Human body size measurement method, device and electronic equipment

Abstract

The present invention provides a method, device and electronic device for measuring human body dimensions. The above-mentioned human body dimension measurement method comprises: according to the human body dimension standard, a set of key feature points that meet the human body dimension standard is obtained based on a depth camera; based on the human body symmetry rule, the key feature point set is corrected for the first type of abnormal points to obtain a first key feature point set; based on the normal points in the first key feature point set, the first key feature point set is corrected for the second type of abnormal points by surface fitting to obtain a target key feature point set; based on the target key feature point set, the dimensions of key parts of the human body are measured. After the method corrects the key feature points of the human body, the accuracy of the key feature points is improved, and the accuracy of human body dimension measurement is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision, and in particular to a method, device and electronic equipment for measuring human body dimensions. Background Art

[0002] As industries such as computers, clothing manufacturing and sales, and film and television animation are rapidly developing towards intelligence, many enterprises, teaching, and research institutions have an increasing demand for human body measurement, and the application of three-dimensional human body scanning is becoming more and more extensive.

[0003] At present, the commonly used methods for measuring 3D human body dimensions include a 3D human body measurement system using 16 ASUS Xtions, a static measurement system using 3 Kinects, and a 3D human body scanner measurement system.

[0004] Existing technologies only take the depth measurement value of the depth camera as the true value. In fact, due to interference from the scene and lighting, it is often difficult for the depth camera to obtain accurate and stable depth measurement values; at the same time, due to the hardware limitations of the depth camera, the depth information of the human body obtained by the depth camera has error fluctuations, resulting in inaccurate three-dimensional coordinates of the key points of the human body, and further causing errors in the accuracy of the human body size. Summary of the invention

[0005] The present invention provides a human body size measurement method, device and electronic equipment, which are used to solve the defect of inaccurate three-dimensional coordinates of key points of the human body obtained in the prior art, realize further correction of the three-dimensional coordinates of the key points of the human body, and improve the accuracy of the three-dimensional coordinates of the key points of the human body.

[0006] The present invention provides a method for measuring human body dimensions, comprising:

[0007] According to the human body size standard, a set of key feature points that meet the human body size standard is obtained based on a depth camera;

[0008] Performing a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set;

[0009] Based on the normal points in the first key feature point set, performing second-type abnormal point correction on the first key feature point set by surface fitting to obtain a target key feature point set;

[0010] The dimensions of key parts of the human body are measured based on the target key feature point set.

[0011] According to a method for measuring human body size provided by the present invention, obtaining a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard includes:

[0012] Based on the depth camera, obtain the three-dimensional depth point cloud data of the human body;

[0013] Determining an initial key feature point set of the human body according to the three-dimensional depth point cloud data of the human body;

[0014] Determining whether the initial key feature point set includes erroneous points that do not meet human body size standards;

[0015] In the case that the initial key feature point set includes the erroneous point, the initial key feature point set is reacquired until a key feature point set that meets the human body size standard is obtained.

[0016] According to a human body size measurement method provided by the present invention, the first type of abnormal point correction is performed on the key feature point set based on the human body symmetry rule to obtain a first key feature point set, including:

[0017] Based on the human body symmetry rule, obtaining the size information of the same parts on both sides of the human body symmetry axis;

[0018] Perform a first type of outlier correction on the key feature point set according to the size information to obtain a first key feature point set.

[0019] According to a human body size measurement method provided by the present invention, performing a first type of abnormal point correction on the key feature point set according to the size information to obtain a first key feature point set includes:

[0020] Calculate the size difference of the same parts on both sides of the symmetry axis of the human body;

[0021] comparing the size difference with a size threshold;

[0022] A first type of outliers is determined according to the comparison result and the first type of outliers is corrected to obtain a first set of key feature points.

[0023] According to a human body size measurement method provided by the present invention, based on the normal points in the first key feature point set, the first key feature point set is corrected for the second type of abnormal points by surface fitting to obtain a target key feature point set, including:

[0024] Screening the second type of abnormal points from the first set of key feature points;

[0025] Solving the surface function by surface fitting according to the normal points in the first set of key feature points;

[0026] Based on the surface function, the depth of the second type of abnormal points is corrected to obtain a set of target key feature points.

[0027] According to a human body size measurement method provided by the present invention, screening the second type of abnormal points in the first key feature point set includes:

[0028] Obtaining depth values ​​of all first key feature points in the first key feature point set;

[0029] Obtaining a depth average of all the first key feature points according to the depth values ​​of all the first key feature points;

[0030] Calculate the difference between the depth value of each of the first key feature points and the depth mean;

[0031] When the difference between the depth value of the first key feature point and the depth mean is greater than a depth threshold, the first key feature point is a second-type abnormal point.

[0032] The present invention also provides a human body dimension measuring device, comprising:

[0033] An acquisition module, used for obtaining a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard;

[0034] A first correction module, used for performing a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set;

[0035] A second correction module is used to correct the second type of abnormal points by surface fitting based on the normal points in the first key feature point set to obtain a target key feature point set;

[0036] The measuring module is used to measure the dimensions of key parts of the human body based on the target key feature point set.

[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned human body dimension measurement methods is implemented.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the human body dimension measurement method described in any one of the above is implemented.

[0039] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for measuring human body dimensions.

[0040] The human body size measurement method, device and electronic device provided by the present invention preliminarily screen the key feature points of the human body through the constraints of the human body size standard, and correct the first type of abnormal points and the second type of abnormal points in the key feature points of the human body after screening, thereby improving the accuracy of the key feature points of the human body and further improving the accuracy of human body size measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a schematic flow chart of the human body size measurement method provided by the present invention;

[0043] Figure 2 It is a schematic diagram of a process of obtaining a set of key feature points that meet human body size standards provided by the present invention;

[0044] Figure 3 It is a schematic diagram of an initial key feature point set provided by the present invention;

[0045] Figure 4 is a schematic diagram of a process for obtaining a first set of key feature points provided by the present invention;

[0046] Figure 5 It is a flow chart of performing first type of abnormal point correction on the key feature point set according to the size information to obtain a first key feature point set provided by the present invention;

[0047] Figure 6 It is a schematic diagram of the dimensions of the same parts on both sides of the symmetry axis of the human body provided by the present invention;

[0048] Figure 7 It is a schematic diagram of a process for obtaining a target key feature point set provided by the present invention;

[0049] Figure 8 is a schematic diagram of the second type of abnormal points provided by the present invention;

[0050] Fig. 9 It is a schematic diagram of the process of screening the second type of abnormal points provided by the present invention;

[0051] Fig.10 It is a structural schematic diagram of a human body dimension measuring device provided by the present invention;

[0052] Fig.11 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figure 1-Figure 9 A method for measuring human body dimensions of the present invention is described, the method comprising:

[0055] S101: According to the human body size standard, a set of key feature points that meet the human body size standard is obtained based on a depth camera.

[0056] For example, the human body size standard may be a human body size standard issued by various countries, such as the "Chinese Adult Human Body Size" issued by China. The selection of which country's standard is based on the physiological characteristics of the person to whom the key feature point set belongs. For example, when the person is a Chinese adult, the "Chinese Adult Human Body Size" can be used as the human body size standard.

[0057] Based on the above human body size standard, a set of key feature points of the human body that meets the human body size standard is obtained.

[0058] S102: performing a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set.

[0059] Taking the line connecting the bridge of nose and navel as the axis, for a complete human body, the two sides of the axis are basically symmetrical. Therefore, the size difference of the same part on the left and right sides of the axis will not be too large. For example, the length of the left forearm and the length of the right forearm are very small or the same.

[0060] Based on the above human body symmetry rule, the first type of abnormal point is found in the key feature point set. The first type of abnormal point is a point that makes the size difference of the same part on the left and right sides of the human body axis too large. After obtaining the first abnormal point, the first abnormal point is corrected, and the first key feature point set is obtained after correction.

[0061] S103: Based on the normal points in the first key feature point set, the first key feature point set is corrected for the second type of abnormal points by means of surface fitting to obtain a target key feature point set.

[0062] Exemplarily, human body surface information can be obtained through surface fitting based on normal points in the first key feature point set. The second type of abnormal points are points floating a certain distance away from the human body surface. The second type of abnormal points are corrected to be located on the human body surface.

[0063] S104: Dimensional measurement of key parts of the human body based on the target key feature point set.

[0064] Specifically, after obtaining the corrected target key feature point set, the size of the key part of the human body can be measured according to the target key feature points in the target key feature point set.

[0065] The human body size measurement method provided by the present invention preliminarily screens the key feature points of the human body through the constraints of the human body size standard, and corrects the first type of abnormal points and the second type of abnormal points in the key feature points of the human body after the screening, thereby improving the accuracy of the key feature points of the human body and further improving the accuracy of the human body size measurement.

[0066] In one embodiment, Figure 2 As shown, the key feature point set that meets the human body size standard is obtained based on the depth camera according to the human body size standard, including:

[0067] S201: Acquire three-dimensional depth point cloud data of a human body based on a depth camera.

[0068] The three-dimensional depth point cloud data is composed of multiple points with three-dimensional coordinates, wherein the plane where the X-axis and the Y-axis in the three-dimensional coordinates are located can be a plane parallel to the coronal plane of the human body, and the Z-axis is perpendicular to the X-axis and the Y-axis respectively.

[0069] S202: Determine an initial key feature point set of the human body according to the three-dimensional depth point cloud data of the human body.

[0070] An initial key feature point set of a human body is determined according to the point cloud data, wherein the initial key feature point set includes a plurality of key feature points of the human body and corresponding three-dimensional coordinate information.

[0071] For example, when selecting the initial key feature points of the human body for human body parts, reference can be made to the existing principles for selecting key feature points of the human body. Figure 3 As shown in , the initial key feature point set may include:

[0072] Key point name Key point symbols nose <![CDATA[P 1 ]]> Chest <![CDATA[P 2 ]]> left wrist <![CDATA[P 3 ]]> Left Arm <![CDATA[P 4 ]]> Left shoulder <![CDATA[P 5 ]]> Right shoulder <![CDATA[P 6 ]]> Right Arm <![CDATA[P 7 ]]> right wrist <![CDATA[P 8 ]]> abdomen <![CDATA[P 9 ]]> Left pelvis <![CDATA[P 10 ]]> Right pelvis <![CDATA[P 11 ]]> Left knee <![CDATA[P 12 ]]> right knee <![CDATA[P 13 ]]> Left ankle <![CDATA[P 14 ]]> Right ankle <![CDATA[P 15 ]]>

[0073] S203: Determine whether the initial key feature point set includes erroneous points that do not meet human body size standards.

[0074] When judging whether the initial key feature point set includes erroneous points that do not meet the human body size standard, the distance function is first defined. The initial key feature point P i With the initial key feature point P j The three-dimensional distance function between is:

[0075]

[0076] Based on the defined distance function, the constraint formula is defined according to the physiological characteristics of the person to whom the initial key feature point set belongs. The key feature points that do not meet the constraint formula are error points.

[0077] For example, when the person to whom the initial key feature point set belongs is an Asian adult, the constraint formula may be defined as follows:

[0078] 0.18m <Distance(P 1 ,P 2 )<0.24m,

[0079] 0.10P <Distance(P 2 ,P 5 ),Distance(P 2 ,P 6 )<0.25m,

[0080] 0.279m <Distance(P 5 ,P 4 ),Distance(P 6 ,P 7 )<0.363m,

[0081] 0.186m <Distance(P 3 ,P 4 ),Distance(P 7 ,P 8 )<0.278m,

[0082] 0.379m <Distance(P 10 ,P 12 ),Distance(P 11 ,P 13 )<0.572m,

[0083] 0.304m <Distance(P 12 ,P 14 ),Distance(P 13 ,P 15 )<0.484m.

[0084] Based on the above constraint formula, for example, when Distance(P 2 ,P 5 )≤0.10m or when Distance(P 2 ,P 5 )≥0.25m, it means P 2 and / or P 5 For error point.

[0085] S204: When the initial key feature point set includes the erroneous point, reacquire the initial key feature point set until a key feature point set that meets the human body size standard is obtained.

[0086] Based on the above steps, it can be understood that when an error point appears, it means that there is an error in the three-dimensional depth point cloud data of the human body obtained based on the depth camera. At this time, the three-dimensional depth point cloud data of the human body obtained this time is abandoned, and the three-dimensional depth point cloud data of the human body is re-acquired based on the depth camera.

[0087] After reacquisition, the initial key feature point set of the human body is determined, and it is judged whether the initial key feature point set includes erroneous points that do not meet the human body size standard. Until it is determined that the initial key feature point set does not include erroneous points that do not meet the human body size standard, the initial key feature point set at this time is the required key feature point set.

[0088] In one embodiment, reference Figure 4 As shown in , the first type of abnormal point correction is performed on the key feature point set based on the human body symmetry rule to obtain a first key feature point set, including:

[0089] S401: Based on the human body symmetry rule, the size information of the same parts on both sides of the human body symmetry axis is obtained.

[0090] Specifically, the first type of abnormal point is a point that causes the size difference of the same part on the left and right sides of the human body axis to be too large. Therefore, before screening the first type of abnormal points, it is necessary to first obtain the size information of the same part on both sides of the human body symmetry axis.

[0091] S402: Performing a first type of outlier correction on the key feature point set according to the size information to obtain a first key feature point set.

[0092] It can be understood that based on the size information of the same parts on both sides of the human body's symmetry axis obtained in the above steps, it can be determined whether there is a first-type abnormal point and which point the first-type abnormal point is.

[0093] After the first outlier point is obtained, the first outlier point is corrected, and after the correction, a first key feature point set is obtained.

[0094] In one embodiment, Figure 5 As shown, the first type of outlier correction is performed on the key feature point set according to the size information to obtain a first key feature point set, including:

[0095] S501: Calculate the size difference of the same parts on both sides of the symmetry axis of the human body.

[0096] Exemplary, reference Figure 6 As shown in , after obtaining the size information of the same parts on both sides of the human body's symmetry axis, the size difference of the same parts on both sides of the human body's symmetry axis is calculated.

[0097] S502: Compare the size difference with a size threshold.

[0098] Furthermore, the size difference is compared with the size threshold. If the size difference is greater than the size threshold, it indicates that there are first-class abnormal points, and if the size difference is less than the size threshold, it indicates that there are no first-class abnormal points.

[0099] S503: Determine a first type of outlier points according to the comparison result and correct the first type of outlier points to obtain a first key feature point set.

[0100] After the first type of outliers are determined according to the comparison results, the first type of outliers need to be corrected. Figure 6 As shown in , the first type of outliers can be corrected by the following formula:

[0101]

[0102] For W i For example, when |W i+3 -W i |<0.2m, it means W i There are no first-class abnormal points in the key feature points at both ends, and no correction is required; when |W i+3 -W i |≥0.2m, it means W i The key feature points at both ends include the first type of outliers. At this time, the first type of outliers need to be repaired to make W i =W i+3 .

[0103] For example, when |W 4 -W 1 |≥0.2m, it can be considered that P 6 is the first abnormal point, so that W 1 =W 4 , then by moving P 6 , so that W 1 =W 4 .

[0104] In one embodiment, Figure 7 As shown, based on the normal points in the first key feature point set, the first key feature point set is corrected for the second type of abnormal points by surface fitting to obtain the target key feature point set, including:

[0105] S701: Screening the second type of abnormal points in the first key feature point set.

[0106] Specifically, after obtaining the first key feature point set, the second type of abnormal points are screened in the first key feature point set.

[0107] S702: solving a surface function by surface fitting according to normal points in the first key feature point set;

[0108] Exemplary, reference Figure 8 As shown in 1 For a determined second-class outlier point, after determining all the second-class outliers, we get the second-class outlier point set P′ K After that, we can get the first key feature point set P I Filter out the normal point set

[0109] After obtaining the normal point set P H Then, the surface function of the normal point set is solved by surface fitting:

[0110] (1) Define the surface function:

[0111] z=ax+by+c

[0112] (2) Solution process:

[0113]

[0114] Among them, r is the normal point set P H The number of midpoints. Through the above solution process, the values ​​of a, b, and c can be solved to obtain the surface function.

[0115] S703: Based on the surface function, the depth of the second type of abnormal points is corrected to obtain a target key feature point set.

[0116] For example, after obtaining the surface function, the second type of outlier point P′ 1 The x′ in the three-dimensional coordinate value of 1 , y′ 1 Substitute the surface function and solve

[0117]

[0118] Solved Afterwards, through For the second type of outlier point P′ 1 After correcting all the second-category outliers, the target key feature point set is obtained.

[0119] In one embodiment, Fig. 9 As shown, the step of screening the second type of abnormal points in the first set of key feature points includes:

[0120] S901: Obtain depth values ​​of all first key feature points in the first key feature point set.

[0121] For example, assuming that there are n first key feature points in the first key feature point set, the first key feature point set is P I , P i ∈P I , P i (x i ,y i ,z i ).

[0122] The depth values ​​of all the first key feature points in the first key feature point set are the Z-axis coordinate values ​​z of each first key feature point. i .

[0123] S902: Obtaining a depth average of all the first key feature points according to the depth values ​​of all the first key feature points.

[0124] Exemplarily, the depth mean of all the first key feature points is calculated:

[0125]

[0126] S903: Calculate the difference between the depth value of each of the first key feature points and the depth mean.

[0127] For example, assume that the second type of outlier set is P′ K , P′ k ∈P′ K , P′ k (x′ k ,y′ k ,z′ k ), calculate the difference between the depth value of each first key feature point and the depth mean:

[0128]

[0129] S904: When the difference between the depth value of the first key feature point and the depth mean is greater than a depth threshold, the first key feature point is a second-type abnormal point.

[0130] Exemplarily, the depth threshold may be set to 0.40 m. When the difference between the depth value of the first key feature point and the depth mean is greater than the depth threshold, the first key feature point is defined as a second type of abnormal point:

[0131]

[0132] It can be seen from the above formula that in the first key feature point set, the first key feature point whose Z-axis coordinate value is 0.40 meters greater than the average Z-axis coordinate value of all points is defined as the second type of outlier.

[0133] The human body dimension measuring device provided by the present invention is described below. The human body dimension measuring device described below and the human body dimension measuring method described above can be referred to each other.

[0134] refer to Fig.10 As shown in , the human body dimension measuring device comprises:

[0135] An acquisition module 1001 is used to obtain a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard;

[0136] A first correction module 1002 is used to perform a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set;

[0137] A second correction module 1003 is used to correct the second type of abnormal points by surface fitting based on the normal points in the first key feature point set to obtain a target key feature point set;

[0138] The measurement module 1004 is used to measure the dimensions of key parts of the human body based on the target key feature point set.

[0139] The human body size measuring device provided by the present invention performs preliminary screening of key feature points of the human body through the constraints of the human body size standard, and corrects the first type of abnormal points and the second type of abnormal points in the key feature points of the human body after screening, thereby improving the accuracy of the key feature points of the human body and further improving the accuracy of human body size measurement.

[0140] Fig.11 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.11As shown, the electronic device may include: a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140. The processor 1110 may call the logic instructions in the memory 1130 to execute a human body size measurement method, the method comprising: obtaining a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard; performing a first type of abnormal point correction on the key feature point set based on the human body symmetry rule to obtain a first key feature point set; performing a second type of abnormal point correction on the first key feature point set by means of surface fitting based on the normal points in the first key feature point set to obtain a target key feature point set; and measuring the size of key parts of the human body based on the target key feature point set.

[0141] In addition, the logic instructions in the above-mentioned memory 1130 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0142] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the human body size measurement method provided by the above methods, which includes: according to the human body size standard, based on a depth camera, obtaining a set of key feature points that meet the human body size standard; based on the human body symmetry rule, performing a first type of abnormal point correction on the key feature point set to obtain a first key feature point set; based on the normal points in the first key feature point set, performing a second type of abnormal point correction on the first key feature point set by surface fitting to obtain a target key feature point set; based on the target key feature point set, measuring the size of key parts of the human body.

[0143] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the human body size measurement method provided by the above methods, the method comprising: obtaining a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard; performing a first type of abnormal point correction on the key feature point set based on the human body symmetry rule to obtain a first key feature point set; performing a second type of abnormal point correction on the first key feature point set by surface fitting based on the normal points in the first key feature point set to obtain a target key feature point set; and measuring the size of key parts of the human body based on the target key feature point set.

[0144] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0146] 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 it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring human body dimensions, It is characterized in that include: According to the human body size standard, a set of key feature points that meet the human body size standard is obtained based on a depth camera; Performing a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set, wherein the first type of abnormal point is a point where the size difference of the same part on the left and right sides of the human body axis is greater than a set size; Based on the normal points in the first key feature point set, the first key feature point set is corrected for the second type of abnormal points by surface fitting to obtain a target key feature point set, including: screening the second type of abnormal points in the first key feature point set; solving the surface function by surface fitting according to the normal points in the first key feature point set; correcting the depth of the second type of abnormal points based on the surface function, so as to obtain a target key feature point set; wherein, screening the second type of abnormal points in the first key feature point set includes: obtaining the depth values ​​of all first key feature points in the first key feature point set; obtaining the depth mean of all the first key feature points according to the depth values ​​of all the first key feature points; calculating the difference between the depth value of each of the first key feature points and the depth mean; when the difference between the depth value of the first key feature point and the depth mean is greater than the depth threshold, the first key feature point is a second type of abnormal point; The dimensions of key parts of the human body are measured based on the target key feature point set.

2. The method for measuring human body dimensions according to claim 1, It is characterized in that The method of obtaining a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard includes: Based on the depth camera, obtain the three-dimensional depth point cloud data of the human body; Determining an initial key feature point set of the human body according to the three-dimensional depth point cloud data of the human body; Determining whether the initial key feature point set includes erroneous points that do not meet human body size standards; In the case that the initial key feature point set includes the erroneous point, the initial key feature point set is reacquired until a key feature point set that meets the human body size standard is obtained.

3. The method for measuring human body dimensions according to claim 1, It is characterized in that The step of performing a first type of abnormal point correction on the key feature point set based on the human body symmetry rule to obtain a first key feature point set includes: Based on the human body symmetry rule, obtaining the size information of the same parts on both sides of the human body symmetry axis; Perform a first type of outlier correction on the key feature point set according to the size information to obtain a first key feature point set.

4. The method for measuring human body dimensions according to claim 3, It is characterized in that The performing a first type of outlier correction on the key feature point set according to the size information to obtain a first key feature point set includes: Calculate the size difference of the same parts on both sides of the symmetry axis of the human body; comparing the size difference with a size threshold; A first type of outliers is determined according to the comparison result and the first type of outliers is corrected to obtain a first set of key feature points.

5. A human body dimension measuring device, It is characterized in that include: An acquisition module is used to obtain a set of key feature points that meet the human body size standard based on a depth camera according to the human body size standard; A first correction module is used to perform a first type of abnormal point correction on the key feature point set based on a human body symmetry rule to obtain a first key feature point set, wherein the first type of abnormal point is a point that makes the size difference of the same part on the left and right sides of the human body axis greater than a set size; The second correction module is used to correct the second type of abnormal points by surface fitting based on the normal points in the first key feature point set to obtain the target key feature point set, including: screening the second type of abnormal points in the first key feature point set; solving the surface function by surface fitting according to the normal points in the first key feature point set; correcting the depth of the second type of abnormal points based on the surface function to obtain the target key feature point set; wherein, the screening of the second type of abnormal points in the first key feature point set includes: obtaining the depth values ​​of all the first key feature points in the first key feature point set; obtaining the depth mean of all the first key feature points according to the depth values ​​of all the first key feature points; calculating the difference between the depth value of each of the first key feature points and the depth mean; when the difference between the depth value of the first key feature point and the depth mean is greater than the depth threshold, the first key feature point is a second type of abnormal point; The measuring module is used to measure the dimensions of key parts of the human body based on the target key feature point set.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the human body dimension measurement method according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the human body dimension measurement method according to any one of claims 1 to 4 is implemented.

8. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the human body dimension measurement method according to any one of claims 1 to 4 is implemented.

Images