Sitting posture reminding method, device and equipment and storage medium

Abstract

The invention is applicable to the technical field of sitting posture detection, and provides a sitting posture reminding method, which comprises the following steps: performing image acquisition on a user in front of a desk through image acquisition equipment to obtain a posture image of the user, and performing human eye detection and human body detection on the posture image respectively to obtain a posture image; obtaining human eye position information and human body position information of the user in the posture image, calculating the distance between the eyes of the user and the desk by adopting a preset eye-desk distance calculation strategy based on the human eye position information and the human body position information to obtain an eye-desk distance, and when the eye-desk distance is lower than a preset distance threshold value, sending the eye-desk distance to the user. According to the method and the device, the user is reminded of too close eye use to correct the bad sitting posture of the user, so that the sitting posture detection cost is reduced, the accuracy of the eye table distance and the timeliness and effectiveness of eye use reminding are improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of sitting posture detection, and in particular relates to a sitting posture reminder method, device, equipment and storage medium. Background Art

[0002] With the popularization of electronic devices and the rise of online education, users often unconsciously get close to their desks (or display devices) during study and work, which makes their eyes too close to the desks (or display devices), which can easily lead to myopia. Especially among primary and secondary school students, the myopia rate has risen rapidly. Many students are already in the dilemma of high myopia even in primary school, which undoubtedly brings distress to students' parents.

[0003] In order to effectively protect students' eyesight, it is particularly important to accurately measure and adjust the distance between the eyes and the desk (or display device) in a timely manner. At present, a variety of eye-desk distance measurement solutions have been developed in the market and in the technical field, among which the more prominent ones are binocular stereo vision technology and ToF (Time of Flight) method. Binocular stereo vision technology uses two cameras to simulate the working mode of the human eye, captures images through the left and right cameras, and uses the principle of triangulation to accurately calculate the distance, showing the significant advantages of non-contact, high precision and strong real-time performance. However, at the same time, it also brings cost considerations that cannot be ignored in hardware, computing resources, software and algorithms, calibration and system integration. For example, in terms of hardware cost, high-resolution and high-frame-rate binocular cameras are relatively expensive, especially industrial-grade cameras. At the same time, in order to obtain a larger field of view and higher resolution, high-quality lenses are required, which will also increase costs. As for the ToF method, it is a technology based on the principle of measuring the time of flight of light pulses. It directly calculates the distance by emitting short pulses of light and receiving the time difference of their reflection. This method is not only fast and has a wide measurement range, but also is less affected by ambient light. Therefore, it has good application prospects in many scenarios. However, this technology also faces multiple challenges in hardware, software, system integration and other costs. For example, in terms of hardware cost, high-precision and high-resolution ToF sensors are expensive, especially industrial-grade sensors, and ToF sensors require matching light source modules, such as lasers, VCSELs, etc. The cost of these devices is not low. In addition, the signal generated by the ToF sensor needs to undergo complex signal processing, which requires additional hardware circuits and increases the hardware cost. In terms of software cost, the ToF ranging algorithm is relatively complex, involving signal processing, filtering, multipath correction, etc., and requires a lot of manpower and material resources for algorithm development. In addition, commercial ToF ranging software usually requires the purchase of authorization, which increases the cost of software use. Therefore, a new low-cost eye-table distance measurement solution is urgently needed for sitting posture detection. Summary of the invention

[0004] The purpose of the present invention is to provide a sitting posture reminder method, device, equipment and storage medium, aiming to solve the problems of high sitting posture detection cost and low effectiveness of eye reminder due to the inability of existing technology.

[0005] In one aspect, the present invention provides a sitting posture reminder method, the method comprising the following steps:

[0006] Capturing an image of a user in front of a desk by an image acquisition device to obtain a posture image of the user;

[0007] Performing eye detection and body detection on the posture image respectively to obtain eye position information and body position information of the user in the posture image;

[0008] Based on the eye position information and the body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance;

[0009] When the eye-desk distance is lower than a preset distance threshold, the user is reminded that he / she is using his / her eyes too close, so as to correct the user's bad sitting posture.

[0010] Preferably, based on the eye position information and the body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk, and the step of obtaining the eye-desk distance includes:

[0011] Based on the eye position information and the body position information, calculating the ratio of the area from the eye to the bottom of the body in the posture image to the image;

[0012] Based on the ratio and the vertical capture length of the image acquisition device, the eye-table distance is calculated using a preset eye-table distance calculation formula.

[0013] Preferably, the step of calculating the eye-table distance using a preset eye-table distance calculation formula based on the ratio and the vertical capture length of the image acquisition device comprises:

[0014] The vertical capture length is calculated using a preset capture length calculation formula according to the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device.

[0015] Preferably, the capture length calculation formula is: Wherein, V is the camera viewing angle, D is the placement distance, and I is the vertical capture length.

[0016] Preferably, the eye-desk distance calculation formula is E=I*R+H*K, wherein R is the ratio, H is the height of the image acquisition device on the desktop of the desk, K is the deviation constant, and E is the eye-desk distance.

[0017] In another aspect, the present invention provides a sitting posture reminder device, the device comprising:

[0018] An image acquisition unit, used to acquire an image of a user located in front of a desk through an image acquisition device to obtain a posture image of the user;

[0019] An image analysis unit, used to perform eye detection and body detection on the posture image, respectively, to obtain eye position information and body position information of the user in the posture image;

[0020] A distance calculation unit, configured to calculate the distance between the user's eyes and the desk based on the eye position information and the body position information, using a preset eye-desk distance calculation strategy to obtain the eye-desk distance;

[0021] The eye reminder unit is used to remind the user that the eyes are too close when the eye-desk distance is lower than a preset distance threshold, so as to correct the user's bad sitting posture.

[0022] Preferably, the distance calculation unit comprises:

[0023] A ratio calculation unit, used for calculating the ratio of the area from the human eye to the bottom of the human body in the posture image to the image based on the human eye position information and the human body position information;

[0024] The distance calculation subunit is used to calculate the eye-table distance based on the ratio and the vertical capture length of the image acquisition device by using a preset eye-table distance calculation formula.

[0025] Preferably, the distance calculation subunit comprises:

[0026] The length calculation unit is used to calculate the vertical capture length using a preset capture length calculation formula according to the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device.

[0027] On the other hand, the present invention also provides an image acquisition device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps described in the above-mentioned sitting posture reminder method when executing the computer program.

[0028] On the other hand, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps described in the above-mentioned sitting posture reminder method are implemented.

[0029] The present invention uses an image acquisition device to acquire an image of a user located in front of a desk to obtain a posture image of the user, performs eye detection and body detection on the posture image respectively to obtain eye position information and body position information of the user in the posture image, and based on the eye position information and body position information, uses a preset eye-desk distance calculation strategy to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance, and when the eye-desk distance is lower than a preset distance threshold, reminds the user that he or she is using his or her eyes too close to the desk to correct the user's bad sitting posture, thereby reducing the sitting posture detection cost, improving the accuracy of the eye-desk distance and the timeliness and effectiveness of eye reminders, and further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of the implementation of the sitting posture reminder method provided in the first embodiment of the present invention;

[0031] Figure 2 is a schematic diagram of various parameters used for calculating the eye-desk distance in the sitting posture reminder method provided in the first embodiment of the present invention;

[0032] Figure 3 is a structural schematic diagram of a sitting posture reminder device provided in Embodiment 2 of the present invention;

[0033] Figure 4 It is a structural schematic diagram of the image acquisition device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0035] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments:

[0036] Embodiment 1:

[0037] Figure 1 The implementation process of the sitting posture reminder method provided in the first embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0038] In step S101, an image acquisition device is used to acquire an image of a user located in front of a desk to obtain a posture image of the user.

[0039] The embodiment of the present invention is applicable to an image acquisition device with a single camera, such as a smart phone, a tablet computer, a smart camera, etc. In the embodiment of the present invention, the image acquisition device only needs to have one built-in camera to reduce the cost of the device, and the device is placed on the desk. The camera in the image acquisition device is used to acquire an image of a user in front of the desk in real time to obtain a posture image of the user.

[0040] In step S102, eye detection and body detection are performed on the gesture image to obtain eye position information and body position information of the user in the gesture image.

[0041] In an embodiment of the present invention, a deep learning technology is used to analyze a posture image to identify and locate the eye region and the body region of a user in the posture image, and obtain the eye position information and the body position information of the user in the posture image. Specifically, an artificial intelligence model composed of an eye detection model and a body detection model performs eye detection and body detection on the posture image respectively, and obtains a rectangular bounding box of the eye and a rectangular bounding box of the body in the posture image respectively. The upper left corner coordinate (x human_min ,y human_min ) and the lower right corner coordinate (x human_max ,y human_max ) determines the human body position information in the posture image. Since people usually have two eyes, the human eye rectangular bounding box includes the left eye bounding box and the right eye bounding box. Here, the lowest point of the upper boundary of the left eye bounding box and the right eye bounding box is used as the reference point of the "human eye". The coordinates of this point (x eye_min ,y eye_min ) is determined as the eye position information in the posture image, wherein the human body detection model is used to identify and locate the human body area in the image, and the eye detection model is used to identify and locate the eye area in the image. In addition, the eye detection model and the human body detection model can be obtained by model training using a mobile neural network (MNN) reasoning framework.

[0042] In step S103, based on the eye position information and the body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance.

[0043] In an embodiment of the present invention, the calculation of the eye-table distance is achieved through the following steps:

[0044] (1) Based on the eye position information and the body position information, the ratio of the area from the eye to the bottom of the body in the posture image to the image is calculated;

[0045] In the embodiment of the present invention, the Y coordinate of the bottom area of ​​the human body (close to the edge of the desktop) in the posture image is usually the Y coordinate of the lower boundary in the human body rectangular bounding box, that is, the y coordinate in the human body position information. human_max Here, first, according to the eye position information and the Y coordinate of the bottom area of ​​the human body, the vertical distance from the eye to the bottom of the human body in the posture image is calculated, that is, d = y human_max -y eye_min , then, according to the calculated vertical distance d and the image height Img of the posture image height , calculate the ratio R of the area from the human eye to the bottom of the body in the posture image, that is, R is the ratio of the distance from the human eye to the bottom of the human body in the posture image to the total image height.

[0046] (2) Based on the ratio and the vertical capture length of the image acquisition device, the eye-table distance is calculated using a preset eye-table distance calculation formula.

[0047] In the embodiment of the present invention, the vertical capture length of the image acquisition device refers to the coverage that can be captured by the camera field of view in the vertical direction (i.e., the up and down direction) in the scene captured by the image acquisition device (such as a camera). Figure 2 As shown, under the camera viewing angle V, the picture height I is its vertical capture length. Here, based on the calculated ratio and the vertical capture length of the image acquisition device, the eye-table distance is calculated using a preset eye-table distance calculation formula.

[0048] In a feasible embodiment, when calculating the eye-table distance using a preset eye-table distance calculation formula based on the ratio and the vertical capture length of the image acquisition device, the vertical capture length is first calculated using a preset capture length calculation formula based on the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device, and then the eye-table distance is calculated using a preset eye-table distance calculation formula based on the calculated vertical capture length and the ratio.

[0049] In the embodiment of the present invention, Figure 2 As shown in the figure, the placement distance of the image acquisition device refers to the distance D from the device to the edge of the table. The camera viewing angle refers to the field of view displayed by the camera lens when capturing an image. It is usually expressed as an angle, which includes horizontal viewing angle and vertical viewing angle. Here, only the vertical viewing angle (i.e. Figure 2 The camera angle V in the image acquisition device is used to calculate the vertical capture length. For the calculation of the eye-table distance, the preset capture length calculation formula is used according to the camera angle of the image acquisition device and the placement distance of the image acquisition device. The vertical capture length I is calculated, and then, based on the ratio R and the vertical capture length I, the eye-to-desk distance E is calculated using the preset eye-to-desk distance calculation formula E=I*R+H*K, thereby improving the accuracy of the eye-to-desk distance measurement, wherein V is the camera viewing angle, D is the placement distance, H is the height of the image acquisition device on the desk surface, and K is a deviation constant used to adjust the deviation caused by the camera installation elevation angle.

[0050] The calculation of the eye-table distance is realized through the above steps (1) and (2), thereby improving the accuracy of the eye-table distance measurement.

[0051] In step S104, when the eye-desk distance is lower than a preset distance threshold, the user is reminded that the eyes are too close together, so as to correct the user's bad sitting posture.

[0052] In an embodiment of the present invention, the calculated eye-desk distance is compared with a preset distance threshold. When the eye-desk distance is lower than the preset distance threshold, the user can be reminded of using the eyes too close by sound or vibration, so as to remind the user to correct the bad sitting posture in time, thereby reducing the risk of myopia. In addition, in terms of guiding students' writing posture, it is usually recommended that the distance between the eyes and the book should be kept at about one foot (about 33 cm). This distance helps to reduce the adjustment burden of the eyes when reading and writing. Based on this, the distance threshold can be set to 33 cm, thereby reducing the risk of visual fatigue.

[0053] In an embodiment of the present invention, an image acquisition device is used to acquire an image of a user located in front of a desk to obtain a posture image of the user, and eye detection and body detection are performed on the posture image to obtain eye position information and body position information of the user in the posture image. Based on the eye position information and body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance. When the eye-desk distance is lower than a preset distance threshold, the user is reminded that he or she is using his or her eyes too close to the desk to correct the user's bad sitting posture, thereby reducing the sitting posture detection cost, improving the accuracy of the eye-desk distance and the timeliness and effectiveness of eye reminders, and thereby improving the user experience.

[0054] Embodiment 2:

[0055] Figure 3 The structure of the sitting posture reminder device provided by the second embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, including:

[0056] The image acquisition unit 31 is used to acquire an image of the user at the desk through an image acquisition device to obtain a posture image of the user.

[0057] In an embodiment of the present invention, the image acquisition device only needs to have a built-in camera to reduce the cost of the device, and it is placed on the desktop of a desk. The camera in the image acquisition device is used to capture images of the user in front of the desk in real time to obtain a posture image of the user.

[0058] The image analysis unit 32 is used to perform eye detection and body detection on the gesture image respectively, and obtain eye position information and body position information of the user in the gesture image.

[0059] In an embodiment of the present invention, a deep learning technology is used to analyze a posture image to identify and locate the eye region and the body region of a user in the posture image, and obtain the eye position information and the body position information of the user in the posture image. Specifically, an artificial intelligence model composed of an eye detection model and a body detection model performs eye detection and body detection on the posture image respectively, and obtains a rectangular bounding box of the eye and a rectangular bounding box of the body in the posture image respectively. The upper left corner coordinate (x human_min ,y human_min ) and the lower right corner coordinate (x human_max ,y human_max ) determines the human body position information in the posture image. Since people usually have two eyes, the human eye rectangular bounding box includes the left eye bounding box and the right eye bounding box. Here, the lowest point of the upper boundary of the left eye bounding box and the right eye bounding box is used as the reference point of the "human eye". The coordinates of this point (x eye_min ,y eye_min ) is determined as the eye position information in the posture image, wherein the human body detection model is used to identify and locate the human body area in the image, and the eye detection model is used to identify and locate the eye area in the image. In addition, the eye detection model and the human body detection model can be obtained by model training using a mobile neural network (MNN) reasoning framework.

[0060] The distance calculation unit 33 is used to calculate the distance between the user's eyes and the desk based on the eye position information and the body position information, and obtain the eye-desk distance by using a preset eye-desk distance calculation strategy.

[0061] In the embodiment of the present invention, preferably, the distance calculation unit includes:

[0062] A ratio calculation unit, used for calculating the ratio of the area from the human eye to the bottom of the human body in the posture image to the image based on the human eye position information and the human body position information;

[0063] In the embodiment of the present invention, the Y coordinate of the bottom area of ​​the human body (close to the edge of the desktop) in the posture image is usually the Y coordinate of the lower boundary in the human body rectangular bounding box, that is, the y coordinate in the human body position information. human_maxHere, first, according to the eye position information and the Y coordinate of the bottom area of ​​the human body, the vertical distance from the eye to the bottom of the human body in the posture image is calculated, that is, d = y human_max -y eye_min , then, according to the calculated vertical distance d and the image height Img of the posture image height , calculate the ratio R of the area from the human eye to the bottom of the body in the posture image, that is, R is the ratio of the distance from the human eye to the bottom of the human body in the posture image to the total image height.

[0064] The distance calculation subunit is used to calculate the eye-table distance based on the ratio and the vertical capture length of the image acquisition device using a preset eye-table distance calculation formula.

[0065] In an embodiment of the present invention, the vertical capture length of the image acquisition device refers to the coverage range that can be captured by the camera field of view in the vertical direction (i.e., the up and down direction) in the scene photographed by the image acquisition device (such as a camera). Here, based on the calculated ratio and the vertical capture length of the image acquisition device, the eye-table distance is calculated using a preset eye-table distance calculation formula.

[0066] Still preferably, the distance calculation subunit comprises:

[0067] The length calculation unit is used to calculate the vertical capture length using a preset capture length calculation formula according to the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device.

[0068] In the embodiment of the present invention, the placement distance of the image acquisition device refers to the distance from the device to the edge of the table, and the camera angle of view refers to the field of view displayed by the camera lens when capturing an image, which is usually expressed as an angle, including a horizontal angle of view and a vertical angle of view. Here, only the vertical angle of view is considered to calculate the vertical capture length. For the calculation of the eye-table distance, firstly, according to the camera angle of view of the image acquisition device and the placement distance of the image acquisition device, a preset capture length calculation formula is used: The vertical capture length I is calculated, and then, based on the ratio R and the vertical capture length I, the eye-to-desk distance E is calculated using the preset eye-to-desk distance calculation formula E=I*R+H*K, thereby improving the accuracy of the eye-to-desk distance measurement, wherein V is the camera viewing angle, D is the placement distance, H is the height of the image acquisition device on the desk surface, and K is a deviation constant used to adjust the deviation caused by the camera installation elevation angle.

[0069] The eye reminder unit 34 is used to remind the user that the eyes are too close when the eye-desk distance is lower than a preset distance threshold, so as to correct the user's bad sitting posture.

[0070] In an embodiment of the present invention, the calculated eye-desk distance is compared with a preset distance threshold. When the eye-desk distance is lower than the preset distance threshold, the user can be reminded of using the eyes too close by sound or vibration, so as to remind the user to correct the bad sitting posture in time, thereby reducing the risk of myopia. In addition, in terms of guiding students' writing posture, it is usually recommended that the distance between the eyes and the book should be kept at about one foot (about 33 cm). This distance helps to reduce the adjustment burden of the eyes when reading and writing. Based on this, the distance threshold can be set to 33 cm, thereby reducing the risk of visual fatigue.

[0071] In the embodiment of the present invention, each unit of the sitting posture reminder device can be implemented by a corresponding hardware or software unit. Each unit can be an independent software or hardware unit or integrated into one software or hardware unit, which is not intended to limit the present invention.

[0072] Embodiment three:

[0073] Figure 4 The structure of the image acquisition device provided by the third embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown.

[0074] The image acquisition device 4 of the embodiment of the present invention includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps of the above-mentioned sitting posture reminder method embodiment are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each unit in the above-mentioned device embodiments are realized, for example Figure 3 Function of the unit shown.

[0075] In an embodiment of the present invention, an image acquisition device is used to acquire an image of a user located in front of a desk to obtain a posture image of the user, and eye detection and body detection are performed on the posture image to obtain eye position information and body position information of the user in the posture image. Based on the eye position information and body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance. When the eye-desk distance is lower than a preset distance threshold, the user is reminded that he or she is using his or her eyes too close to the desk to correct the user's bad sitting posture, thereby reducing the sitting posture detection cost, improving the accuracy of the eye-desk distance and the timeliness and effectiveness of eye reminders, and thereby improving the user experience.

[0076] The image acquisition device of the embodiment of the present invention can be a smart phone, a tablet computer, or a smart camera. The steps implemented when the processor 40 in the image acquisition device 4 executes the computer program 42 to implement a sitting posture reminder method can refer to the description of the aforementioned method embodiment, which will not be repeated here.

[0077] Embodiment 4:

[0078] In an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned sitting posture reminder method embodiment are implemented, for example, Figure 1 Alternatively, when the computer program is executed by a processor, the functions of each unit in the above-mentioned device embodiments are realized, for example Figure 3 Function of the unit shown.

[0079] In an embodiment of the present invention, an image acquisition device is used to acquire an image of a user located in front of a desk to obtain a posture image of the user, and eye detection and body detection are performed on the posture image to obtain eye position information and body position information of the user in the posture image. Based on the eye position information and body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance. When the eye-desk distance is lower than a preset distance threshold, the user is reminded that he or she is using his or her eyes too close to the desk to correct the user's bad sitting posture, thereby reducing the sitting posture detection cost, improving the accuracy of the eye-desk distance and the timeliness and effectiveness of eye reminders, and thereby improving the user experience.

[0080] The computer-readable storage medium of the embodiment of the present invention may include any entity or device or recording medium capable of carrying computer program code, for example, ROM / RAM, magnetic disk, optical disk, flash memory and other memories.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A sitting posture reminder method, characterized in that: The method comprises the following steps: Capturing an image of a user in front of a desk by an image acquisition device to obtain a posture image of the user; Performing eye detection and body detection on the posture image respectively to obtain eye position information and body position information of the user in the posture image; Based on the eye position information and the body position information, a preset eye-desk distance calculation strategy is used to calculate the distance between the user's eyes and the desk to obtain the eye-desk distance; When the eye-desk distance is lower than a preset distance threshold, the user is reminded that he / she is using his / her eyes too close, so as to correct the user's bad sitting posture.

2. The method according to claim 1, characterized in that The step of calculating the distance between the user's eyes and the desk based on the eye position information and the body position information using a preset eye-desk distance calculation strategy to obtain the eye-desk distance includes: Based on the eye position information and the body position information, calculating the ratio of the area from the eye to the bottom of the body in the posture image to the image; Based on the ratio and the vertical capture length of the image acquisition device, the eye-table distance is calculated using a preset eye-table distance calculation formula.

3. The method according to claim 2, characterized in that The step of calculating the eye-table distance using a preset eye-table distance calculation formula based on the ratio and the vertical capture length of the image acquisition device comprises: The vertical capture length is calculated using a preset capture length calculation formula according to the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device.

4. The method according to claim 3, characterized in that The capture length calculation formula is: Wherein, V is the camera viewing angle, D is the placement distance, and I is the vertical capture length.

5. The method according to claim 4, characterized in that The eye-desk distance calculation formula is E=I*R+H*K, wherein R is the ratio, H is the height of the image acquisition device on the desktop of the desk, K is the deviation constant, and E is the eye-desk distance.

6. A sitting posture reminder device, characterized in that: The device comprises: An image acquisition unit, used to acquire an image of a user located in front of a desk through an image acquisition device to obtain a posture image of the user; An image analysis unit, used to perform eye detection and body detection on the posture image, respectively, to obtain eye position information and body position information of the user in the posture image; A distance calculation unit, configured to calculate the distance between the user's eyes and the desk based on the eye position information and the body position information, using a preset eye-desk distance calculation strategy to obtain the eye-desk distance; The eye reminder unit is used to remind the user that the eyes are too close when the eye-desk distance is lower than a preset distance threshold, so as to correct the user's bad sitting posture.

7. The device according to claim 6, characterized in that The distance calculation unit comprises: A ratio calculation unit, used for calculating the ratio of the area from the human eye to the bottom of the human body in the posture image to the image based on the human eye position information and the human body position information; The distance calculation subunit is used to calculate the eye-table distance based on the ratio and the vertical capture length of the image acquisition device by using a preset eye-table distance calculation formula.

8. The device according to claim 6, characterized in that The distance calculation subunit comprises: The length calculation unit is used to calculate the vertical capture length using a preset capture length calculation formula according to the camera viewing angle of the image acquisition device and the placement distance of the image acquisition device.

9. An image acquisition device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images