CN115205981B - Standing posture detection method and device, electronic equipment and readable storage medium - Google Patents
Standing posture detection method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN115205981B CN115205981B CN202211092375.6A CN202211092375A CN115205981B CN 115205981 B CN115205981 B CN 115205981B CN 202211092375 A CN202211092375 A CN 202211092375A CN 115205981 B CN115205981 B CN 115205981B
- Authority
- CN
- China
- Prior art keywords
- track
- gravity center
- detection
- center change
- head
- 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
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Abstract
The application discloses a standing posture detection method, a device, an electronic device and a readable storage medium, wherein the standing posture detection method comprises the following steps: identifying the standing posture of each human head in a target video, and screening the target heads suspected to be in the standing posture from the human heads; monitoring a trajectory of change of the center of gravity of the target head; if the moving-up amplitude of the gravity center change track corresponding to the target head is larger than a first preset threshold value and the gravity center change track is kept unchanged in a first preset time period, detecting whether a detected object corresponding to the target head is in a standing posture or not by performing abnormity detection on the gravity center change track, wherein the abnormity detection at least comprises one of track vertical component abnormity detection, track horizontal component abnormity detection and track terminal height abnormity detection. The method and the device solve the technical problem that the standing posture detection method is low in adaptability.
Description
Technical Field
The present application relates to the field of multimedia teaching, and in particular, to a method and an apparatus for detecting a standing posture, an electronic device, and a readable storage medium.
Background
In recent years, a full-automatic recording and broadcasting system is widely recognized and used in the teaching field, the system comprises a recording and broadcasting host, a teacher close-up, a teacher full view, a student close-up, a student full view, a blackboard writing and other multi-digit camera, a teacher microphone and other equipment, a close-up picture can be switched according to the standing posture of students, and the standing posture detection is characterized by multiple targets, targets are mutually overlapped and interfered, and the target motion track is short, so that the good effect is difficult to achieve in the conventional moving target detection method.
Disclosure of Invention
The present application mainly aims to provide a method and an apparatus for detecting a standing posture, an electronic device, and a readable storage medium, and aims to solve the technical problem in the prior art that the standing posture detection method is low in adaptability.
In order to achieve the above object, the present application provides a method for detecting an upright posture, including:
identifying the standing posture of each human head in a target video, and screening the target heads suspected to be in the standing posture from the human heads;
monitoring a trajectory of change of the center of gravity of the target head;
if the moving-up amplitude of the gravity center change track corresponding to the target head is larger than a first preset threshold value and the gravity center change track is kept unchanged in a first preset time period, detecting whether a detected object corresponding to the target head is in a standing posture or not by performing abnormity detection on the gravity center change track, wherein the abnormity detection at least comprises one of track vertical component abnormity detection, track horizontal component abnormity detection and track terminal height abnormity detection.
Optionally, the step of screening, by performing standing posture recognition on each human head in the target video, target heads suspected to be in a standing posture in each human head includes:
acquiring a target video, carrying out 3D head detection on the target video, and identifying to obtain each target head;
carrying out target tracking on each target head and acquiring head coordinate information corresponding to each target head;
and when head coordinate information with the upward movement amount larger than a second preset threshold exists in each piece of head coordinate information, judging that the target head corresponding to the head coordinate information is a target head suspected to be in a standing posture.
Optionally, before the step of monitoring the trajectory of change of center of gravity of the target head, the method further comprises:
acquiring an initial coordinate value and a current coordinate value of the target head, wherein the initial coordinate value is a coordinate value before the target head is screened as suspected to be in a standing posture, and the current coordinate value is a coordinate value after the target head is screened as suspected to be in the standing posture;
and determining the upward moving amplitude of the gravity center change track corresponding to the target head according to the difference value between the current coordinate value and the initial coordinate value.
Optionally, the step of detecting whether the detection object corresponding to the target head is in an upright posture by performing anomaly detection on the gravity center change track includes;
carrying out distortion error compensation on the gravity center change track to obtain a standard upward moving amplitude value;
detecting track vertical component abnormity according to the standard upward moving amplitude value, and judging whether the gravity center change track has track vertical component abnormity; and/or
Performing track horizontal component abnormity detection on the gravity center change track, and judging whether track horizontal component abnormity exists in the gravity center change track; and/or
Detecting track end point height abnormity of the gravity center change track, and judging whether the gravity center change track has track end point height abnormity;
and if not, judging that the detection object corresponding to the target head is in the standing posture.
Optionally, the step of performing track horizontal component abnormality detection on the gravity center change track, and determining whether there is track horizontal component abnormality in the gravity center change track includes:
extracting a horizontal movement component in the gravity center change track, and judging whether the horizontal movement component is greater than a third preset threshold value or not;
if the horizontal movement component is larger than the third preset threshold value, judging that the track horizontal component abnormality exists in the gravity center change track;
and if the horizontal movement component is not larger than the third preset threshold, judging that the gravity center change track has no track horizontal component abnormality.
Optionally, the step of determining that track end height abnormality detection is performed on the gravity center change track, and determining whether track end height abnormality exists in the gravity center change track includes:
judging whether the end point height of the gravity center change track is within a preset normal position range, wherein the preset normal position range is obtained by counting the gravity center height of each human head;
if the terminal height of the gravity center change track is within the preset normal position range, judging that track terminal height abnormality exists in the gravity center change track;
and if the height of the end point of the gravity center change track is not in the preset normal position range, judging that the gravity center change track has no track end point height abnormality.
Optionally, the standing posture detecting method further includes:
if the detection object is in the standing posture, continuously monitoring head coordinate information corresponding to the detection object;
and if the downward movement amplitude of the head coordinate information is larger than a fourth preset threshold, judging that the detection object is switched to a sitting posture.
The present application further provides a standing posture detection device, standing posture detection device is applied to standing posture detection equipment, standing posture detection device includes:
the identification screening module is used for identifying the standing postures of the human heads in the target video and screening the target heads suspected to be in the standing postures in the human heads;
the gravity center monitoring module is used for monitoring the gravity center change track of the target head;
and the standing detection module is used for detecting whether a detection object corresponding to the target head is in a standing posture or not by performing anomaly detection on the gravity center change track if the upward moving amplitude of the gravity center change track corresponding to the target head is monitored to be larger than a first preset threshold and the gravity center change track is kept unchanged within a first preset time period, wherein the anomaly detection at least comprises one of track vertical component anomaly detection, track horizontal component anomaly detection and track end point height anomaly detection.
Optionally, the identification screening module is further configured to:
acquiring a target video, carrying out 3D head detection on the target video, and identifying to obtain each target head;
carrying out target tracking on each target head and acquiring head coordinate information corresponding to each target head;
and when head coordinate information with the upward movement amount larger than a second preset threshold exists in each piece of head coordinate information, judging that the target head corresponding to the head coordinate information is a target head suspected to be in a standing posture. Optionally, the center of gravity monitoring module is further configured to:
acquiring an initial coordinate value and a current coordinate value of the target head, wherein the initial coordinate value is a coordinate value before the target head is screened as suspected to be in a standing posture, and the current coordinate value is a coordinate value after the target head is screened as suspected to be in the standing posture;
and determining the upward moving amplitude of the gravity center change track corresponding to the target head according to the difference value between the current coordinate value and the initial coordinate value.
Optionally, the standing detection module is further configured to:
carrying out distortion error compensation on the gravity center change track to obtain a standard upward moving amplitude value;
detecting track vertical component abnormity according to the standard upward moving amplitude value, and judging whether the gravity center change track has track vertical component abnormity; and/or
Performing track horizontal component abnormity detection on the gravity center change track, and judging whether track horizontal component abnormity exists in the gravity center change track; and/or
Track end point height abnormity detection is carried out on the gravity center change track, and whether track end point height abnormity exists in the gravity center change track or not is judged;
and if not, judging that the detection object corresponding to the target head is in the standing posture.
Optionally, the standing-up detection module is further configured to:
extracting a horizontal movement component in the gravity center change track, and judging whether the horizontal movement component is greater than a third preset threshold value;
if the horizontal movement component is larger than the third preset threshold value, judging that the track horizontal component abnormality exists in the gravity center change track;
and if the horizontal movement component is not larger than the third preset threshold, judging that the gravity center change track has no track horizontal component abnormality.
Optionally, the standing-up detection module is further configured to:
judging whether the end point height of the gravity center change track is within a preset normal position range, wherein the preset normal position range is obtained by counting the gravity center height of each human head;
if the terminal height of the gravity center change track is within the range of the preset normal position, judging that the track terminal height of the gravity center change track is abnormal;
and if the terminal height of the gravity center change track is not in the preset normal position range, judging that the gravity center change track has no track terminal height abnormality.
Optionally, the standing posture detecting device is further configured to:
if the detection object is in the standing posture, continuously monitoring head coordinate information corresponding to the detection object;
and if the downward movement amplitude of the head coordinate information is larger than a fourth preset threshold, judging that the detection object is switched to a sitting posture.
The present application further provides an electronic device, the electronic device is an entity device, the electronic device includes: a memory, a processor and a program of the standing posture detection method stored on the memory and executable on the processor, which when executed by the processor, may implement the steps of the standing posture detection method as described above.
The present application also provides a computer-readable storage medium having stored thereon a program for implementing the standing posture detection method, which when executed by a processor implements the steps of the standing posture detection method as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the standing posture detection method as described above.
The application provides a standing posture detection method, a standing posture detection device, electronic equipment and a computer readable storage medium, wherein the method comprises the steps of identifying the standing posture of each human head in a target video, screening the target head suspected to be in the standing posture from each human head, monitoring the gravity center change track of the target head, and detecting whether a detection object corresponding to the target head is in the standing posture or not by performing abnormity detection on the gravity center change track if the upward moving amplitude of the gravity center change track corresponding to the target head is greater than a first preset threshold and the gravity center change track is kept unchanged in a first preset time period, wherein the abnormity detection at least comprises one of track vertical component abnormity detection, track horizontal component abnormity detection and track terminal height abnormity detection.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a first embodiment of a method for detecting a standing posture of the present application;
FIG. 2 is a schematic diagram of a distortion error compensation projection according to a first embodiment of the present invention;
FIG. 3 is a schematic flow chart diagram illustrating a second embodiment of a method for detecting a standing posture of the present application;
FIG. 4 is a schematic flow chart diagram illustrating a third embodiment of a method for detecting a standing posture of the present application;
FIG. 5 is a schematic diagram of the upright attitude sensing device of the present application;
fig. 6 is a schematic structural diagram of a hardware operating environment related to the standing posture detection method in the embodiment of the present application.
The implementation of the objectives, functional features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments of the present application are described in detail below with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
Example one
With the wide acceptance and use of a full-automatic recording and broadcasting system in the teaching field, the system consists of a recording and broadcasting host, a teacher close-up, a teacher full view, a student close-up, a student full view, a blackboard writing and other multi-digit cameras, a teacher microphone and other equipment, a close-up picture can be switched according to the standing posture of a student, and the standing posture detection is characterized by multiple targets, targets are mutually overlapped and interfered, and the target motion track is short, so that the good effect is difficult to achieve in the conventional moving target detection method.
In a first embodiment of the present invention, with reference to fig. 1, a method for detecting a standing posture includes:
step S10, identifying the standing posture of each human head in a target video, and screening the target heads suspected to be in the standing posture from the human heads;
step S20, monitoring the gravity center change track of the target head;
step S30, if it is monitored that the upward moving amplitude of the gravity center change track corresponding to the target head is larger than a first preset threshold and the gravity center change track is kept unchanged within a first preset time period, detecting whether a detected object corresponding to the target head is in a standing posture or not by performing anomaly detection on the gravity center change track, wherein the anomaly detection at least comprises one of track vertical component anomaly detection, track horizontal component anomaly detection and track end point height anomaly detection.
In this embodiment, it should be noted that the target video may be video data acquired by a camera in a teaching scene; the reason for synchronously identifying each human body is that in a teaching scene, most students are sitting, head coordinate information is easily acquired in a video and can accurately reflect the posture change condition of the students as reference information; monitoring the gravity center change track of the target head, including detecting the total rising amount and the vector angle of the track from head to tail; the first preset threshold is used for judging whether the detection object really completes the standing action or not so as to eliminate the interference caused by slight head movement of the detection object; the first preset time period is used for eliminating interference caused by the fact that the detection object accidentally stands up to adjust sitting posture or other actions, and the gravity center change track comprises a gravity center point coordinate, a vertex height and a movement orientation angle; the first preset threshold is used for eliminating the situation that the student accidentally stands up instead of standing up, for example, the range of upward movement of the head coordinate information caused by adjusting the table and chair when the student stands up is large; the preset standing posture eliminating conditions can include the rising amplitude of the head coordinate information and other abnormal situations which influence the posture judgment, and are used for eliminating the interference of the conditions such as sitting posture adjustment, sitting on the back, horizontal movement, lens distortion and the like, and improving the accuracy of the standing posture detection.
As an example, steps S10 to S30 include: acquiring a target video acquired by a camera, and identifying and analyzing each target head from the target video through 3D head detection; performing multi-target tracking on each target head, and acquiring corresponding target head coordinate information; judging whether a detection object corresponding to the target head information is suspected to be in other postures or not according to the coordinate upward-moving amplitude value of the target head information; if so, monitoring the gravity center change track of the detection object; if the upward moving amplitude of the gravity center changing track corresponding to the detected object is larger than a first preset threshold value and the gravity center changing track is kept unchanged in a first preset time period, performing abnormal detection on the gravity center changing track, and if the gravity center changing track is abnormal, judging that the detected object corresponding to the target head is not in a standing posture; and if the gravity center change track is not abnormal, judging that the detection object corresponding to the target head is in a standing posture.
As another example, the human synchronization may be replaced with a human upper body, or a human head + upper body two-class object detection model.
As another example, the first preset time period may be replaced with a preset number of movements, and other execution steps are not changed.
Preferably, the preset number of movements may be 5, and for example, when the target head moves 5 times in total and the moving direction is not upward, the detection of the standing posture is performed according to the change trajectory of the center of gravity corresponding to the target head.
The step of screening each human head suspected to be in an upright posture in each human head by identifying the upright posture of each human head in the target video includes:
s11, acquiring a target video, carrying out 3D head detection on the target video, and identifying to obtain each target head;
step S12, carrying out target tracking on each target head and acquiring head coordinate information corresponding to each target head;
step S13, when there is head coordinate information whose upward movement amount is greater than a second preset threshold in each piece of head coordinate information, determining that the target head corresponding to the head coordinate information is a target head suspected to be in a standing posture.
In this embodiment, it should be noted that the 3D head detection may be a MediaPipe Objectron model, where the MediaPipe Objectron model is trained to identify the student heads in the target video, and the hardware of the detection model may use a common call module such as an ARM (Advanced RISC machine), an embedded SOC chip, e.g., a BPU (Branch Processing Unit), an NPU (Natural Processing Unit) such as RKNN of RV1126, and so on, to implement embedded end deep neural network learning identification with ultra-low power consumption, and identify each target head in the target video with high efficiency and low consumption; the target tracking mode can be a Kalman filtering mode, wherein a two-dimensional computing mode of Kalman filtering is flexibly expanded into a three-dimensional computing mode to realize the tracking of the head of each student, because the situations of multi-target cross movement, transposition and the like rarely occur in a classroom scene, a simple tracking mechanism such as Kalman filtering can achieve the aim, the second preset threshold value is used for judging the head of a target suspected to have a standing posture, and a certain suspected object can be focused to improve the detection accuracy; the method for acquiring the coordinate information of each target head comprises the step of updating the head top height mean value and the variance of the head coordinate information in each frame in a weighted average mode of historical information and current information, wherein the coordinate information of the target head can also be used as a reference of a subsequent preset normal position range, and comprises the head top height, the gravity center point coordinate and a motion orientation angle.
As an example, steps S11 to S13 include: acquiring a target video in a teaching scene acquired by a camera; identifying the target video through a 3D head detection model to obtain each target head, wherein the 3D head detection model is generated by training of a training set containing human head information; performing multi-target tracking on each target head through Kalman filtering, and acquiring head coordinate information corresponding to each target head; judging whether head coordinate information with the upward movement amount larger than a second preset threshold exists in each head coordinate information or not; and if so, judging that the target head corresponding to the head coordinate information is the target head suspected to be in the standing posture.
As an example, the step of acquiring head coordinate information of the target head includes: tracking and matching the head coordinate information through a Kalman filter to obtain a corresponding detection object; according to the video data updated in real time, carrying out weighted updating on the historical head top height mean value and variance information in the head coordinate information of each detection object and the current head top height mean value and variance information; and recording the coordinates of the gravity point in the head coordinate information and the change direction of the coordinates of the gravity point in real time.
Preferably, the updating calculation mode of the mean value mu and the variance sigma of the vertex height Z coordinate per frame is historical and current weighted average, the weight value is 0.9/0.1, namely mu = 0.1 mu + 0.9 mu, and the variance sigma is the same.
As another example, the kalman filtering may be replaced by a binocular or Lidar (Laser Radar) based method or any other method that can obtain real-time 3D coordinate information of the human head, and other steps are performed unchanged.
Wherein, prior to the step of monitoring the trajectory of change of center of gravity of the target head, the method further comprises:
step S21, obtaining an initial coordinate value and a current coordinate value of the target head, wherein the initial coordinate value is a coordinate value before the target head is screened as suspected to be in an upright posture, and the current coordinate value is a coordinate value after the target head is screened as suspected to be in the upright posture;
and S22, determining the upward moving amplitude of the gravity center change track corresponding to the target head according to the difference value between the current coordinate value and the initial coordinate value.
As an example, steps S21 to S21 include: obtaining a coordinate value before the target head is screened as suspected to be in a standing posture, namely an initial coordinate value; obtaining a coordinate value after the target head is screened to be suspected to be in a standing posture, namely a current coordinate value, wherein the current coordinate value is changed in real time; and calculating the difference value of the current coordinate value and the initial coordinate value in the vertical direction to obtain the upward moving amplitude of the gravity center change track corresponding to the target head.
Wherein the step of detecting whether the detection object corresponding to the target head is in the standing posture by performing abnormality detection on the gravity center change trajectory includes:
s31, carrying out distortion error compensation on the gravity center change track to obtain a standard upward moving amplitude value;
step S32, track vertical component abnormity detection is carried out according to the standard upward shifting amplitude value, and whether track vertical component abnormity exists in the gravity center change track is judged; and/or
Step S33, track horizontal component abnormity detection is carried out on the gravity center change track, and whether track horizontal component abnormity exists in the gravity center change track is judged; and/or
Step S34, carrying out track end point height abnormity detection on the gravity center change track, and judging whether track end point height abnormity exists in the gravity center change track;
and step S35, if the detected object corresponding to the target head is not in the standing posture, judging that the detected object corresponding to the target head is in the standing posture.
In this embodiment, it should be noted that the distortion error compensation includes mainly initiating a position close to an edge of a target video picture, and a vertical rise in actual calculation, and if an average direction of a center-of-gravity motion trajectory of a head of the target substantially coincides with an end-to-end trajectory vector along a distortion direction, a line segment length, a vector modulus, and the like related to the vertical direction are projected in this direction to compensate for the distortion error. The distortion error compensation is used for making up the objective existence of imaging distortion of the camera lens and the imperfection of distortion correction, and because a horizontal plane in a target video is a curved surface with a certain radian, the closer to the edge of a picture, the larger the error of plane modeling is; the track vertical component abnormality detection means that the upward moving amplitude of the gravity center change track in the vertical direction does not reach a preset total rising amount threshold, wherein the preset total rising amount threshold is set by the natural figure proportion of a human body, for example, when a person sits down, the height of a stool usually enables feet to fall on the ground, and the difference of the height of the top of the head of the person standing up and sitting down is about the distance length from the knee to the hip (commonly called thigh). The thigh length and the head width of a person have relatively stable natural proportion, the threshold value proportion is taken to be near 2.0 according to different sensitivities, and the threshold value total rising amount threshold value can be taken to be 2 times of the head width of the target head as an optimal threshold value; the track horizontal component abnormity means that the movement component of the gravity center change track in the horizontal direction is larger, and is used for avoiding the misjudgment of the standing posture of the detection object caused by the oblique or front-back movement; the track end point height abnormity refers to the height of the end point of the moved target head at a normal position rather than the height of a standing position, and is used for avoiding the motion track from being interfered by other actions, for example, a student lies on a desk and then sits straight; the track vertical component abnormity detection, the track horizontal component abnormity detection and the track terminal height abnormity detection are respectively carried out without order limitation, the front and back orders of all detection can be exchanged, and the detection result is not influenced.
As an example, steps S31 to S35 include: based on the gravity center change track, projecting in the head-to-tail distortion direction with the same average direction of the gravity center change track to obtain a standard moving track; extracting an upward moving amplitude value in the standard moving track to obtain a standard upward moving amplitude value; judging whether the standard upward shifting amplitude value is not larger than a preset total ascending amount threshold value or not; extracting a horizontal change component in the gravity center change track, and judging whether the horizontal change component is greater than a third preset threshold value; judging whether the track end point height of the gravity center change track is within a preset normal position range or not; if yes, judging that the detection object corresponding to the target head is not in the standing posture; and if the judgment result is no, judging that the detection object corresponding to the target head is in the standing posture.
As an example, the step of projecting the center-of-gravity change trajectory in the end-to-end distortion direction where the average direction of the center-of-gravity change trajectory is consistent to obtain the standard movement trajectory includes: the extra compensation is mainly initiated for the position close to the edge of the picture, and when the Z-direction rise and the Z-axis height of the trajectory end point are actually calculated, if the average direction of the trajectories from frame to frame and the trajectory vectors from head to tail are substantially consistent along the distortion direction (refer to fig. 2,
direction and
substantially coincident) then the Z-axis related segment lengths, vector modes, etc. are projected in this direction to compensate for distortion errors.
As another example, the step of detecting whether the detection object corresponding to the target head is in an upright posture by performing abnormality detection on the gravity center change trajectory includes: projecting in the end-to-end distortion direction with the average direction of the gravity center change track consistent to obtain a standard movement track; extracting an upward moving amplitude value in the standard moving track to obtain a standard upward moving amplitude value; judging whether the standard upward shifting amplitude value is not larger than a preset total ascending amount threshold value or not; if the standard upward moving amplitude value is not larger than a preset total ascending amount threshold value, judging that the detection object corresponding to the target head is not in a standing posture; and if the standard upward moving amplitude value is larger than a preset total ascending amount threshold value, determining that the detection object corresponding to the target head is in the standing posture.
As another example, the step of detecting whether the detection object corresponding to the target head is in the standing posture by performing abnormality detection on the gravity center change trajectory includes: projecting in the head-to-tail distortion direction with the same average direction of the gravity center change track to obtain a standard movement track; extracting an upward moving amplitude value in the standard moving track to obtain a standard upward moving amplitude value; judging whether the standard upward shifting amplitude value is not larger than a preset total ascending amount threshold value or not; if the standard upward moving amplitude value is not larger than a preset total ascending amount threshold value, judging that the detection object corresponding to the target head is not in a standing posture; if the standard upward moving amplitude is larger than a preset total ascending amount threshold, extracting a horizontal change component in the gravity center change track, and judging whether the horizontal change component is larger than a third preset threshold; if the horizontal variation component is greater than the third preset threshold, it is determined that the detection object corresponding to the target head is not in the standing posture, and if the horizontal variation component is less than the third preset threshold, it is determined that the detection object corresponding to the target head is in the standing posture.
The step of detecting track horizontal component abnormality of the gravity center change track and judging whether the gravity center change track has track horizontal component abnormality includes:
step S321, extracting a horizontal movement component in the gravity center change track, and judging whether the horizontal movement component is greater than a third preset threshold value;
step S322, if the horizontal movement component is greater than the third preset threshold, determining that the track horizontal component of the gravity center change track is abnormal;
step S323, if the horizontal movement component is not greater than the third preset threshold, determining that there is no track horizontal component abnormality in the gravity center change track.
In this embodiment, it should be noted that the horizontal movement component includes a movement component in an x-axis direction on a horizontal plane, and further includes a movement component in a y-axis direction on the horizontal plane, and each of the movement components is used for eliminating interference of backward movement and interference of oblique movement of students, where the y-axis direction may be a direction along a straight line where the teacher and the students are located, and the x-axis direction may be a direction perpendicular to the straight line along the straight line where the teacher and the students are located.
As one example, steps S321 to S323 include: extracting movement components in the x-axis direction and the y-axis direction in the horizontal direction from the gravity center change track, and respectively judging whether the movement components in the x-axis direction and the y-axis direction are greater than the third threshold value; if the movement component in the x-axis direction is greater than the third threshold value and the movement component in the y-axis direction is greater than the third threshold value, judging that the gravity center change track is an abnormal track; if the movement component in the x-axis direction is greater than the third threshold value and the movement component in the y-axis direction is less than the third threshold value, judging that the gravity center change track is an abnormal track; if the movement component in the x-axis direction is smaller than the third threshold value and the movement component in the y-axis direction is larger than the third threshold value, judging that the gravity center change track is an abnormal track; and if the movement component in the x-axis direction is smaller than the third threshold value and the movement component in the y-axis direction is smaller than the third threshold value, judging that the gravity center change track is not an abnormal track.
The step of detecting track end height abnormality of the gravity center change track and judging whether the gravity center change track has track end height abnormality includes:
step S324, judging whether the end point height of the gravity center change track is within a preset normal position range, wherein the preset normal position range is obtained by counting the gravity center height of each human head;
step S325, if the height of the end point of the gravity center change track is within the preset normal position range, determining that the height of the end point of the gravity center change track is abnormal;
in step S326, if the end point height of the center of gravity change trajectory is not within the preset normal position range, it is determined that there is no track end point height abnormality in the center of gravity change trajectory.
In this embodiment, it should be noted that, a maximum likelihood range in the normal distribution mathematical model of the parietal height of each target head may be within the preset normal position range, and as a preferable range, 68.27% may be taken.
As an example, steps S324 to S326 include: extracting the head top height of the target head from the gravity center change track to obtain the terminal point height; judging whether the terminal height of the gravity center change track is within a preset normal position range; if the height of the end point of the gravity center change track is within the range of the preset normal position, judging that the height of the track end point corresponding to the gravity center change track belongs to an abnormal height, namely the track end point is a normal position rather than a standing position; if the height of the end point of the gravity center changing track is not in the preset normal position range, judging that the height of the track end point does not belong to an abnormal height, namely the height of the end point of the track does not exist in the gravity center changing track.
The embodiment of the application provides a standing posture detection method, which comprises the steps of firstly identifying and obtaining each target head from a target video, and tracking and collecting each target head to obtain corresponding head coordinate information; judging whether a detection object corresponding to the head coordinate information is in a standing posture or not based on the change condition of the head coordinate information and a preset standing condition; if the detection object is in the standing posture, monitoring the change condition of the head coordinate information corresponding to the detection object, and judging whether the detection object is switched to the sitting posture, wherein the preset standing condition avoids the interference of lens distortion and non-standing actions of the detection object.
Example two
Further, based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents to the first embodiment described above may be referred to the above description, and are not repeated herein. On this basis, the standing posture detection method further includes:
step A10, if the detection object is in a standing posture, continuously monitoring head coordinate information corresponding to the detection object;
step A20, if the downward movement amplitude of the head coordinate information is greater than a fourth preset threshold, determining that the detection object has been switched to the sitting posture.
In this embodiment, the fourth preset threshold is used to determine whether the downward movement of the center of gravity of the detected object is a sitting movement, so as to avoid the interference of the downward movement of the center of the head caused by an action such as bowing.
As an example, steps a10 to a20 include: when the detection object is in a standing posture, recording head coordinate information of the detection object to generate initial head coordinate information; continuously monitoring the head coordinate information of the detection object to generate current head coordinate information; and when the difference value between the initial head coordinate information and the current head coordinate information, namely the downward moving amplitude value is larger than a third preset threshold value, judging that the detection object is in a sitting posture.
Preferably, the third preset threshold may be equal to the second preset threshold, so as to ensure that the detection object is determined to have returned to the sitting posture when the head of the detection object returns to the coordinate position before standing up.
In the embodiment of the application, a method for judging a sitting posture is provided, and firstly, when a detection object is in a standing posture, head coordinate information corresponding to the detection object is continuously monitored; when the downward movement amplitude of the head coordinate information is larger than a fourth preset threshold, the detection object is judged to be switched to the sitting posture.
EXAMPLE III
Further, based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents to the first embodiment described above may be referred to the above description, and are not repeated herein. On this basis, the standing posture detection method further includes:
step B10, if the detection object is in a standing posture, performing close-up shooting on the detection object;
and step B20, if the detection object is in the sitting posture, ending the close-up shooting of the detection object.
In this embodiment, it should be noted that the close-up shooting is used for giving a close-up shooting of classmates due to classroom participation in other teaching activities such as question answering or questioning in a teaching scene, so as to better show details in the teaching activities.
As an example, steps B10 to B20 include: detecting a posture state of the detection object; when the detection object is in a standing posture, turning the direction of a lens to the detection object and zooming in the lens to perform close-up shooting on the detection object; and when the detection object is detected to be in the sitting posture, zooming out the lens, and turning the direction of the lens back to the initial direction so as to finish the close-up shooting of the detection object.
In the embodiment of the application, a method for adjusting a camera is provided, and particularly, when the detection object is in a standing posture, the detection object is shot in a close-up manner; when the detection object is in a sitting posture, close-up shooting of the detection object is ended. The embodiment of the application provides the control to the camera, has realized shooting standing student's pursuit feature, is convenient for record more details and effective information in the teaching scene.
Example four
The embodiment of the present application further provides a standing posture detection device, standing posture detection device is applied to standing posture detection equipment, standing posture detection device includes:
the identification screening module is used for screening the target heads suspected to be in the standing postures in the human heads by identifying the standing postures of the human heads in the target video;
the gravity center monitoring module is used for monitoring the gravity center change track of the target head;
and the standing detection module is used for detecting whether a detection object corresponding to the target head is in a standing posture or not by performing anomaly detection on the gravity center change track if the upward moving amplitude of the gravity center change track corresponding to the target head is monitored to be larger than a first preset threshold and the gravity center change track is kept unchanged within a first preset time period, wherein the anomaly detection at least comprises one of track vertical component anomaly detection, track horizontal component anomaly detection and track end point height anomaly detection.
Optionally, the identification screening module is further configured to:
acquiring a target video, carrying out 3D head detection on the target video, and identifying to obtain each target head;
carrying out target tracking on each target head and acquiring head coordinate information corresponding to each target head;
and when head coordinate information with the upward movement amount larger than a second preset threshold exists in each piece of head coordinate information, judging that the target head corresponding to the head coordinate information is a target head suspected to be in a standing posture. Optionally, the center of gravity monitoring module is further configured to:
acquiring an initial coordinate value and a current coordinate value of the target head, wherein the initial coordinate value is a coordinate value before the target head is screened as suspected to be in a standing posture, and the current coordinate value is a coordinate value after the target head is screened as suspected to be in the standing posture;
and determining the upward moving amplitude of the gravity center change track corresponding to the target head according to the difference value between the current coordinate value and the initial coordinate value.
Optionally, the standing detection module is further configured to:
carrying out distortion error compensation on the gravity center change track to obtain a standard upward moving amplitude value;
detecting track vertical component abnormity according to the standard upward moving amplitude value, and judging whether the gravity center change track has track vertical component abnormity; and/or
Track horizontal component abnormity detection is carried out on the gravity center change track, and whether track horizontal component abnormity exists in the gravity center change track is judged; and/or
Track end point height abnormity detection is carried out on the gravity center change track, and whether track end point height abnormity exists in the gravity center change track or not is judged;
and if not, judging that the detection object corresponding to the target head is in the standing posture.
Optionally, the standing detection module is further configured to:
extracting a horizontal movement component in the gravity center change track, and judging whether the horizontal movement component is greater than a third preset threshold value;
if the horizontal movement component is larger than the third preset threshold, judging that the track horizontal component abnormality exists in the gravity center change track;
and if the horizontal movement component is not larger than the third preset threshold, judging that the gravity center change track has no track horizontal component abnormality.
Optionally, the standing detection module is further configured to:
judging whether the end point height of the gravity center change track is within a preset normal position range, wherein the preset normal position range is obtained by counting the gravity center height of each human head;
if the terminal height of the gravity center change track is within the range of the preset normal position, judging that the track terminal height of the gravity center change track is abnormal;
and if the terminal height of the gravity center change track is not in the preset normal position range, judging that the gravity center change track has no track terminal height abnormality.
Optionally, the standing posture detecting device is further configured to:
if the detection object is in the standing posture, continuously monitoring head coordinate information corresponding to the detection object;
and if the downward movement amplitude of the head coordinate information is larger than a fourth preset threshold, judging that the detection object is switched to a sitting posture.
The standing posture detection device provided by the application adopts the standing posture detection method in the embodiment, and the technical problem of low adaptability of the standing posture detection method is solved. Compared with the prior art, the advantages of the standing posture detection device provided by the embodiment of the application are the same as those of the standing posture detection method provided by the embodiment, and other technical features of the standing posture detection device are the same as those disclosed in the method of the previous embodiment, which are not repeated herein.
Example four
An embodiment of the present application provides an electronic device, and the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the storage stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for detecting standing posture in the first embodiment.
Referring now to FIG. 6, shown is a block diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, the electronic device may include a processing means (e.g., a central processing unit, a graphic processor, etc.) that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage means into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the functions defined in the methods of the embodiments of the present disclosure.
The electronic device provided by the application adopts the standing posture detection method in the embodiment, and the technical problem of low adaptability of the standing posture detection method is solved. Compared with the prior art, the electronic device provided by the embodiment of the present application has the same beneficial effects as the standing posture detection method provided by the first embodiment, and other technical features of the electronic device are the same as those disclosed in the method of the previous embodiment, which are not repeated herein.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon for performing the method of standing posture detection in the first embodiment.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be separate and not incorporated into the electronic device.
The computer-readable storage medium carries one or more programs which, when executed by an electronic device, cause the electronic device to: identifying the standing posture of each human head in a target video, and screening the target heads suspected to be in the standing posture from the human heads;
monitoring a trajectory of change of the center of gravity of the target head; if the moving-up amplitude of the gravity center change track corresponding to the target head is larger than a first preset threshold value and the gravity center change track is kept unchanged in a first preset time period, detecting whether a detected object corresponding to the target head is in a standing posture or not by performing abnormity detection on the gravity center change track, wherein the abnormity detection at least comprises one of track vertical component abnormity detection, track horizontal component abnormity detection and track terminal height abnormity detection.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium provided by the application stores computer-readable program instructions for executing the above-mentioned standing posture detection method, and solves the technical problem of standing posture detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the present application are the same as the beneficial effects of the standing posture detection method provided by the above embodiment, and are not described herein again.
EXAMPLE six
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method of detecting a standing posture as described above.
The computer program product provided by the application solves the technical problem of standing posture detection. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the standing posture detection method provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (7)
1. A standing posture detecting method, characterized by comprising:
identifying the standing posture of each human head in a target video, and screening the target heads suspected to be in the standing posture from the human heads;
monitoring a trajectory of change of the center of gravity of the target head;
if the upward moving amplitude of the gravity center change track corresponding to the target head is monitored to be larger than a first preset threshold and the gravity center change track is kept unchanged in a first preset time period, detecting whether a detection object corresponding to the target head is in a standing posture or not by performing abnormity detection on the gravity center change track, wherein the abnormity detection at least comprises one of track vertical component abnormity detection, track horizontal component abnormity detection and track terminal height abnormity detection;
wherein the step of detecting whether the detection object corresponding to the target head is in an upright posture by performing anomaly detection on the gravity center change trajectory comprises;
carrying out distortion error compensation on the gravity center change track to obtain a standard upward moving amplitude value;
detecting track vertical component abnormity according to the standard upward moving amplitude value, and judging whether the gravity center change track has track vertical component abnormity; and/or
Performing track horizontal component abnormity detection on the gravity center change track, and judging whether track horizontal component abnormity exists in the gravity center change track; and/or
Detecting track end point height abnormity of the gravity center change track, and judging whether the gravity center change track has track end point height abnormity;
if not, judging that the detection object corresponding to the target head is in the standing posture;
the step of performing track horizontal component anomaly detection on the gravity center change track and judging whether track horizontal component anomaly exists in the gravity center change track comprises the following steps:
extracting a horizontal movement component in the gravity center change track, and judging whether the horizontal movement component is greater than a third preset threshold value;
if the horizontal movement component is larger than the third preset threshold value, judging that the track horizontal component abnormality exists in the gravity center change track;
if the horizontal movement component is not larger than the third preset threshold, judging that the gravity center change track has no track horizontal component abnormality;
the step of detecting track end height abnormality of the gravity center change track and judging whether the gravity center change track has track end height abnormality includes:
judging whether the terminal height of the gravity center change track is within a preset normal position range or not, wherein the preset normal position range is obtained by counting the gravity center height of each human head;
if the terminal height of the gravity center change track is within the range of the preset normal position, judging that the track terminal height of the gravity center change track is abnormal;
and if the terminal height of the gravity center change track is not in the preset normal position range, judging that the gravity center change track has no track terminal height abnormality.
2. The standing posture detecting method as claimed in claim 1, wherein the step of screening each of the human heads for a target head suspected to be in a standing posture by performing the standing posture recognition on each of the human heads in the target video comprises:
acquiring a target video, performing 3D head detection on the target video, and identifying to obtain each target head;
carrying out target tracking on each target head and acquiring head coordinate information corresponding to each target head;
and when head coordinate information with the upward movement amount larger than a second preset threshold exists in each piece of head coordinate information, judging that the target head corresponding to the head coordinate information is a target head suspected to be in a standing posture.
3. The upright posture detection method of claim 1 wherein prior to said step of monitoring the trajectory of the change in the center of gravity of said target head, said method further comprises:
acquiring an initial coordinate value and a current coordinate value of the target head, wherein the initial coordinate value is a coordinate value before the target head is screened as suspected to be in a standing posture, and the current coordinate value is a coordinate value after the target head is screened as suspected to be in the standing posture;
and determining the upward moving amplitude of the gravity center change track corresponding to the target head according to the difference value between the current coordinate value and the initial coordinate value.
4. The standing posture detecting method as claimed in claim 1, wherein the standing posture detecting method further comprises:
if the detection object is in the standing posture, continuously monitoring head coordinate information corresponding to the detection object;
and if the downward movement amplitude of the head coordinate information is larger than a fourth preset threshold, judging that the detection object is switched to a sitting posture.
5. An upright posture detection device characterized by comprising:
the identification screening module is used for screening the target heads suspected to be in the standing postures in the human heads by carrying out standing posture identification on the human heads in the target video;
the gravity center monitoring module is used for monitoring the gravity center change track of the target head;
the standing detection module is used for detecting whether a detection object corresponding to the target head is in a standing posture or not by performing anomaly detection on the gravity center change track if the upward moving amplitude of the gravity center change track corresponding to the target head is larger than a first preset threshold and the gravity center change track is kept unchanged within a first preset time period, wherein the anomaly detection at least comprises one of track vertical component anomaly detection, track horizontal component anomaly detection and track end point height anomaly detection;
the standing detection module is further used for carrying out distortion error compensation on the gravity center change track to obtain a standard upward shift amplitude value; performing track vertical component abnormity detection according to the standard upward moving amplitude value, and judging whether the gravity center change track has track vertical component abnormity; and/or track horizontal component abnormity detection is carried out on the gravity center change track, and whether track horizontal component abnormity exists in the gravity center change track is judged; and/or track end point height abnormity detection is carried out on the gravity center change track, and whether track end point height abnormity exists in the gravity center change track is judged; if not, judging that the detection object corresponding to the target head is in the standing posture;
the standing detection module is further configured to extract a horizontal movement component in the gravity center change trajectory, and determine whether the horizontal movement component is greater than a third preset threshold; if the horizontal movement component is larger than the third preset threshold, judging that the track horizontal component abnormality exists in the gravity center change track; if the horizontal movement component is not larger than the third preset threshold, judging that the gravity center change track has no track horizontal component abnormality;
the standing detection module is further configured to determine whether a terminal height of the gravity center change trajectory is within a preset normal position range, where the preset normal position range is obtained by counting the gravity center height of each human head; if the terminal height of the gravity center change track is within the range of the preset normal position, judging that the track terminal height of the gravity center change track is abnormal; and if the terminal height of the gravity center change track is not in the preset normal position range, judging that the gravity center change track has no track terminal height abnormality.
6. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the upright posture detection method of any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program implementing the standing posture detection method, the program implementing the standing posture detection method being executed by a processor to implement the steps of the standing posture detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092375.6A CN115205981B (en) | 2022-09-08 | 2022-09-08 | Standing posture detection method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092375.6A CN115205981B (en) | 2022-09-08 | 2022-09-08 | Standing posture detection method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115205981A CN115205981A (en) | 2022-10-18 |
| CN115205981B true CN115205981B (en) | 2023-01-31 |
Family
ID=83573137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211092375.6A Active CN115205981B (en) | 2022-09-08 | 2022-09-08 | Standing posture detection method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115205981B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017073941A1 (en) * | 2015-10-30 | 2017-05-04 | 삼성전자 주식회사 | Gesture sensing method and electronic device supporting same |
| CN109528201A (en) * | 2018-10-30 | 2019-03-29 | 天津科技大学 | A kind of balanced capacity detection method |
| CN111131713A (en) * | 2019-12-31 | 2020-05-08 | 深圳市维海德技术股份有限公司 | Lens switching method, device, equipment and computer readable storage medium |
| CN111493882A (en) * | 2020-06-02 | 2020-08-07 | 上海健康医学院 | Old people falling prediction and exercise rehabilitation intervention guidance system and method |
| CN112487964A (en) * | 2020-11-27 | 2021-03-12 | 深圳市维海德技术股份有限公司 | Gesture detection and recognition method, device and computer readable storage medium |
| CN113850248A (en) * | 2021-12-01 | 2021-12-28 | 中科海微(北京)科技有限公司 | Motion attitude evaluation method and device, edge calculation server and storage medium |
| CN114333235A (en) * | 2021-12-23 | 2022-04-12 | 安徽信息工程学院 | Human body multi-feature fusion falling detection method |
-
2022
- 2022-09-08 CN CN202211092375.6A patent/CN115205981B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017073941A1 (en) * | 2015-10-30 | 2017-05-04 | 삼성전자 주식회사 | Gesture sensing method and electronic device supporting same |
| CN109528201A (en) * | 2018-10-30 | 2019-03-29 | 天津科技大学 | A kind of balanced capacity detection method |
| CN111131713A (en) * | 2019-12-31 | 2020-05-08 | 深圳市维海德技术股份有限公司 | Lens switching method, device, equipment and computer readable storage medium |
| CN111493882A (en) * | 2020-06-02 | 2020-08-07 | 上海健康医学院 | Old people falling prediction and exercise rehabilitation intervention guidance system and method |
| CN112487964A (en) * | 2020-11-27 | 2021-03-12 | 深圳市维海德技术股份有限公司 | Gesture detection and recognition method, device and computer readable storage medium |
| CN113850248A (en) * | 2021-12-01 | 2021-12-28 | 中科海微(北京)科技有限公司 | Motion attitude evaluation method and device, edge calculation server and storage medium |
| CN114333235A (en) * | 2021-12-23 | 2022-04-12 | 安徽信息工程学院 | Human body multi-feature fusion falling detection method |
Non-Patent Citations (7)
| Title |
|---|
| Human Posture Recognition by Simple Rules;Chien-Cheng Li等;《2006 IEEE International Conference on Systems, Man and Cybernetics》;20070716;第3237-3240页 * |
| 人体步态信息及运动重心轨迹检测方法研究;杨志方;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;20190115(第1期);第E080-29页 * |
| 便携式多功能人体重心位置动态检测系统的研制;单信海等;《中国体育科技》;20070110(第1期);第106-109页 * |
| 单目图像3D物体的姿态检测;3Ｄ视觉工坊;《https://blog.csdn.net/Yong_Qi2015/article/details/103209910》;20191122;第1页 * |
| 基于OpenCV的摄像头动态手势轨迹识别及其应用;江超等;《计算机应用》;20120710;第32卷(第S1期);第128-133页 * |
| 微信团队建设联合奥塔戈运动在防止社区老年人跌倒中的应用;陈涛等;《微信团队建设联合奥塔戈运动在防止社区老年人跌倒中的应用》;20220725;第43卷(第14期);第37-40页 * |
| 李晟 等 | 基于人体姿态识别的立定跳远动作智能评估系统;未来教育高精尖创新中心;《https://mp.weixin.qq.com/s?__biz=MzIyNjUzODU3Ng==&mid=2247516222&idx=1&sn=14527aad283a6f682720888c92636ecd&chksm=e86c2501df1bac179ad6e75744d4f8088e966e5d42727093d9c7a2bc53acfa618805f74c93a4&scene=27》;20220628;第1页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115205981A (en) | 2022-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108615248B (en) | Method, device and equipment for relocating camera attitude tracking process and storage medium | |
| CN110322500B (en) | Optimization method and device for instant positioning and map construction, medium and electronic equipment | |
| CN107077738B (en) | System and method for tracking object | |
| CN103985137B (en) | It is applied to the moving body track method and system of man-machine interaction | |
| CN108805917B (en) | Method, medium, apparatus and computing device for spatial localization | |
| CN103164022B (en) | Many fingers touch method and device, portable terminal | |
| CN109325456B (en) | Target identification method, target identification device, target identification equipment and storage medium | |
| CN111553282A (en) | Method and device for detecting vehicle | |
| US11675178B2 (en) | Virtual slide stage (VSS) method for viewing whole slide images | |
| CN111738072A (en) | Training method and device of target detection model and electronic equipment | |
| CN110555426A (en) | Sight line detection method, device, equipment and storage medium | |
| TWI794905B (en) | Method and apparatus for controlling video frame image in live classroom | |
| CN111814587A (en) | Human behavior detection method, teacher behavior detection method, and related system and device | |
| CN113177432B (en) | Head posture estimation method, system, equipment and medium based on multi-scale lightweight network | |
| JP2017523498A (en) | Eye tracking based on efficient forest sensing | |
| US10437342B2 (en) | Calibration systems and methods for depth-based interfaces with disparate fields of view | |
| CN111589138B (en) | Action prediction method, device, equipment and storage medium | |
| CN111797733A (en) | Behavior recognition method, behavior recognition device, behavior recognition equipment and storage medium based on image | |
| CN110969045A (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN109902675A (en) | The method and apparatus of the pose acquisition methods of object, scene reconstruction | |
| CN107704106B (en) | Attitude positioning method and device and electronic equipment | |
| CN115205981B (en) | Standing posture detection method and device, electronic equipment and readable storage medium | |
| CN114125659A (en) | Volume real-time compensation method, electronic device and readable storage medium | |
| CN112580584A (en) | Method, device and system for detecting standing behavior and storage medium | |
| CN115460353B (en) | Teaching tracking camera equipment configuration method and device, electronic equipment and medium |
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 |