An adaptive adjustment high-precision body feature measurement system

Abstract

The application discloses a kind of self-adapting adjustment high-precision body feature measurement system, including depth camera, computer is according to the image obtained by depth camera and executes algorithm operation and obtains body feature data, it is characterized in that, including mobile device, depth camera is installed on mobile device, can be imaged to measured object, and output camera to the distance of measured object.According to the instruction, hand is opened in the depth camera visual field range, and initial palm length h1 is obtained by being photographed and being operated.Mobile device adjusts the height of shooting, the distance with the object of being photographed, makes the object of being photographed in the 80% visual field range of depth camera, palm length value h2 is measured again in new position, so repeatedly measure until the change of adjacent two measurement results is less than A.By the method of the application, depth camera can be operated, combined with visual program, the palm length of person is accurately measured.The method of the application is simple to operate, scientific method, wide adaptation range, low system cost, and is worth popularization and application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of visual detection, more particularly, to a self-adaptive adjustment high-precision body feature measurement system. BACKGROUND

[0002] Computer vision is widely used in engineering field. At present, some researches have applied visual detection technology to body feature measurement to quickly screen suitable talents, such as athlete selection. For example, a depth camera and a Mediapipe framework are used for data acquisition and analysis. Mediapipe is an open-source cross-platform multimedia processing framework developed by Google, which focuses on building machine learning applications, such as face detection, key point extraction, gesture recognition, and posture recognition. The pre-trained model of Mediapipe can quickly extract body features such as palm length, palm contour, palm area, height, and arm span. However, the image acquisition based on the depth camera still faces the problem of lens distortion, especially in the edge area of the image, which leads to a large error in the detection result. The existing technology mainly deals with the distortion problem through image correction algorithms, such as a machine vision image correction method for online detection disclosed in application No. 2019100624027, which converts the distorted image from the distorted coordinate system to the standard coordinate system through a checkerboard calibration plate. However, such methods usually require complex correction processes and a large amount of computing resources, which are difficult to meet the real-time and high-efficiency requirements. SUMMARY

[0003] The purpose of the present application is to provide a self-adaptive adjustment high-precision body feature measurement system, which can solve the problem of lens distortion affecting the detection result through simple operation and limited calculation. The system uses a simple and scientific calculation method to obtain more accurate body feature data, thereby overcoming the shortcomings of the prior art.

[0004] The technical solution of the present application is a self-adaptive adjustment high-precision body feature measurement system, which comprises a depth camera, and a computer performs algorithm operation on the image obtained by the depth camera to obtain body feature data, characterized in that it further comprises a mobile device, and the depth camera is installed on the mobile device to adjust the shooting height and the distance from the photographed object. The measurement method comprises the following steps:

[0005] 1) An imaging system obtains image data of a photographed object, and a computer algorithm operation obtains initial body feature data containing an initial palm length value h1;

[0006] 2) Adjust the height Ch and the distance d of the depth camera from the test platform, so that the photographed object is within the 80% visual range of the depth camera, and the formula is obtained:

[0007]

[0008] 3) Depth camera moves in X axis, Z axis direction ΔM X with ΔM Z Again, measure the palm length value h2 of the human body:

[0009] ΔM Z = Ch1-Ch2 (3)

[0010] ΔM X = d1-d2 (4)

[0011] 4) Return to step 2, calculate Ch n with d n , until |Δh| or |ΔCh| is less than A, the measurement is finished,

[0012]

[0013] The adaptive adjustment high-precision body feature measurement system has A less than 3%.

[0014] The adaptive adjustment high-precision body feature measurement system has A being 1%.

[0015] The adaptive adjustment high-precision body feature measurement system has the moving device including a base, a support, a servo motor, a first sliding part and a second sliding part driven by the servo motor, the first sliding part enabling the support to move linearly along the base, and the second sliding part enabling the depth camera to move linearly along the support.

[0016] The present application has the following beneficial effects: the present application enables the photographed object to be arranged within the 80% visual range of the depth camera by moving the depth camera, and through N times of movement and measurement data, until the data change of adjacent two times of measurement is less than 1%, the accurate body feature data of the measured person is obtained. The present application has simple operation, avoids a large amount of system operation workload, and combines the depth camera displacement device, so that accurate data can be obtained through simple and limited times of measurement. The method is scientific, has wide adaptation range, has low system cost, and is worth popularization and application. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The adaptive adjustment high-precision body feature measurement system is a flow chart.

[0018] Figure 2 The adaptive adjustment high-precision body feature measurement system is a practical working schematic diagram.

[0019] Figure 3 The adaptive adjustment high-precision body feature measurement system is a measurement object length schematic diagram.

[0020] Figure 4The structure schematic diagram of the adaptive adjustment high-precision body feature measurement system of the present application.

[0021] Figure 5 The structure schematic diagram of another embodiment of the adaptive adjustment high-precision body feature measurement system of the present application.

[0022] Correspondence between reference signs and component names in the drawings is as follows: Figures 1 to 5

[0023] 1 mobile device, 2 base, 3 support, 4 servo motor, 5 first sliding part, 6 second sliding part, 7 sliding block, 8 screw rod, 9 third sliding part, 10 belt, 11 two-dimensional code. DETAILED DESCRIPTION

[0024] The technical solutions of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0025] The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application.

[0026] Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts fall within the scope of protection of the present application.

[0027] In the description of the present application, it should be noted that the orientations or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and are not intended to indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0028] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. ​

[0029] Referring to Figures 1-5 The adaptive adjustment high-precision body feature measurement system of the present application is described by taking the detection of the palm length of a human body as an example, and the measurement method of the system comprises the following steps:

[0030] S1) The imaging system acquires image data of the photographed object, and the computer algorithm calculates the initial body feature data; taking the measurement of the palm length as an example, the subject sits beside the test platform, and a vertical plate is placed on the platform, and a two-dimensional code 11 is attached to the plate, which is used to activate the Mediapipe open source framework program built in the depth camera during the test, so that the depth camera automatically collects data; the subject is required to place the palm vertically on the platform, beside the two-dimensional code 11, and in the same plane as the vertical plate; the depth camera is in front of the palm of the person to be measured, and the distance between the depth camera and the vertical plate is dcm, the height of the depth camera from the test platform is Chcm, and the vertical viewing angle of the depth camera is 55°; in the first measurement, the depth camera is at a height of Ch1 from the test platform and at a distance of d1 (by default, the distance from the vertical plate) from the photographed object, and the initial palm length value of the human body is h1;

[0031] S2) According to the fact that the local distortion of the image within 80% of the field of view of the depth camera is low, the height Ch and the distance d of the depth camera are adjusted so that the photographed object is within the 80% field of view of the depth camera, at this time, the distance of the depth camera from the test platform is adjusted to be half of the initial palm length value, and the formula is obtained:

[0032]

[0033]

[0034] In formula (1), h1 is the height of the measured object measured for the first time, Ch2 is the adjusted height of the depth camera, d2 is the distance of the adjusted depth camera from the measured object, and a is the vertical viewing angle of the depth camera (the depth lens A VD of the Obi Middle Light Gemini2 is 66°, and the RGB lens A VC is 55°, and a = min(A VD , Avc) = 55°).

[0035] S3) The servo motor 4 drives the depth camera to move in the X-axis and Z-axis directions, and the moving distance is AM X and AM Z , unit: cm:

[0036] AM Z = Ch1-Ch2 (3)

[0037] AM X = d1-d2 (4)

[0038] In formula (3), ΔM Z is the distance that the depth camera needs to offset in the Z axis, and Ch1 is the initial height of the depth camera; in formula (4), ΔM X is the distance that the depth camera needs to offset in the X axis, and d1 is the initial horizontal distance of the depth camera from the measured object.

[0039] The palm length value of the human body is measured again as h2;

[0040] S4) return to step S2), calculate Ch n and d n When Δh or ΔCh is less than 1%, the measurement is ended, and the system outputs the last measured value h n as the palm length value of the measured object.

[0041]

[0042] In formula (5), h n represents the height of the measured object measured for the nth time, h n-1 represents the height of the measured object measured for the (n-1)th time.

[0043] In addition, the moving device 1 comprises a base 2, a support 3, a servo motor 4, a first sliding part 5 driven by the servo motor 4, the first sliding part 5 enabling the support 3 to move linearly along the base 2, and a second sliding part 6 driven by the servo motor 4, the second sliding part 6 enabling the depth camera to move linearly along the support 3. The first sliding part 5 and the second sliding part 6 are both composed of a sliding block 7, a sliding block nut, and a screw rod 8. In another embodiment of the moving device, a third sliding part 9 driven by the servo motor 4 is comprised, the third sliding part 9 is composed of the sliding block 7, a belt 10, a belt pulley, and a motor, and the third sliding part 10 enables the sliding block 7 to move linearly along the belt 10.

[0044] Although the embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An adaptive adjustment high-precision body feature measurement system comprising a depth camera, a computer performing algorithm operation according to images obtained by the depth camera to obtain body feature data, characterized in that, Also included is a mobile device, the depth camera is installed on the mobile device to adjust the shooting height and distance to the object, the measuring method includes the following steps: 1) The imaging system acquires image data of the object, and a computer algorithm calculates the initial body feature data containing an initial palm length value h1; 2) Adjust the height Ch and distance d of the depth camera so that the object is within the 80% visual range of the depth camera, and the formula is obtained: Ch2= h1 (1) d2= =0.625h1 / tg (2) In formula (1), h1 is the height of the measured object measured for the first time, Ch2 is the height of the depth camera from the test platform after adjustment, d2 is the distance of the depth camera from the measured object after adjustment, and a is the vertical visual angle of the depth camera; 3) Depth camera moves in X-axis, Z-axis direction by ΔM X with ΔM Z， Measure the palm length value of the human body again h2: ΔM Z = Ch1 - Ch2 (3) ΔM X = d1 - d2 (4) In formula (3), ΔM Z is the distance that the depth camera needs to offset in the Z axis, and Ch1 is the initial height of the depth camera from the test platform; in formula (4), ΔM X is the distance that the depth camera needs to offset in the X axis, and d1 is the initial horizontal distance of the depth camera from the measured object. 4) Return to step 2 and calculate Δh until |Δh| is less than A, and the measurement is complete, Δh= (5) In formula (5), represents the height of the measured object measured at the nth time, represents the height of the measured object measured at the n-1th time.

2. The self-adapting high precision body feature measurement system of claim 1, wherein, A is less than 3%.

3. The self-adjusting high precision body feature measurement system of claim 1, wherein, A is 1%.

4. The self-adjusting high precision body feature measurement system of claim 1, wherein, The mobile device includes a base, a support, a servo motor, a first sliding part driven by the servo motor, the first sliding part moving the support linearly along the base, and a second sliding part moving the depth camera linearly along the support.

Images