CN111127848A - Human body sitting posture detection system and method - Google Patents
Human body sitting posture detection system and method Download PDFInfo
- Publication number
- CN111127848A CN111127848A CN201911377612.1A CN201911377612A CN111127848A CN 111127848 A CN111127848 A CN 111127848A CN 201911377612 A CN201911377612 A CN 201911377612A CN 111127848 A CN111127848 A CN 111127848A
- Authority
- CN
- China
- Prior art keywords
- sitting posture
- human body
- human
- rgbd
- image
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a human body sitting posture measuring system and a method, wherein the system comprises: the RGBD camera is used for acquiring RGBD images of human body sitting postures and transmitting the RGBD images to the server; the server is used for receiving the RGBD image, acquiring three-dimensional information of key points of the human body sitting posture according to the RGBD image, and transmitting the three-dimensional information of the key points of the human body sitting posture to the control and processor; the control and processor is used for receiving and processing the three-dimensional information of the key points of the human body sitting posture to obtain a human body sitting posture result, comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to the reminding equipment, controlling the reminding equipment to give out a prompt, and transmitting the human body sitting posture result to the memory for storing the human body sitting posture result; the memory is used for storing the human body sitting posture result; the server and the memory are located on the cloud side, and the control and processor, the reminding device and the RGBD camera are located on the end side. The bad sitting posture of the human body is effectively monitored and reminded in time.
Description
Technical Field
The invention relates to the technical field of human body sitting posture detection, in particular to a human body sitting posture detection system and a human body sitting posture detection method.
Background
Today, people sit for longer and longer periods of time each day due to learning and work needs. According to statistics, the average daily sitting time of people is more than 8 hours, and in the long-time sitting situation, the people are difficult to keep good sitting posture all the time, and the poor sitting posture can seriously affect the health of the human body, such as vision attenuation, spinal development, cervical spondylosis and the like. Therefore, it is very necessary to perform sitting posture detection in order to promote people to correct bad sitting postures, develop good sitting posture habits and reduce the probability of diseases such as myopia and cervical spondylosis.
At present, a plurality of technical schemes for detecting, preventing myopia and correcting sitting postures exist. Such as ultrasonic ranging, wearing acceleration sensors/gyroscopes, and RGB camera detection. The ultrasonic ranging signal is single, only the front and back inclination can be measured, the important sitting postures such as sight distance and left and right inclination cannot be measured, the signal data accuracy is not enough, and the situations such as false alarm are easy to occur; devices such as a gravity acceleration device, a gyroscope and the like need to be worn by a user, are not convenient enough, and cannot measure important indexes such as a sight distance and the like; although the RGB camera can acquire rich image information, the RGB camera cannot acquire depth information, detection errors such as front-back inclination and sight distance are easily caused, the scheme is generally embedded, a high-precision image algorithm cannot be operated, and the feature extraction is not accurate enough.
The prior art lacks a sitting posture detection system and method with high detection accuracy.
Disclosure of Invention
The invention provides a human body sitting posture detection system and a human body sitting posture detection method for solving the existing problems.
In order to solve the above problems, the technical solution adopted by the present invention is as follows:
a human sitting posture measuring system comprising: the RGBD camera is used for acquiring an RGBD image of a human body sitting posture and transmitting the RGBD image to the server; the server is used for receiving the RGBD image, acquiring three-dimensional information of key points of human sitting postures according to the RGBD image, and transmitting the three-dimensional information of the key points of the human sitting postures to the control and processor; the control and processor is used for receiving and processing the three-dimensional information of the key points of the human body sitting posture to obtain a human body sitting posture result, comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to a reminding device, controlling the reminding device to give a reminding function, and transmitting the human body sitting posture result to a memory for storing the human body sitting posture result; the memory is used for storing human body sitting posture results; the server and the memory are located on a cloud side, the control and processor, the reminding device and the RGBD camera are located on an end side, and the control and processor are respectively connected with the reminding device and the RGBD camera.
In one embodiment of the present invention, the RGBD camera includes a depth camera and an RGB camera, and a depth map and an RGB map are independently acquired by the depth camera and the RGB camera, respectively, and the depth image and the RGB map are registered so that the RGBD image of the human body sitting posture is obtained. The RGBD camera includes an RGB-IR image sensor for acquiring RGB images and IR images simultaneously. The RGBD image comprises an RGB map and a depth map which correspond to pixels one by one.
In another embodiment of the present invention, the end side further comprises a client application for viewing the human sitting posture results stored in the memory.
The invention also provides a human body sitting posture detection method, which comprises the following steps: s1: controlling an RGBD camera to acquire an RGBD image of a human body sitting posture; s2: the RGBD image is controlled to be transmitted to a cloud side server, the cloud side server is received, three-dimensional information of key points of human body sitting postures is obtained according to the RGBD image, and the three-dimensional information of the key points is processed to obtain human body sitting posture results; s3: and comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to a reminding device, controlling the reminding device to send out a reminder, and transmitting the human body sitting posture result to a cloud side memory.
In one embodiment of the invention, the RGBD image comprises an RGB map and a depth map in one-to-one correspondence with pixels. And the cloud side server extracts the key point information of the human sitting posture according to the RGB image, and maps the key point of the human sitting posture to the depth image to obtain the three-dimensional information of the key point of the human sitting posture.
The invention also provides a human body sitting posture detection method, which comprises the following steps: t1: receiving an RGBD camera to obtain an RGBD image of the human body sitting posture; t2: acquiring three-dimensional information of key points of human body sitting postures according to the RGBD images, and transmitting the three-dimensional information of the key points to a control and processor; t3: and storing the human body sitting posture result obtained by the control and processor.
In an embodiment of the invention, the obtaining three-dimensional information of key points of human body sitting posture according to the RGBD image comprises: the RGBD image comprises an RGB image and a depth image, wherein pixels of the RGB image and the depth image correspond to one another; and extracting human sitting posture key point information according to the RGB image, and mapping the human sitting posture key points to the depth image to obtain three-dimensional information of the human sitting posture key points.
The invention has the beneficial effects that: the human body sitting posture detection system and method are characterized in that a cloud side and end side scheme is adopted, a deep convolution neural network is used for extracting two-dimensional information of key points of a human body, three-dimensional information of the key points of the human body is obtained through RGBD multi-view fusion, poor sitting posture data are collected, a three-dimensional human body sitting posture database is established, evaluation indexes and threshold values of poor sitting postures are extracted, and identification of the poor sitting postures of the human body is finally achieved. The method has the characteristics of high recognition rate, high sight distance measurement precision and the like, and can effectively monitor the bad sitting posture of the human body and give a prompt in time.
Drawings
Fig. 1 is a schematic structural diagram of a human sitting posture detecting system according to an embodiment of the present invention.
Fig. 2 is a schematic end-side structure diagram of the human body sitting posture detecting system in the embodiment of the invention.
Fig. 3 is a schematic structural diagram of another human sitting posture detecting system in the embodiment of the invention.
FIG. 4 is a diagram of a keypoint model in an embodiment of the invention.
Fig. 5 is a schematic diagram of a human sitting posture detecting method according to an embodiment of the invention.
Fig. 6 is a schematic diagram of another human sitting posture detecting method according to an embodiment of the present invention.
The system comprises a human body sitting posture detection system 10, a human body sitting posture detection system 11, a human body sitting posture detection system 12, a human body sitting posture detection system 111, an RGBD camera 112, a reminding device 113, a control and processor.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the embodiments of the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element. In addition, the connection may be for either a fixing function or a circuit connection function.
It is to be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for convenience in describing the embodiments of the present invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be in any way limiting of the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present invention, "a plurality" means two or more unless specifically limited otherwise.
Fig. 1 is a schematic structural diagram of a human sitting posture detecting system 10 according to an embodiment of the present invention. The human sitting posture detecting system 10 includes: end side 11, cloud side 12.
As shown in fig. 2, the end side 11 includes an RGBD camera 111, a reminder device 112, and a control and processor 113 respectively connected to the RGBD camera 111 and the reminder device 112; the cloud side 12 includes servers and memory (not shown). The RGBD camera 111 is used for acquiring an RGBD image of a human body sitting posture and transmitting the RGBD image to the server on the cloud side 102; the server is used for receiving the RGBD image, acquiring three-dimensional information of key points of the human body sitting posture according to the RGBD image, and transmitting the three-dimensional information of the key points to the control and processor 113; the control and processor 113 is configured to receive the three-dimensional information of the key point and process the three-dimensional information to obtain a human body sitting posture result, compare the result with a pre-stored sitting posture threshold, transmit the comparison result to the reminder device 112, control the reminder device 112 to issue a reminder, and transmit the human body sitting posture result to a memory for storing the human body sitting posture result.
It can be understood that the amount of calculation for obtaining the key point information of the human body sitting posture is large, so that the server on the cloud side 12 firstly processes to obtain the three-dimensional information of the key point of the human body sitting posture, and thus the processing speed and the processing precision are improved; then, the control and processor 113 is configured to receive the three-dimensional information of the key point of the human sitting posture and process the three-dimensional information to obtain a human sitting posture result, and transmit the result to the reminder device 112 after comparing the result with a pre-stored sitting posture threshold. The pre-stored sitting posture thresholds include thresholds under different sitting posture classifications, such as upright, head left, head right, body left, body right, body forward, body backward. The current human body sitting posture result can be judged to belong to which sitting posture classification according to the sitting posture threshold value, when the reminding device sends out the reminding, the user can be informed together or how to adjust the reminding to the client, namely the reminding sent out by the reminding device can comprise one or two or all of the following: whether the sitting posture is standard or not and which sitting posture the current sitting posture belongs to can meet the standard by how to adjust the current sitting posture. The sitting posture threshold value can be used for establishing a three-dimensional human body sitting posture database by collecting bad sitting posture data, extracting an evaluation index and a threshold value of bad sitting postures and realizing the recognition of the bad sitting postures.
In one embodiment of the invention, the pre-stored sitting posture threshold comprises only a sitting posture threshold in a straight sitting posture, i.e. a reasonable sitting posture threshold, as long as the threshold outside the sitting posture threshold is an unreasonable sitting posture.
In one embodiment, the RGBD camera 111 includes a depth camera and an RGB camera, the depth camera and the RGB camera are respectively used to independently acquire a depth image and an RGB image, and then registration is performed according to the position relationship of the depth camera and the RGB camera and respective internal parameters, such as a focal length, a resolution, an image sensor size, and the like, to eliminate a parallax between the two cameras, so as to acquire an RGBD image of the target to be measured.
In yet another embodiment, the RGBD camera 111 includes an RGB-IR image sensor that is composed of four different filtering units that pass R, G, B and IR light components, respectively, preferably, the ratio of the four light components is R (25%): g (25%): b (25%): after the IR (25%) image sensor in the RGBD camera 111 acquires the information of each component (e.g. R, G, B, IR), each information only occupies a part of the pixels, and therefore, the intensity information of the other three components on each pixel needs to be recovered by interpolation, so as to finally achieve synchronous acquisition of the RGB image and the IR image. There are various methods for interpolation, such as weighted averaging, etc.; the depth image is calculated by the acquired IR image, so that an RGBD image without parallax can be acquired.
The RGBD image comprises an RGB map and a depth map, and pixels of the RGB map and the depth map correspond to each other one by one. Therefore, in the depth map, the key points in the RGB map are the key points in the depth map, and the key points in the RGB map and the key points in the depth map are combined to be the key points in the RGBD image.
The server extracts the information of the key points of the human body according to the RGB map, maps the key points to the depth map to obtain three-dimensional information of the key points of the human body, and transmits the three-dimensional information of the key points to the control and processor 113. For example, the server acquires accurate and stable two-dimensional information of skeleton points from the RGB map based on a human skeleton point detection algorithm, then maps the skeleton points to the depth map to acquire three-dimensional information of the skeleton points, and transmits the three-dimensional information of the skeleton points to the control and processor 113.
The control and processor 113 is configured to receive and process three-dimensional information of a key point of a human body to be detected to obtain a human body sitting posture result, compare the result with a pre-stored sitting posture threshold, transmit the comparison result to the reminder device 112, control the reminder device 112 to issue a reminder, and transmit the human body sitting posture result to a memory for storing the human body sitting posture result to be detected. The reminding device 112 may be one or more of a display panel, a buzzer, a microphone or a loudspeaker, for example, a comparison result is displayed by the display panel or a voice reminding is performed by a voice device (microphone, loudspeaker), etc., without any limitation.
The memory can store the human body sitting posture result to be detected processed by the reminding device, and can also store a program result, wherein the program result can be used for executing human body sitting posture detection, and the program result comprises computer program codes, and the computer program codes can be in a source code form, an object code form, an executable file or some intermediate form. The Memory may be a portable storage medium such as any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice. It is to be understood that the memory may be various media such as a server that can store the program code.
As shown in fig. 3, the human sitting posture detecting system 10 further includes a client application 103 located at the end side, the client application 103 may be an APP or a wechat applet, the memory in the cloud is used to store the human sitting posture result of the user to be detected obtained through the control and processor 113, and the user can check the human sitting posture result to be detected stored in the memory synchronously through the client application 103 and analyze the result to help adjust the sitting posture state of the user. It will be appreciated that the user objects of the client application 103 may be more than just individuals, but also multiple children or entire classes, and that teachers or parents may view the results simultaneously through the client application 103 to correct the sitting posture of the children. Furthermore, the sitting posture of the user can be recorded, and the user is reminded to rest or get up to move according to the duration time of the sitting posture.
FIG. 4 is a diagram of a keypoint model according to an embodiment of the present invention. As shown in FIG. 4, A is the apex of the head, B is the nose, C1 is the left shoulder, C2 is the neck, C3 is the right shoulder, and D is the center point of the lower part of the body. L1 is the angle between the line from the nose to the neck and the line between the shoulders, L2 is the angle between the center of the lower part of the body and the line between the neck and the line between the shoulders, L3 is the depth difference between the nose and the shoulders (not shown), and L4 is the apparent distance (distance between the eyes and the table top, not shown). According to the RGB map and the depth map photographed by the RGBD camera, the processor extracts the keypoint information from the RGB map, maps the keypoint to the depth map to obtain the three-dimensional information of the keypoint, and transmits the three-dimensional information of the keypoint to the control and processor 113. The control and processor 113 processes the three-dimensional information of the key points to obtain values of L1, L2, L3, and L4, thereby determining whether the sitting posture is reasonable. For example, the sitting posture is reasonable when L1 ∈ [82.5 °,105.0 ° ], L2 ∈ [78.4 °,98.7 ° ], L3 ∈ [64.5,125.7], L4 ∈ (333, + ∞).
According to human morphology, the relative positions of key points corresponding to different sitting postures are different, and the obtained three-dimensional information of the key points is also different, so that the obtained values of L1, L2, L3 and L4 are also different. For example, when the head is deviated, the angle between the nose and the shoulder is greatly changed; when the body inclines, the center line of the body obviously deviates; when the patient leans forward, the depth difference between the nose and the shoulders becomes large, and the visual range also becomes small. A large number of human body bad posture images are collected through an RGBD camera, a three-dimensional human body sitting posture database is established, and evaluation indexes and threshold values of various bad sitting postures are obtained through statistical analysis and are shown in table 1:
TABLE 1 evaluation index and threshold for various sitting postures
| Sitting posture classification | Evaluation index and threshold (L1, L2 units are L3L 4 units are mm) |
| Straight and straight | L1∈[82.5,105.0]&&L2∈[78.4,98.7]&&L3∈[64.5,125.7] |
| Head left deviation | L1∈(-∞,82.5) |
| Head right deviation | L1∈(105,+∞) |
| Left inclination of body | L2∈(-∞,78.4) |
| Right inclination of body | L2∈(98.7,+∞) |
| Anteversion of the body | L3∈(125.7,+∞) |
| Retroversion of the body | L3∈(-∞,64.5) |
| Normal vision distance | L4∈(333,+∞) |
| Myopia (nearsightedness) | L4∈(-∞,333) |
The human body sitting posture detection system 10 is used for randomly collecting 50 individual bad sitting postures to serve as a test set, three-dimensional information of key points of the collected human body is compared with a pre-stored reasonable sitting posture threshold value, and a comparison result is output, wherein the test result is shown in the following table 2:
TABLE 2 test results
As can be seen from table 2, the recognition rate for each sitting posture was above 95%, especially for the front-back inclination. Meanwhile, the error of the sight distance measurement can be controlled within 5 mm. The human sitting posture detecting system 10 has great advantages in both precision and detection dimension.
Fig. 5 is a schematic diagram of a human sitting posture detecting method according to an embodiment of the present invention, including the following steps:
s1: controlling an RGBD camera to acquire an RGBD image of a human body sitting posture;
specifically, the RGBD camera on the end side 101 acquires an RGBD image of a human body sitting posture to be measured, the RGBD image includes an RGB diagram and a depth diagram, and pixels of the RGB diagram and the depth diagram correspond to each other one to one. Therefore, in the depth image, the key points in the RGB map are the key points in the depth map, and the key points in the RGB map and the key points in the depth map are combined to be the key points in the RGBD image.
S2: the RGBD image is controlled to be transmitted to a cloud side server, the cloud side server is received, three-dimensional information of key points of human body sitting postures is obtained according to the RGBD image, and the three-dimensional information of the key points is processed to obtain human body sitting posture results;
specifically, the control and processor 113 of the end side 101 transmits the human sitting posture results to the memory of the cloud side 101, and the user can synchronously view the human sitting posture results through the client application.
S3: and comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to a reminding device, controlling the reminding device to send out a reminder, and transmitting the human body sitting posture result to a cloud side memory.
It is understood that the above method is described mainly in terms of the end side.
As shown in fig. 6, a schematic diagram of another human sitting posture detecting method in an embodiment of the present invention includes the following steps:
t1: receiving an RGBD camera to obtain an RGBD image of the human body sitting posture;
t2: acquiring three-dimensional information of key points of human body sitting postures according to the RGBD images, and transmitting the three-dimensional information of the key points to a control and processor;
specifically, the server of the cloud side 102 extracts the human body key point information according to the RGB map, maps the key point onto the depth map to obtain the three-dimensional information of the human body key point, and transmits the three-dimensional information of the key point to the control and processor 113 of the end side 101.
T3: and storing the human body sitting posture result obtained by the control and processor.
It is understood that the above method is described with the cloud side as the main subject.
The human body sitting posture detection method has the same principle as the human body sitting posture detection system, and is not described in detail herein.
According to the method, a cloud side and end side scheme is adopted, a deep convolutional neural network is utilized to extract two-dimensional information of key points of a human body, three-dimensional information of the key points of the human body is obtained through RGBD multi-view fusion, poor sitting posture data is collected, a three-dimensional human body sitting posture database is established, evaluation indexes and threshold values of the poor sitting postures are extracted, and identification of the poor sitting postures of the human body is finally achieved. The method has the characteristics of high recognition rate, high sight distance measurement precision and the like, and can effectively monitor the bad sitting posture of the human body and give a prompt in time.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several equivalent substitutions or obvious modifications can be made without departing from the spirit of the invention, and all the properties or uses are considered to be within the scope of the invention.
Claims (10)
1. A human sitting posture measuring system, comprising:
the RGBD camera is used for acquiring an RGBD image of a human body sitting posture and transmitting the RGBD image to the server;
the server is used for receiving the RGBD image, acquiring three-dimensional information of key points of human sitting postures according to the RGBD image, and transmitting the three-dimensional information of the key points of the human sitting postures to the control and processor;
the control and processor is used for receiving and processing the three-dimensional information of the key points of the human body sitting posture to obtain a human body sitting posture result, comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to a reminding device, controlling the reminding device to give a reminding function, and transmitting the human body sitting posture result to a memory for storing the human body sitting posture result;
the memory is used for storing human body sitting posture results;
the server and the memory are located on a cloud side, the control and processor, the reminding device and the RGBD camera are located on an end side, and the control and processor are respectively connected with the reminding device and the RGBD camera.
2. The human seating posture measurement system of claim 1, wherein the RGBD camera comprises a depth camera and an RGB camera, a depth map and an RGB map are independently acquired with the depth camera and the RGB camera, respectively, and the depth image and the RGB map are registered so that the RGBD image of the human seating posture is obtained.
3. The human sitting posture measuring system of claim 1, wherein the RGBD camera comprises an RGB-IR image sensor for acquiring RGB images and IR images simultaneously.
4. The human sitting posture measuring system of any one of claims 1-3, wherein the RGBD image comprises an RGB map and a depth map with one-to-one pixel correspondence.
5. The human seating posture measurement system of claim 1, wherein the end side further comprises a client application for viewing the human seating posture results stored by the memory.
6. A human body sitting posture detection method is characterized by comprising the following steps:
s1: controlling an RGBD camera to acquire an RGBD image of a human body sitting posture;
s2: the RGBD image is controlled to be transmitted to a cloud side server, the cloud side server is received, three-dimensional information of key points of human body sitting postures is obtained according to the RGBD image, and the three-dimensional information of the key points is processed to obtain human body sitting posture results;
s3: and comparing the human body sitting posture result with a pre-stored sitting posture threshold value, transmitting the comparison result to a reminding device, controlling the reminding device to send out a reminder, and transmitting the human body sitting posture result to a cloud side memory.
7. The human sitting posture detecting method as claimed in claim 6, wherein the RGBD image comprises an RGB map and a depth map with pixels in one-to-one correspondence.
8. The human sitting posture detection method as claimed in claim 7, wherein the cloud side server extracts human sitting posture key point information according to the RGB map and maps the human sitting posture key points onto the depth map to obtain three-dimensional information of the human sitting posture key points.
9. A human body sitting posture detection method is characterized by comprising the following steps:
t1: receiving an RGBD camera to obtain an RGBD image of the human body sitting posture;
t2: acquiring three-dimensional information of key points of human body sitting postures according to the RGBD images, and transmitting the three-dimensional information of the key points to a control and processor;
t3: and storing the human body sitting posture result obtained by the control and processor.
10. The human sitting posture detecting method as claimed in claim 9, wherein the obtaining of three-dimensional information of key points of human sitting posture from the RGBD image comprises:
the RGBD image comprises an RGB image and a depth image, wherein pixels of the RGB image and the depth image correspond to one another; and extracting human sitting posture key point information according to the RGB image, and mapping the human sitting posture key points to the depth image to obtain three-dimensional information of the human sitting posture key points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377612.1A CN111127848A (en) | 2019-12-27 | 2019-12-27 | Human body sitting posture detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377612.1A CN111127848A (en) | 2019-12-27 | 2019-12-27 | Human body sitting posture detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111127848A true CN111127848A (en) | 2020-05-08 |
Family
ID=70504061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911377612.1A Pending CN111127848A (en) | 2019-12-27 | 2019-12-27 | Human body sitting posture detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127848A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639574A (en) * | 2020-05-22 | 2020-09-08 | 广东小天才科技有限公司 | Sitting posture correcting method, electronic equipment and storage medium |
| CN111814731A (en) * | 2020-07-23 | 2020-10-23 | 科大讯飞股份有限公司 | Sitting posture detection method, device, equipment and storage medium |
| CN111967376A (en) * | 2020-08-14 | 2020-11-20 | 上海大学 | Pose identification and detection method based on neural network |
| CN112861704A (en) * | 2021-02-04 | 2021-05-28 | 开望(杭州)科技有限公司 | Children writing analysis system and method based on sensor analysis and image processing |
| CN113065532A (en) * | 2021-05-19 | 2021-07-02 | 南京大学 | Sitting posture geometric parameter detection method and system based on RGBD image |
| WO2021248815A1 (en) * | 2020-06-13 | 2021-12-16 | 德派(嘉兴)医疗器械有限公司 | High-precision child sitting posture detection and correction method and device |
| CN114038016A (en) * | 2021-11-16 | 2022-02-11 | 平安普惠企业管理有限公司 | Sitting posture detection method, device, equipment and storage medium |
| WO2023273492A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市优必选科技股份有限公司 | Human body gesture determination method and mobile machine using same |
| CN115909394A (en) * | 2022-10-25 | 2023-04-04 | 珠海视熙科技有限公司 | Sitting posture identification method and device, intelligent desk lamp and computer storage medium |
| CN117746505A (en) * | 2023-12-21 | 2024-03-22 | 武汉星巡智能科技有限公司 | Learning accompanying method and device combined with abnormal sitting posture dynamic detection and robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050013599A1 (en) * | 2002-08-30 | 2005-01-20 | Toshiaki Nakanishi | Image extraction device, image extraction method, image processing device, image processing method, and imaging device |
| CN107169456A (en) * | 2017-05-16 | 2017-09-15 | 湖南巨汇科技发展有限公司 | A kind of sitting posture detecting method based on sitting posture depth image |
| CN107169453A (en) * | 2017-05-16 | 2017-09-15 | 湖南巨汇科技发展有限公司 | A kind of sitting posture detecting method based on depth transducer |
| CN108810255A (en) * | 2018-05-22 | 2018-11-13 | 深圳奥比中光科技有限公司 | User health is urged to use the method and intelligent mobile terminal of intelligent mobile terminal |
| CN108833772A (en) * | 2018-05-30 | 2018-11-16 | 深圳奥比中光科技有限公司 | Taking pictures based on depth camera guides system and method |
| CN110309787A (en) * | 2019-07-03 | 2019-10-08 | 电子科技大学 | A kind of human body sitting posture detection method based on depth camera |
| CN110345407A (en) * | 2019-06-20 | 2019-10-18 | 华南理工大学 | A kind of intelligent posture correction desk lamp and strong attitude positioning method based on deep learning |
| CN110440697A (en) * | 2019-08-08 | 2019-11-12 | 肖乐 | Correcting sitting postures intelligence system and method |
-
2019
- 2019-12-27 CN CN201911377612.1A patent/CN111127848A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050013599A1 (en) * | 2002-08-30 | 2005-01-20 | Toshiaki Nakanishi | Image extraction device, image extraction method, image processing device, image processing method, and imaging device |
| CN107169456A (en) * | 2017-05-16 | 2017-09-15 | 湖南巨汇科技发展有限公司 | A kind of sitting posture detecting method based on sitting posture depth image |
| CN107169453A (en) * | 2017-05-16 | 2017-09-15 | 湖南巨汇科技发展有限公司 | A kind of sitting posture detecting method based on depth transducer |
| CN108810255A (en) * | 2018-05-22 | 2018-11-13 | 深圳奥比中光科技有限公司 | User health is urged to use the method and intelligent mobile terminal of intelligent mobile terminal |
| CN108833772A (en) * | 2018-05-30 | 2018-11-16 | 深圳奥比中光科技有限公司 | Taking pictures based on depth camera guides system and method |
| CN110345407A (en) * | 2019-06-20 | 2019-10-18 | 华南理工大学 | A kind of intelligent posture correction desk lamp and strong attitude positioning method based on deep learning |
| CN110309787A (en) * | 2019-07-03 | 2019-10-08 | 电子科技大学 | A kind of human body sitting posture detection method based on depth camera |
| CN110440697A (en) * | 2019-08-08 | 2019-11-12 | 肖乐 | Correcting sitting postures intelligence system and method |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639574B (en) * | 2020-05-22 | 2023-09-26 | 广东小天才科技有限公司 | Sitting posture correcting method, electronic equipment and storage medium |
| CN111639574A (en) * | 2020-05-22 | 2020-09-08 | 广东小天才科技有限公司 | Sitting posture correcting method, electronic equipment and storage medium |
| WO2021248815A1 (en) * | 2020-06-13 | 2021-12-16 | 德派(嘉兴)医疗器械有限公司 | High-precision child sitting posture detection and correction method and device |
| CN111814731A (en) * | 2020-07-23 | 2020-10-23 | 科大讯飞股份有限公司 | Sitting posture detection method, device, equipment and storage medium |
| CN111814731B (en) * | 2020-07-23 | 2023-12-01 | 科大讯飞股份有限公司 | Sitting posture detection method, device, equipment and storage medium |
| CN111967376A (en) * | 2020-08-14 | 2020-11-20 | 上海大学 | Pose identification and detection method based on neural network |
| CN112861704A (en) * | 2021-02-04 | 2021-05-28 | 开望(杭州)科技有限公司 | Children writing analysis system and method based on sensor analysis and image processing |
| CN113065532A (en) * | 2021-05-19 | 2021-07-02 | 南京大学 | Sitting posture geometric parameter detection method and system based on RGBD image |
| CN113065532B (en) * | 2021-05-19 | 2024-02-09 | 南京大学 | Sitting posture geometric parameter detection method and system based on RGBD image |
| WO2023273492A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市优必选科技股份有限公司 | Human body gesture determination method and mobile machine using same |
| CN114038016A (en) * | 2021-11-16 | 2022-02-11 | 平安普惠企业管理有限公司 | Sitting posture detection method, device, equipment and storage medium |
| CN115909394A (en) * | 2022-10-25 | 2023-04-04 | 珠海视熙科技有限公司 | Sitting posture identification method and device, intelligent desk lamp and computer storage medium |
| CN115909394B (en) * | 2022-10-25 | 2024-04-05 | 珠海视熙科技有限公司 | Sitting posture identification method and device, intelligent table lamp and computer storage medium |
| CN117746505A (en) * | 2023-12-21 | 2024-03-22 | 武汉星巡智能科技有限公司 | Learning accompanying method and device combined with abnormal sitting posture dynamic detection and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111127848A (en) | Human body sitting posture detection system and method | |
| CN106598221B (en) | 3D direction of visual lines estimation method based on eye critical point detection | |
| CN105139447A (en) | Sitting posture real-time detection method based on double cameras | |
| CN103099602B (en) | Based on the physical examinations method and system of optical identification | |
| WO2021138964A1 (en) | Read/write distance identification method based on smart watch | |
| CN102812416B (en) | Pointing input device, indicative input method, program, recording medium and integrated circuit | |
| CN110032278A (en) | A kind of method for recognizing position and attitude, the apparatus and system of human eye attention object | |
| CN104219992A (en) | Asperger's diagnosis assistance method and system, and asperger's diagnosis assistance device | |
| CN108629946A (en) | A kind of tumble detection method for human body based on RGBD sensors | |
| CN104157107A (en) | Human body posture correction device based on Kinect sensor | |
| CN105354825B (en) | The intelligent apparatus of reading matter position and its application in automatic identification read-write scene | |
| CN106060142A (en) | Mobile phone capable of checking eyesight, and method for checking eyesight by using mobile phone | |
| WO2020020022A1 (en) | Method for visual recognition and system thereof | |
| US10620454B2 (en) | System and method of obtaining fit and fabrication measurements for eyeglasses using simultaneous localization and mapping of camera images | |
| CN105147235A (en) | Vision test system | |
| CN111084603A (en) | Pupil distance measuring method and system based on depth camera | |
| CN105354822B (en) | The intelligent apparatus of read-write element position and application in automatic identification read-write scene | |
| CN109785396A (en) | Writing posture monitoring method based on binocular camera, system, device | |
| CN112101124A (en) | Sitting posture detection method and device | |
| CN105147237A (en) | Vision test method | |
| CN106537217A (en) | Wide field-of-view depth imaging | |
| CN115409774A (en) | Eye detection method based on deep learning and strabismus screening system | |
| CN111999999A (en) | Child intelligent watch capable of correcting sitting posture and correcting method | |
| KR20190036929A (en) | System for managing posture in real time | |
| CN114190879A (en) | Visual function detection system for amblyopia children based on virtual reality technology |
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 | ||
| CB02 | Change of applicant information |
Address after: 11-13 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000 Applicant after: Obi Zhongguang Technology Group Co., Ltd Address before: 12 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Nanshan District, Shenzhen, Guangdong 518000 Applicant before: SHENZHEN ORBBEC Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |