Pedestrian height measuring method and system based on 3D vision technology and pass gate

Through the pedestrian height measurement method based on 3D vision technology, using camera equipment and image processing algorithms, the problems of inaccurate and low efficiency of pedestrian height measurement in the existing technology are solved, high-precision and efficient height recognition are achieved, and the passive experience is improved .

CN119091468AInactive Publication Date: 2024-12-06SHENZHEN TELEWAY INTELLIGENT FACILITY
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411285970.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-13
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art has problems such as large measurement error, low efficiency and susceptibility to the environment in pedestrian height measurement, which cannot meet the needs of high-precision measurement of dynamic walking.

Method used

The pedestrian height measurement method based on 3D vision technology is adopted to capture pedestrian images through the camera equipment, obtain relative position data, combine the current height of the camera equipment, and calculate the pedestrian height value using image processing and algorithms to achieve dynamic high-precision height recognition.

Benefits of technology

It improves the accuracy and stability of measurement, realizes high-precision height recognition without any sense of pedestrians, and improves traffic efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091468A_ABST
    Figure CN119091468A_ABST
Patent Text Reader

Abstract

The invention discloses a pedestrian height measuring method and system based on a 3D vision technology and a pass gate. The method comprises the following steps: shooting a person image of a to-be-measured person entering a passing area through a camera device; acquiring relative position data between the camera equipment and the personnel according to the personnel image; and calculating the height value of the person to be measured according to the current height of the camera device and the relative position data. Pedestrian images are captured in real time through the 3D vision technology, dynamic measurement of the height of pedestrians is achieved through image processing and an algorithm, and non-inductive high-precision height recognition of the pedestrians is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a pedestrian height measurement method, system and access gate based on 3D vision technology. Background Art

[0002] At present, height recognition equipment has been widely used in various scenarios and fields. In some usage scenarios, it is necessary to recognize the heights of people of different heights in order to divide them into different groups.

[0003] For example, in some public places and entertainment venues, it is necessary to determine whether pedestrians can enjoy preferential policies or participate in certain activities based on their height. Existing technologies mainly rely on manual measurement or simple sensors (such as infrared and ultrasonic sensors) or visual cameras to measure height. These measurement methods have problems such as large measurement errors, low efficiency, and susceptibility to environmental influences. At the same time, they cannot meet the needs of high-precision measurement of dynamic pedestrian walking. Summary of the invention

[0004] The purpose of the present invention is to provide a pedestrian height measurement method, system and access gate based on 3D vision technology, aiming to solve the problem of inaccurate pedestrian height measurement in existing traffic scenarios.

[0005] In a first aspect, an embodiment of the present invention provides a method for measuring a person's height based on 3D vision technology, comprising: Capture images of persons to be measured who enter the passage area through a camera device; Acquiring relative position data between the camera device and the person according to the person image; The height value of the person to be measured is calculated according to the current height of the camera device and the relative position data.

[0006] In a second aspect, an embodiment of the present invention provides a system for measuring a person's height based on 3D vision technology, comprising: An image acquisition unit, used to capture images of persons to be measured who enter the passage area through a camera device; A position acquisition unit, used for acquiring relative position data between the camera device and the person according to the person image; The height calculation unit is used to calculate the height value of the person to be measured according to the current height of the camera device and the relative position data.

[0007] In a third aspect, an embodiment of the present invention provides a passage gate, including an automatic gate and a camera device; the camera device is mounted on the automatic gate and is at a preset height, and the camera device is equipped with a pedestrian height measurement system based on 3D vision technology as described above.

[0008] The beneficial effects of the embodiments of the present invention are: introducing 3D vision technology to capture pedestrian images in real time, using image processing and algorithms to achieve dynamic measurement of pedestrian height, and realizing high-precision height recognition of pedestrians without feeling, which effectively improves the accuracy and stability of measurement and improves traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for measuring the height of a pedestrian provided by an embodiment of the present invention; Figure 2 A schematic diagram of a sub-process of a pedestrian height measurement method provided by an embodiment of the present invention; Figure 3 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Figure 4 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Figure 5 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Figure 6 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Figure 7 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Figure 8 A schematic diagram of another sub-process of the pedestrian height measurement method provided by an embodiment of the present invention; Fig. 9 A schematic block diagram of a pedestrian height measurement system provided by an embodiment of the present invention; Fig.10 A schematic diagram of the principle of a method for measuring the height of a pedestrian provided by an embodiment of the present invention; Fig.11 A schematic diagram of the principle of another pedestrian height measurement method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments 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.

[0012] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0013] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0014] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] To facilitate understanding of the present invention, the scenarios in which the embodiments of the present invention are applied are first introduced.

[0016] The present invention can be applied to various scenarios that require passage detection, such as scenic spots, amusement parks, stadiums, museums, cinemas and other scenarios that require ticket inspection for entry. Pedestrians can enter after successful identification in front of the passage gate; the passage gate of the present application includes an automatic gate and a camera device (such as a 3D camera); the camera device is placed on the automatic gate, and when the pedestrian enters the measuring range of the camera device, the height of the pedestrian can be automatically measured for measurement, so as to determine which type of pedestrian the pedestrian belongs to, and automatically screen out pedestrians with non-compliant heights when checking tickets (for example, over-tall tourists using children's discount tickets and height-restricted amusement facilities are effectively prohibited from entering), thereby realizing true self-service passage with ticket inspectors on duty.

[0017] Based on the application scenario of the present invention, the pedestrian height measurement method of the present invention is specifically introduced below.

[0018] See also Figure 1 , Figure 1 A schematic diagram of a flow chart of a method for measuring the height of a pedestrian based on 3D vision technology provided by an embodiment of the present invention; like Figure 1 As shown, the method includes steps S101 to S103.

[0019] S101, capturing an image of a person to be measured who enters a traffic area through a camera device; In this step, the camera device can be placed at any height (e.g. Fig.10 then Fig.11 The camera is used at the height of D0 in the image processing unit, D0=H), and the measuring range is set to a shooting range that can obtain a complete body image of the pedestrian. When the pedestrian enters the field of view of the camera device, the pedestrian is automatically identified. When the pedestrian completely enters the measuring range, the current pedestrian image of the pedestrian is collected.

[0020] S102, acquiring relative position data between the camera device and the person according to the person image; In this step, the relative position data may include: the horizontal distance between the camera device and the person's body in the horizontal direction, the straight-line distance between the camera device and the top of the person's head in space, and the relative angle between the camera device and the top of the person's head in space.

[0021] S103, calculating the height of the person to be measured according to the current height and relative position data of the camera device; In this step, based on the horizontal distance, straight-line distance and relative angle obtained in step S102, combined with the current height of the camera device, the height value of the person to be measured can be calculated through a geometric function algorithm. Among them, regarding the current height of the camera device, when the camera device is installed and started up (or each time it is started), a height correction will be performed, that is, the horizontal ground is identified by the camera device, and the relative point of the vertical position of the camera relative to the ground is obtained, so as to know the current height of the camera device, so as to ensure the accuracy of subsequent height detection.

[0022] Based on the process of steps S101 to S103, in this embodiment, 3D vision technology (such as ToF, structured light, lidar and other technologies) is used to capture pedestrian images in real time, and image processing and algorithms are used to realize dynamic measurement of pedestrian height, thereby realizing non-perceptible high-precision height recognition of pedestrians.

[0023] Based on the pedestrian height measurement method of steps S101 to S103, a specific example is used to introduce the effect of its application in actual scenarios. For example, in a gate at the entrance of a park, the gate needs to verify the pedestrian's group when checking tickets. The pedestrian group includes adults whose height exceeds the preset height and children whose height does not exceed the preset height. The adult group needs to buy a full ticket, and the child group can receive a preferential ticket. After the pedestrian enters the measurement range, the current pedestrian image is collected, and the height value of the current pedestrian is calculated using the pedestrian height measurement method of this embodiment. When the pedestrian uses the ticket verification voucher to check the ticket in front of the gate, it is determined whether the height value of the current pedestrian meets the height condition in the ticket verification voucher. If it meets the condition, the gate is controlled to open. If it does not meet the condition, the gate is controlled to close and prompt. In this way, it can realize automatic screening of tourists with non-compliant heights during ticket checking, and realize self-service passage with real ticket inspectors on duty. Moreover, the height measurement is realized synchronously during the passage of tourists, which can realize the non-sensing passage of tourists and provide a better passage experience.

[0024] In one embodiment, if Figure 2 As shown, step S102 includes: S201. Acquire the horizontal distance between the camera device and the person's body in the horizontal direction according to the resolution information of the person's image, or measure the horizontal distance between the camera device and the person's body in the horizontal direction according to the distance measuring device; S202, acquiring the coordinates of the camera device and the top of the person's head according to the resolution information of the person's image, and calculating the straight-line distance between the camera device and the top of the person's head in space according to the coordinates of the camera device and the top of the person's head; S203: Convert the coordinates of the camera device and the top of the person's head from image coordinates to actual coordinates to obtain the relative angle between the camera device and the top of the person's head in space.

[0025] In this embodiment, the object of 3D visual processing is the object and scene in the three-dimensional space. It not only includes the resolution information on the X and Y axes, but also includes the resolution information on the Z axis. The three-dimensional coordinate information of each pixel in the image can be obtained through the resolution information of the personnel image. As for the camera device, after starting, it first identifies and finds the ground plane, and can confirm that the projection position of the camera device on the ground plane is recorded as D0 (X0, Y0), and at the same time confirm that the current height of the camera device is H.

[0026] Based on this, for the process of step S201, by obtaining the three-dimensional coordinate information of the pixel points of the person's body (specifically, the chest position) in the person image, and combining the coordinate position of the camera device, the horizontal distance between the coordinates of the two in the horizontal direction can be calculated. It should be understood that a distance measuring device (such as an infrared rangefinder) can also be directly set below the camera device, and the distance measuring device can be used to directly measure the horizontal distance between the camera device and the person's body in the horizontal direction.

[0027] Based on this, for the process of step S202, by obtaining the three-dimensional coordinate information of the pixel point at the top of the person's head in the person image and combining it with the coordinate position of the camera device, the straight-line distance between the coordinates of the two in the three-dimensional space position can be calculated.

[0028] Based on this, for the process of step S203, Fig.10 and Fig.11 Take the following scenario as an example: First, confirm the pixel size of the current pedestrian image: horizontal pixel size △x=θ H / W, vertical pixel size △y=θ V / W. Then, calculate the difference between the coordinates of the camera and the top of the person's head: horizontal angle difference △θ H = (X1-X0)·Δx = (X1-X0)·(θ H / W), vertical angle difference △θ V = (y1-y0)·Δx = (y1-y0)·(θV / H); where, θ H Represents the horizontal viewing angle of the camera, θ V represents the vertical viewing angle of the camera, W represents the width of the image (number of pixels), and H represents the height of the image (number of pixels). Finally, according to the horizontal angle difference △θ H and the vertical angle difference △θ V The relative angle between the camera device and the top of the person's head in space can be obtained.

[0029] The following describes two specific embodiments of the height measurement method preferred in this application.

[0030] Height measurement method of embodiment 1: In one embodiment, if Figure 3 As shown, step S103 includes: S301, calculating the height difference between the top of the person's head and the camera device in the height direction according to the linear distance and relative angle between the camera device and the top of the person's head in space; S302: Obtain the height value of the person to be measured according to the current height and height difference of the camera device.

[0031] In this embodiment, please refer to Fig.10According to the relative angle α and the straight-line distance L1, the trigonometric function Cosα=L2 / L1 is used to calculate the height difference L2 between the position of the camera device and the position of the pedestrian's head; then the difference between the height H of the camera device and the height difference L2 is calculated to obtain the height of the pedestrian's head from the ground, which is used as the height value of the pedestrian in the current pedestrian image.

[0032] The height measurement method of the second embodiment: In one embodiment, if Figure 4 As shown, step S103 includes: S401, calculating the angle formed between the horizontal distance and the straight-line distance; S402, calculating the height difference between the top of the person's head and the camera device in the height direction according to the included angle and the horizontal distance / straight distance; S403: Obtain the actual height of the person to be measured according to the current height and height difference of the camera device.

[0033] In this embodiment, please refer to Fig.11 , according to the horizontal distance L3 and the straight distance L1, the angle α formed between the horizontal distance and the straight distance is calculated using the trigonometric function Cosα=L3 / L1. Then, according to the formula sinα=L2 / L1 or tanα=L2 / L3, the height difference L2 between the position of the camera device and the position of the pedestrian's head in the vertical direction can be calculated; then, the height H of the camera position and the height difference L2 are calculated to obtain the height of the pedestrian's head from the ground, which is used as the height value of the pedestrian in the current pedestrian image.

[0034] Based on the solutions of the above two embodiments, 3D vision technology is used to capture pedestrian images in real time, and the combination of image processing and trigonometric functions is used to accurately measure the height of adults and children, and realize high-precision height recognition of pedestrians without feeling. This effectively improves the accuracy and stability of measurement and improves traffic efficiency.

[0035] The following describes a further optimization scheme for the height measurement process of this application.

[0036] Optimization 1: In order to improve the accuracy of height measurement, the present invention performs multiple consecutive measurements on pedestrians, and optimizes and filters the results of the multiple measurements, thereby improving the accuracy.

[0037] In one embodiment, if Figure 5 As shown, the pedestrian height measurement method based on 3D vision technology also includes: S501, collecting multiple images of persons to be measured who enter the passage area through a camera device; S502, based on a preset standard walking posture, performing credibility recognition on the walking posture of the person in each person image, and outputting the posture credibility of the walking posture of the person in each person image; S503, selecting images of persons whose posture credibility reaches a preset value as qualified images; S504, calculating the height value corresponding to the person to be measured in each qualified image; S505, selecting the maximum value of the height values ​​corresponding to all qualified images as the final height value of the person to be measured; S506: Taking the posture credibility of the qualified image corresponding to the final height value as the height credibility of the current person to be measured.

[0038] In this embodiment, based on the process of steps S501 to S506, the person to be measured in the passage area is measured multiple times by a camera device. The multiple measurements here will obtain multiple images of the person in various postures. The posture recognition algorithm is used to screen out the images of the person whose walking posture meets the standard walking posture (for example, an upright posture, unbent knees, and other postures close to a standing state, in which the height value is more accurate) from the multiple images of the person as qualified images, and then only the screened qualified images are recognized, which can greatly increase the accuracy of the measurement.

[0039] Further, all the qualified images screened out are measured for height, and after obtaining multiple pedestrian height values, the maximum value among all the pedestrian height values ​​is selected as the final height value of the pedestrian. The reason for selecting the maximum value here is that the gate is usually a single-person passage, and pedestrians usually walk through it, so pedestrians basically walk within the measurement range. When walking, one foot of the pedestrian is usually basically on the ground. Therefore, although the height of the pedestrian will fluctuate during the walking process, it will generally not exceed (or slightly exceed) the actual height of the pedestrian. Therefore, after obtaining multiple pedestrian height values ​​through multiple measurements, it is more accurate to select the maximum value among all the pedestrian height values ​​as the final height value of the current pedestrian. It should be noted that in this embodiment, the posture credibility in the qualified image corresponding to the final height value is also used as the height credibility of the current person to be measured, that is, the higher the height credibility, the higher the accuracy of the measured final height value.

[0040] In one embodiment, if Figure 6 As shown, after step S502, the following steps are also included: S601: If a qualified image whose posture credibility reaches the preset value is not screened out, the person image whose posture credibility does not reach the preset value is output as an unqualified image; S602, based on the preset non-standard walking posture, performing posture type recognition on the walking posture of the person in each unqualified image, and outputting the non-standard posture type corresponding to each unqualified image; S603, calculating the height value corresponding to the person to be measured in each unqualified image; S604: Providing a warning of abnormal traffic by displaying or broadcasting.

[0041] In this embodiment, when the credibility of the walking posture of the person in each person image is identified through the posture recognition algorithm, if the posture credibility of the walking posture of the person in each output person image does not reach the preset value of the qualified image, it means that the walking posture of the pedestrian at this time is a non-standard posture (that is, abnormal postures such as bending over and squatting). In this case, the height value of the person to be measured in each unqualified image will continue to be measured and recorded. After the measurement, a warning prompt of abnormal passage will be displayed through the display module on the pass gate or a warning of abnormal passage will be broadcast through the voice module, thereby warning pedestrians who are not passing normally.

[0042] Optimization 2: In order to further improve the accuracy of height measurement, the present invention can also perform error correction on the height value of pedestrians, thereby improving accuracy.

[0043] In one embodiment, if Figure 7 As shown, the pedestrian height measurement method based on 3D vision technology also includes: S701, pre-identifying the ground plane within the measurement range by using a camera or other measuring equipment to obtain the ground plane height of each position point in the ground plane; S702: confirm the ground plane height corresponding to the foot position of the pedestrian in the current pedestrian image, so as to correct the height value of the pedestrian outputted in the current pedestrian image.

[0044] In this embodiment, each time the camera device is started, the ground plane within the measurement range can be self-checked and identified to obtain the height of the ground plane at each position point, thereby avoiding errors caused by uneven ground.

[0045] Optimization three: In order to further improve the efficiency of height measurement, the present invention can also measure the height values ​​of multiple pedestrians within the measurement range at the same time, thereby improving traffic efficiency.

[0046] In one embodiment, if Figure 8 As shown, the pedestrian height measurement method based on 3D vision technology also includes: S801, if there are multiple persons to be measured in the person image, determine the measurement order of the multiple persons to be measured according to the resolution of the person image; S802, acquiring relative position data between the camera device and each person to be measured in a measurement order; S803: Calculate the height of each person to be measured according to the current height of the camera device and the relative position data of each person to be measured.

[0047] In this embodiment, during the peak hours of gate traffic, there are often multiple pedestrians queuing to pass through, and multiple persons to be measured will appear in the person image at the same time; based on the height measurement method of the above embodiment 1 of this application, when measuring the heights of multiple persons to be measured, this embodiment only needs to confirm the measurement order of multiple persons to be measured through the resolution of the person image, and then sequentially obtain the linear distance and relative angle between the camera device and the top of each person to be measured in space; and then calculate the height value of each person to be measured in combination with the current height of the camera device. This allows the height measurement of multiple pedestrians to be achieved at the same time.

[0048] The embodiment of the present invention further provides a pedestrian height measurement system based on 3D vision technology, and the pedestrian height measurement system based on 3D vision technology is used to perform any embodiment of the above-mentioned pedestrian height measurement method based on 3D vision technology. Fig. 9 , Fig. 9 It is a schematic block diagram of a pedestrian height measurement system based on 3D vision technology provided by an embodiment of the present invention.

[0049] Based on the height measurement methods described in the above-mentioned embodiments 1 and 2, the first embodiment is installed at a higher place (usually higher than 2 meters), and the second embodiment is installed at a lower place (usually lower than 1.2 meters).

[0050] In some specific embodiments, two camera devices of different heights are installed on the access gate to respectively perform the height measurement methods of embodiment one and embodiment two on test persons of different height ranges. The height values ​​obtained by the two measurement methods are compared with the actual heights of the corresponding test persons, thereby realizing different height measurement methods for pedestrians of different height ranges, thereby improving the accuracy of height measurement.

[0051] In a specific example scenario, for example, camera A is installed at a height of 2.3 meters to perform the measurement method of embodiment 1; camera B is installed at a height of 0.9 meters to perform the measurement method of embodiment 2; test personnel include test personnel in a first height range, a second height range, a third height range, and other ranges with increasing heights. The measurement result example is: the height value obtained by the test personnel in the first height range using embodiment 2 is closer to the real height than the height value obtained by embodiment 1; therefore, in actual applications, camera A and camera B are used to measure pedestrians at the same time. If the height value of the pedestrian is measured to be in the first height range, the height value measured by embodiment 2 is selected as the final height value of the pedestrian. Similarly, if the height value of the pedestrian is measured to be in the second height range, the third height range, or other ranges, the same selection principle is also used.

[0052] like Fig. 9 As shown, a pedestrian height measurement system 900 based on 3D vision technology includes: an image acquisition unit 901 , a position acquisition unit 902 and a height calculation unit 903 .

[0053] An image acquisition unit 901 is used to capture an image of a person to be measured who enters the passage area through a camera device; A position acquisition unit 902, configured to acquire relative position data between the camera device and the person according to the person image; The height calculation unit 903 is used to calculate the height value of the person to be measured according to the current height of the camera device and the relative position data.

[0054] The system uses 3D vision technology to capture pedestrian images in real time, and uses image processing and algorithms to dynamically measure pedestrian heights, achieving high-precision height recognition without any sense of movement. This effectively improves the accuracy and stability of measurement and increases traffic efficiency.

[0055] An embodiment of the present invention further provides a passage gate, comprising an automatic gate and a camera device; the camera device is mounted on the automatic gate and at a preset height, and the camera device is equipped with a pedestrian height measurement system based on 3D vision technology as claimed in claim 9.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0057] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for measuring a person's height based on 3D vision technology, characterized in that: include: Capture images of persons to be measured who enter the passage area through a camera device; Acquiring relative position data between the camera device and the person according to the person image; The height value of the person to be measured is calculated according to the current height of the camera device and the relative position data.

2. The method for measuring height of a person based on 3D vision technology according to claim 1, characterized in that: The relative position data specifically includes: The horizontal distance between the camera device and the person's body in the horizontal direction; The straight-line distance between the camera device and the top of the person's head in space; The relative angle between the camera device and the top of the person's head in space.

3. The method for measuring height of a person based on 3D vision technology according to claim 2, characterized in that: The step of calculating the height of the person to be measured according to the current height of the camera device and the relative position data specifically includes: Calculate the height difference between the top of the person's head and the camera device in the height direction according to the linear distance and relative angle between the camera device and the top of the person's head in space; The height value of the person to be measured is obtained according to the current height of the camera device and the height difference.

4. The method for measuring height of a person based on 3D vision technology according to claim 2, characterized in that: The step of calculating the height of the person to be measured according to the current height of the camera device and the relative position data specifically includes: Calculating the angle formed between the horizontal distance and the straight-line distance; Calculate the height difference between the top of the person's head and the camera device in the height direction according to the angle and the horizontal distance / straight-line distance; The height value of the person to be measured is obtained according to the current height of the camera device and the height difference.

5. The method for measuring height of a person based on 3D vision technology according to claim 2, characterized in that: The acquiring the relative position data between the camera device and the person according to the person image specifically includes: Acquire the horizontal distance between the camera device and the person's body in the horizontal direction according to the resolution information of the person's image, or measure the horizontal distance between the camera device and the person's body in the horizontal direction according to a distance measuring device; Acquire the coordinates of the camera device and the top of the person's head according to the resolution information of the person's image, and calculate the straight-line distance between the camera device and the top of the person's head in space according to the coordinates of the camera device and the top of the person's head; The coordinates of the camera device and the top of the person's head are converted from image coordinates to actual coordinates to obtain the relative angle between the camera device and the top of the person's head in space.

6. The method for measuring height of a person based on 3D vision technology according to claim 1, characterized in that: Also includes: Collecting multiple images of persons to be measured who enter the passage area by the camera device; Based on a preset standard walking posture, the credibility of the walking posture of the person in each person image is identified, and the posture credibility of the walking posture of the person in each person image is output; Screen out images of people whose posture credibility reaches a preset value as qualified images; Calculate the height value of the person to be measured in each qualified image; The maximum value of the height values ​​corresponding to all qualified images is selected as the final height value of the person to be measured; The posture credibility in the qualified image corresponding to the final height value is used as the height credibility of the current person to be measured.

7. The method for measuring height of a person based on 3D vision technology according to claim 6, characterized in that: Also includes: If a qualified image whose posture credibility reaches the preset value is not screened out, the image of the person whose posture credibility does not reach the preset value is output as an unqualified image; Based on the preset non-standard walking posture, the walking posture type of the person in each unqualified image is identified, and the non-standard posture type corresponding to each unqualified image is output; Calculate the height value of the person to be measured in each unqualified image; Providing warnings of abnormal traffic by display or broadcast.

8. The method for measuring height of a person based on 3D vision technology according to claim 1, characterized in that: Also includes: Identify the ground plane in the passage area by using the camera device or other measuring equipment to obtain the ground plane height of each position point in the ground plane; Confirm the ground plane height corresponding to the sole position of the person in the current person image to correct the height value output by the current person image.

9. The method for measuring height of a person based on 3D vision technology according to claim 1, characterized in that: Also includes: If there are multiple persons to be measured in the person image, determining the measurement order of the multiple persons to be measured according to the resolution of the person image; Acquire the relative position data between the camera device and each person to be measured in a measurement order; The height value of each person to be measured is calculated according to the current height of the camera device and the relative position data of each person to be measured.

10. The method for measuring height of a person based on 3D vision technology according to claim 1, characterized in that: Also includes: According to the height value of the measured person, determine the group of people to which the measured person belongs when checking tickets at the gate, wherein the group of people includes adults whose height exceeds a preset height and children whose height does not exceed the preset height; Based on the ticket verification certificate of the measured person, it is determined whether the height value of the measured person meets the height condition in the ticket verification certificate. If so, the gate is controlled to open; if not, the gate is controlled to close and a prompt is given.

11. A system for measuring height of a person based on 3D vision technology, characterized in that: include: An image acquisition unit, used to capture images of persons to be measured who enter the passage area through a camera device; A position acquisition unit, used for acquiring relative position data between the camera device and the person according to the person image; The height calculation unit is used to calculate the height value of the person to be measured according to the current height of the camera device and the relative position data.

12. A traffic gate, characterized in that: It comprises an automatic gate and a camera device; the camera device is placed on the automatic gate and at a preset height, and the camera device is equipped with a pedestrian height measurement system based on 3D vision technology as described in claim 11.

Citation Information

Patent Citations

  • Measuring method and measuring device for height of human body based on binocular vision technique

    CN104173054A

  • Gate passing behavior identification and control method combining target detection and binocular vision

    CN113781578A

  • Gate passing behavior recognition and control method combining target detection and binocular vision

    CN113870356A

  • Height measuring method and device based on human body image

    CN115187652A

  • Channel gate control method, apparatus and system

    WO2021180060A1