Method and system for automatically adjusting height of terminal equipment through AI visual judgment

Abstract

The invention discloses a method and system for automatically adjusting the height of terminal equipment through AI visual judgment, and relates to the technical field of visual recognition. The method for automatically adjusting the height of the terminal equipment through AI visual judgment comprises the following steps: acquiring a visual image; the visual image is shot based on a camera device; acquiring the height of the user based on the visual image; and adjusting the height of a display screen and / or an operation platform of the terminal equipment based on the height. The height of the user is accurately identified through the visual image, and the height of the terminal device is adjusted to the height suitable for the user to operate based on the height of the user, so that the convenience and intelligence of the terminal device can be improved.

Description

Technical Field

[0001] The present application relates to the field of visual recognition technology, and specifically to a method and system for automatically adjusting the height of a terminal device using AI visual judgment. Background Art

[0002] Self-service terminal equipment (for example, self-service lending and returning machines or self-service cash registers) is an electronic information device that uses multimedia databases such as videos, images, text, and audio to create an interactive environment. It is used to store information and provide various service functions such as information query, printing, payment, and product sales.

[0003] Most self-service terminals are either non-adjustable or require manual adjustment to accommodate users of varying heights. For example, patents with publication number CN222014810U, titled "A Smart Library Loan and Return Machine," and CN216450044U, titled "A Self-Service Loan and Return Machine Based on Facial Recognition," both disclose similar self-service terminals. These terminals lack the ability to automatically adjust the height of the display or operating platform based on the user's height, resulting in insufficient convenience and intelligence. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for automatically adjusting the height of a terminal device based on AI visual judgment, so as to solve the technical problem that existing terminal devices cannot automatically adjust their own height based on the user's height.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] In the first aspect, the present application proposes a technical solution for a method for automatically adjusting the height of a terminal device using AI visual judgment, wherein the height of the display screen and / or operating platform of the terminal device is electrically adjustable. The method for automatically adjusting the height of a terminal device using AI visual judgment comprises:

[0007] Acquire a visual image; the visual image is obtained by taking a picture with a camera;

[0008] Based on the visual image, obtaining the user's height;

[0009] Based on the height, the height of the display screen and / or operating platform of the terminal device is adjusted.

[0010] In a second aspect, the present application proposes a technical solution for a system for automatically adjusting the height of a terminal device using AI visual judgment, wherein the height of the display screen and / or operating platform of the terminal device is electrically adjustable; the system for automatically adjusting the height of the terminal device using AI visual judgment comprises:

[0011] a camera device for acquiring visual images;

[0012] a processing device for obtaining a user's height based on the visual image;

[0013] A control device is used to adjust the height of the display screen and / or operating platform of the terminal device based on the body height.

[0014] Compared with the prior art, the present invention has the following advantages:

[0015] This application accurately identifies the user's height through visual images, and then adjusts the height of the terminal device to a height suitable for the user to operate based on the user's height, which can improve the convenience and intelligence of the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of a method for automatically adjusting the height of a terminal device using AI visual judgment, as proposed in an embodiment of the present application;

[0017] Figure 2 Schematic diagram of the structural principle of camera imaging;

[0018] Figure 3 A schematic diagram of a camera arrangement for obtaining a user's height proposed in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of a method for identifying key points in a visual image according to an embodiment of the present application;

[0020] Figure 5 This is a structural diagram of a system for automatically adjusting the height of a terminal device through AI visual judgment proposed in an embodiment of the present application.

[0021] In the figure: 1, target object; 2, convex lens; 21, first camera; 22, second camera; 23, third camera; 3, imaging. DETAILED DESCRIPTION

[0022] The terms "first", "second", etc. in the description and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects (for example, the first image and the second image are represented as different images, and are otherwise similar), and are not necessarily used to describe a specific order or sequence. It should be understood that the names used in this way are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that shown or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of modules that appears in the embodiments of the present application is merely a logical division. In actual applications, there may be other division methods, for example, multiple modules can be combined or integrated into another system, or some features can be ignored or not performed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling between modules, and the communication connection can be electrical or other similar forms, which are not limited in the embodiments of the present application. Moreover, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed into multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0023] In order to solve the technical problem that the existing terminal equipment cannot automatically adjust its height based on the height of the user, the present application proposes a method for automatically adjusting the height of the terminal equipment by AI visual judgment. In this embodiment, the display screen and / or operating platform of the terminal equipment can be electrically adjusted. It should be clear that the terminal equipment capable of electrically adjusting the height of the display screen and / or operating platform is a mature technology and will not be described in detail here. For example, similar terminal equipment is disclosed in the patent documents with publication number: CN216211158U, title: A face recognition device for a library self-service lending machine, and publication number: CN206133820U, title: A self-service lending machine.

[0024] In the embodiments of the present application, the terminal device can be any reasonable device that achieves service goals based on interaction with the user, for example, the terminal device can be a self-service lending machine or a self-service cash register, etc. In the following, the present application only uses the self-service lending machine or the self-service cash register to illustrate the embodiments of the present application. This does not mean that the method of automatically adjusting the height of the terminal device by AI visual judgment proposed in the present application is only applicable to the automatic height adjustment of the self-service lending machine or the self-service cash register. It is also applicable to other terminal devices similar to the self-service lending machine or the self-service cash register, such as: facial recognition clock-in machine, or hospital self-service registration machine, etc.

[0025] In the embodiments of the present application, the display screen of the terminal device may be a display screen having any function, for example, the display screen of the terminal device may be a display screen for performing facial recognition in conjunction with a camera, or a display screen for displaying interactive information (for example, information about borrowed and returned books or information about purchased goods). The operating platform of the terminal device may be a platform having any function, for example, the operating platform may be a platform for inputting information to the terminal device (for example, a platform provided with a keyboard or a touch screen, etc.), or a platform for placing items (for example, a platform for placing borrowed books or purchased goods, etc.).

[0026] In an embodiment, Figure 1 As shown, the method for automatically adjusting the height of the terminal device by AI visual judgment includes steps S100 to S300.

[0027] Step S100: Acquire a visual image.

[0028] In this embodiment, the visual image is pre-photographed by a camera device, which may be any device capable of capturing a visual image, for example, a webcam or a digital camera.

[0029] Step S200: Acquire the height of the user based on the visual image.

[0030] In this embodiment, any reasonable method can be used to obtain the user's height based on the visual image. For example, obtaining the user's height based on the visual image can be based on the method disclosed in patent application publication number CN118229996A, entitled "A Real-time Height Measurement Method Based on Key Point Detection," or patent application publication number CN117830130A, entitled "A Human Height Measurement Method Based on Two RGB Images."

[0031] The method for obtaining the user's height based on the visual image listed in the above embodiments is relatively complex and requires a large amount of data processing. In order to reduce the complexity of obtaining the user's height based on the visual image and thereby reduce the amount of data processing, in this application, the user's height can be obtained as shown in Examples 1 and 2.

[0032] Example 1 of obtaining the user's height

[0033] In this embodiment, the visual image is an image of the user standing in a designated position. The camera device includes a first camera. The visual image is captured by the first camera.

[0034] In this embodiment, step S200, obtaining the height of the user based on the visual image, includes steps S210 to S240.

[0035] Step S210: Obtain the pixel height of the user's outline from the visual image based on an edge detection algorithm.

[0036] It should be noted that obtaining the user's outline from the visual image using an edge detection algorithm is a mature technology. For example, similar methods are disclosed in patent applications with publication number CN110245575A, entitled "A Method for Capturing Human Body Parameters Based on Human Contour Lines," and CN110197117A, entitled "Human Contour Point Extraction Method, Apparatus, Terminal Device, and Computer-Readable Storage Medium."

[0037] It should be noted that obtaining the pixel height of the user's profile based on the user's profile is also a mature technology. For example, assuming that the coordinates of the i-th pixel point in the user's profile are (x i ,y i ), where the y-axis direction is the height direction, the pixel height of the user's profile can be y max -y min ; Among them, y max is the maximum value of the y-axis coordinate value corresponding to each pixel point in the user's profile; min is the minimum value of the y-axis coordinate values ​​corresponding to each pixel point in the user's profile.

[0038] Step S220: Acquire imaging height based on the contour pixel height.

[0039] In this embodiment, the imaging height refers to the height of the image of the user formed by the first camera when capturing a visual image. Obtaining the imaging height based on the outline pixel height is a mature technology. Generally, the calculation formula for obtaining the imaging height based on the outline pixel height is as follows:

[0040] h=(y max -y min )*P

[0041] Where h represents the imaging height of the user in the visual image; y max is the maximum value of the y-axis coordinate value corresponding to each pixel point in the user's profile; min is the minimum value of the y-axis coordinate values ​​corresponding to each pixel point in the user's outline; P represents the pixel size corresponding to the first camera. If the first camera is determined, the corresponding pixel size can also be determined, which is not repeated here.

[0042] Step S230: Based on the first camera, obtain a first object distance and a first image distance.

[0043] In this embodiment, the first object distance is the distance from the designated position to the first camera. The first image distance is the image distance when the first camera captures the visual image.

[0044] As can be seen from the foregoing, the visual image is an image of the user standing at the designated location. That is, when capturing the visual image, the distance between the user and the first camera is fixed (i.e., the object distance). This object distance is approximately equal to the horizontal distance from the designated location to the first camera.

[0045] Step S240: Acquire the height of the user based on the imaging height, the first object distance, and the first image distance.

[0046] Specifically, Figure 2 The following is a diagram of the optical imaging principle, where H is the actual height of the target object 1 (e.g., the user); W1 is the distance between the target object 1 and the convex lens 2 (approximately equal to the first object distance); X1 is the distance between the image 3 and the convex lens 2 (also known as the first image distance); and h1 is the image height corresponding to the target object 1. Based on the imaging principle, the following calculation formula (hereinafter referred to as the first calculation formula) can be obtained:

[0047]

[0048] According to the first calculation formula, in step S240, the calculation formula for obtaining the user's height based on the imaging height, the first object distance, and the first image distance is as follows:

[0049]

[0050] Wherein, H represents the height of the user; W1 represents the first object distance; h1 represents the imaging height; and X1 represents the first image distance.

[0051] It should be noted that in this embodiment, the user must be standing in a designated location to obtain the user's height. In other words, if some users are not aware of the usage rules and do not stand in the designated location, the user's height cannot be obtained. In order to obtain the user's height even without standing in the designated location, the user's height can be obtained as shown in the method of Example 2.

[0052] Example 2 of obtaining the user's height

[0053] In this embodiment, the visual image includes a first image, a second image, and a third image. The first image, the second image, and the third image are images obtained at the same time. Figure 3 As shown, the camera device includes a first camera 21, a second camera 22 and a third camera 23. The first image is captured by the first camera 21; the second image is captured by the second camera 22; and the third image is captured by the third camera 23. Figure 3 As shown, the first camera 21, the second camera 22 and the third camera 23 are arranged horizontally in a straight line. The distance between the first camera 21 and the second camera 22 is a first distance (i.e., Figure 3 The distance between the second camera 22 and the third camera 23 is the second distance (i.e., Figure 3 The distance S2 shown).

[0054] In this embodiment, step S200, obtaining the height of the user based on the visual image, includes step S250 and step S260.

[0055] Step S250: Based on the visual image, obtain a first ratio, a second ratio, and a third ratio.

[0056] In this embodiment, the first ratio is the ratio of the first object distance to the height of the user. The second ratio is the ratio of the second object distance to the height of the user. The third ratio is the ratio of the third object distance to the height of the user. The first object distance is the object distance corresponding to the first image (i.e., Figure 3 The second object distance is the object distance corresponding to the second image (i.e., the distance W1 shown). Figure 3 The third object distance shown is the object distance corresponding to the third image (i.e., Figure 3 The distance W3 shown).

[0057] From steps S210 to S240 , it can be seen that if the visual image (ie, the first image, the second image, or the third image) is determined, the ratio of the object distance corresponding to the visual image and the height of the target object 1 (ie, the height of the user) is also determined.

[0058] Step S260: Acquire the height of the user based on the first ratio, the second ratio, the third ratio, the first distance, and the second distance.

[0059] In this embodiment, no matter where the target object 1 (ie, the user) is (for example, Figure 3 The position shown in the figure), then according to the cosine theorem and the triangle interior angle theorem, we can get the following equation group (hereinafter referred to as the first equation group):

[0060]

[0061] Among them, S1 represents the first distance; S2 represents the second distance; W1 represents the first object distance; W2 represents the second object distance; W3 represents the third object distance; θ represents the diagonal angle value of the side length corresponding to the first object distance in the triangle formed by the first camera 21, the third camera 23 and the target object 1 as vertices (hereinafter referred to as the first triangle); α represents the diagonal angle value of the side length corresponding to the third object distance in the first triangle; β represents the diagonal angle value of the side length corresponding to the line between the first camera 21 and the third camera 23 in the first triangle.

[0062] As can be seen from the foregoing, the first ratio, the second ratio, and the third ratio can be obtained based on step S250. In other words, based on step S250, the following set of equations (hereinafter referred to as the second set of equations) can be obtained:

[0063]

[0064] Wherein, W1 represents the first object distance; W2 represents the second object distance; W3 represents the third object distance; k1 represents the first ratio; k2 represents the second ratio; k3 represents the third ratio; and H represents the height of the user.

[0065] In this embodiment, if the first distance S1, the second distance S2, the first ratio k1, the second ratio k2 and the third ratio k3 are all known, the user's height can be obtained by substituting the second set of equations into the first set of equations.

[0066] In a specific embodiment of the present application, if the first distance S1 is 10 meters; the second distance S2 is 10 meters; the first ratio k1 is 7.5; the second ratio k2 is 5; and the third ratio k3 is 7.5; then these values ​​are substituted into the first and second equations to obtain the user's height of approximately 1.79 meters.

[0067] This concludes the introduction to the second embodiment of obtaining the user's height.

[0068] It should be noted that in Examples 1 and 2, the camera device must capture the entire target object 1 in order to calculate the actual height of the target object 1. That is, in the embodiments of the present application, there is no restriction on the installation location of the camera device; it only requires that the camera device be able to capture a visual image of the user's entire body when the user uses the terminal device. For example, in Example 1 of the present application, since the user needs to stand in a designated position, the terminal device will not obstruct the user's entire body. That is, in Example 1, the camera device can be installed in the terminal device. In Example 2 of the present application, if the camera device (i.e., the first camera 21, the second camera 22, and the third camera 23) is installed in the terminal device and the user is relatively close to the terminal device, it is likely that a visual image of the user's entire body will not be captured. Based on this, in Example 2, the camera device and the terminal device can be arranged relative to each other so that the user is located between the camera device and the terminal device during use. If the user is located between the camera device and the terminal device during use, the terminal device will not obstruct the user, which means that the camera device can easily capture a visual image of the user's entire body.

[0069] Step S300: Based on the body height, adjust the height of the display screen and / or operating platform of the terminal device.

[0070] In the embodiments of the present application, the height of the display screen and / or operating platform of the terminal device can be adjusted in any reasonable manner based on the height of the user. To avoid redundancy, the following explanation of step S300 in the present application will only use the height adjustment of the operating platform of a self-service lending and returning machine as an example.

[0071] It should be noted that for a standing user, if the height of the self-service lending and returning machine operating platform is approximately 0.7 times the user's height, the user will feel more comfortable operating the machine. Therefore, in this embodiment, the height of the self-service lending and returning machine operating platform can be adjusted to 0.7 times the user's height. Of course, in other embodiments of the present application, the height can also be adjusted to 0.5 times or 0.6 times the user's height, etc.

[0072] It should be noted that for users who require a wheelchair (e.g., disabled users or users with leg problems), the optimal comfortable height of the operating platform or display screen is different from that of users who do not require a wheelchair. For example, for a wheelchair user, if the height of the self-service lending and returning machine operating platform is approximately 0.5 times the user's height, the user will feel more comfortable operating it. Therefore, in this embodiment, the height of the self-service lending and returning machine operating platform can be adjusted to 0.5 times the user's height. Of course, in other embodiments of the present application, it can also be adjusted to 0.4 times or 0.6 times the user's height, etc.

[0073] In order to be able to adjust the display screen and / or operating platform to the user's optimal usage height based on the user's posture (i.e., standing or sitting) and height, in one embodiment of the present application, in step S300, before adjusting the height of the display screen and / or operating platform of the terminal device based on the height, the method also includes step S270.

[0074] Step S270: Acquire the user's posture based on the visual image.

[0075] In this embodiment, the posture includes at least standing and sitting. In the embodiment of the present application, the posture of the user can be obtained based on the visual image in any reasonable manner. For example, the artificial intelligence model can be trained on the standing and sitting postures of humans, and then the posture of the user in the visual image can be recognized based on the trained artificial intelligence model. The technology of training the artificial intelligence model and then recognizing the posture of a person through the artificial intelligence model is a mature technology and will not be described in detail here. For example, similar methods are disclosed in the patent application documents with publication number: CN117274151A, entitled: A method for analyzing spinal posture of visual images based on artificial intelligence; and publication number: CN117671738A, entitled: Human posture recognition system based on artificial intelligence.

[0076] It should be noted that training an AI model and then recognizing a user's posture based on the AI ​​model is highly complex and computationally intensive. To reduce computational complexity, in one embodiment of the present application, step S270, obtaining the user's posture based on the visual image, includes steps S271 to S274.

[0077] Step S271: obtaining a first key point, a second key point, and a third key point from the visual image based on a human posture estimation model.

[0078] In this embodiment, the first key point is the key point corresponding to the user's torso (ie, Figure 4 The second key point is the key point corresponding to the user's buttocks (i.e., Figure 4 The third key point is the key point corresponding to the user's knee (i.e., Figure 4 Key point D5 or D6 shown).

[0079] In this embodiment, there are no restrictions on the human pose estimation model. It only needs to be able to obtain the corresponding key points from the visual image. For example, the human pose estimation model can be any of OpenPose, MoveNet, and PoseNet. OpenPose, MoveNet, and PoseNet are all mature technologies and will not be described in detail here.

[0080] Step S272: Based on the first key point, the second key point and the third key point, obtain a first slope and a second slope.

[0081] In this embodiment, the first slope is the slope of the line connecting the first key point and the second key point, and the second slope is the slope of the line connecting the second key point and the third key point.

[0082] It should be clear that obtaining the slope between two coordinate points (ie, the first key point and the second key point or the second key point and the third key point) is a mature technology and will not be described in detail here.

[0083] Step S273: Obtain a first difference value based on the first slope and the second slope.

[0084] In this embodiment, the first difference value is used to at least characterize the difference between the first slope and the second slope. In the embodiment of the present application, the first difference value can be obtained based on the first slope and the second slope in any reasonable manner. For example, the first difference value can be the absolute value of the difference between the first slope and the second slope, or the absolute value of the ratio of the first slope to the second slope.

[0085] Step S274: Acquire the user's posture based on the first difference value.

[0086] In this embodiment, if the first difference value is smaller, it means that the line connecting the three points of the user's torso, hips and knees is closer to a straight line, that is, the user's posture is standing; if the first difference value is larger, it means that the line connecting the three points of the user's torso, hips and knees is closer to a curve, that is, the user's posture is sitting.

[0087] It should be noted that using only a single visual image to determine a user's posture can result in significant errors. For example, if the user in the visual image is bending over to pick up something, a standing user might be identified as sitting. To avoid this error, multiple visual images of the user can be obtained, and the average of the difference values ​​corresponding to the multiple visual images (for example, the ratio of the first slope to the second slope) can be used as the first difference value. This way, even if the user is not standing upright in a particular visual image, a standing user will not be identified as sitting.

[0088] Step S274, obtaining the user's posture based on the first difference value, including: if the first difference value is greater than or equal to a first preset value, determining that the user's posture is a sitting posture; if the first difference value is less than the first preset value, determining that the user's posture is a standing posture.

[0089] In the embodiments of the present application, the first preset value can be selected as needed. For example, if the first difference value is the absolute value of the difference between the first slope and the second slope, the first preset value can be 3 or 4, etc.; if the first difference value is the absolute value of the ratio of the first slope to the second slope, the first preset value can be 1 or 2, etc.

[0090] Step S300, adjusting the height of the display screen and / or operating platform of the terminal device based on the body height, includes steps S310 and S320.

[0091] Step S310: If the user is sitting, the display screen and / or operating platform of the terminal device is adjusted to a first height based on the user's height.

[0092] In this embodiment, the first height is obtained based on the height. As can be seen from the foregoing, if the user is sitting, the display screen and / or operating platform of the terminal device can be moved to 0.5 times the height of the user (ie, the first height).

[0093] Step S320: If the user is standing, the display screen and / or operating platform of the terminal device is adjusted to a second height based on the height.

[0094] In this embodiment, the second height is obtained based on the height. As can be seen from the foregoing, if the user is standing, the display screen and / or operating platform of the terminal device can be adjusted to 0.7 times the height of the user (ie, the second height).

[0095] It should be noted that, when the user is standing, the user's height can only be accurately obtained based on the above-mentioned embodiments 1 and 2 if the user in the visual image is standing upright. In other words, if the user is not standing upright (for example, bending over or squatting), it is difficult to accurately obtain the user's height based on the above-mentioned embodiments 1 and 2.

[0096] In order to obtain the accurate height of a user in a standing position, in one embodiment of the present application, the average value of the user's height in multiple visual images can be used as the user's height, thereby reducing the error in obtaining the user's height. It is easy to understand that when a user operates a terminal device, a non-straight standing state rarely occurs. In other words, by using the average value of the user's height in multiple visual images as the user's height, the phenomenon of mistakenly taking the user's height in a non-straight standing state as the user's true height can be effectively avoided, thereby reducing the error in obtaining the user's true height.

[0097] In order to further reduce the error in obtaining the user's real height, in one embodiment of the present application, after obtaining the user's posture in step S270, the method further includes steps S400 to S600.

[0098] Step S400: If the user's posture is standing, then based on multiple visual images of the user, a posture straightness value and a first height corresponding to each visual image are obtained.

[0099] In this embodiment, the posture straightness value is positively correlated with the degree of straightness of the user's standing posture in the corresponding visual image. That is, the straighter the user's standing posture in the visual image, the larger the corresponding posture straightness value.

[0100] In this embodiment, the first height is the height of the user in the corresponding visual image. Specifically, the method for obtaining the first height can refer to the above embodiment 1 and embodiment 2, and will not be repeated here.

[0101] In the embodiments of the present application, any reasonable method can be used to obtain the posture straightness value corresponding to each visual image (for example, Examples 1 and 2 below). For example, step S400, based on multiple visual images of the user, obtains the posture straightness value corresponding to each visual image, including steps S410 to S430.

[0102] Step S410: Acquire a first visual image based on each visual image.

[0103] In this embodiment, the first visual image is any one of the visual images. That is, in this application, the method for obtaining the posture straightness values ​​of the remaining visual images (i.e., the other visual images except the first visual image) in the visual images is the same as that of the first visual image.

[0104] Step S420: Acquire multiple key points from the first visual image based on a human posture estimation model.

[0105] It should be clear that obtaining multiple key points from the corresponding image (ie, the first visual image) based on the human posture estimation model is a mature technology and will not be described in detail here.

[0106] Step S430: Based on each key point, obtain a posture straightness value of the first visual image.

[0107] Specifically, the posture straightness value of the first visual image may be at least as shown in Example 1 and Example 2.

[0108] Example 1 of obtaining the value of posture straightness

[0109] In this embodiment, each key point includes the top key point (ie, Figure 4 The key point D1 shown), the chin key point (also as shown Figure 4 The key point D2 shown), the torso key point (that is, Figure 4 Key point D3 shown), hip key point (also as shown Figure 4 Key point D4 shown), knee key point (also as shown Figure 4 The key point D5 or D6 shown) and the heel key point (ie, Figure 4 Key point D7 or D8 shown).

[0110] Step S430 , obtaining a posture straightness value of the first visual image based on each key point, includes steps S431 to S433 .

[0111] Step S431: Based on each key point, obtain multiple slope values.

[0112] In this embodiment, the slope value is the absolute value of the slope between any two key points in each key point. It should be understood that obtaining the slope between the two key points based on two key points is a mature technology and will not be described in detail here.

[0113] Step S432: Obtain a second difference value based on each slope value.

[0114] In this embodiment, the second difference value is used to at least represent the difference between the slope values. It is easy to understand that the smaller the second difference value, the straighter the user stands; the larger the second difference value, the less straight the user stands.

[0115] In the embodiment of the present application, the second difference value may be obtained based on each slope value in any reasonable manner. For example, the second difference value may be the variance or standard deviation of each slope value.

[0116] Step S433: Based on the second difference value, obtain a posture straightness value of the first visual image.

[0117] In the embodiment of the present application, any reasonable method can be used to obtain the posture straightness value of the first visual image based on the second difference value. For example, in step S433, the calculation formula for obtaining the posture straightness value of the first visual image based on the second difference value can be as follows:

[0118]

[0119] Among them, B represents the posture straightness value of the first visual image; C represents the second difference value; norm() represents the normalization function, which is used to map the numerical value in the brackets to the interval range of [0, 1].

[0120] In this embodiment, if the user stands straighter in the first visual image, the posture straightness value is closer to 1; if the user stands less straight in the first visual image, the posture straightness value is closer to 0.

[0121] Example 2 of obtaining the value of posture straightness

[0122] In this embodiment, each key point includes the top key point (ie, Figure 4 The key point D1 shown), the chin key point (also as shown Figure 4 The key point D2 shown) and the heel key point (also as shown Figure 4 Key point D7 or D8 shown).

[0123] Step S430 , based on each key point, obtains the posture straightness value of the first visual image, including steps S434 to S436 .

[0124] Step S434: Based on each key point, obtain the third distance and the fourth distance.

[0125] In this embodiment, the third distance is the pixel distance between the top of the head keypoint and the chin keypoint. The fourth distance is the pixel distance between the top of the head keypoint and the heel keypoint. It should be noted that obtaining the distance between two coordinate points based on two coordinate points (i.e., the top of the head keypoint and the chin keypoint, or the top of the head keypoint and the heel keypoint) is a mature technology and will not be described in detail here.

[0126] Step S435: Acquire a fourth ratio based on the third distance and the fourth distance.

[0127] In this embodiment, the fourth ratio is a ratio of the fourth distance to the third distance.

[0128] Step S436: If the fourth ratio exceeds the preset range, the posture straightness value of the first visual image is equal to the third preset value; otherwise, the posture straightness value of the first visual image is equal to the fourth preset value.

[0129] It should be noted that the normal human body-to-head ratio is generally between 7 and 8. In other words, if the user is standing upright, the fourth ratio mentioned above should also fall between 7 and 8. In other words, if the fourth ratio does not fall between 7 and 8, it indicates that the user may not be standing upright.

[0130] In an embodiment of the present application, a preset range may be set based on demand, for example, the preset range may be greater than or equal to 7.0 and less than or equal to 8.0; or the preset range may be greater than or equal to 6.9 and less than or equal to 8.1, etc.

[0131] In the embodiment of the present application, the third preset value and the fourth preset value may also be set as required. For example, the third preset value may be 0 and the fourth preset value may be 1; of course, the third preset value may also be -1 and the fourth preset value may be 2, etc.

[0132] Step S500: Acquire multiple second heights based on the straightness values ​​of the postures.

[0133] In this embodiment, the second height is the first height having a posture straightness value greater than or equal to a second preset value.

[0134] It should be noted that the second preset value can be set according to needs, for example, the second preset value can be 0.5 or 0.6.

[0135] Step S600: updating the user's height based on each second height.

[0136] In this embodiment, by screening out each first height whose posture straightness value is less than the second preset value, that is, screening out the height of the user who may be in a non-straight standing state, the error of the user's real height obtained subsequently is reduced.

[0137] In this embodiment, the user's height can be updated based on each second height in any reasonable manner. For example, the user's height can be equal to the average of each second height; or the user's height can be equal to the average of each second height excluding the maximum and minimum values.

[0138] The embodiment of the method of automatically adjusting the height of a terminal device by AI visual judgment proposed in this application accurately identifies the user's height through visual images, and then adjusts the height of the terminal device to a height suitable for the user to operate based on the user's height, which can improve the convenience and intelligence of the terminal device.

[0139] After introducing the method for automatically adjusting the height of a terminal device using AI visual judgment proposed in an embodiment of this application, the following describes an embodiment of a system for automatically adjusting the height of a terminal device using AI visual judgment proposed in this application. In this embodiment, the height of the display screen and / or operating platform of the terminal device is electrically adjustable.

[0140] In this embodiment, if Figure 5 As shown, the system 10 for automatically adjusting the height of a terminal device by AI visual determination includes:

[0141] A camera device 11, for acquiring visual images;

[0142] a processing device 12 for obtaining a user's height based on the visual image;

[0143] The control device 13 is used to adjust the height of the display screen and / or operating platform of the terminal device based on the body height.

[0144] As a specific embodiment of the present application, the visual image is an image of the user standing at a specified position, and the camera device 11 includes a first camera; the visual image is captured by the first camera;

[0145] The processing device 12 is further configured to obtain the pixel height of the user's outline from the visual image based on an edge detection algorithm;

[0146] and, obtaining an imaging height based on the contour pixel height;

[0147] And, based on the first camera, obtaining a first object distance and a first image distance; the first object distance is the distance from the designated position to the first camera; the first image distance is the image distance when the first camera captures the visual image;

[0148] And, based on the imaging height, the first object distance and the first image distance, the height of the user is obtained.

[0149] As a specific embodiment of the present application, the visual image includes a first image, a second image, and a third image; the first image, the second image, and the third image are images obtained at the same time; the camera device 11 includes a first camera, a second camera, and a third camera; the first image is captured by the first camera; the second image is captured by the second camera; the third image is captured by the third camera; the first camera, the second camera, and the third camera are arranged horizontally in a straight line; the distance between the first camera and the second camera is a first distance; the distance between the second camera and the third camera is a second distance;

[0150] The processing device 12 is further configured to obtain, based on the visual image, a first ratio, a second ratio, and a third ratio; the first ratio being a ratio of a first object distance to a height of the user; the second ratio being a ratio of a second object distance to a height of the user; and the third ratio being a ratio of a third object distance to the height of the user; the first object distance being an object distance corresponding to the first image; the second object distance being an object distance corresponding to the second image; and the third object distance being an object distance corresponding to the third image;

[0151] And, based on the first ratio, the second ratio, the third ratio, the first distance and the second distance, the height of the user is obtained.

[0152] As a specific embodiment of the present application, the processing device 12 is further configured to obtain the user's posture based on the visual image; the posture includes at least standing and sitting;

[0153] The control device 13 is further configured to, if the user is in a sitting position, adjust the display screen and / or operating platform of the terminal device to a first height based on the height of the user; the first height is obtained based on the height of the user;

[0154] And, if the user is standing, the display screen and / or operating platform of the terminal device is adjusted to a second height based on the height; the second height is obtained based on the height.

[0155] As a specific embodiment of the present application, the processing device 12 is further configured to obtain a first key point, a second key point, and a third key point from the visual image based on a human posture estimation model; the first key point is a key point corresponding to the user's torso; the second key point is a key point corresponding to the user's hip; and the third key point is a key point corresponding to the user's knee;

[0156] And, based on the first key point, the second key point and the third key point, obtaining a first slope and a second slope; the first slope is the slope between the first key point and the second key point; the second slope is the slope between the second key point and the third key point;

[0157] And, based on the first slope and the second slope, obtaining a first difference value; the first difference value is at least used to represent the difference between the first slope and the second slope;

[0158] And, based on the first difference value, obtaining the user's posture.

[0159] As a specific embodiment of the present application, the processing device 12 is further configured to, if the first difference value is greater than or equal to a first preset value, determine that the user's posture is a sitting posture;

[0160] And, if the first difference value is smaller than a first preset value, it is determined that the user's posture is standing.

[0161] As a specific embodiment of the present application, the processing device 12 is further configured to, if the user's posture is standing, obtain, based on multiple visual images of the user, a posture straightness value and a first height corresponding to each visual image; the posture straightness value is positively correlated with the degree of standing straightness of the user in the corresponding visual image; the first height is the height of the user in the corresponding visual image;

[0162] and, based on each posture straightness value, obtaining a plurality of second heights; the second height being any first height whose posture straightness value is greater than or equal to a second preset value;

[0163] And, based on each second height, updating the height of the user.

[0164] As a specific embodiment of the present application, the processing device 12 is further configured to obtain a first visual image based on each visual image; the first visual image is any one of the visual images; and the method for obtaining the posture straightness values ​​of the remaining visual images in each visual image is the same as that for the first visual image.

[0165] and, obtaining a plurality of key points from the first visual image based on a human pose estimation model;

[0166] And, based on each key point, a posture straightness value of the first visual image is obtained.

[0167] As a specific embodiment of the present application, each key point includes a top of the head key point, a chin key point, a torso key point, a hip key point, a knee key point, and a heel key point;

[0168] The processing device 12 is further configured to obtain a plurality of slope values ​​based on each key point; the slope value is an absolute value of the slope between any two key points among the key points;

[0169] And, based on each slope value, obtaining a second difference value; the second difference value is at least used to characterize the difference between each slope value;

[0170] And, based on the second difference value, obtaining a posture straightness value of the first visual image.

[0171] As a specific embodiment of the present application, the key points include a top of the head key point, a chin key point, and a heel key point;

[0172] The processing device 12 is further configured to obtain a third distance and a fourth distance based on each key point; the third distance is the pixel distance between the top key point and the chin key point; and the fourth distance is the pixel distance between the top key point and the heel key point.

[0173] and, obtaining a fourth ratio based on the third distance and the fourth distance; the fourth ratio being a ratio of the fourth distance to the third distance;

[0174] And, if the fourth ratio exceeds the preset range, the posture straightness value of the first visual image is equal to the third preset value; otherwise, the posture straightness value of the first visual image is equal to the fourth preset value.

[0175] The embodiment of the system for automatically adjusting the height of a terminal device based on AI visual judgment proposed in this application accurately identifies the user's height through visual images, and then adjusts the height of the terminal device to a height suitable for the user to operate based on the user's height, which can improve the convenience and intelligence of the terminal device.

[0176] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0177] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0178] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0179] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0180] In addition, the functional modules in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into a module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0181] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0182] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, a computer, a server, or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive Solid State Disk (SSD)), etc.

[0183] The above is a detailed introduction to the technical solutions provided in the embodiments of the present application. Specific examples are used in the embodiments of the present application to illustrate the principles and implementation methods of the embodiments of the present application. The description of the above embodiments is only used to help understand the methods and core ideas of the embodiments of the present application. At the same time, for those skilled in the art, according to the ideas of the embodiments of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the embodiments of the present application.

Claims

1. A method for automatically adjusting the height of a terminal device using AI visual judgment, wherein the height of the display screen and / or operating platform of the terminal device is electrically adjustable; characterized in that: include: Acquire visual images; The visual image is obtained by taking pictures with a camera; Based on the visual image, obtaining the user's height; Based on the height, the height of the display screen and / or operating platform of the terminal device is adjusted.

2. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 1, characterized in that: The visual image is an image of the user standing at a specified position, and the camera device includes a first camera; the visual image is captured by the first camera; The obtaining the height of the user based on the visual image includes: Obtaining a pixel height of a contour of the user from the visual image based on an edge detection algorithm; Acquiring imaging height based on the outline pixel height; Based on the first camera, a first object distance and a first image distance are obtained; the first object distance is the distance from the designated position to the first camera; the first image distance is the image distance when the first camera captures the visual image; The height of the user is acquired based on the imaging height, the first object distance, and the first image distance.

3. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 1, characterized in that: The visual image includes a first image, a second image, and a third image; the first image, the second image, and the third image are images obtained at the same time; the camera device includes a first camera, a second camera, and a third camera; the first image is captured by the first camera; The second image is captured by the second camera; The third image is captured by the third camera; The first camera, the second camera, and the third camera are arranged horizontally in a straight line; the distance between the first camera and the second camera is a first distance; The distance between the second camera and the third camera is a second distance; and obtaining the height of the user based on the visual image includes: Based on the visual image, a first ratio, a second ratio, and a third ratio are obtained; the first ratio is a ratio of a first object distance to a height of the user; the second ratio is a ratio of a second object distance to a height of the user; and the third ratio is a ratio of a third object distance to the height of the user; the first object distance is an object distance corresponding to the first image; the second object distance is an object distance corresponding to the second image; and the third object distance is an object distance corresponding to the third image; The height of the user is obtained based on the first ratio, the second ratio, the third ratio, the first distance, and the second distance.

4. The method for automatically adjusting the height of a terminal device using AI visual judgment according to any one of claims 1 to 3, characterized in that: Before adjusting the height of the display screen and / or operating platform of the terminal device based on the body height, the method further includes: Based on the visual image, obtaining the user's posture; the posture includes at least standing and sitting; The adjusting the height of the display screen and / or operating platform of the terminal device based on the body height includes: If the user is sitting, adjusting the display screen and / or operating platform of the terminal device to a first height based on the height; the first height is obtained based on the height; If the user is standing, the display screen and / or operating platform of the terminal device is adjusted to a second height based on the height; the second height is obtained based on the height.

5. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 4, characterized in that: The acquiring the user's posture based on the visual image includes: Obtaining a first key point, a second key point, and a third key point from the visual image based on a human posture estimation model; the first key point is a key point corresponding to the user's torso; the second key point is a key point corresponding to the user's hip; and the third key point is a key point corresponding to the user's knee; Based on the first key point, the second key point, and the third key point, obtaining a first slope and a second slope; the first slope is a slope between the first key point and the second key point; the second slope is a slope between the second key point and the third key point; Obtaining a first difference value based on the first slope and the second slope; the first difference value is at least used to characterize the difference between the first slope and the second slope; The user's posture is acquired based on the first difference value.

6. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 5, characterized in that: The acquiring the user's posture based on the first difference value includes: If the first difference value is greater than or equal to a first preset value, determining that the user's posture is a sitting posture; If the first difference value is smaller than a first preset value, it is determined that the user's posture is standing.

7. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 4, characterized in that: After obtaining the user's posture, the method further includes: If the user's posture is standing, then based on the multiple visual images of the user, obtaining a posture straightness value and a first height corresponding to each visual image; the posture straightness value is positively correlated with the degree of straightness of the user's standing posture in the corresponding visual image; the first height is the height of the user in the corresponding visual image; Based on the respective posture straightness values, a plurality of second heights are obtained; the second height is any first height whose posture straightness value is greater than or equal to a second preset value; Based on each second height, the height of the user is updated.

8. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 7, characterized in that: The acquiring, based on the plurality of visual images of the user, a posture straightness value corresponding to each visual image, comprises: Based on each visual image, a first visual image is obtained; the first visual image is any one of the visual images; the method for obtaining the posture straightness values ​​of the remaining visual images in each visual image is the same as that of the first visual image; Acquire a plurality of key points from the first visual image based on a human posture estimation model; Based on each key point, a posture straightness value of the first visual image is obtained.

9. The method for automatically adjusting the height of a terminal device using AI visual judgment according to claim 8, characterized in that: The key points include a top of the head key point, a chin key point, a torso key point, a hip key point, a knee key point, and a heel key point; and obtaining a posture straightness value of the first visual image based on the key points includes: Based on each key point, a plurality of slope values ​​are obtained; the slope value is the absolute value of the slope between any two key points in each key point; Based on each slope value, a second difference value is obtained; the second difference value is at least used to represent the difference between each slope value; Based on the second difference value, a posture straightness value of the first visual image is obtained.

10. A system for automatically adjusting the height of a terminal device using AI visual judgment, wherein the height of the display screen and / or operating platform of the terminal device can be electrically adjusted; characterized in that: include: a camera device for acquiring visual images; a processing device for obtaining a user's height based on the visual image; A control device is used to adjust the height of the display screen and / or operating platform of the terminal device based on the body height.

Images