CN119888840B - Sitting posture detection device and control method thereof, and sitting posture detection method - Google Patents
Sitting posture detection device and control method thereof, and sitting posture detection methodInfo
- Publication number
- CN119888840B CN119888840B CN202411749791.8A CN202411749791A CN119888840B CN 119888840 B CN119888840 B CN 119888840B CN 202411749791 A CN202411749791 A CN 202411749791A CN 119888840 B CN119888840 B CN 119888840B
- Authority
- CN
- China
- Prior art keywords
- target
- sitting posture
- key point
- camera
- angle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了一种坐姿检测装置及其控制方法、坐姿检测方法，坐姿检测装置包括：底座；固定支撑支架，其一端与底座的一端固定连接；高度调节支架，其一端与底座的另一端通过第一调节装置转动连接；摄像装置，包括壳体支架、摄像头和第二调节装置，壳体支架的一端与高度调节支架的另一端通过第三调节装置转动连接，摄像头和第二调节装置皆设于壳体支架内部，第二调节装置设于摄像头背面且与摄像头转动连接，摄像头用于检测目标图像；底座、固定支撑支架、高度调节支架和摄像装置构成长方形结构；控制装置，用于根据目标图像调整第一调节装置、第二调节装置和第三调节装置的转动角度，以及调整摄像头的摄像参数。本发明能够提高坐姿检测的准确率。
The present invention discloses a sitting posture detection device, a control method thereof, and a sitting posture detection method. The sitting posture detection device includes: a base; a fixed support bracket, one end of which is fixedly connected to one end of the base; a height adjustment bracket, one end of which is rotatably connected to the other end of the base via a first adjustment device; a camera device, including a shell bracket, a camera, and a second adjustment device, one end of the shell bracket and the other end of the height adjustment bracket being rotatably connected via a third adjustment device, the camera and the second adjustment device both being located inside the shell bracket, the second adjustment device being located on the back of the camera and rotatably connected to the camera, and the camera being used to detect a target image; the base, the fixed support bracket, the height adjustment bracket, and the camera device forming a rectangular structure; and a control device for adjusting the rotation angles of the first adjustment device, the second adjustment device, and the third adjustment device according to the target image, as well as adjusting the camera parameters. The present invention can improve the accuracy of sitting posture detection.
Description
Technical Field
The invention relates to the technical field of sitting posture detection, in particular to a sitting posture detection device, a control method thereof and a sitting posture detection method.
Background
Sitting habit is "muscle memory" created by long-term body posture maintenance. The healthy sitting posture can help people to improve the working efficiency, lighten the spinal pressure and is beneficial to bone health, and the poor sitting posture is one of the important reasons for causing the spinal diseases such as soreness and backache, scoliosis, lumbar disc herniation and the like of people. Therefore, the good sitting habit is beneficial to the health of the body, and the probability of people suffering from chronic diseases of skeletal muscle meat can be reduced.
The traditional sitting posture correcting mode is that the wrong sitting posture of people is forcedly corrected by the physical stretching action of the bandage, but the body is possibly damaged irreversibly, and the posture correcting effect is weak. The existing intelligent sitting posture detection equipment can meet the requirements of different table heights only by adjusting the front-back rotation angle of the detection body on the base, and the conditions of the width of the table top, the dynamic position of a user and the like can enable the camera to acquire incomplete portrait data, so that the accuracy of sitting posture detection is greatly reduced. And the accuracy of the existing bad gesture detection result is not high.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a sitting posture detection device which can improve the accuracy of sitting posture detection.
The invention also provides a control method of the sitting posture detection device, a sitting posture detection method, a control device for executing the control method of the sitting posture detection device and the sitting posture detection method, and a computer readable storage medium.
An embodiment of a sitting posture detection device according to the first aspect of the present invention includes:
a base;
One end of the fixed support bracket is fixedly connected with one end of the base;
One end of the height adjusting bracket is rotationally connected with the other end of the base through a first adjusting device;
The camera device comprises a shell bracket, a camera and a second adjusting device, wherein one end of the shell bracket is rotationally connected with the other end of the height adjusting bracket through a third adjusting device, the camera and the second adjusting device are arranged in the shell bracket, and the second adjusting device is arranged on the back of the camera and rotationally connected with the camera and is used for detecting a target image;
The control device is arranged inside the base and is respectively and electrically connected with the first adjusting device, the second adjusting device, the third adjusting device and the camera, and the control device is used for adjusting the rotation angles of the first adjusting device, the second adjusting device and the third adjusting device according to the target image and is used for adjusting the shooting parameters of the camera.
The sitting posture detection device provided by the embodiment of the invention has at least the following beneficial effects:
The rotation of the height adjusting bracket can be adjusted by controlling the rotation angle of the first adjusting device, so that the height of the image pickup device is adjusted; the camera can be adjusted in lateral direction by controlling the rotation angle of the second adjusting device, and the angle of the camera can be adjusted by controlling the rotation angle of the third adjusting device, so that the height, the angle and the lateral position of the camera can be dynamically adjusted to adaptively track a target object, the camera can always acquire complete portrait data, and the accuracy of sitting posture detection is improved.
A control method of a sitting posture detecting device according to an embodiment of a second aspect of the present invention is applied to the sitting posture detecting device according to the embodiment of the first aspect, and the method includes:
acquiring a target image;
determining a target key point set of a target object according to the target image;
determining an integrity state of the target key point set;
If the integrity state represents an incomplete state, calculating a current three-dimensional bounding box formed by the target key point set, and predicting a target three-dimensional bounding box containing a complete portrait area;
determining a displacement vector according to the current three-dimensional bounding box and the target three-dimensional bounding box;
And adjusting the rotation angles of the first adjusting device, the second adjusting device and the third adjusting device and the shooting parameters of the camera based on the displacement vector.
The control method of the sitting posture detection device provided by the embodiment of the invention has at least the following beneficial effects:
the method comprises the steps of obtaining a target image, determining a target key point set of a target object according to the target image, obtaining all human body key points of the target object in a shooting picture, determining whether all human body key points of the target object appear in the shooting picture or not through determining the integrity state of the target key point set, if the target key point set is in an incomplete state, calculating a current three-dimensional bounding box formed by the target key point set, predicting a target three-dimensional bounding box containing a complete portrait area, determining displacement vectors according to the current three-dimensional bounding box and the target three-dimensional bounding box, determining the amount of movement required by a camera, and then dynamically adjusting the height, the angle and the lateral position of the camera to adaptively track the target object through controlling the rotation angles of a first adjusting device, a second adjusting device and a third adjusting device and the camera, so that the camera can always acquire complete portrait data, and the accuracy of sitting posture detection is improved.
According to some embodiments of the invention, the determining the target keypoint set of the target object according to the target image includes:
extracting a depth value of each pixel in the target image;
Constructing a three-dimensional point cloud model according to the depth value of each pixel;
and calibrating the target key point set of the target object based on the three-dimensional point cloud model.
According to some embodiments of the invention, the predicting a target three-dimensional bounding box containing a complete portrait region includes:
acquiring current point cloud data of all key points in the target key point set;
inputting the current point cloud data of all key points in the target key point set into a pre-trained NeRF model, and predicting to obtain target point cloud data of all key points of a complete key point set containing a complete portrait area;
and constructing the target three-dimensional bounding box according to the target point cloud data of all the key points of the complete key point set.
According to some embodiments of the invention, the determining the integrity status of the target set of keypoints comprises:
Obtaining depth values corresponding to all key points in the target key point set;
And if the difference between the depth value corresponding to at least one key point and the depth value corresponding to other key points is larger than the preset normal distribution distance, determining the integrity state as the incompleteness state.
According to some embodiments of the invention, the determining the integrity status of the target set of keypoints comprises:
determining the number of key points of the target key point set;
And if the number of the key points is smaller than a preset complete key point threshold value, determining the integrity state as the incomplete state.
According to a third aspect of the present invention, a sitting posture detecting method is applied to the sitting posture detecting device according to the first aspect, and the method includes:
acquiring a target image;
Determining left eye key point coordinates, right eye key point coordinates, left ear key point coordinates, right ear key point coordinates, left shoulder key point coordinates and right shoulder key point coordinates of a target object according to the target image;
determining a left eye ear vector, a right eye ear vector, a left shoulder ear vector, a right shoulder ear vector and a shoulder height difference according to the left eye key point coordinates, the right eye key point coordinates, the left ear key point coordinates, the right ear key point coordinates, the left shoulder key point coordinates and the right shoulder key point coordinates;
calculating a first included angle between the left eye ear vector and the left shoulder ear vector, and a second included angle between the right eye ear vector and the right shoulder ear vector;
and determining the sitting posture state of the target object according to the shoulder height difference, the first included angle and the second included angle.
The sitting posture detection method provided by the embodiment of the invention has at least the following beneficial effects:
According to the embodiment of the invention, the sitting posture state of the target object is comprehensively judged through the included angle between the eye and ear vectors and the shoulder height difference, so that the low head behaviors and the accompanying posture abnormalities thereof can be accurately identified, and more effective sitting posture correction reminding and data feedback are provided for the user.
According to some embodiments of the invention, the determining the sitting posture state of the target object according to the shoulder height difference, the first included angle and the second included angle includes:
If the first included angle and the second included angle are smaller than a preset low head threshold value and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a low head state;
Or if the first included angle or the second included angle is smaller than a preset low head threshold value and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a low head state.
According to some embodiments of the invention, the determining the sitting posture state of the target object according to the shoulder height difference, the first included angle and the second included angle includes:
and if the first included angle or the second included angle is smaller than a preset low head threshold value and the shoulder height difference is larger than a preset abnormal height difference, determining that the sitting posture state of the target object is a head rolling state.
According to some embodiments of the invention, the determining the sitting posture state of the target object according to the shoulder height difference, the first included angle and the second included angle includes:
If the first included angle and the second included angle are both in a preset normal included angle range, and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a normal state, wherein the minimum value of the normal included angle range is a preset low head threshold value.
A control device according to an embodiment of a fourth aspect of the present invention includes a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed implements the control method of the sitting posture detection device according to the embodiment of the second aspect and the sitting posture detection method according to the embodiment of the third aspect. The control device adopts all the technical schemes of the control method and the sitting posture detection method of the sitting posture detection device of the embodiment, so that the control device has at least all the beneficial effects brought by the technical schemes of the embodiment.
A computer-readable storage medium according to an embodiment of a fifth aspect of the present invention stores computer-executable instructions for performing the control method of the sitting posture detection apparatus according to the embodiment of the second aspect and the sitting posture detection method according to the embodiment of the third aspect described above. The computer readable storage medium adopts all the technical schemes of the control method and the sitting posture detection method of the sitting posture detection device of the above embodiment, so that the control method and the sitting posture detection device at least have all the beneficial effects brought by the technical schemes of the above embodiment.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a block diagram of a sitting posture detecting apparatus according to an embodiment of the present invention;
FIG. 2 is a flow chart of a control method of a sitting posture detecting apparatus according to an embodiment of the present invention;
fig. 3 is a flowchart of a sitting posture detecting method according to an embodiment of the present invention.
Reference numerals:
A base 100;
a fixed support bracket 200;
a height-adjusting bracket 300;
A housing bracket 410 and a camera 420.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In the description of the present invention, the description of first, second, etc. is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, it should be understood that the direction or positional relationship indicated with respect to the description of the orientation, such as up, down, etc., is based on the direction or positional relationship shown in the drawings, is merely for convenience of describing the present invention and simplifying the description, and does not indicate or imply that the apparatus or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be determined reasonably by a person skilled in the art in combination with the specific content of the technical solution.
The sitting posture detecting device according to the embodiment of the present invention will be clearly and completely described below with reference to fig. 1, and it is obvious that the embodiments described below are some, but not all, embodiments of the present invention.
Referring to fig. 1, fig. 1 is a block diagram of a sitting posture detecting apparatus according to an embodiment of the present invention.
A sitting posture detecting apparatus according to an embodiment of the first aspect of the present invention includes a base 100, a fixed support bracket 200, a height adjusting bracket 300, an image pickup apparatus, and a control apparatus.
A base 100;
a fixed support bracket 200, one end of which is fixedly connected with one end of the base 100;
A height adjusting bracket 300, one end of which is rotatably connected with the other end of the base 100 through a first adjusting means;
The camera device comprises a shell bracket 410, a camera 420 and a second adjusting device, wherein one end of the shell bracket 410 is rotationally connected with the other end of the height adjusting bracket 300 through a third adjusting device, the camera 420 and the second adjusting device are both arranged in the shell bracket 410, and the second adjusting device is arranged on the back of the camera 420 and rotationally connected with the camera 420, and the camera 420 is used for detecting a target image;
The control device is arranged inside the base 100 and is respectively and electrically connected with the first adjusting device, the second adjusting device, the third adjusting device and the camera 420, and the control device is used for adjusting the rotation angles of the first adjusting device, the second adjusting device and the third adjusting device according to the target image and adjusting the shooting parameters of the camera 420.
It will be appreciated that the base 100, the fixed support bracket 200, the height adjustment bracket 300 and the camera device form a rectangular structure, so that the sitting posture detecting device according to the embodiment of the invention has small size and is convenient to carry and place.
The first adjusting device, the second adjusting device and the third adjusting device may be stepping motors, or other devices capable of controlling the rotation angle may be used, which is not limited herein.
The control device, the first adjusting device, the second adjusting device, the third adjusting device and the camera 420 can be connected in a wired mode or in a wireless mode.
The specific shapes and sizes of the base 100, the fixed support bracket 200, the height adjusting bracket 300 and the image pickup device may be selected according to actual situations, and the structure shown in fig. 1 should not be construed as limiting the present invention.
The sitting posture detection device provided by the embodiment of the invention can be directly placed on a desktop, and can be provided with an adjustable support or clamp to adapt to the width and thickness of the desktop, so that the sitting posture detection device can be compatible with various desks with different widths, infant safety monitoring and more desktop scenes.
According to the sitting posture detection device, the rotation angle of the first adjusting device is controlled, the height adjusting support 300 can be adjusted to rotate, so that the height of the camera device can be adjusted, the rotation angle of the second adjusting device is controlled, the lateral position of the camera 420 can be adjusted, the rotation angle of the third adjusting device is controlled, the angle of the camera 420 can be adjusted, the height, the angle and the lateral position of the camera 420 can be dynamically adjusted to be adaptive to tracking a target object, the camera 420 can always acquire complete portrait data, and therefore the accuracy of sitting posture detection is improved.
The control method of the sitting posture detecting device according to the embodiment of the present invention will be clearly and completely described with reference to fig. 1 and 2, and it is apparent that the embodiments described below are some, but not all, embodiments of the present invention.
Referring to fig. 1 and 2, fig. 1 is a block diagram of a sitting posture detecting apparatus according to an embodiment of the present invention, and fig. 2 is a flowchart of a control method of the sitting posture detecting apparatus according to an embodiment of the present invention.
The control method of the sitting posture detecting device according to the embodiment of the second aspect of the present invention is applied to the sitting posture detecting device of the embodiment of the first aspect, and the method includes:
acquiring a target image;
Determining a target key point set of a target object according to the target image;
determining the integrity state of a target key point set;
If the integrity state represents an incomplete state, calculating a current three-dimensional bounding box formed by the target key point set, and predicting a target three-dimensional bounding box containing a complete portrait area;
determining a displacement vector according to the current three-dimensional bounding box and the target three-dimensional bounding box;
The rotation angles of the first, second, and third adjusting devices, and the photographing parameters of the camera 420 are adjusted based on the displacement vectors.
According to the embodiment of the invention, a NeRF model is adopted to model a human body, when the fact that the target object is not fully in a shot picture is detected, the height, the angle and the lateral position of the camera 420 are automatically adjusted to be adaptive to tracking the target object, the fact that the human face is in the center of the picture is ensured, and convenience and detection accuracy are greatly improved.
The NeRF model is a technical method for realizing accurate reconstruction of a three-dimensional scene by means of a neural network, and unlike the traditional method, the NeRF model only needs to predict the color and depth value of each pixel point from a single or a few 2D view angles, and does not need to use a plurality of 2D images or view angles. It achieves this by learning a neural radiation field function that represents each point in the scene, which makes the model well applicable to single view sitting position detection devices of embodiments of the invention.
Through training, spatial position and viewing direction (5D input) can be used to map to color and opacity (4D output), acting as a "volume", so that a new view can be rendered using volume rendering to achieve three-dimensional scene reconstruction. And then analyzing the depth value, predicting and reasoning out the displacement vector of the camera 420 which can completely shoot the human image in front, so that the camera 420 can automatically adjust the height, angle and lateral position, thereby realizing the tracking of the human face of the target object.
In some embodiments of the present invention, determining a target set of keypoints for a target object from a target image comprises:
extracting a depth value of each pixel in the target image;
Constructing a three-dimensional point cloud model according to the depth value of each pixel;
and calibrating based on the three-dimensional point cloud model to obtain a target key point set of the target object.
The depth value is the distance of each pixel captured by the camera 420 from the optical axis of the camera 420 for reconstructing the portrait position in three-dimensional space. The camera 420 according to the embodiment of the present invention may adopt an RGB-D camera 420, and the depth value of each pixel is extracted from the target image by the RGB-D camera 420, and it is assumed that the depth value of each pixel in the depth map is D (u, v), where (u, v) is the image plane coordinate of the pixel, and the depth value is the distance z from the camera 420 to the point. Is provided withThe core camera 420 is used for capturing a target image of the sitting posture of a target object, and is a main source of data acquisition and is used for detecting the key point postures of the head, the shoulders and the like.
=(x,y,z)=;
Wherein, the ,For the focal length of the camera head 420,,And z is a depth value, which is an optical center coordinate.
The set of target keypoints includes, but is not limited to, eye keypoints, nose keypoints, mouth keypoints, ear keypoints, and shoulder keypoints. Firstly, constructing a three-dimensional point cloud model according to the depth value of each pixel, calibrating the spatial positions of an eye key point, a nose key point, a mouth key point, an ear key point and a shoulder key point, extracting key information of a target object by using a YOLO-Pose algorithm or other similar key point detection algorithms, and reconstructing three-dimensional key point coordinates by combining a depth map.
In some embodiments of the invention, determining the integrity status of the set of target keypoints comprises:
obtaining depth values corresponding to all key points in a target key point set;
If the difference between the depth value corresponding to at least one key point and the depth value corresponding to other key points is larger than the preset normal distribution distance, the integrity state is determined to be an incomplete state.
It will be appreciated that if the keypoints are significantly separated from other points in the scene, typically due to noise, occlusion, or out of range of the camera 420, it may also be desirable to determine that the target set of keypoints is incomplete.
In some embodiments of the invention, determining the integrity status of the set of target keypoints comprises:
determining the number of key points of a target key point set;
If the number of the key points is smaller than a preset complete key point threshold value, determining the complete state as an incomplete state.
It can be appreciated that if a part of the important key points are not detected, the target key point set is judged to be incomplete.
It should be noted that, whether the key point is absent may be determined by other methods, and is not limited to the number determination.
For the whole shot picture, it is necessary to preliminarily judge whether the current picture contains enough effective information to perform sitting posture analysis. If the important points of the ear, shoulder, etc. are not detected, or the distribution of the depth values of the key points (i.e., the 3D positions) is abnormal, it may indicate that the pose of the target object in the target image is incomplete or that the view angle of the camera 420 is problematic.
In some embodiments of the present invention, predicting a target three-dimensional bounding box containing a complete portrait region includes:
acquiring current point cloud data of all key points in a target key point set;
Inputting current point cloud data of all key points in a target key point set into a pre-trained NeRF model, and predicting to obtain target point cloud data of all key points of a complete key point set containing a complete portrait area;
and constructing a target three-dimensional bounding box according to the target point cloud data of all the key points of the complete key point set.
It will be appreciated that based on the currently detected set of target keypoints, it is necessary to further confirm whether the target region of the target object is within the field of view of the camera 420, ensuring that the bounding box completely covers the target region of the target object, e.g. whether the shoulder or head is beyond the screen boundary. If the current three-dimensional bounding box does not match the target region (e.g., the head and the shoulder) of the target object (e.g., the shoulder or head portion exceeds the current three-dimensional bounding box boundary), the camera 420 needs to be adjusted, and if the number of keypoints within the current three-dimensional bounding box is insufficient or the distribution of the depth values of the keypoints is not reasonable (e.g., the key region such as the shoulder is not covered), the camera 420 also needs to be adjusted.
The displacement vector is determined according to the current three-dimensional bounding box and the target three-dimensional bounding box, and is obtained by calculating a difference vector of three-dimensional coordinates, and the specific process is common knowledge and will not be described in detail herein.
The rotation angles of the first adjusting device, the second adjusting device and the third adjusting device and the photographing parameters of the camera 420 are adjusted based on the displacement vectors, and the parameters are converted into parameters of the first adjusting device, the second adjusting device and the third adjusting device adjusted by the camera 420 and parameters of the camera 420.
The first adjustment means corresponds to the height adjustment such that the height adjustment bracket 300 is rotated in a vertical direction with respect to the base 100.
The second adjustment means corresponds to a horizontal adjustment, i.e. a lateral position adjustment, such that the camera 420 is rotated in a horizontal direction.
The third adjusting means corresponds to a depth adjustment, i.e., an angle adjustment, such that the housing bracket 410 is rotated up and down with respect to the height adjustment bracket 300 or adjusts the focal length of the camera 420.
The housing bracket 410 may be rotated up and down with respect to the height adjustment bracket 300 or adjust the focal length of the camera 420 while the height adjustment bracket 300 is rotated in a vertical direction with respect to the base 100, so as to improve the adjustment efficiency.
In some embodiments, if the integrity status characterizes the integrity status, a sitting position detection may be performed directly. If the integrity state represents the integrity state, the current three-dimensional bounding box can be calculated continuously, and after the current three-dimensional bounding box is calculated, the current three-dimensional bounding box is found to not completely cover the target area of the target object, and the camera 420 is required to be adjusted automatically. If part of the key points in the current three-dimensional bounding box are missing or the distribution of the key points is abnormal, the integrity state of the target key point set can be determined again.
According to the embodiment of the invention, the position and the angle of the camera 420 are optimized through real-time calculation and feedback, the position of the camera 420 is adjusted, the picture is captured again after adjustment, and the integrity of the bounding box is verified. If the target is not reached, continuing to iteratively adjust until the target area is completely covered. The embodiment of the invention also establishes an accurate three-dimensional scene model through depth value analysis and NeRF model, analyzes the position of the portrait in the scene, deduces the displacement vector of the camera 420 based on complete portrait prediction, dynamically adjusts the position and angle of the camera 420, realizes automatic tracking and visual angle optimization, and improves the accuracy and applicability of sitting gesture detection.
According to the control method of the sitting posture detection device, through obtaining the target image, determining the target key point set of the target object according to the target image, all human body key points of the target object in a shooting picture can be obtained, whether all human body key points of the target object appear in the shooting picture can be determined through determining the integrity state of the target key point set, if the state is incomplete, the current three-dimensional bounding box formed by the target key point set is calculated, the target three-dimensional bounding box containing a complete portrait area is predicted, displacement vectors are determined according to the current three-dimensional bounding box and the target three-dimensional bounding box, the amount of movement required by the camera 420 is determined, and then the rotation angles of the first adjusting device, the second adjusting device and the third adjusting device and the shooting parameters of the camera 420 are controlled, so that the height, the angle and the lateral position of the camera 420 are dynamically adjusted to be self-adaptively tracked to the target object, and the camera 420 can always acquire complete portrait data, and the accuracy of sitting posture detection is improved.
The following description of the sitting posture detecting method according to the embodiments of the present invention will be made in detail with reference to fig. 1 and 3, and it is apparent that the embodiments described below are some, but not all, embodiments of the present invention.
Referring to fig. 1 and 3, fig. 1 is a block diagram of a sitting posture detecting apparatus according to an embodiment of the present invention, and fig. 3 is a flowchart of a sitting posture detecting method according to an embodiment of the present invention.
The sitting posture detecting method according to the embodiment of the third aspect of the present invention is applied to the sitting posture detecting device of the embodiment of the first aspect, and the method includes:
acquiring a target image;
Determining left eye key point coordinates, right eye key point coordinates, left ear key point coordinates, right ear key point coordinates, left shoulder key point coordinates and right shoulder key point coordinates of a target object according to the target image;
determining left eye ear vectors, right eye ear vectors, left shoulder ear vectors, right shoulder ear vectors and shoulder height differences according to the left eye key point coordinates, the right eye key point coordinates, the left ear key point coordinates, the right ear key point coordinates, the left shoulder key point coordinates and the right shoulder key point coordinates;
calculating a first included angle between the left eye ear vector and the left shoulder ear vector, and a second included angle between the right eye ear vector and the right shoulder ear vector;
and determining the sitting posture state of the target object according to the shoulder height difference, the first included angle and the second included angle.
The main current human body posture estimation algorithm can be divided into two ideas, namely a top-down (top-down) one, a boundary box is firstly obtained by detecting human body targets, then human body key points are detected in the range of the region box and are connected into the posture of each person, and the other is a bottom-up (bottom-up) one, wherein the main current human body posture estimation algorithm firstly detects all human body key points in a picture, then whether the points belong to the same target is defined, and the boundary of the target is obtained to determine the detection target. The embodiment of the invention adopts a YOLO-Pose algorithm, belongs to a bottom-up method, and adopts a specific principle in the prior art known to those skilled in the art, and is not described herein.
Firstly, detecting left eye key point coordinates, right eye key point coordinates, left ear key point coordinates, right ear key point coordinates, left shoulder key point coordinates and right shoulder key point coordinates of a target object in a target image through a YOLO-Pose algorithm, wherein the coordinates are three-dimensional coordinates and are the center points of eyes, ears and shoulders respectively. And detecting target objects in the target image through a YOLO-Pose algorithm training model, screening according to key points if a plurality of target objects exist, eliminating the target objects without facial key points, selecting one with the highest confidence as a detection target object if a plurality of target objects exist in the condition is met, detecting the feasibility of each key vector, and carrying out correction reminding after the abnormal sitting posture appears and lasts for a period of time.
The principle of determining the left eye ear vector, the right eye ear vector, the left shoulder ear vector, the right shoulder ear vector and the shoulder height difference according to the left eye key point coordinate, the right eye key point coordinate, the left ear key point coordinate, the right ear key point coordinate, the left shoulder key point coordinate and the right shoulder key point coordinate, and the principle of determining the included angle between the two vectors are all common general knowledge, and will not be described in detail herein.
In some embodiments of the present invention, determining a sitting posture state of a target object according to a shoulder height difference, a first included angle, and a second included angle includes:
if the first included angle and the second included angle are smaller than a preset low head threshold value and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a low head state;
Or if the first included angle or the second included angle is smaller than a preset low head threshold value and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a low head state.
When the target object is in a low head state, the eye-ear vector is inclined downwards, so that the included angle between the eye-ear vector and the shoulder-ear vector is reduced, and when the included angle is smaller than a preset low head threshold value, the low head state can be judged. Specifically, the low head threshold may be set to 70 °, or may be set to another value according to the actual situation, and this should not be construed as limiting the present invention.
In some embodiments, the sitting posture state of the target object may be considered as the low head state by a single-side determination that the first angle or the second angle is smaller than a preset low head threshold. The sitting posture state of the target object can be considered to be the low head state by double-side comprehensive judgment, namely, the first included angle and the second included angle are smaller than the preset low head threshold value. And the shoulder height difference is smaller than or equal to the preset abnormal height difference, and under the normal sitting posture, the absolute value of the shoulder height difference is usually close to zero, specifically, the abnormal height difference can be set to be 10mm, can be set to be other values according to actual conditions, and cannot be regarded as limiting the invention.
In some embodiments of the present invention, determining a sitting posture state of a target object according to a shoulder height difference, a first included angle, and a second included angle includes:
If the first included angle or the second included angle is smaller than a preset low head threshold value and the shoulder height difference is larger than a preset abnormal height difference, determining that the sitting posture state of the target object is a head tilting state.
When the eye-ear vector on only one side of the head is less than 70 ° from the shoulder-ear vector, this generally indicates that there may be a sideways tilt of the head rather than a completely lowered head. To further confirm whether the posture abnormality is related to low head, an analysis may be performed in conjunction with the shoulder height difference. When the shoulder height difference is larger than the preset abnormal height difference, the target object is indicated to have abnormal sitting gesture behaviors such as rolling, single shoulder sinking and the like. If the first included angle or the second included angle is smaller than a preset low head threshold value and the shoulder height difference is larger than a preset abnormal height difference, determining that the sitting posture state of the target object is a head tilting state, specifically, the left shoulder height indicates that the head is deviated to the left side, and the right shoulder height indicates that the head is deviated to the right side.
In some embodiments, if the first angle and the second angle are both smaller than a preset low head threshold and the shoulder height difference is larger than a preset abnormal height difference, determining that the sitting posture of the target object is forward leaning with single shoulder sinking or unbalanced head posture.
In some embodiments of the present invention, determining a sitting posture state of a target object according to a shoulder height difference, a first included angle, and a second included angle includes:
If the first included angle and the second included angle are both in a preset normal included angle range, and the shoulder height difference is smaller than or equal to a preset abnormal height difference, determining that the sitting posture state of the target object is a normal state, wherein the minimum value of the normal included angle range is a preset low head threshold value.
Under a standard sitting posture, when the included angle between the eye and ear vectors and the shoulder and ear vectors is close to a right angle (generally 80-100 ℃), the head is basically kept upright, and the minimum value of the normal included angle range can be set to be a preset low head threshold value, namely 70 DEG, so that no judgment standard is ensured when the included angle is 70-80 deg. The absolute value of the shoulder height difference is typically near zero.
According to the sitting posture detection method provided by the embodiment of the invention, the sitting posture state of the target object is comprehensively judged through the included angle between the eye and ear vectors and the shoulder height difference, so that the low head behaviors and the accompanying posture abnormalities thereof can be accurately identified, and more effective sitting posture correction reminding and data feedback are provided for the user.
In some embodiments, the overall flow of the embodiments of the present invention is:
Receiving a video stream acquired by the camera 420, and performing image acquisition on the video stream to acquire a target image;
detecting whether the portrait features exist in the target image, if not, continuing to receive the target image for detection, and if so, analyzing the vectors of the feature points in the target image;
detecting whether the gesture of the target object in the target image is optimal or not, calculating the height and the angle of the optimal camera 420 under the limited condition according to NeRF neural field algorithm, and transmitting data to the first adjusting device, the second adjusting device, the third adjusting device and the camera 420 to carry out gesture correction;
Analyzing whether the sitting posture of the target object is normal or not according to the YOLO-Pose algorithm, and if the sitting posture of the target object is abnormal, increasing the value of an abnormal sitting posture counter;
detecting every 2s, if the abnormal sitting posture counter reaches a preset threshold within 5 minutes, triggering an abnormal sitting posture reminding mechanism, and sending a corresponding data packet to an intelligent prompting bracelet.
In some embodiments, in consideration of the situation that parents cannot remind the bad sitting posture of children in real time, in order to enable the children to better realize the harm of the bad sitting postures, the invention further designs a device for reminding and correcting the bad sitting postures of the children by means of intelligent reminding bracelets matched with the sitting posture detection device. The method specifically comprises the following functions:
(1) Posture reminding, namely when the sitting posture detection device detects that the child keeps bad postures for a long time, the sitting posture detection device sends data to the parent end and the bracelet, the intelligent reminding bracelet reminds a user of adjusting the postures through vibration and reminding sounds, and the child can also check the schematic diagram of the bad sitting postures of the child on the bracelet, so that the child can help the child to improve sitting posture habits.
(2) Habit development, namely the intelligent prompting bracelet helps users to develop good sitting habit through a regular prompting mode, a reward mechanism mode and the like. The user can set personalized reminding frequency and rewarding targets, and the sitting habit of the user is gradually improved.
(3) And the health analysis, namely, in addition to monitoring sitting habits, the intelligent prompting bracelet can be combined with other health data (such as step numbers, heart rate and the like) of the user to carry out comprehensive analysis, so that comprehensive health management service is provided for the user.
In addition, the sitting posture detection device provided by the embodiment of the invention can be further provided with dedicated application software, and the application has the functions of monitoring data visualization and intelligently generating the sitting posture report, so that parents can be helped to analyze the daily sitting posture change of children, and corresponding adjustment suggestions can be provided. The following is a main functional introduction of the proprietary application software:
(1) Data recording and analysis the application is able to record and visualize the user's sitting position data, including duration, frequency and correctness of the posture. This data is presented to the parents of the user, helping them get deep into the sitting habits of the child and motivate them to improve positively. Meanwhile, the data is intelligently converted into a culture scheme, so that scientific guiding basis is provided for parents.
(2) Data cloud synchronization-the sitting posture data of the user can be saved to the cloud through a cloud synchronization function, so that the user can access and track the progress of the user on a plurality of devices. This feature allows the user to record and monitor at any time and place, providing them with greater convenience and flexibility.
(3) Personalized advice the application provides tailored health advice and sitting improvement plans depending on the user's specific situation.
(4) And the interactive course is used for providing a series of sitting posture correction courses and exercise videos, so that the user can actively improve the sitting posture in daily life.
After the sitting posture detecting device provided by the embodiment of the invention detects that the sitting posture of the user is bad, specific real-time feedback data can be given. Specifically including, but not limited to, sitting abnormality type, abnormality duration, detection time point, abnormality count, abnormality distribution period, abnormality accumulation period, sitting score, posture trend chart, fatigue index, bone pressure assessment, and specific improvement advice.
The types of sitting postures include, but are not limited to, low head (head over forward leaning), humpback (back bending angle exceeding standard), high and low shoulders (left and right shoulder height difference being too large), and head deflection (head leaning to one side).
Recording the time of abnormal sitting posture maintenance (such as '10 seconds above' at the beginning), recording the occurrence frequency of various abnormal sitting postures according to the day, week and month when the abnormal sitting postures are detected every time, analyzing the high-frequency time period of abnormal sitting postures in one day, recording the accumulated time of different types of abnormal sitting postures, being convenient for the user to trace back, and providing long-term trend analysis of the sitting postures habit of the user.
The overall sitting posture performance of the user is scored through an algorithm, and the sitting posture performance of the user on the same day can be reflected in a scoring form of 0-100. The change trend of the sitting posture score in a period of time is displayed by using the chart, so that a user is helped to intuitively know the improvement effect.
According to the frequency and the duration of sitting abnormal state, whether the user is likely to be in a fatigue state is judged, and based on the long-time abnormal sitting state (such as humpback), the possible pressure on the spine is prompted, so that the possible physical state of the user can be estimated.
The improvement advice specifically comprises guiding how to adjust sitting postures, such as please straighten back, relax shoulders and raise head to keep level. If the continuous working time is too long, the user is reminded of short rest, for example, "working for 1 hour, and the rising activity is recommended for 5 minutes".
The correction advice should incorporate ergonomic principles for different types of misseated postures, providing specific and easily understood guidelines. The following are detailed correction recommendations for common misseated postures:
(1) Low head (head over forward tilt). The problem is represented by excessive forward tilting of the head, too close a line of sight to the table top or book, and excessive pressure on the cervical vertebrae. The correction proposal is ① to remind the user to raise the head and straighten the chest, and slightly retract the chin to align the ear position with the shoulder. ② It is recommended to adjust the distance between the line of sight and the desktop or screen to be kept at 0-40 cm. ③ If a writing desk is used, a book support is recommended to be added or the height of a desk and a chair is recommended to be adjusted, so that the sight line forms a downward included angle of 5-20 degrees with the book.
(2) Humpback (dorsiflexion). The problem is represented by the bending of the back and the compression of the thoracic region, resulting in the collapse of the waist with the chest. The correction advice ① reminds the user to open the shoulder backwards, imagine that the scapula is clamped, keeping the back straight. ② If the chair does not provide adequate support, it is advisable to add a cushion or lumbar pillow behind the waist. ③ The user is reminded of rising to take the body every 30 minutes, and the bending posture is prevented from being maintained for a long time.
(3) High and low shoulders. The problem is expressed by that the shoulder is high on one side and low on the other side, and the uneven stress on the reclining table top or one side can be caused. The correction proposal is ① to remind the user to adjust the sitting posture so as to enable the shoulders to be horizontal and avoid supporting the tabletop by one hand or arm for a long time. ② It is recommended to center the body's center of gravity in the chair to avoid tilting of the body. ③ If the writing habit leads to unilateral stress, it is recommended to adjust the writing posture, so as to avoid long-time effort to press down the shoulders.
(4) Offset head (head inclined to one side). The problem is that the head is deviated to one side, and the head may sink along with a single shoulder. The correction advice ① alerts the user to keep his head neutral and the ears should be aligned with the shoulders. ② The position of the screen or the book is guided and adjusted, the sight of the user is guaranteed to be opposite, and the head deviation caused by the asymmetric sight is avoided. ③ The user is encouraged to gently stretch the neck muscles at regular intervals and relieve the tension of the neck muscles.
(5) Sitting posture is askew. The problem manifests itself in a shift of the pelvis side, resulting in a body tilt or a shift of the center of gravity to one side. The correction proposal is ① to remind the user to adjust the buttocks to sit on the seat surface, the feet are horizontally placed on the ground, and the knees are parallel to the hips. ② It is recommended that the body weights on both sides are evenly distributed in the sitting posture, so that one-side overstress is avoided. ③ If the chair is unstable or lacks support, it is recommended to replace it with a more stable chair.
(6) The body is hyperanteverted. The problem is that the whole body leans forward, the chest is too close to the table top, and the spinal load is increased. The correction proposal is ① to remind the user to keep the back close to the chair back as much as possible when sitting, adjust the height of the desktop or put articles, and reduce the forward tilting requirement. ② The adjustable chair is encouraged to be used, and the adjustable chair is adjusted to be at a proper height, so that the arm can be naturally placed on the desktop.
(7) The static posture is maintained for a long time. The problem is represented by the long-term maintenance of a single posture, and the increase of muscle fatigue and joint pressure. And the correction proposal is ① for reminding the user of rising or stretching every 30 minutes so as to relieve fatigue. ② Some simple actions such as standing up, turning the shoulders, etc. may be suggested by the reminder function.
The concrete reminding mode is ① vibration reminding, namely light vibration reminding when the abnormal duration reaches a set threshold value. ② Screen prompt, which is to explain the questions and suggestions in text and animation form through the matched equipment or application program. ③ Voice prompt, which is to play simple voice instructions, such as "please raise the head", "sit straight a little", etc.
Through the targeted suggestions, the user can clearly know the reasons of the problems and how to improve, so that the user can develop good sitting habit and reduce the negative influence of the bad sitting habit on the body for a long time.
In addition, one embodiment of the present invention also provides a control device including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor and the memory may be connected by a bus or other means.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Non-transitory software programs and instructions required to implement the control method and the sitting posture detection method of the above-described embodiments are stored in a memory, and when executed by a processor, the control method and the sitting posture detection method of the above-described embodiments are performed.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Further, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or a controller, for example, by the processor of the above embodiment, so that the above processor performs the control method and the sitting posture detection method of the sitting posture detection apparatus of the above embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411749791.8A CN119888840B (en) | 2024-12-02 | 2024-12-02 | Sitting posture detection device and control method thereof, and sitting posture detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411749791.8A CN119888840B (en) | 2024-12-02 | 2024-12-02 | Sitting posture detection device and control method thereof, and sitting posture detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119888840A CN119888840A (en) | 2025-04-25 |
| CN119888840B true CN119888840B (en) | 2025-10-21 |
Family
ID=95436295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411749791.8A Active CN119888840B (en) | 2024-12-02 | 2024-12-02 | Sitting posture detection device and control method thereof, and sitting posture detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119888840B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114623400A (en) * | 2022-03-22 | 2022-06-14 | 广东卫明眼视光研究院 | Sitting posture identification desk lamp system based on remote intelligent monitoring and identification method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN212776593U (en) * | 2020-08-18 | 2021-03-23 | 甘肃奥莱克信息产业服务有限公司 | Folding camera |
| CN114220163B (en) * | 2021-11-18 | 2023-01-06 | 北京百度网讯科技有限公司 | Human body posture estimation method, device, electronic equipment and storage medium |
| KR20230165153A (en) * | 2022-05-26 | 2023-12-05 | 서울대학교산학협력단 | Apparatus and method for analyzing pattern of behavior based on three-dimensional |
| CN115848482A (en) * | 2022-11-23 | 2023-03-28 | 浙江智马达智能科技有限公司 | Driver state monitoring method and device and electronic equipment |
| JP7778105B2 (en) * | 2023-03-28 | 2025-12-01 | 三菱電機株式会社 | Object detection device and object detection system |
-
2024
- 2024-12-02 CN CN202411749791.8A patent/CN119888840B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114623400A (en) * | 2022-03-22 | 2022-06-14 | 广东卫明眼视光研究院 | Sitting posture identification desk lamp system based on remote intelligent monitoring and identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119888840A (en) | 2025-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11857726B2 (en) | Mask sizing tool using a mobile application | |
| US12076134B2 (en) | Posture analysis systems and methods | |
| KR101868597B1 (en) | Apparatus and method for assisting in positioning user`s posture | |
| CN104239860B (en) | Sitting posture detection and reminding method and device during use of intelligent terminal | |
| CN111444789B (en) | Myopia prevention method and system based on video induction technology | |
| CN108601133A (en) | A kind of intelligent desk lamp and the sitting posture correction function method based on intelligent desk lamp | |
| CN113341748B (en) | Sofa intelligent control method and system based on posture and storage medium | |
| CN104581113B (en) | Adaptive holographic display methods and holographic display based on viewing angle | |
| CN104836999A (en) | Holographic three-dimensional display mobile terminal and method used for vision self-adaption | |
| KR20200030434A (en) | Internet connection cushion system with things | |
| CN105943327B (en) | Vision exercise health care system with anti-dizziness device | |
| CN103838245B (en) | Indicator screen system for regulating angle and method | |
| CN113903161A (en) | Sitting posture reminding device and method | |
| CN119888840B (en) | Sitting posture detection device and control method thereof, and sitting posture detection method | |
| CN111580646A (en) | Method, device and system for adjusting position of visual equipment according to face | |
| CN214619150U (en) | Table lamp for monitoring sitting posture | |
| CN109190562A (en) | Intelligent sitting posture monitoring method, device, intelligent elevated table and storage medium | |
| US20230098579A1 (en) | Mask sizing tool using a mobile application | |
| CN111290303B (en) | Intelligent control system for adjusting use state of seat | |
| JP7682838B2 (en) | Aspiration risk determination device, method, and program | |
| US20250107750A1 (en) | Posture evaluation apparatus, posture evaluation system, posture evaluation method, and computer readable medium | |
| CN114688473A (en) | Table lamp for monitoring sitting posture | |
| JP2024114354A (en) | Posture improvement support system, posture improvement support method, and program | |
| CN118486070A (en) | A system and method for monitoring children's writing posture and evaluating writing quality | |
| CN120616250A (en) | Study desk system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |