Self-adaptive adjustment high-precision body feature measurement system

Abstract

The invention discloses a self-adaptive adjustment high-precision body feature measurement system, which comprises a depth camera and a computer, and is characterized in that the computer executes algorithm operation according to an image obtained by the depth camera to obtain body feature data, and the self-adaptive adjustment high-precision body feature measurement system comprises a mobile device, the depth camera is mounted on the mobile device and can image a measured object; and outputting the distance from the camera to the measured object. The testee opens the hand within the visual field range of the depth camera according to the guidance, and the initial palm length h1 is obtained through shooting and operation. The mobile device adjusts the shooting height and the distance between the mobile device and the shot object, so that the shot object measures the palm length value h2 again at a new position within the 80% vision field range of the depth camera, and the measurement is repeated until the change of two adjacent measurement results is smaller than A. Through the method, the depth camera can be operated, and the palm length of a person can be accurately measured in combination with a visual program. The method is simple to operate, scientific, wide in application range, low in system cost and worthy of popularization and application.

Description

Technical Field

[0001] The present invention relates to the field of visual detection technology, and more specifically, to an adaptively adjusted high-precision body feature measurement system. Background Art

[0002] Computer vision is widely used in the engineering field. At present, some studies have applied visual detection technology to the measurement of physical features to quickly screen suitable talents, such as athlete selection. For example, a depth camera and Mediapipe framework are used for data collection and analysis. Mediapipe is an open source cross-platform multimedia processing framework developed by Google, focusing on building machine learning applications, supporting 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, image acquisition based on depth cameras still faces the problem of lens distortion, especially in the edge area of ​​the image, resulting in large errors in the detection results. The existing technology mainly handles the distortion problem through image correction algorithms. For example, a machine vision image correction method for online detection disclosed in Application No. 2019100624027 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 requirements of real-time and high efficiency. Summary of the invention

[0003] The purpose of the present invention is to provide an adaptively adjusted high-precision body feature measurement system, which can solve the problem of lens distortion affecting the detection results through simple operation and limited calculation. The system adopts 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 invention is: an adaptively adjusted high-precision body feature measurement system, comprising a depth camera, a computer executing an algorithm operation based on an image obtained by the depth camera to obtain body feature data, characterized in that it also includes a mobile device, the depth camera is installed on the mobile device so that the depth camera adjusts the shooting height and the distance from the photographed object, and the measurement method comprises the following steps:

[0005] 1) The imaging system obtains the image data of the photographed object, and the computer algorithm calculates the initial palm length value h 1 Initial physical characteristics data;

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

[0007]

[0008] 3) The depth camera moves ΔM in the X-axis and Z-axis directions X With ΔM Z , measure the length of the human palm again 2 :

[0009] ΔM Z =Ch 1 -Ch 2 (3)

[0010] ΔM X =d 1 -d 2 (4)

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

[0012]

[0013] In the above-mentioned self-adaptive high-precision body feature measurement system, the value of A is less than 3%.

[0014] In the above-mentioned adaptive adjustment high-precision body feature measurement system, A is 1%.

[0015] The above-mentioned adaptive adjustment high-precision body feature measurement system, the moving device includes a base, a bracket, a servo motor, and a first and a second sliding pair driven by the servo motor. The first sliding pair enables the bracket to move linearly along the base, and the second sliding pair enables the depth camera to move linearly along the bracket.

[0016] The present invention has the following beneficial effects: the present invention arranges the photographed object within 80% of the field of view of the depth camera by moving the depth camera, and after N times of movement and measurement of data, until the data change between two adjacent measurements is less than 1%, the accurate physical characteristic data of the subject is obtained. The method of the present invention is simple to operate, avoids a large amount of system calculation workload, and is combined with a depth camera displacement device to obtain accurate data with simple and limited measurements. The method is scientific, has a wide range of applications, and has a low system cost, and is worthy of promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the adaptively adjusted high-precision body feature measurement system of the present invention.

[0018] Figure 2 This is a schematic diagram of the actual working of the self-adaptive high-precision body feature measurement system of the present invention.

[0019] Figure 3Schematic diagram of the length of the object being measured by the adaptively adjusting high-precision body feature measurement system of the present invention.

[0020] Figure 4 It is a schematic diagram of the structure of the adaptively adjusted high-precision body feature measurement system of the present invention.

[0021] Figure 5 A schematic structural diagram of another embodiment of the adaptively adjusted high-precision body feature measurement system of the present invention.

[0022] in, Figures 1 to 5 The corresponding relationship between the reference numerals and component names in the figure is:

[0023] 1 moving device, 2 base, 3 bracket, 4 servo motor, 5 first sliding pair, 6 second sliding pair, 7 slider, 8 screw rod, 9 third sliding pair, 10 belt, 11 QR code. DETAILED DESCRIPTION

[0024] The technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0025] The components of the embodiments of the present application generally 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 application claimed, but merely represents the selected embodiments of the present application.

[0026] Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of this application.

[0027] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0028] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0029] See also Figure 1-Figure 5 Taking the detection of the length of a human palm as an example, the self-adaptive adjustment high-precision body feature measurement system of the present invention is described. The measurement method of the system includes the following steps:

[0030] S1) The imaging system obtains the image data of the photographed object, and the computer algorithm calculates the initial body feature data; taking the measurement of palm length as an example, the subject sits next to the test platform, a vertical board is placed on the platform, and a QR code 11 is attached to the board. This QR code 11 is used to activate the Mediapipe open source framework program built into the depth camera during the test, so that the depth camera automatically collects data; let the subject place the palm vertically on the platform, next to the QR code 11, and in the same plane as the vertical board; the depth camera is directly in front of the palm of the person to be tested, and the distance from the vertical board is dcm, the height of the depth camera from the test platform is Chcm, the vertical viewing angle α of the depth camera is 55°, and when measuring for the first time, the depth camera is at a height of Ch from the test platform 1 , the distance from the subject is d 1 (Default is the distance from the vertical board), and the initial palm length of the person is measured as h 1 ;

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

[0032]

[0033]

[0034] In formula (1), h 1 is the height of the object measured for the first time, Ch 2 is the adjusted height of the depth camera, d2 is the adjusted distance between the depth camera and the object being measured, and α is the vertical viewing angle of the depth camera (the depth lens A of the Obbec Gemini2 VD =66°, RGB lens A VC =55°, take α=min(AVD , Avc)=55°).

[0035] S3) Servo motor 4 drives the depth camera to move in the X-axis and Z-axis directions, and the moving distance is ΔM X With ΔM Z , in cm:

[0036] ΔM Z =Ch 1 -Ch 2 (3)

[0037] ΔM X =d 1 -d 2 (4)

[0038] In formula (3), ΔM Z is the distance that the depth camera needs to be offset on the Z axis, Ch 1 is the initial height of the depth camera; in equation (4), ΔM X is the distance that the depth camera needs to be offset on the X axis, d 1 is the initial horizontal distance between the depth camera and the object being measured.

[0039] Measure the length of the human palm again and find it is h 2 ;

[0040] S4) returns to step S2), calculates Ch n With d n When Δh or ΔCh is less than 1%, the measurement ends and the system outputs the last measured value h n is the length of the subject’s palm.

[0041]

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

[0043] In addition, the mobile device 1 includes a base 2, a bracket 3, a servo motor 4, and a first and second sliding pair driven by the servo motor 4. The first sliding pair 5 makes the bracket 3 move linearly along the base 2, and the second sliding pair 6 makes the depth camera move linearly along the bracket 3. The first sliding pair 5 and the second sliding pair 6 are both composed of a slider 7, a slider nut and a screw 8. In another embodiment of the mobile device, the servo motor 4 is included, and the third sliding pair 9 driven by the servo motor 4 is composed of a slider 7, a belt 10, a pulley and a motor. The third sliding pair 10 makes the slider 7 move linearly along the belt 10.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptively adjusted high-precision body feature measurement system, comprising a depth camera, a computer executing an algorithm based on an image obtained by the depth camera to obtain body feature data, characterized in that: The mobile device is also included, and the depth camera is installed on the mobile device so that the depth camera can adjust the shooting height and the distance from the object being photographed. The measurement method includes the following steps: 1) The imaging system acquires image data of the photographed object, and the computer algorithm calculates and obtains initial body feature data including an initial palm length value h1; 2) Adjust the height Ch and distance d of the depth camera so that the object is within 80% of the field of view of the depth camera, and obtain the formula: In formula (1), h1 is the height of the object measured for the first time, Ch2 is the height of the depth camera from the test platform after adjustment, d2 is the distance between the depth camera and the object after adjustment, and α is the vertical viewing angle of the depth camera; 3) The depth camera moves ΔM in the X-axis and Z-axis directions X With ΔM Z , measure the human palm length h2 again: ΔM Z =Ch1-Ch2 (3) ΔM X =d1-d2 (4) In formula (3), ΔM Z is the distance that the depth camera needs to be offset on the Z axis, 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 be offset on the X axis, and d1 is the initial horizontal distance between the depth camera and the object being measured; 4) Return to step 2 and calculate Δh. When |Δh| is less than A, the measurement ends. In formula (5), h n Indicates the height of the object measured for the nth time, h n-1 Indicates the height of the object measured for the n-1th time.

2. The self-adaptive high-precision body feature measurement system according to claim 1, characterized in that: The value of A is less than 3%.

3. The self-adaptive high-precision body feature measurement system according to claim 1, characterized in that: A is 1%.

4. The self-adaptive high-precision body feature measurement system according to claim 1, characterized in that: The mobile device includes a base, a bracket, a servo motor, and a first and a second sliding pair driven by the servo motor. The first sliding pair enables the bracket to move linearly along the base, and the second sliding pair enables the depth camera to move linearly along the bracket.

Images