CN113191319A - Human body posture intelligent recognition method and computer equipment - Google Patents
Human body posture intelligent recognition method and computer equipment Download PDFInfo
- Publication number
- CN113191319A CN113191319A CN202110560152.7A CN202110560152A CN113191319A CN 113191319 A CN113191319 A CN 113191319A CN 202110560152 A CN202110560152 A CN 202110560152A CN 113191319 A CN113191319 A CN 113191319A
- Authority
- CN
- China
- Prior art keywords
- human body
- target
- posture
- target human
- video stream
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000036544 posture Effects 0.000 claims description 129
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 210000003128 head Anatomy 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 208000001491 myopia Diseases 0.000 description 3
- 230000004379 myopia Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 208000010412 Glaucoma Diseases 0.000 description 2
- 206010041591 Spinal osteoarthritis Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000002688 persistence Effects 0.000 description 2
- 201000009487 Amblyopia Diseases 0.000 description 1
- 208000024806 Brain atrophy Diseases 0.000 description 1
- 208000002177 Cataract Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 206010052904 Musculoskeletal stiffness Diseases 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 206010038848 Retinal detachment Diseases 0.000 description 1
- 208000004350 Strabismus Diseases 0.000 description 1
- 206010046543 Urinary incontinence Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000036319 cervical spondylosis Diseases 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000004925 denaturation Methods 0.000 description 1
- 230000036425 denaturation Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000000302 ischemic effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 208000002780 macular degeneration Diseases 0.000 description 1
- 231100000862 numbness Toxicity 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000004197 pelvis Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004264 retinal detachment Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 210000000278 spinal cord Anatomy 0.000 description 1
- 208000005801 spondylosis Diseases 0.000 description 1
- 208000026843 stiff neck Diseases 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000004127 vitreous body Anatomy 0.000 description 1
- 238000004017 vitrification Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a human body posture intelligent recognition method, which is used for human body posture intelligent recognition based on camera equipment arranged in an office scene, and comprises the following steps: s1, acquiring a video stream in a preset period collected by the camera equipment; s2, acquiring a ghost image of the target human body according to the video stream and the target human body; and S3, recognizing the posture of the target human body according to the ghost image of the target human body. A new solution is provided for human posture recognition, and the accuracy and the intelligent degree of human posture recognition are enhanced. Another aspect of the invention provides a computer apparatus.
Description
Technical Field
The invention relates to the technical field of posture recognition, in particular to an intelligent human posture recognition method and computer equipment.
Background
In modern society, more and more work can be handled by sitting in an office, which makes people spend more and more time sitting at a desk for handling business every day.
Medical science has proven that a human body sits upright in an optimal posture with minimal physical burden. When sitting improperly, the vision is sharply reduced and myopia is easily caused, and the myopia also causes a plurality of eye complications, such as: 1. retinal detachment; 2. cataract; 3. macular hemorrhage and macular degeneration; 4. vitrification denaturation of vitreous humor; 5. glaucoma, and glaucoma; 6. strabismus and amblyopia. The higher the degree of myopia, the greater the likelihood of causing complications. The long-term sitting disorder can also cause cervical spondylosis and lumbar spondylosis, the symptoms of ache of the head, the neck, the shoulders, the back and the arms, stiff neck, limited movement and the like are caused, dizziness and ischemic brain atrophy can be seriously caused, and weakness, numbness of lower limbs, paralysis and incontinence of urine and stool can be caused if the spinal cord is pressed.
In order to correct the bad sitting posture of the human body, the posture of the human body needs to be recognized first. Therefore, there is a need for an intelligent human body posture recognition method, which can accurately recognize the bad posture of the user, so as to prompt the user to correct the posture in time.
Disclosure of Invention
Technical problem to be solved
In view of the problems in the art described above, the present invention is at least partially addressed. Therefore, an object of the present invention is to provide an intelligent human body posture recognition method, which provides a new solution for human body posture recognition and enhances the accuracy and intelligence of human body posture recognition.
A second object of the invention is to propose a computer device.
(II) technical scheme
In order to achieve the above object, an aspect of the present invention provides a human body posture intelligent recognition method for human body posture intelligent recognition based on an image pickup apparatus set in an office scene, including:
s1, acquiring a video stream in a preset period collected by the camera equipment;
s2, acquiring a ghost image of the target human body according to the video stream and the target human body;
and S3, recognizing the posture of the target human body according to the ghost image of the target human body.
Optionally, before S1, the method further includes:
and S0, receiving a human body posture identification request of the user, matching the human body characteristic information of the user from a pre-stored human body characteristic information base according to the identification request, and determining a target human body according to the human body characteristic information of the user.
Optionally, acquiring a ghost image of the target human body according to the video stream and the target human body, including: acquiring the position information of the same target human body in each video frame according to the video stream; and according to the position information of the same target human body in each video frame, overlapping the image information of the same target human body in each video frame to the same image to obtain a target ghost image.
Optionally, obtaining position information of the same target human body in each video frame according to the video stream, including: carrying out image segmentation on each video frame to obtain each binary video frame; acquiring position information of each target in each video frame according to each binary video frame; processing every two continuous video frames by adopting a KNN algorithm to obtain the position information of the same target in every two continuous video frames; and acquiring the position information of the same target in each video frame according to the position information of the same target in each two continuous video frames.
Optionally, recognizing the posture of the target human body according to the ghost image of the target human body includes: and carrying out attitude analysis on each ghost of each target human body, determining the attitude of all the ghosts of each target human body, determining the ghost attitude of each target human body meeting the improper attitude according to the attitude and the improper attitude setting conditions of all the ghosts of each target human body, and identifying the attitude of each target human body according to the number of the ghost attitudes of each target human body meeting the improper attitude.
Optionally, the gesture analysis comprises: determining the relative posture of the target ghost relative to the target camera equipment, and calculating a rotation matrix of the target ghost relative to the camera equipment in an upright state according to the relative posture of the target ghost relative to the target camera equipment and the pre-stored posture of the target camera equipment; calculating the attitude angle of the target ghost in the geodetic coordinate system according to the rotation matrix; the attitude angle comprises a head attitude angle and/or a back attitude angle, and the target camera shooting equipment is camera shooting equipment for collecting target ghost image information.
Optionally, after S3, the method further includes:
and S4, outputting posture adjustment prompt information to the target human body with the bad posture when the posture of the target human body is the bad posture.
Optionally, after S1 and before S2, further comprising:
s21, when more than two video streams collected by the camera equipment exist, determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream;
accordingly, S2 is:
and identifying the video stream according to the target human body and the posture thereof to obtain a ghost image of the target human body.
Optionally, determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream includes: and determining the relative posture of each target human body relative to the camera equipment of the target human body in each video stream according to the posture information of the target human body in each video stream, and taking the video stream related to the relative posture as the posture recognition video stream of the target human body related to the posture according to the relative posture meeting the set condition.
Another aspect of the present invention provides a computer device, including a memory, a processor, and a human body posture identifying program stored in the memory and executable on the processor, wherein the processor implements the human body posture identifying method as described above when executing the human body posture identifying program.
(III) advantageous effects
The invention has the beneficial effects that:
1. the human body posture is recognized based on the video stream in the preset period, and a basis is provided for accurately recognizing the human body posture and recognizing the human body posture in a humanized mode.
2. By acquiring the ghost image of the target human body and integrating all information of the target human body from appearance to finish in the preset period video stream, a new image processing foundation is formed, and the accuracy and the intelligent degree of human body posture recognition are enhanced.
3. The posture of the target human body at each moment is considered according to the ghost image, and the continuity of the poor posture of the target human body is considered, so that the posture of the target human body is recognized, the posture of the target human body is allowed to be temporarily improper, and the posture of the target human body is recognized as the poor posture only when the improper posture of the target human body is too long, so that a user is reminded to correct the posture. Compared with the existing method for recognizing the human body posture based on the real-time acquired human body posture image processing, the method provided by the invention can accurately recognize the human body posture of the user while providing the user with larger freedom of movement so as to remind the user to correct the posture in time, and has the advantages of higher humanization degree and more comfortable use for the user.
4. When more than two video streams collected by the camera equipment exist, the gesture recognition video stream of each target human body is determined, so that the ghost image of the target human body is obtained according to the target human body and the gesture recognition video stream of the target human body. The method has simpler operation and improves the operation efficiency of the algorithm.
Drawings
The invention is described with the aid of the following figures:
fig. 1 is a schematic flow chart of a human body posture intelligent recognition method according to an embodiment of the invention.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.
The human body posture intelligent recognition method provided by the embodiment of the invention is used for human body posture intelligent recognition based on the camera equipment arranged in an office scene, obtains the position information of the same target human body in each video frame according to the video stream by obtaining the video stream in the preset period collected by the camera equipment, superposes the image information of the same target human body in each video frame to the same image according to the position information of the same target human body in each video frame, obtains the target ghost image, and finally recognizes the posture of the target human body according to the target ghost image. Compared with the existing method for recognizing the human body posture based on the real-time acquired human body posture image processing, the method provides a new solution for human body posture recognition, provides a basis for human body posture recognition, recognizes the posture of the target human body according to the target ghost image, and enhances the precision and intelligent degree of human body posture recognition.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The following describes a human body gesture intelligent recognition method proposed according to an embodiment of the present invention with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a human body posture intelligent recognition method according to an embodiment of the present invention.
As shown in fig. 1, the intelligent human body posture identification method includes the following steps:
and step S1, receiving a human body posture identification request of the user, matching the human body characteristic information of the user from a pre-stored human body characteristic information base according to the identification request, and determining a target human body according to the human body characteristic information of the user.
Specifically, the human body feature information includes human body key point information and/or human face information; the key point information of the human body comprises key points of the head, five sense organs, neck, spine, pelvis and main joints of four limbs. The human body key point information supports the positioning of human bodies in complex scenes such as the back, the side, the middle and low altitude oblique shooting, the large movement and the like of the human bodies.
And step S2, acquiring the video stream in the preset period collected by the camera device.
In particular, the video stream comprises successive video frames in which one or more objects are present. The human body posture is recognized based on the video stream in the preset period, and a basis is provided for accurately recognizing the human body posture and recognizing the human body posture in a humanized mode.
And step S3, acquiring a ghost image of the target human body according to the video stream and the target human body.
By acquiring the ghost image of the target human body and integrating all information of the target human body from appearance to finish in the preset period video stream, a new image processing foundation is formed, and the accuracy and the intelligent degree of human body posture recognition are enhanced.
Preferably, step S3 includes: acquiring the position information of the same target human body in each video frame according to the video stream; and according to the position information of the same target human body in each video frame, overlapping the image information of the same target human body in each video frame to the same image to obtain a ghost image of the target human body.
Further, according to the video stream, obtaining the position information of the same target human body in each video frame, including: performing image segmentation on each video frame to obtain each binary video frame, and obtaining the position information of each target in each video frame according to each binary video frame; processing every two continuous video frames by adopting a KNN algorithm to obtain the position information of the same target in every two continuous video frames; and acquiring the position information of the same target in each video frame according to the position information of the same target in each two continuous video frames.
Specifically, the image segmentation is performed on each video frame to obtain each binary video frame, and the method includes: preprocessing each video frame by a corrosion and expansion morphological method to obtain each preprocessed video frame; and carrying out binarization processing on each preprocessed video frame based on a graythresh function to obtain each binary video frame. Of course, image segmentation using dilation and erosion in morphological processing in combination with the graythresh function is only preferred, and it is conceivable that similar effects can be achieved using Otsu threshold segmentation, region growing method, watershed segmentation, and global threshold segmentation.
And step S4, recognizing the posture of the target human body according to the ghost image of the target human body.
Preferably, step S4 includes: and carrying out attitude analysis on each ghost of each target human body, determining the attitude of all the ghosts of each target human body, determining the ghost attitude of each target human body meeting the improper attitude according to the attitude and the improper attitude setting conditions of all the ghosts of each target human body, and identifying the attitude of each target human body according to the number of the ghost attitudes of each target human body meeting the improper attitude.
Specifically, recognizing the postures of the target human body according to the number of ghost postures of each target human body satisfying the improper postures comprises the following steps: if the number of the ghost gestures of the target human body meeting the improper gestures exceeds a preset threshold value, the gesture of the target human body is identified as a bad posture, and otherwise, the gesture of the target human body is identified as a good posture.
The posture of the target human body is recognized by considering the posture of the target human body at each moment and considering the persistence of the bad posture of the target human body, so that the posture of the target human body is allowed to be temporarily improper, and the posture of the target human body is recognized as the bad posture only when the improper posture of the target human body is too long, so that a user is reminded to correct the posture. Compared with the existing method for recognizing the human body posture based on the real-time acquired human body posture image processing, the method provided by the invention can accurately recognize the human body posture of the user while providing the user with larger freedom of movement so as to remind the user to correct the posture in time, and has the advantages of higher humanization degree and more comfortable use for the user.
Further, the gesture analysis includes: determining the relative posture of the target ghost relative to the target camera equipment, and calculating a rotation matrix of the target ghost relative to the camera equipment in an upright state according to the relative posture of the target ghost relative to the target camera equipment and the pre-stored posture of the target camera equipment; and calculating the attitude angle of the target ghost in the geodetic coordinate system according to the rotation matrix. The attitude angle comprises a head attitude angle and/or a back attitude angle, and the target camera shooting equipment is camera shooting equipment for collecting target ghost image information.
Further, determining a relative pose of the target ghost with respect to the target imaging device includes: and acquiring key feature points of a human body in the target ghost, performing matching mapping on the key feature points and the feature points in the preset human body model, and determining the relative posture of the target ghost relative to the target camera equipment according to the matching mapping result.
Specifically, the head attitude angle includes a head pitch angle, a head roll-over angle, and a head yaw angle, and is used for indicating the head attitude of the user; the back attitude angle includes a back pitch angle, a back roll angle, and a back yaw angle for indicating the back attitude of the user.
And step S5, outputting posture adjustment prompt information to the target human body with bad posture when the posture of the target human body is in bad posture.
Optionally, after step S2 and before step S3, the method further includes: and step S21, when more than two video streams collected by the camera equipment exist, determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream. Accordingly, step S3 is: and identifying the video stream according to the target human body and the posture thereof to obtain a ghost image of the target human body. The method has simpler operation and improves the operation efficiency of the algorithm.
Preferably, determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream includes: and determining the relative posture of each target human body relative to the camera equipment of the target human body in each video stream according to the posture information of the target human body in each video stream, and taking the video stream related to the relative posture as the posture recognition video stream of the target human body related to the posture according to the relative posture meeting the set condition.
In conclusion, the method provides a new solution for human body posture recognition, the ghost image of the target human body is obtained based on the video stream in the preset period, all information of the target human body from appearance to completion in the video stream in the preset period is integrated to form a new image processing basis, and the precision and the intelligent degree of human body posture recognition are enhanced; according to the ghost image, the posture of the target human body at each moment is considered, and the persistence of the bad posture of the target human body is considered, so that the posture of the human body of the user can be accurately identified while the greater freedom of movement is provided for the user, the user is reminded to correct the posture in time, the humanization degree is higher, and the user feels more comfortable to use; when more than two video streams collected by the camera equipment exist, the gesture recognition video stream of each target human body is determined, so that the ghost image of the target human body is obtained according to the target human body and the gesture recognition video stream, the method disclosed by the invention is simpler in operation, and the operation efficiency of the algorithm is improved.
In addition, the embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a human body posture recognition program stored in the memory and operable on the processor, and when the processor executes the human body posture recognition program, the human body posture recognition method as described above is implemented.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third and the like are for convenience only and do not denote any order. These words are to be understood as part of the name of the component.
Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.
Claims (10)
1. The intelligent human body posture recognition method is used for intelligently recognizing human body postures based on camera equipment arranged in an office scene, and comprises the following steps of:
s1, acquiring a video stream in a preset period collected by the camera equipment;
s2, acquiring a ghost image of the target human body according to the video stream and the target human body;
and S3, recognizing the posture of the target human body according to the ghost image of the target human body.
2. The human body gesture intelligent recognition method of claim 1, before S1, further comprising:
s0, receiving a human body posture identification request of a user, matching the human body characteristic information of the user from a pre-stored human body characteristic information base according to the identification request, and determining a target human body according to the human body characteristic information of the user.
3. The method for intelligently recognizing human body gestures according to claim 1, wherein the acquiring of the ghost image of the target human body according to the video stream and the target human body comprises:
acquiring the position information of the same target human body in each video frame according to the video stream; and according to the position information of the same target human body in each video frame, overlapping the image information of the same target human body in each video frame to the same image to obtain a target ghost image.
4. The method for intelligently recognizing human body gestures according to claim 3, wherein the obtaining the position information of the same target human body in each video frame according to the video stream comprises:
carrying out image segmentation on each video frame to obtain each binary video frame; acquiring position information of each target in each video frame according to each binary video frame;
processing every two continuous video frames by adopting a KNN algorithm to obtain the position information of the same target in every two continuous video frames; and acquiring the position information of the same target in each video frame according to the position information of the same target in each two continuous video frames.
5. The intelligent human body posture recognition method according to claim 1, wherein the recognizing the posture of the target human body according to the ghost image of the target human body comprises:
and carrying out attitude analysis on each ghost of each target human body, determining the attitude of all the ghosts of each target human body, determining the ghost attitude of each target human body meeting the improper attitude according to the attitude and the improper attitude setting conditions of all the ghosts of each target human body, and identifying the attitude of each target human body according to the number of the ghost attitudes of each target human body meeting the improper attitude.
6. The human body gesture intelligent recognition method according to claim 5, wherein the gesture analysis comprises:
determining the relative posture of the target ghost relative to the target camera equipment, and calculating a rotation matrix of the target ghost relative to the camera equipment in an upright state according to the relative posture of the target ghost relative to the target camera equipment and the pre-stored posture of the target camera equipment;
calculating the attitude angle of the target ghost in a geodetic coordinate system according to the rotation matrix;
the attitude angle comprises a head attitude angle and/or a back attitude angle, and the target camera shooting equipment is camera shooting equipment for collecting target ghost image information.
7. The human body gesture intelligent recognition method of claim 1, further comprising, after S3:
and S4, outputting posture adjustment prompt information to the target human body with the bad posture when the posture of the target human body is the bad posture.
8. The human body gesture intelligent recognition method of claim 2, after S1 and before S2, further comprising:
s21, when more than two video streams collected by the camera equipment exist, determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream;
accordingly, S2 is:
and identifying the video stream according to the target human body and the posture thereof to obtain a ghost image of the target human body.
9. The method for intelligently recognizing human body gestures according to claim 8, wherein the determining the gesture recognition video stream of each target human body according to the gesture information of the target human body in each video stream comprises:
and determining the relative posture of each target human body relative to the camera equipment of the target human body in each video stream according to the posture information of the target human body in each video stream, and taking the video stream related to the relative posture as the posture recognition video stream of the target human body related to the posture according to the relative posture meeting the set condition.
10. A computer device comprising a memory, a processor, and a human gesture recognition program stored on the memory and executable on the processor, the processor implementing the human gesture recognition method of any one of claims 1-9 when executing the human gesture recognition program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560152.7A CN113191319B (en) | 2021-05-21 | 2021-05-21 | Human body posture intelligent recognition method and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560152.7A CN113191319B (en) | 2021-05-21 | 2021-05-21 | Human body posture intelligent recognition method and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191319A true CN113191319A (en) | 2021-07-30 |
| CN113191319B CN113191319B (en) | 2022-07-19 |
Family
ID=76984839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110560152.7A Expired - Fee Related CN113191319B (en) | 2021-05-21 | 2021-05-21 | Human body posture intelligent recognition method and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191319B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495015A (en) * | 2022-03-30 | 2022-05-13 | 行为科技(北京)有限公司 | Human body posture detection method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120057761A1 (en) * | 2010-09-01 | 2012-03-08 | Sony Corporation | Three dimensional human pose recognition method and apparatus |
| CN110210284A (en) * | 2019-04-12 | 2019-09-06 | 哈工大机器人义乌人工智能研究院 | A kind of human body attitude behavior intelligent Evaluation method |
| CN110287923A (en) * | 2019-06-29 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Human body attitude acquisition methods, device, computer equipment and storage medium |
| CN110298332A (en) * | 2019-07-05 | 2019-10-01 | 海南大学 | Method, system, computer equipment and the storage medium of Activity recognition |
| CN110633004A (en) * | 2018-06-21 | 2019-12-31 | 杭州海康威视数字技术股份有限公司 | Interaction method, device and system based on human body posture estimation |
| CN110807407A (en) * | 2019-10-30 | 2020-02-18 | 东北大学 | Feature extraction method for highly approximate dynamic target in video |
| WO2021051579A1 (en) * | 2019-09-17 | 2021-03-25 | 平安科技（深圳）有限公司 | Body pose recognition method, system, and apparatus, and storage medium |
| WO2021052016A1 (en) * | 2019-09-18 | 2021-03-25 | 华为技术有限公司 | Body posture detection method and electronic device |
| CN112633196A (en) * | 2020-12-28 | 2021-04-09 | 浙江大华技术股份有限公司 | Human body posture detection method and device and computer equipment |
-
2021
- 2021-05-21 CN CN202110560152.7A patent/CN113191319B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120057761A1 (en) * | 2010-09-01 | 2012-03-08 | Sony Corporation | Three dimensional human pose recognition method and apparatus |
| CN110633004A (en) * | 2018-06-21 | 2019-12-31 | 杭州海康威视数字技术股份有限公司 | Interaction method, device and system based on human body posture estimation |
| CN110210284A (en) * | 2019-04-12 | 2019-09-06 | 哈工大机器人义乌人工智能研究院 | A kind of human body attitude behavior intelligent Evaluation method |
| CN110287923A (en) * | 2019-06-29 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Human body attitude acquisition methods, device, computer equipment and storage medium |
| CN110298332A (en) * | 2019-07-05 | 2019-10-01 | 海南大学 | Method, system, computer equipment and the storage medium of Activity recognition |
| WO2021051579A1 (en) * | 2019-09-17 | 2021-03-25 | 平安科技（深圳）有限公司 | Body pose recognition method, system, and apparatus, and storage medium |
| WO2021052016A1 (en) * | 2019-09-18 | 2021-03-25 | 华为技术有限公司 | Body posture detection method and electronic device |
| CN110807407A (en) * | 2019-10-30 | 2020-02-18 | 东北大学 | Feature extraction method for highly approximate dynamic target in video |
| CN112633196A (en) * | 2020-12-28 | 2021-04-09 | 浙江大华技术股份有限公司 | Human body posture detection method and device and computer equipment |
Non-Patent Citations (3)
| Title |
|---|
| XIALIN LI 等: "Foldover Features for Dynamic Object Behaviour Description in Microscopic Videos", 《IEEE ACCESS》, vol. 8, 22 June 2020 (2020-06-22), pages 2169 - 3536 * |
| 丰婧 等: "基于PHOG特征的坐姿识别方法研究", 《国外电子测量技术》, vol. 40, no. 5, 15 May 2021 (2021-05-15), pages 83 - 87 * |
| 朱国安等: "基于Zhang-Suen算法的人体坐姿的识别方法研究", 《数码世界》, no. 01, 1 January 2020 (2020-01-01) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495015A (en) * | 2022-03-30 | 2022-05-13 | 行为科技(北京)有限公司 | Human body posture detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191319B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392120B (en) | Attention intelligent supervision method based on sight line estimation | |
| CN107169453B (en) | Sitting posture detection method based on depth sensor | |
| WO2020042345A1 (en) | Method and system for acquiring line-of-sight direction of human eyes by means of single camera | |
| CN102662476B (en) | Gaze estimation method | |
| US11844608B2 (en) | Posture analysis systems and methods | |
| CN213423969U (en) | Intelligent seat control device based on posture recognition | |
| CN111666998B (en) | Endoscope intelligent intubation decision-making method based on target point detection | |
| CN105487665B (en) | A kind of intelligent Mobile Service robot control method based on head pose identification | |
| CN106529409A (en) | Eye ocular fixation visual angle measuring method based on head posture | |
| CN110321786A (en) | A kind of human body sitting posture based on deep learning monitors method and system in real time | |
| CN113191319B (en) | Human body posture intelligent recognition method and computer equipment | |
| CN111696140B (en) | Monocular-based three-dimensional gesture tracking method | |
| CN103390174A (en) | Physical education assisting system and method based on human body posture recognition | |
| WO2023011339A1 (en) | Line-of-sight direction tracking method and apparatus | |
| CN111881886A (en) | Intelligent seat control method and device based on posture recognition | |
| CN109559332A (en) | A kind of sight tracing of the two-way LSTM and Itracker of combination | |
| CN109766007A (en) | A kind of the blinkpunkt compensation method and compensation device, display equipment of display equipment | |
| CN110345407A (en) | A kind of intelligent posture correction desk lamp and strong attitude positioning method based on deep learning | |
| CN106767833A (en) | A kind of robot localization method of fusion RGBD depth transducers and encoder | |
| CN113255476B (en) | Target tracking method, system and storage medium based on eye movement tracking | |
| CN112099622A (en) | Sight tracking method and device | |
| CN103839050A (en) | ASM positioning algorithm based on feature point expansion and PCA feature extraction | |
| CN113940812B (en) | Cornea center positioning method for excimer laser cornea refractive surgery | |
| CN106774879B (en) | A kind of plastic operation experiencing system based on AR virtual reality technology | |
| CN110288813A (en) | It is a kind of health sitting posture monitoring method with and its monitoring 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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220719 |