rotation, the present application uses a preset error range to stop the detection in time and remind the user to adjust the position when the error range of the human body contour line is exceeded during the rotation process, so as to improve the accuracy of the detection process.

[0040] Furthermore, the method of obtaining the first parameter data group of the human body to be measured collected by the parameter collection device also includes:

[0041] Receiving the human body current information to be measured collected by the current transceiver;

[0042] Obtaining body fat data of the human body to be tested according to the current information of the human body to be tested;

[0043] The body fat data of the human body to be tested is added to the first parameter data group.

[0044] By adopting the above technical solution, in addition to height data and weight data, the measurement method of body fat data is also relatively simple, and only requires detection through human body current. Therefore, the first parameter data group can also include body fat data, so as to more accurately obtain the approximate body shape of the human body to be measured, so as to increase the prediction accuracy of the human body contour line.

[0045] In the second aspect, the human body parameter detection device provided by the present application adopts the following technical solution:

[0046] A human body parameter detection device, comprising a detection device body and a detection platform, wherein a processor is installed inside the detection device body, the processor is electrically connected to the detection platform, and the processor is used to execute a human body parameter detection method according to the first aspect;

[0047] An interactive device is provided on a side of the detection device body close to the detection platform, and the interactive device is electrically connected to the processor;

[0048] A plurality of movable detection devices are movably mounted on the edge of the detection device body, and the plurality of movable detection devices are electrically connected to the processor;

[0049] It also includes a parameter collection device, which includes a height data collection device and a weight data collection device. The height data collection device is installed at the upper end of the detection device body, and the weight data collection device is installed on the top of the detection platform. The height data collection device and the weight data collection device are electrically connected to the processor respectively.

[0050] In a third aspect, the present application provides a computer-readable storage medium that adopts the following technical solution:

[0051] A computer-readable storage medium stores a computer program that can be loaded by a processor and executes a human body parameter detection method as described in the first aspect.

[0052] In summary, the present application includes at least one of the following beneficial technical effects:

[0053] 1. Before controlling the detection device to detect human body parameters, the present application first obtains the approximate body shape data of the human body to be detected and generates the human body contour line, so that the user can align the detection device according to the human body contour line, so as to reduce the position deviation of the detection device caused by the user's misalignment with the detection device during the detection process;

[0054] 2. The detection device of the present application is a movable detection device, so that the detection device can adjust its detection position according to the human body contour line of the human body to be detected before detection, further reducing the position deviation during the detection process;

[0055] 3. This application filters out unnecessary positioning point information through denoising to obtain the required key positioning point information, and calculates more specific human body parameter data through the key positioning point information to improve the accuracy of human body parameter detection;

[0056] 4. This application uses a neural network prediction model to predict the key positioning point information that has not been acquired, increase the accuracy of the prediction results of the key positioning point information prediction model, and thus improve the accuracy of human body parameter detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flow chart of a human body parameter detection method according to an embodiment of the present application;

[0058] Figure 2 is a flow chart of a method for predicting a human body contour line according to an embodiment of the present application;

[0059] Figure 3 is a flow chart of an error prompt method according to an embodiment of the present application;

[0060] Figure 4 is a structural diagram of a human body parameter detection device according to an embodiment of the present application;

[0061] Figure 5 is a schematic diagram of the connection relationship of the human body parameter detection device according to an embodiment of the present application;

[0062] In the figure, 1. detection device body; 2. detection platform; 3. processor; 4. movable detection equipment; 5. height data collection equipment; 6. weight data collection equipment; 7. interactive equipment. DETAILED DESCRIPTION

[0063] The following is combined with Figure 1 -Attached Figure 5 , further details of this application are given.

[0064] Since in the process of human body parameter detection, for users of different body shapes, the positions of the human body parts located may differ greatly, and if the user does not align the detection device during the detection process, the positioning position may also be deviated. Therefore, in the process of detecting users of different body shapes, it is easy for the detection device to be inaccurately positioned, resulting in large errors in the detection results, thereby affecting the accuracy of human body parameter detection. Therefore, the embodiment of the present application provides a human body parameter detection method, referring to Figure 1 ,include:

[0065] S1. Acquire a first parameter data group of a human body to be measured collected by a parameter collection device.

[0066] Specifically, the first parameter data set includes but is not limited to the height data and weight data of the person to be measured. The first parameter data set includes relatively easy to collect human parameter data, such as height and weight. The first parameter data set can reflect the approximate body shape of the person to be measured and can be used to preliminarily locate the person to be measured.

[0067] S2. Generate a human body contour line according to the first parameter data group of the human body to be measured, and send the human body contour line to the interactive device so that the interactive device displays the human body contour line.

[0068] Specifically, before performing human body parameter detection, a human body contour line is generated according to the approximate body shape of the human body to be detected, and displayed through an interactive device, so that the user can align the detection range of the detection device according to the contour line suitable for his or her body shape.

[0069] S3. Sending the human body contour line to the movable detection device, so that the movable detection device moves to the target detection position according to the human body contour line.

[0070] Specifically, before performing human body parameter detection, the position of the movable detection device is adjusted according to the human body contour line to ensure that the human body to be detected is located within the detection range of the movable detection device.

[0071] S4. Acquire information of several positioning points of the human body to be detected by the movable detection device at the target detection position.

[0072] Specifically, the human body to be tested rotates 360° within the detection range of the movable detection device, and the movable detection device collects information of several positioning points during the rotation. In the specific implementation process, the movable detection device usually uses multiple structured light sensor devices with visual detection functions. The structured light sensor emits light to the human body to be tested, and each beam of light detects a positioning point information, and then receives the reflected light to obtain information of several positioning points.

[0073] S5. Obtain a second parameter data group of the human body to be measured according to information of a plurality of positioning points of the human body to be measured.

[0074] Specifically, the second parameter data group includes human body parameter data that are difficult to collect directly, usually including three measurements, shoulder width, arm length, leg length, arm circumference and leg circumference. Since these data cannot be collected directly, it is necessary to detect the positioning point information through a movable detection device and then calculate them based on the positioning point information.

[0075] S6. Obtain a human body parameter detection result according to the first parameter data group and the second parameter data group of the human body to be detected, and send the human body parameter detection result to the interactive device.

[0076] Specifically, all required human body parameter data of the human body to be tested can be obtained by combining the first parameter data group and the second parameter data group. In the specific implementation process, a human body detection report can be generated according to the human body parameter data and displayed on an interactive device or mobile phone APP for users to view.

[0077] In another embodiment, a human body model of the human body to be tested can be generated according to the human body parameter detection results, and the human body model can be displayed on an interactive device or a mobile phone APP, so that clothing recommendations and other items can be made according to the human body model.

[0078] The implementation principle of the embodiment of the present application is: by generating a human body contour line that is adapted to the human body to be tested according to the first parameter data group, the user can align the detection range of the movable detection device according to the human body contour line, and the movable detection device can also adjust the detection position according to the human body contour line to reduce the position deviation of the movable detection device during the detection process due to the user's misalignment of the movable detection device and the inaccurate positioning of the movable detection device, which helps to improve the accuracy of human body parameter detection.

[0079] Since each person's body shape is quite different, if a standard fixed human body contour line is used to detect a human body of different body shapes, it may still lead to a large error in the detection process. Therefore, this embodiment needs to generate a human body contour line according to the first parameter data set of the human body to be tested, such as Figure 2 As shown, the specific steps include:

[0080] S201. Acquire several groups of first parameter data sample groups in a database.

[0081] Specifically, each group of first parameter data samples includes but is not limited to a height data sample and a corresponding weight data sample.

[0082] S202: Obtain human body contour line samples corresponding to several groups of first parameter data sample groups in a database.

[0083] Specifically, the data samples in the database can be obtained by pre-collection, and the collected contents include height data samples, weight data samples of multiple sample users, and human body contour line samples corresponding to the actual body shapes of the users.

[0084] S203: Associating several groups of first parameter data sample groups with corresponding human body contour line samples to construct a human body contour line prediction sample set.

[0085] Specifically, the first parameter data sample group is used as input, and the human body contour line samples are used as output to construct a human body contour line prediction sample set.

[0086] S204, constructing a neural network prediction model, inputting a human body contour prediction sample set to train and test the neural network prediction model, and obtaining a human body contour prediction model.

[0087] Specifically, the neural network prediction model can use a recurrent neural network (RNN) model. When training and testing the neural network model, 70% of the first parameter data sample groups and their corresponding human contour samples in the human contour prediction sample set can be constructed as a training set, and 30% of the first parameter data sample groups and their corresponding human contour samples can be constructed as a training set and a test set. First, the first parameter data sample group of the training set and its corresponding human contour samples are input into the neural network prediction model for training to obtain a human contour prediction model to be tested. The first parameter data sample group in the test set is input into the human contour prediction model to be tested to obtain a predicted human contour to be tested. All predicted human contours to be tested obtained in the test set are compared with the human contour samples corresponding to the first parameter data sample group. The accuracy of the test set is obtained by calculating the loss function corresponding to the predicted human contour to be tested and the human contour samples. If the accuracy meets the standard, it indicates that the training of the human contour prediction model is completed. If the accuracy does not meet the standard, the sample set is continued to be used for iterative optimization until the accuracy of the test set reaches the standard, and a trained human contour prediction model is obtained.

[0088] S205 , inputting the collected first parameter data group of the human body to be measured into a human body contour line prediction model to obtain a predicted human body contour line of the human body to be measured.

[0089] The implementation principle of the embodiment of the present application is: by constructing a neural network prediction model, the neural network prediction model is used to predict the height data and weight data of the human body to be tested to obtain a human body contour line that is closest to the human body to be tested. Compared with directly displaying a baseline contour line, it can be more suitable for users of different body shapes to perform human body parameter detection.

[0090] In another embodiment, the first parameter data group may also include body fat data, which can be obtained by simply detecting the human body current, and the specific steps are: receiving the current information of the human body to be tested collected by the current transceiver; obtaining the body fat data of the human body to be tested according to the current information of the human body to be tested; and adding the body fat data of the human body to be tested to the first parameter data group. By combining the body fat data to generate the human body contour line, the approximate body shape of the human body to be tested can be obtained more accurately, so as to increase the prediction accuracy of the human body contour line.

[0091] Since the detection process involves the rotation of the human body to be detected, multiple mobile detection devices simultaneously detect the positioning point information of the rotating human body to be detected. The human body to be detected may not be able to remain still during the entire rotation process. Therefore, mobile detection devices are also required to monitor the position of the human body to be detected in real time, and to give a reminder when the human body to be detected exceeds the detection range of the mobile detection device during the rotation process. Figure 3 As shown, when performing step S4 of this embodiment, it also includes:

[0092] S401, presetting an error range beyond the human body contour line during the rotation of the human body to be measured.

[0093] Specifically, the human body contour line is usually the front contour line. During the rotation process, the artificial human body to be measured remains motionless and does not exceed the human body contour line, but usually cannot remain motionless throughout the entire process. Therefore, an error range is preset, and the error range can be set according to the detection range of the movable detection equipment.

[0094] S402: When a signal is received from the movable detection device that the detected human body exceeds the error range of the human body contour line during rotation, a detection pause signal and an out-of-range prompt signal are generated.

[0095] Specifically, when the human body to be measured moves beyond the error range, it will exceed the detection range of the movable detection device, resulting in the inability to accurately detect the positioning point information. Therefore, when the movable detection device detects that the human body to be measured exceeds the error range, it sends a signal that exceeds the error range of the human body contour line.

[0096] S403: Send a detection suspension signal to the movable detection device to make the movable detection device suspend detection.

[0097] Specifically, when the movement of the human body to be detected exceeds the error range, the movable detection device is controlled to suspend detection to avoid detecting data with large errors.

[0098] S404: Send an out-of-range prompt signal to the interactive device, so that the interactive device displays an out-of-range prompt.

[0099] Specifically, when the movement of the human body to be tested exceeds the error range, it is displayed through the interactive device so that the user can adjust the position according to the prompt in time to ensure that the detection process can continue. In another embodiment, the user can also be prompted by voice broadcast.

[0100] At the same time, in order to protect the privacy of users, the mobile detection equipment needs to avoid facial detection or blur the user's facial data when detecting the human body.

[0101] During the detection process, there may be problems such as repeated detection of the same positioning point information or fuzzy positioning point information due to human body shaking, resulting in the presence of certain noise information in the collected positioning point information. In order to solve the above problems, step S5 of this embodiment specifically includes: denoising several positioning point information of the human body to be measured; selecting key positioning point information from the several positioning point information after denoising; and obtaining a second parameter data group of the human body to be measured based on the key positioning point information.

[0102] In the specific implementation process, the second parameter data group includes specific parameter data of the human body, such as three measurements, shoulder width, arm length, leg length, arm circumference and leg circumference, etc. Taking the detection of shoulder width data as an example, the movable detection device detects the positioning point information of the left shoulder and the right shoulder of the human body to be tested. The shoulder width data can be calculated based on the above two positioning point information. Since the shoulder width data can be detected by collecting the front of the human body to be tested, the other shoulder positioning point information collected during the rotation of the human body to be tested is noise data, and the noise data needs to be filtered through denoising processing. The positioning point information of the left shoulder and the right shoulder that are finally left are the key positioning point information of the shoulder width data.

[0103] During the detection process, due to the occlusion of other parts of the human body, some positioning point information of the human body may not be directly detected by the movable detection device, for example, the positioning point information of the armpit will be blocked by the arm, and the positioning point information of the crotch will be blocked by the thigh, etc. However, since each part of the human body is associated, the key positioning point information that has not been obtained can be predicted based on the key positioning point information that has been obtained of the human body to be tested. The specific steps include: selecting a human body data sample that is the same as the first parameter data group of the human body to be tested from the database, and obtaining a key positioning point information sample set in the human body data sample. Specifically, a plurality of human body data samples with different first parameter data groups, that is, different height data and weight data, are stored in the database. The key positioning point information that is difficult to detect by the movable detection device is manually measured, and the data obtained by the manual measurement are stored in the database to construct a key positioning point information sample set, and the key positioning point information sample set of the human body data sample that is the same or similar to the first parameter data group of the human body to be tested is selected. Construct a neural network prediction model, take the key positioning point information samples obtained in the key positioning point information sample set as input, take the key positioning point information samples not obtained in the key positioning point information sample set as output, train and test the neural network prediction model, and obtain the key positioning point information prediction model. Input the key positioning point information obtained by the human body to be tested into the key positioning point information prediction model, and obtain the prediction results of the key positioning point information not obtained by the human body to be tested.

[0104] This embodiment constructs a neural network prediction model to predict the key positioning point information that has not been acquired based on the key positioning point information that has been acquired, and selects human body data samples that are the same as the first parameter data group of the human body to be tested, that is, human body data samples that are similar to the approximate body shape of the human body to be tested, to ensure the accuracy of the prediction results.

[0105] The present application also provides a human body parameter detection device, referring to Figure 4 and Figure 5 , including a detection device body 1 and a detection platform 2, the detection platform 2 is a rotatable turntable, the detection device body 1 is used to detect the human body parameters of the user standing on the detection platform 2. A processor 3 is installed inside the detection device body 1, the detection platform 2 is electrically connected to the processor 3, and the processor 3 is used to execute a human body parameter detection method:

[0106] S1. Acquire a first parameter data group of a human body to be measured collected by a parameter collection device.

[0107] S2. Generate a human body contour line according to the first parameter data group of the human body to be measured, and send the human body contour line to the interactive device 7 so that the interactive device 7 displays the human body contour line.

[0108] S3. Send the human body contour line to the movable detection device 4, so that the movable detection device 4 moves to the target detection position according to the human body contour line.

[0109] S4. Acquire information of several positioning points of the human body to be detected by the movable detection device 4 at the target detection position.

[0110] S5. Obtain a second parameter data group of the human body to be measured according to information of a plurality of positioning points of the human body to be measured.

[0111] S6. Obtain a human body parameter detection result according to the first parameter data group and the second parameter data group of the human body to be detected, and send the human body parameter detection result to the interactive device 7.

[0112] The two movable detection devices 4 of this embodiment are movably mounted on the left and right edges of the detection device body 1, and the two movable detection devices 4 are electrically connected to the processor 3 respectively. The movable detection device 4 moves up and down through the slide rail and the built-in electric push rod. When the processor 3 generates the human body contour line, it is sent to the movable detection device 4. The movable detection device 4 adjusts the upper and lower positions according to the human body contour line to adapt to the body shape of the human body to be tested. In the specific implementation process, the movable detection device 4 is a structured light sensor capable of visual detection.

[0113] The parameter acquisition device of this embodiment includes a height data acquisition device 5 installed on the upper end of the detection device body 1 and a weight data acquisition device 6 installed on the top of the detection platform 2. The height data acquisition device 5 and the weight data acquisition device 6 are electrically connected to the processor 3 respectively. The height data acquisition device 5 is used to collect the height data of the user standing on the detection platform 2. In specific implementation, a visual detection sensor can be used to obtain the height data of the user standing on the detection platform 2 by scanning the user on the detection platform 2 up and down. The weight data acquisition device 6 is used to collect the weight data of the user standing on the detection platform 2. In specific implementation, a weight scale can be used. In another embodiment, the parameter acquisition device can also include a body fat data acquisition device. The body fat data acquisition device is electrically connected to the processor 3. The body fat data acquisition device is a body fat scale installed on the top of the detection platform 2, and the body fat data of the user standing on the detection platform 2 is measured by human body current.

[0114] In this embodiment, the interactive device 7 is installed on the side of the detection device body 1 facing the user, so that the user can view the human body contour displayed on the interactive device 7, as well as the data such as the human body parameter detection results subsequently displayed on the interactive device 7. In the specific implementation process, the interactive device 7 uses a mirror display, so that the user can see both the content displayed on the interactive device 7 and his own reflection on the interactive device 7, so that the interactive device 7 can be used as a mirror.

[0115] In the specific implementation process, the user stands on the testing platform 2 and first enters the user registration information on the interactive device 7 for matching the human body parameter data detected subsequently; after the user registration is completed, the processor 3 controls the weight data acquisition device 6 in the testing platform 2 to collect the user's weight data, and uploads the weight data to the processor 3; the processor 3 controls the height data acquisition device 5 above the detection device body 1 to obtain the user's height data through visual detection, and uploads the height data to the processor 3; the processor 3 generates a human body contour line according to the user's height data and weight data, and the human body contour line is displayed on the interactive device 7, so that the user can adjust his position according to the human body contour line displayed by the interactive device 7 and his own reflection, so that the user's position is aligned with the human body contour line. At the same time, the processor 3 adjusts the position of the movable detection device 4 according to the human body contour line to adapt to the user's body shape; after the position of the movable detection device 4 and the user's position are adjusted, the human body parameter detection starts, and the processor 3 controls the testing platform 2 to start rotating slowly, driving the user standing on the testing platform 2 to rotate; during the rotation process , the movable detection device 4 continuously detects all the positioning point information of the user from beginning to end, and after a 360° rotation, a total of about 1.2 million positioning point information can be detected, and all the positioning point information is uploaded to the processor 3; during the rotation process, if the user moves and causes the error range of the human body contour frame to be exceeded, the processor 3 controls the movable detection device 4 to stop detection and the detection table 2 to stop rotating, and displays an error prompt on the teaching device to facilitate the user to adjust the position in time; after receiving about 1.2 million positioning point information, the processor 3 obtains about 180 key positioning point information after denoising; if any key positioning point information is not successfully obtained, the unobtained key positioning point information is predicted based on the acquired key positioning point information; finally, the processor 3 calculates specific human body parameters such as measurements, shoulder width, arm length, leg length, arm circumference and leg circumference based on the key positioning point information, and generates a human body parameter detection report, such as physical examination data, body shape data, clothing size, dressing recommendation and other reports, and the processor 3 sends the detection report to the interactive device 7 for display so that the user can view it.

[0116] The embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 3, the following steps are implemented:

[0117] S1. Acquire a first parameter data group of a human body to be measured collected by a parameter collection device.

[0118] S2. Generate a human body contour line according to the first parameter data group of the human body to be measured, and send the human body contour line to the interactive device 7 so that the interactive device 7 displays the human body contour line.

[0119] S3. Send the human body contour line to the movable detection device 4, so that the movable detection device 4 moves to the target detection position according to the human body contour line.

[0120] S4. Acquire information of several positioning points of the human body to be detected by the movable detection device 4 at the target detection position.

[0121] S5. Obtain a second parameter data group of the human body to be measured according to information of a plurality of positioning points of the human body to be measured.

[0122] S6. Obtain a human body parameter detection result according to the first parameter data group and the second parameter data group of the human body to be detected, and send the human body parameter detection result to the interactive device 7.

[0123] When executing the computer program, the processor 3 can also execute the steps of the human body parameter detection method in any of the above embodiments.

[0124] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0125] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0126] The embodiments of this specific implementation are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. The same components are represented by the same figure marks. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for detecting human body parameters, characterized in that: include: Acquire a first parameter data group of a human body to be measured collected by a parameter collection device, wherein the first parameter data group includes but is not limited to height data and weight data of the human body to be measured; Generate a human body contour line according to the first parameter data group of the human body to be measured, and send the human body contour line to the interactive device so that the interactive device displays the human body contour line; Sending the human body contour line to the movable detection device so that the movable detection device moves to the target detection position according to the human body contour line; Obtaining information of several positioning points of a human body to be detected by a movable detection device at a target detection position; Acquire a second parameter data group of the human body to be measured according to information of a plurality of positioning points of the human body to be measured; Obtaining a human body parameter detection result according to the first parameter data group and the second parameter data group of the human body to be detected, and sending the human body parameter detection result to the interactive device; The steps of generating a human body contour line according to the first parameter data group of the human body to be measured include: Acquire several groups of first parameter data sample groups in the database, each group of first parameter data sample groups including but not limited to a height data sample and a corresponding weight data sample; Obtaining human body contour line samples corresponding to a plurality of groups of first parameter data sample groups in a database; Associating a plurality of first parameter data sample groups with corresponding human body contour line samples to construct a human body contour line prediction sample set; Construct a neural network prediction model, input a human body contour prediction sample set to train and test the neural network prediction model, and obtain a human body contour prediction model; Inputting the collected first parameter data group of the human body to be tested into the human body contour line prediction model to obtain the predicted human body contour line of the human body to be tested; The step of obtaining the second parameter data set of the human body to be measured according to the information of a plurality of positioning points of the human body to be measured specifically includes: Perform denoising on the information of several positioning points of the human body to be measured; Select key positioning point information from among the plurality of positioning point information after denoising; Obtaining a second parameter data group of the human body to be tested according to the key positioning point information; When all key positioning point information cannot be obtained, the method further includes: predicting the unobtained key positioning point information according to the key positioning point information already obtained on the human body to be tested, and the specific steps include: Selecting a human body data sample that is identical to the first parameter data group of the human body to be tested from the database, and obtaining a key positioning point information sample set in the human body data sample; Constructing a neural network prediction model, taking key positioning point information samples obtained in the key positioning point information sample set as input, taking key positioning point information samples not obtained in the key positioning point information sample set as output, training and testing the neural network prediction model, and obtaining a key positioning point information prediction model; The key positioning point information acquired by the human body to be tested is input into the key positioning point information prediction model to obtain the prediction result of the key positioning point information not acquired by the human body to be tested.

2. A human body parameter detection method according to claim 1, characterized in that: The step of obtaining information of several positioning points of the human body to be detected by the movable detection device at the target detection position specifically includes: obtaining information of several positioning points of the human body to be detected by the movable detection device at the target detection position during 360° rotation.

3. A human body parameter detection method according to claim 2, characterized in that: The process of obtaining information of a plurality of positioning points of the human body to be detected detected by the movable detection device at the target detection position also includes: Preset the error range beyond the human body contour line during the rotation of the human body to be measured; When receiving a signal from the movable detection device that the detected human body exceeds the error range of the human body contour line during rotation, a detection pause signal and an out-of-range prompt signal are generated; Sending a detection suspension signal to the movable detection device to cause the movable detection device to suspend detection; An out-of-range prompt signal is sent to the interactive device so that the interactive device displays an out-of-range prompt.

4. A human body parameter detection method according to any one of claims 1 to 3, characterized in that: The method of obtaining the first parameter data group of the human body to be measured collected by the parameter collection device also includes: Receiving the human body current information to be measured collected by the current transceiver; Obtaining body fat data of the human body to be tested according to the current information of the human body to be tested; The body fat data of the human body to be tested is added to the first parameter data group.

5. A human body parameter detection device, characterized in that: The device comprises a detection device body (1) and a detection platform (2), wherein a processor (3) is installed inside the detection device body (1), the processor (3) is electrically connected to the detection platform (2), and the processor (3) is used to execute a human body parameter detection method according to any one of claims 1 to 4; An interactive device (7) is provided on a side of the detection device body (1) close to the detection platform (2), and the interactive device (7) is electrically connected to the processor (3); A plurality of movable detection devices (4) are movably mounted on the edge of the detection device body (1), and the plurality of movable detection devices (4) are electrically connected to the processor (3); The device also comprises a parameter acquisition device, the parameter acquisition device comprising a height data acquisition device (5) and a weight data acquisition device (6), the height data acquisition device (5) being mounted on the upper end of the detection device body (1), the weight data acquisition device (6) being mounted on the top of the detection platform (2), the height data acquisition device (5) and the weight data acquisition device (6) being electrically connected to the processor (3) respectively.

6. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor (3) and execute a human body parameter detection method as claimed in any one of claims 1 to 4.

Images