CN111275031A - Flat plate support detection method, device, equipment and medium based on human body key points - Google Patents
Flat plate support detection method, device, equipment and medium based on human body key points Download PDFInfo
- Publication number
- CN111275031A CN111275031A CN202010377362.8A CN202010377362A CN111275031A CN 111275031 A CN111275031 A CN 111275031A CN 202010377362 A CN202010377362 A CN 202010377362A CN 111275031 A CN111275031 A CN 111275031A
- Authority
- CN
- China
- Prior art keywords
- included angle
- action
- key point
- threshold value
- elbow
- 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
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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention discloses a flat panel support detection method, a device, equipment and a medium based on human body key points, wherein the method comprises the steps of identifying each original frame image according to the time sequence of the original frame image, acquiring bone key points to be identified corresponding to each tester, acquiring an elbow key point included angle and a hip key point included angle, establishing a detection horizontal plane, acquiring a foot key point included angle, and when the elbow key point included angle, the hip key point included angle and the foot key point included angle meet judgment conditions corresponding to different stages, scoring the actual action duration according to scoring standards, determining whether the flat panel support action of the tester is standard or not according to the scored scores, so that manual participation is not needed, the detection efficiency and accuracy are improved, and the labor cost is saved.
Description
Technical Field
The invention relates to the field of body-building action detection, in particular to a flat plate support detection method, a flat plate support detection device, flat plate support detection equipment and a flat plate support detection medium based on human body key points.
Background
The flat plate support (plank) is a training action which is mainly in a prone posture during body building or exercise and keeps the body in a line balance, and the action can effectively exercise the transverse abdominal muscles and is known as an effective method for training a core muscle group. Specifically, when the flat plate support is carried out, the elbows need to be bent and supported on the ground, the shoulders and the elbow joints are perpendicular to the ground, the feet step on the ground, the body leaves the ground, the trunk is straightened, the head, the shoulders, the buttocks and the ankles are kept on the same plane, the abdominal muscles are tightened, the pelvic floor muscles are tightened, the spine is lengthened, and the eyes look at the ground, so that the flat plate support is standard. At present, whether the flat plate supporting action of a tester is standard or not is determined mainly through manual observation, and the method is high in labor cost, low in efficiency and large in error.
Disclosure of Invention
The invention aims to solve the technical problems of low efficiency, large error and high labor cost when manually determining whether the flat plate supporting action of a tester is standard. Therefore, the flat plate support detection method, the flat plate support detection device, the flat plate support detection equipment and the flat plate support detection medium based on the key points of the human body are provided, so that the judgment efficiency and the judgment accuracy are improved, and the labor cost is reduced.
The invention is realized by the following technical scheme:
a flat plate support detection method based on human body key points comprises the following steps:
acquiring original frame images, identifying each original frame image according to the time sequence of the original frame images based on a human body posture identification algorithm, and acquiring bone key points to be identified corresponding to each tester;
acquiring an elbow key point included angle and a hip key point included angle based on the bone key points to be identified;
establishing a detection horizontal plane based on the bone key points to be identified, and acquiring foot key point included angles based on the bone key points to be identified and the detection horizontal plane;
judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the current original frame image, and determining that the action state identification of the tester is that the action does not start when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
when the action state mark indicates that the action is not started, continuously judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the next original frame image, and when the elbow key point included angle is within a first elbow included angle threshold value and a second elbow included angle threshold value range, the hip key point included angle is within a first hip included angle threshold value and a second hip included angle threshold value range, and meanwhile, the foot key point included angle is within a first foot included angle threshold value and a second foot included angle threshold value range, determining that the action state mark of the tester is the action start;
when the action state mark is the action start, continuously judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the next original frame image, and when the elbow key point included angle is not in the range of a first elbow included angle threshold value and a second elbow included angle threshold value, or the hip key point included angle is not in the range of a first hip included angle threshold value and a second hip included angle threshold value, or the foot key point included angle is not in the range of a first foot included angle threshold value and a second foot included angle threshold value, determining that the action state mark of the tester is the action end;
when the action state mark is an action end, taking the moment when the action state mark is the action start as an action start moment, taking the moment when the action state mark is the action end as an action end moment, and acquiring an actual action duration based on the action start moment and the action end moment;
and scoring the actual action duration based on a scoring standard, and acquiring an action score corresponding to the actual action duration.
Further, the obtaining of the included angle of the elbow key point and the included angle of the hip key point based on the bone key point to be identified includes:
selecting elbow key points, shoulder key points, wrist key points, hip key points and foot key points based on the bone key points to be identified;
establishing an elbow keypoint angle based on the shoulder keypoints, the elbow keypoints, and the wrist keypoints;
and establishing a hip key point included angle based on the shoulder key points, the hip key points and the foot key points.
Further, the establishing a detection horizontal plane based on the bone key points to be identified, and obtaining the included angle of the foot key points based on the bone key points to be identified and the detection horizontal plane include:
establishing a detection horizontal plane based on wrist key points and elbow key points in the skeleton key points to be identified, and acquiring little toe key points from the skeleton key points to be identified;
and establishing a foot key point included angle based on the ankle key point, the little toe key point and the detection horizontal plane.
Further, the acquiring of the original frame images, based on a human body posture recognition algorithm, recognizing each of the original frame images according to a time sequence of the original frame images, and acquiring the bone key points to be recognized corresponding to each tester includes:
acquiring original frame images, and tracking each original frame image according to the time sequence of the original frame images based on a pedestrian detection algorithm to acquire a target to be identified;
carrying out face recognition on each target to be recognized based on a face recognition algorithm to obtain identity information;
and identifying each target to be identified based on a human body posture identification algorithm to obtain the bone key points to be identified corresponding to each tester.
Further, the acquiring of the original frame images, based on a pedestrian detection algorithm, performing target tracking on each of the original frame images according to the time sequence of the original frame images, and acquiring a target to be identified includes:
acquiring original frame images, and preprocessing each pair of original frame images according to the time sequence of the original frame images to acquire effective frame images;
and tracking the target of each effective frame image based on a pedestrian detection algorithm to obtain the target to be identified.
Further, the scoring the actual action duration based on the scoring standard to obtain an action score corresponding to the actual action duration includes:
selecting a corresponding scoring standard based on the identity information of the tester;
and scoring the actual action duration based on the scoring standard, and acquiring an action score corresponding to the actual action duration.
Further, the flat panel support detection method based on human body key points further comprises the following steps:
selecting a passing flat plate supporting action and counting the number of the passing flat plate supporting actions based on the action score;
according to the time sequence, calculating a time interval between the action ending moment of the first passing flat plate supporting action and the action starting moment of the next passing flat plate supporting action as an action interval;
and when the action interval is less than or equal to a preset interval and the number of the passing flat plate supporting actions reaches a preset number within a preset training time, the flat plate supporting motion of the tester reaches the standard.
A flat plate support detection device based on human key points comprises:
the original frame image recognition module is used for acquiring original frame images, recognizing each original frame image according to the time sequence of the original frame images based on a human body posture recognition algorithm, and acquiring bone key points to be recognized corresponding to each tester;
the first detection parameter acquisition module is used for acquiring an elbow key point included angle and a hip key point included angle based on the bone key point to be identified;
the second detection parameter acquisition module is used for establishing a detection horizontal plane based on the bone key points to be identified and acquiring an included angle of the foot key points based on the bone key points to be identified and the detection horizontal plane;
an action non-start judging module, configured to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in the current original frame image, and determine that an action state identifier of the tester is that an action is not started when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
an action starting judging module, configured to, when the action state identifier indicates that an action is not started, continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in a next original frame image, and when the elbow key point included angle is within a first elbow included angle threshold value and a second elbow included angle threshold value range, and the hip key point included angle is within a first hip included angle threshold value and a second hip included angle threshold value range, and meanwhile, the foot key point included angle is within a first foot included angle threshold value and a second foot included angle threshold value range, determine that the action state identifier of the tester is an action start;
an action ending judging module, configured to continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in a next original frame image when the action state identifier indicates that an action starts, and determine that the action state identifier of the tester is an action end when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
the actual action duration calculation module is used for taking the moment when the action state is marked as action start moment when the action state is marked as action end, taking the moment when the action state is marked as action end moment, and acquiring actual action duration based on the action start moment and the action end moment;
and the actual action duration scoring module is used for scoring the actual action duration based on a scoring standard and acquiring an action score corresponding to the actual action duration.
A computer device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the human body key point-based flat plate support detection method.
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described human body keypoint-based flat panel support detection method.
The invention relates to a flat panel support detection method, a flat panel support detection device, flat panel support detection equipment and a flat panel support detection medium based on human body key points, wherein each original frame image is identified through a human body posture identification algorithm, bone key points to be identified corresponding to each tester are obtained, so that an elbow key point included angle and a hip key point included angle are obtained, a detection horizontal plane is established, a foot key point included angle is obtained, and an accurate data source is provided for a subsequent detection process. And finally, grading the duration of the actual action according to a grading standard, and determining whether the flat plate supporting action of the tester is standard or not according to the graded fraction, so that manual participation is not needed, the detection efficiency and accuracy are improved, and the labor cost is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flow chart of the flat panel support detection method based on human body key points according to the present invention.
Fig. 2 is a specific flowchart of step S20 in fig. 1.
Fig. 3 is a specific flowchart of step S30 in fig. 1.
Fig. 4 is a specific flowchart of step S10 in fig. 1.
Fig. 5 is a specific flowchart of step S11 in fig. 4.
Fig. 6 is a specific flowchart of step S80 in fig. 1.
FIG. 7 is another flowchart of the method for detecting a flat panel support based on human body key points according to the present invention.
FIG. 8 is a schematic structural diagram of the flat panel support detection device based on human body key points.
FIG. 9 is a schematic diagram of the computer apparatus of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1
The invention provides a tablet support detection method based on human body key points, which can be applied to different computer equipment, wherein the computer equipment comprises but is not limited to various personal computers, notebook computers, smart phones and tablet computers.
As shown in fig. 1, the invention provides a flat panel support detection method based on human body key points, comprising the following steps:
s10: acquiring original frame images, identifying each original frame image according to the time sequence of the original frame images based on a human body posture identification algorithm, and acquiring bone key points to be identified corresponding to each tester.
The original frame image is a single frame image which is sent by a server and shoots a flat panel supporting action of a tester.
Specifically, after acquiring the original frame images, the server identifies each original frame image according to the time sequence of the original frame images, and acquires the bone key points to be identified from each original frame image. The skeleton key points to be recognized refer to points which represent a human body frame and are obtained by recognizing a human body in the original frame image through a human body posture recognition algorithm.
In this embodiment, the number of the skeletal key points to be identified is 25, which are 0 nose, 1 neck, 2 right shoulder, 3 right elbow, 4 right wrist, 5 left shoulder, 6 left elbow, 7 left wrist, 8 middle hip, 9 right hip, 10 right knee, 11 right ankle, 12 left hip, 13 left knee, 14 left ankle, 15 right eye, 16 left eye, 17 right ear, 18 left ear, 19 left thumb, 20 left little thumb, 21 left heel, 22 right thumb, 23 right little thumb and 24 right heel, and the 25 skeletal key points to be identified are connected by line segments to form a human body frame.
The human body gesture recognition algorithm in this embodiment refers to an algorithm of a human body bone key point in an image, and the human body gesture recognition algorithm in this embodiment includes, but is not limited to, OpenPose and AlphaPose.
S20: and acquiring an included angle of the elbow key point and an included angle of the hip key point based on the bone key point to be identified.
Wherein, the included angle v of the key point of the elbow1The included angle formed by the key points of the bones to be identified corresponding to the left wrist, the left elbow and the left shoulder, or the included angle formed by the key points of the bones to be identified corresponding to the right wrist, the right elbow and the right shoulder.
Hip key point included angle v2The included angle formed by the key points of the bones to be identified corresponding to the left shoulder, the left hip and the left knee, or the included angle formed by the key points of the bones to be identified corresponding to the right shoulder, the right hip and the right knee.
S30: and establishing a detection horizontal plane based on the bone key points to be identified, and acquiring the included angles of the foot key points based on the bone key points to be identified and the detection horizontal plane.
Specifically, after acquiring the bone key points to be identified, the server connects the two bone key points to be identified of the left wrist and the left elbow, and uses a horizontal plane corresponding to a connection line parallel to the two bone key points to be identified as a detection horizontal plane, or connects the two bone key points to be identified of the right wrist and the right elbow, and uses a horizontal plane corresponding to a connection line parallel to the two bone key points to be identified as an established detection horizontal plane, and the detection horizontal plane established by the left wrist and the left elbow or the detection horizontal plane established by the right wrist and the right elbow can be determined by the user according to actual conditions. It is understood that the detection horizontal plane in this embodiment is a supporting plane for the tester to perform the flat panel support detection operation, including but not limited to the ground.
After the detection horizontal plane is established, the left ankle and the left little finger are connected, and the included angle formed by the connecting line of the left ankle and the left little finger and the detection horizontal plane is used as the included angle v of the key point of the foot3Or connecting the right ankle and the right little toe, and taking an included angle formed by a connecting line of the right ankle and the right little toe and the detection horizontal plane as a key point included angle v of the foot3。
S40: judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the current original frame image, and determining that the action state identification of the tester is that the action does not start when the elbow key point included angle is not in the range of a first elbow included angle threshold value and a second elbow included angle threshold value, or the hip key point included angle is not in the range of a first hip included angle threshold value and a second hip included angle threshold value, or the foot key point included angle is not in the range of a first foot included angle threshold value and a second foot included angle threshold value.
The action state identification is used for uniquely identifying the state of a tester doing the flat plate supporting action.
Specifically, after the server acquires the elbow key point included angle, the hip key point included angle and the foot key point included angle from the current original frame image, whether the elbow key point included angle, the hip key point included angle and the foot key point included angle in the current original frame image meet the corresponding requirements of each other or not can be judged, when the elbow key point included angle is not in the range of the first elbow included angle threshold value and the second elbow included angle threshold value, or the hip key point included angle is not in the range of the first hip included angle threshold value and the second hip included angle threshold value, or the foot key point included angle is not in the range of the first foot included angle threshold value and the second foot included angle threshold value, it indicates that the tester does not start to do the flat plate supporting action yet, namely, the action state identification of the tester does not start to do the action.
The first elbow included angle threshold value and the second elbow included angle threshold value both refer to preset values for judging whether the elbow key point included angle meets the requirements of making the flat panel supporting action, and the first elbow included angle threshold value is smaller than the second elbow included angle threshold value. The first hip included angle threshold value and the second hip included angle threshold value refer to preset values used for judging whether the hip key point included angle meets the requirements of flat plate supporting actions or not, and the first hip included angle threshold value is smaller than the second hip included angle threshold value. The first foot included angle threshold value is smaller than the second foot included angle threshold value, which is a preset value used for judging whether the included angle of the key points of the feet meets the requirement of making a flat plate supporting action, and the first foot included angle threshold value is smaller than the second foot included angle threshold value.
S50: when the action state identification is that the action is not started, the elbow key point included angle, the hip key point included angle and the foot key point included angle in the next original frame image are continuously judged, when the elbow key point included angle is in the range of the first elbow included angle threshold value and the second elbow included angle threshold value, the hip key point included angle is in the range of the first hip included angle threshold value and the second hip included angle threshold value, and meanwhile, the foot key point included angle is in the range of the first foot included angle threshold value and the second foot included angle threshold value, the action state identification of the tester is determined as the action start.
S60: and when the action state identifier is the action start, continuously judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the next original frame image, and when the elbow key point included angle is not in the range of the first elbow included angle threshold value and the second elbow included angle threshold value, or the hip key point included angle is not in the range of the first hip included angle threshold value and the second hip included angle threshold value, or the foot key point included angle is not in the range of the first foot included angle threshold value and the second foot included angle threshold value, determining that the action state identifier of the tester is the action end.
S70: and when the action state mark is the action end, the moment when the action state mark is the action start is used as the action start moment, the moment when the action state mark is the action end is used as the action end moment, and the actual action time length is obtained based on the action start moment and the action end moment.
In particular, by
Calculating the actual action duration, wherein,
the time when the motion is started is referred to as the motion starting time,
the time when the finger movement is finished is referred to,
refers to the actual action duration. The actual action duration in this embodiment refers to the duration that the tester actually adheres to the flat plate support action once.
S80: and scoring the actual action duration based on the scoring standard, and acquiring an action score corresponding to the actual action duration.
The scoring standard refers to a pre-stored standard for scoring different actual action durations. For example, 40s-50s corresponds to 60 points, and 50s and above correspond to 90 points.
Specifically, after the actual action duration corresponding to the tester is obtained, the processor scores the actual action duration according to a pre-stored scoring standard, and obtains an action score corresponding to the actual action duration. The action score refers to a score obtained after the processor evaluates the actual action duration according to the scoring standard.
S10-S80, identifying each original frame image according to the time sequence of the original frame image through a human body posture identification algorithm, acquiring a bone key point to be identified corresponding to each tester, acquiring an elbow key point included angle and a hip key point included angle based on the bone key point to be identified, establishing a detection horizontal plane based on the bone key point to be identified to acquire a foot key point included angle, determining whether the process of the tester doing the flat panel supporting action is executed according to the requirement by judging whether the elbow key point included angle, the hip key point included angle and the foot key point included angle meet the set judgment conditions, scoring the actual action duration of the tester through a scoring standard when the process of the tester doing the flat panel supporting action meets the requirement, determining whether the flat panel supporting action of the tester is standard according to the scored score, and simultaneously detecting whether the flat panel supporting actions of a plurality of testers meet the standard without manual participation, the detection efficiency and accuracy are improved, manual participation is not needed, and the labor cost is saved.
As shown in fig. 2, further, in step S20, based on the bone key points to be identified, obtaining an elbow key point included angle and a hip key point included angle, which specifically includes the following steps:
s21: based on the bone key points to be identified, selecting elbow key points, shoulder key points, wrist key points, hip key points and foot key points.
S22: an elbow keypoint angle is established based on the shoulder keypoints, the elbow keypoints, and the wrist keypoints.
S23: and establishing a hip key point included angle based on the shoulder key points, the hip key points and the foot key points.
As shown in fig. 3, further, in step S30, establishing a detection horizontal plane based on the bone key points to be identified, and obtaining the included angle of the foot key points based on the bone key points to be identified and the detection horizontal plane, the method specifically includes the following steps:
s31: and establishing a detection horizontal plane based on wrist key points and elbow key points in the skeleton key points to be identified, and acquiring little toe key points from the skeleton key points to be identified.
Specifically, a wrist key point and an elbow key point are selected from the bone key points to be identified and connected, and a formed plane is a detection horizontal plane.
S32: and establishing a foot key point included angle based on the ankle key point, the little toe key point and the detection horizontal plane.
Specifically, after acquiring a detection horizontal plane and a foot key point, acquiring a little toe key point of a tester, and then connecting the ankle key point with the little toe key point, wherein an included angle formed by a connecting line of the foot key point and a foot contact point and the detection horizontal plane is a foot key point included angle.
As shown in fig. 4, further, in step S10, acquiring original frame images, identifying each original frame image according to a time sequence of the original frame images based on a human body posture identification algorithm, and acquiring bone key points to be identified corresponding to each tester, specifically including the following steps:
s11: and acquiring original frame images, and tracking the target of each original frame image according to the time sequence of the original frame images based on a pedestrian detection algorithm to acquire the target to be identified.
The pedestrian detection algorithm in the embodiment refers to an algorithm for detecting and tracking a pedestrian in an original frame image, and includes two algorithms of pedestrian detection and pedestrian tracking.
Wherein, the target to be identified refers to the image data of the original frame image of each tester doing the flat plate supporting action.
S12: and carrying out face recognition on each target to be recognized based on a face recognition algorithm to obtain identity information.
The Face recognition algorithm in this embodiment includes, but is not limited to, a Face recognition open source library Dlib, libfacedetection, or a commercial open Face recognition library SDK, a Face + + Face recognition library, and a hundredth AI Face recognition library.
The identity information refers to information which can represent the identity of a tester and is obtained by carrying out face recognition on each target to be recognized according to a face recognition algorithm. The identity information in this embodiment includes, but is not limited to, gender and age of the tester.
S13: and identifying each target to be identified based on a human body posture identification algorithm, and acquiring the bone key points to be identified corresponding to each tester.
As shown in fig. 5, further, in step S11, acquiring original frame images, and based on a pedestrian detection algorithm, performing target tracking on each original frame image according to the time sequence of the original frame images to acquire a target to be identified, specifically including the following steps:
s111: and acquiring original frame images, preprocessing each pair of original frame images according to the time sequence of the original frame images, and acquiring effective frame images.
The effective frame image refers to an image obtained by performing image processing on an original frame image.
S112: and tracking the target of each effective frame image based on a pedestrian detection algorithm to obtain the target to be identified.
As shown in fig. 6, further, in step S80, based on the scoring criterion, scoring the actual action duration to obtain an action score corresponding to the actual action duration, specifically including the following steps:
s81: and selecting a corresponding scoring standard based on the identity information of the tester.
Since the physical qualities of testers of different ages and different sexes are different, different scoring standards are set for the testers of different ages and sexes in the embodiment.
For example, the duration of the male plate supporting action between the ages of 20 and 25 is 50s-60s corresponding to 80 minutes, 60s and above corresponds to 95 minutes, the duration of the male plate supporting action between the ages of 25 and 35 is 60s-65s corresponding to 80 minutes, 65s and above corresponds to 95 minutes, the duration of the female plate supporting action between the ages of 20 and 25 is 40s-45s corresponding to 80 minutes, 45s and above corresponds to 95 minutes, and the duration of the female plate supporting action between the ages of 25 and 35 is 45s-50s corresponding to 80 minutes, 50s and above corresponds to 95 minutes.
By setting different score judgment standards for different ages and different sexes, the setting of the score standards is more reasonable.
S82: and scoring the actual action duration based on the scoring standard, and acquiring an action score corresponding to the actual action duration.
If the tester is a 24-year-old male, the actual action duration is 58s, and the action score of the tester is 80 points according to the scoring standard that the action duration of a male with the age between 20 and 25 is 50s-60s and corresponds to 80 points.
As shown in fig. 7, further, the method further includes the following steps:
s91: and selecting the passing plate supporting action and counting the number of the passing plate supporting actions based on the action scores.
Wherein the passing plate supporting action means a plate supporting action with a passing score or more. If the passing score in this embodiment is 80 points, the passing plate supporting motion is the plate supporting motion corresponding to the score of 80 points or more.
S92: and according to the time sequence, calculating the time interval between the action ending moment of the first passing flat plate supporting action and the action starting moment of the next passing flat plate supporting action as the action interval.
S93: when the action interval is less than or equal to the preset interval and the number of the grid flat plate supporting actions reaches the preset number within the preset training time, the flat plate supporting motion of the tester reaches the standard.
The preset interval refers to a preset value, such as 20s, for determining whether the action interval meets the requirement. The preset training time refers to the preset time for the flat plate support training, such as 6 minutes.
Specifically, when the action interval of the tester is less than or equal to the preset interval and the number of passing plate supports in the preset training time reaches the preset number, the set motion standard of the tester is completed in the motion time, and the motion of the tester reaches the standard. The preset number refers to the number of the preset flat plate supporting actions required to be performed by the tester within the preset training time, such as 4.
If a male tester with the specified age of 20-25 years performs 5 passing flat plate supporting actions in 7 minutes, the action interval of each passing flat plate supporting action is less than or equal to the preset interval of 20s, the movement reaches the standard, the corresponding scoring standard is that the action time length is 50s-60s corresponding to 80 minutes, 60s and above correspond to 95 minutes, and 80 minutes are taken as passing scores.
When a male tester 24 years old performs 5 flat plate supporting actions within 7 minutes, the actual action duration of the first flat plate supporting action is 67s, the actual action duration of the second flat plate supporting action at an interval of 10s is 75s, the actual action duration of the third flat plate supporting action at an interval of 10s is 80s, the actual action duration of the fourth flat plate supporting action at an interval of 10s is 63s, and the actual action duration of the fifth flat plate supporting action at an interval of 10s is 49s, according to a grading standard corresponding to the tester, the first 4 flat plate supporting actions of the tester are passing flat plate supporting actions, the last flat plate supporting action is a failing flat plate supporting action, and the number of 4 passing flat plate supporting actions of the tester does not reach the preset number of 5, the flat plate supporting actions of the tester do not reach the standard.
If the tester performs 7 plate supporting actions within 7 minutes, the actual action duration of the first plate supporting action is 53s, the actual action duration of the second plate supporting action at an interval of 10s is 51s, the actual action duration of the third plate supporting action at an interval of 10s is 56s, the actual action duration of the fourth plate supporting action at an interval of 10s is 49s, the actual action duration of the fifth plate supporting action at an interval of 10s is 52s, the actual action duration of the sixth plate supporting action at an interval of 10s is 48s, and the actual action duration of the seventh plate supporting action at an interval of 10s is 51s, according to the corresponding scoring standard of the tester, the previous first, second, third, fifth and seventh plate supporting actions of the tester are used as grid-connected plate supporting actions, and the fourth and sixth plate supporting actions are used as grid-disconnected plate supporting actions, the number of the passing flat plate supporting actions of the tester is 5, the preset number is reached, but the action interval 59s of the third passing flat plate supporting action and the fifth passing flat plate supporting action of the tester and the action interval 58s of the fifth passing flat plate supporting action and the seventh passing flat plate supporting action of the tester exceed the preset interval 20s, and the flat plate supporting motion of the tester is considered to reach the standard.
According to the flat panel support detection method based on the human body key points, the effective frame image is obtained by preprocessing the original frame image, so that the data of subsequent image processing is reduced, and the efficiency of the subsequent image processing is improved. The method comprises the steps of firstly tracking the target of each effective frame image through a pedestrian detection algorithm and a face recognition algorithm, and then carrying out face recognition on the tracked target so as to accurately recognize the identity information of each tester in the effective frame image, so that a corresponding scoring standard is selected according to the identity information of the tester in the following process. The method comprises the steps of identifying skeleton key points to be identified of all testers in each frame of original frame image through a human body posture identification algorithm, obtaining an elbow key point included angle and a hip key point included angle, establishing a detection horizontal plane based on wrist key points and elbow key points, obtaining a foot key point included angle by combining ankle key points and little toe key points, and determining whether the process of the testers performing flat plate supporting actions is executed according to requirements by judging whether the elbow key point included angle, the hip key point included angle and the foot key point included angle meet respective corresponding conditions. When the process of the tester doing the flat plate supporting action meets the requirement, the duration of the tester doing the flat plate supporting action is acquired, the corresponding scoring standard is selected according to the identity information of the tester to complete scoring of the flat plate supporting action, and whether the flat plate supporting action of the tester is standard or not is determined according to the scored score. When the scores of the flat plate supporting actions are passing scores, whether the action interval between two adjacent passing flat plate supporting actions meets the requirement is calculated, whether the number of the passing flat plate supporting actions in the preset training time meets the requirement is calculated, and when the scores of the two passing flat plate supporting actions meet the requirement, the flat plate supporting motion of the tester is considered to reach the standard. The method can automatically detect the flat plate supporting actions of a plurality of testers at the same time, does not need manual participation, improves the detection efficiency and the detection accuracy, and reduces the labor cost.
Example 2
As shown in fig. 8, the present embodiment is different from embodiment 1 in that a flat panel support detection device based on key points of a human body includes:
and the original frame image identification module 10 is configured to acquire an original frame image, identify each original frame image according to a time sequence of the original frame image based on a human body posture identification algorithm, and acquire a bone key point to be identified corresponding to each tester.
And the first detection parameter obtaining module 20 is configured to obtain an elbow key point included angle and a hip key point included angle based on the bone key point to be identified.
And the second detection parameter acquisition module 30 is configured to establish a detection horizontal plane based on the bone key points to be identified, and acquire an included angle between the foot key points based on the bone key points to be identified and the detection horizontal plane.
And an action non-start judging module 40, configured to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in the current original frame image, and when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range, determine that the action state identifier of the tester is that the action is not started.
And an action start judging module 50, configured to, when the action state identifier indicates that the action is not started, continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in a next original frame image, when the elbow key point included angle is within a first elbow included angle threshold value and a second elbow included angle threshold value range, and the hip key point included angle is within a first hip included angle threshold value and a second hip included angle threshold value range, and at the same time, the foot key point included angle is within a first foot included angle threshold value and a second foot included angle threshold value range, determine that the action state identifier of the tester is the action start.
And an action ending judging module 60, configured to continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in the next original frame image when the action state identifier indicates that the action starts, and determine that the action state identifier of the tester is an action ending when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range.
And the actual action duration calculation module 70 is configured to, when the action state is identified as the action end, identify the moment when the action state is identified as the action start moment, identify the moment when the action state is identified as the action end moment, and obtain the actual action duration based on the action start moment and the action end moment.
And the actual action duration scoring module 80 is configured to score the actual action duration based on the scoring criteria, and obtain an action score corresponding to the actual action duration.
Further, the first detection parameter obtaining module 20 includes a bone key point selecting unit to be identified, an elbow key point included angle obtaining unit, and a hip key point included angle obtaining unit.
And the bone key point selection unit is used for selecting an elbow key point, a shoulder key point, a wrist key point, a hip key point and a foot key point based on the bone key point to be identified.
And the elbow key point included angle acquisition unit is used for establishing an elbow key point included angle based on the shoulder key point, the elbow key point and the wrist key point.
And the hip key point included angle acquisition unit is used for establishing a hip key point included angle based on the shoulder key point, the hip key point and the foot key point.
Further, the second detection parameter obtaining module 30 includes a detection level establishing unit and a foot key point included angle obtaining unit.
And the detection horizontal plane establishing unit is used for establishing a detection horizontal plane based on the wrist key points and the elbow key points in the bone key points to be identified and acquiring the little toe key points from the bone key points to be identified.
And the foot key point included angle acquisition unit is used for establishing a foot key point included angle based on the ankle key point, the little toe key point and the detection horizontal plane.
Further, the module 10 for acquiring a bone key point to be recognized includes an acquiring unit of a target to be recognized, an acquiring unit of identity information, and an acquiring unit of a bone key point to be recognized.
And the target to be recognized acquisition unit is used for acquiring the original frame images, and tracking the target of each original frame image according to the time sequence of the original frame images based on a pedestrian detection algorithm to acquire the target to be recognized.
And the identity information acquisition unit is used for carrying out face recognition on each target to be recognized based on a face recognition algorithm to acquire identity information.
And the bone key point acquisition unit to be recognized is used for recognizing each target to be recognized based on a human body posture recognition algorithm and acquiring the bone key points to be recognized corresponding to each tester.
Further, the target to be identified acquisition unit comprises an original frame image processing unit and a target tracking unit
And the original frame image processing unit is used for acquiring original frame images, preprocessing each pair of original frame images according to the time sequence of the original frame images and acquiring effective frame images.
And the target tracking unit is used for tracking the target of each effective frame image based on a pedestrian detection algorithm to obtain the target to be identified.
Further, the actual action duration scoring module 80 includes a scoring criterion selecting unit and an action score obtaining unit.
And the scoring standard selecting unit is used for selecting a corresponding scoring standard based on the identity information of the tester.
And the action score acquisition unit is used for scoring the actual action duration based on the scoring standard and acquiring an action score corresponding to the actual action duration.
Furthermore, the flat plate support detection device based on the key points of the human body further comprises a passing flat plate support action number counting module, an action interval calculating module and a motion standard reaching judging module.
And the passing flat plate supporting action number counting module is used for selecting the passing flat plate supporting action and counting the number of the passing flat plate supporting actions based on the action scores.
And the action interval calculation module is used for calculating the time interval between the action ending moment of the first passing flat plate supporting action and the action starting moment of the next passing flat plate supporting action as the action interval according to the time sequence.
And the motion standard-reaching judgment module is used for judging whether the motion interval is smaller than or equal to a preset interval or not, and if the number of the qualified flat plate supporting motions reaches a preset number within a preset training time, the flat plate supporting motion of the tester reaches the standard.
For specific definition of the human body key point-based flat panel support detection, reference may be made to the above definition of the human body key point-based flat panel support detection method, which is not described herein again. All or part of the modules in the flat panel support detection based on the human body key points can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example 3
The embodiment provides a computer device, which may be a server, and the internal structure diagram of the computer device may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a computer readable storage medium, an internal memory. The computer readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the computer-readable storage medium. The database of the computer device is used for storing data involved in the method of human body key point-based flat panel support detection. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a human body keypoint-based flat panel support detection method.
The present embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for detecting a flat panel support based on human body keypoints in the foregoing embodiments when executing the computer program, for example, steps S10-S80 shown in fig. 1 or steps shown in fig. 2 to 7, which are not repeated herein for avoiding repetition. Alternatively, the processor, when executing the computer program, implements the functions of the modules/units of the apparatus for human body keypoint-based flat panel support detection in the above-described embodiments, such as the functions of modules 10 to 80 shown in fig. 8. To avoid repetition, further description is omitted here.
Example 4
The present embodiment provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps of the information pushing method in the foregoing embodiments, for example, steps S10-S80 shown in fig. 1 or steps shown in fig. 2 to fig. 7, which are not repeated herein to avoid repetition. Alternatively, the processor implements the functions of each module/unit in the embodiment of the information pushing apparatus when executing the computer program, for example, the functions of the modules 10 to 80 shown in fig. 8. To avoid repetition, further description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A flat plate support detection method based on human body key points is characterized by comprising the following steps:
acquiring original frame images, identifying each original frame image according to the time sequence of the original frame images based on a human body posture identification algorithm, and acquiring bone key points to be identified corresponding to each tester;
acquiring an elbow key point included angle and a hip key point included angle based on the bone key points to be identified;
establishing a detection horizontal plane based on the bone key points to be identified, and acquiring foot key point included angles based on the bone key points to be identified and the detection horizontal plane;
judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the current original frame image, and determining that the action state identification of the tester is that the action does not start when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
when the action state mark indicates that the action is not started, continuously judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the next original frame image, and when the elbow key point included angle is within a first elbow included angle threshold value and a second elbow included angle threshold value range, the hip key point included angle is within a first hip included angle threshold value and a second hip included angle threshold value range, and meanwhile, the foot key point included angle is within a first foot included angle threshold value and a second foot included angle threshold value range, determining that the action state mark of the tester is the action start;
when the action state mark is the action start, continuously judging an elbow key point included angle, a hip key point included angle and a foot key point included angle in the next original frame image, and when the elbow key point included angle is not in the range of a first elbow included angle threshold value and a second elbow included angle threshold value, or the hip key point included angle is not in the range of a first hip included angle threshold value and a second hip included angle threshold value, or the foot key point included angle is not in the range of a first foot included angle threshold value and a second foot included angle threshold value, determining that the action state mark of the tester is the action end;
when the action state mark is an action end, taking the moment when the action state mark is the action start as an action start moment, taking the moment when the action state mark is the action end as an action end moment, and acquiring an actual action duration based on the action start moment and the action end moment;
and scoring the actual action duration based on a scoring standard, and acquiring an action score corresponding to the actual action duration.
2. The method for detecting the flat panel support based on the key points of the human body according to claim 1, wherein the obtaining of the included angle of the key points of the elbow and the included angle of the key points of the hip based on the key points of the bone to be identified comprises:
selecting elbow key points, shoulder key points, wrist key points, hip key points and foot key points based on the bone key points to be identified;
establishing an elbow keypoint angle based on the shoulder keypoints, the elbow keypoints, and the wrist keypoints;
and establishing a hip key point included angle based on the shoulder key points, the hip key points and the foot key points.
3. The method for detecting the flat panel support based on the key points of the human body according to claim 1, wherein the establishing of the detection horizontal plane based on the key points of the bones to be identified and the obtaining of the included angles of the key points of the feet based on the key points of the bones to be identified and the detection horizontal plane comprise:
establishing a detection horizontal plane based on wrist key points and elbow key points in the skeleton key points to be identified, and acquiring little toe key points from the skeleton key points to be identified;
and establishing a foot key point included angle based on the ankle key point, the little toe key point and the detection horizontal plane.
4. The method for detecting a flat panel support based on human body key points according to claim 1, wherein the obtaining of original frame images, identifying each original frame image according to a time sequence of the original frame images based on a human body posture identification algorithm, and obtaining bone key points to be identified corresponding to each tester comprises:
acquiring original frame images, and tracking each original frame image according to the time sequence of the original frame images based on a pedestrian detection algorithm to acquire a target to be identified;
carrying out face recognition on each target to be recognized based on a face recognition algorithm to obtain identity information;
and identifying each target to be identified based on a human body posture identification algorithm to obtain the bone key points to be identified corresponding to each tester.
5. The method for detecting flat panel support based on human body key points according to claim 4, wherein the acquiring original frame images, performing target tracking on each original frame image according to the time sequence of the original frame images based on a pedestrian detection algorithm, and acquiring the target to be identified comprises:
acquiring original frame images, and preprocessing each pair of original frame images according to the time sequence of the original frame images to acquire effective frame images;
and tracking the target of each effective frame image based on a pedestrian detection algorithm to obtain the target to be identified.
6. The method for detecting the flat panel support based on the human body key points according to claim 4, wherein the step of scoring the actual action duration based on a scoring standard to obtain an action score corresponding to the actual action duration comprises the following steps:
selecting a corresponding scoring standard based on the identity information of the tester;
and scoring the actual action duration based on the scoring standard, and acquiring an action score corresponding to the actual action duration.
7. The method for detecting the support of the flat panel based on the key points of the human body according to claim 1, further comprising:
selecting a passing flat plate supporting action and counting the number of the passing flat plate supporting actions based on the action score;
according to the time sequence, calculating a time interval between the action ending moment of the first passing flat plate supporting action and the action starting moment of the next passing flat plate supporting action as an action interval;
and when the action interval is less than or equal to a preset interval and the number of the passing flat plate supporting actions reaches a preset number within a preset training time, the flat plate supporting motion of the tester reaches the standard.
8. The utility model provides a dull and stereotyped detection device that supports based on human key point which characterized in that includes:
the original frame image recognition module is used for acquiring original frame images, recognizing each original frame image according to the time sequence of the original frame images based on a human body posture recognition algorithm, and acquiring bone key points to be recognized corresponding to each tester;
the first detection parameter acquisition module is used for acquiring an elbow key point included angle and a hip key point included angle based on the bone key point to be identified;
the second detection parameter acquisition module is used for establishing a detection horizontal plane based on the bone key points to be identified and acquiring an included angle of the foot key points based on the bone key points to be identified and the detection horizontal plane;
an action non-start judging module, configured to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in the current original frame image, and determine that an action state identifier of the tester is that an action is not started when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
an action starting judging module, configured to, when the action state identifier indicates that an action is not started, continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in a next original frame image, and when the elbow key point included angle is within a first elbow included angle threshold value and a second elbow included angle threshold value range, and the hip key point included angle is within a first hip included angle threshold value and a second hip included angle threshold value range, and meanwhile, the foot key point included angle is within a first foot included angle threshold value and a second foot included angle threshold value range, determine that the action state identifier of the tester is an action start;
an action ending judging module, configured to continue to judge an elbow key point included angle, a hip key point included angle, and a foot key point included angle in a next original frame image when the action state identifier indicates that an action starts, and determine that the action state identifier of the tester is an action end when the elbow key point included angle is not within a first elbow included angle threshold value and a second elbow included angle threshold value range, or the hip key point included angle is not within a first hip included angle threshold value and a second hip included angle threshold value range, or the foot key point included angle is not within a first foot included angle threshold value and a second foot included angle threshold value range;
the actual action duration calculation module is used for taking the moment when the action state is marked as action start moment when the action state is marked as action end, taking the moment when the action state is marked as action end moment, and acquiring actual action duration based on the action start moment and the action end moment;
and the actual action duration scoring module is used for scoring the actual action duration based on a scoring standard and acquiring an action score corresponding to the actual action duration.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the human keypoint-based plate support detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the human keypoint-based slab support detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010377362.8A CN111275031B (en) | 2020-05-07 | 2020-05-07 | Flat plate support detection method, device, equipment and medium based on human body key points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010377362.8A CN111275031B (en) | 2020-05-07 | 2020-05-07 | Flat plate support detection method, device, equipment and medium based on human body key points |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111275031A true CN111275031A (en) | 2020-06-12 |
| CN111275031B CN111275031B (en) | 2020-09-08 |
Family
ID=71004089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010377362.8A Active CN111275031B (en) | 2020-05-07 | 2020-05-07 | Flat plate support detection method, device, equipment and medium based on human body key points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111275031B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560817A (en) * | 2021-02-22 | 2021-03-26 | 西南交通大学 | Human body action recognition method and device, electronic equipment and storage medium |
| CN112973097A (en) * | 2021-03-18 | 2021-06-18 | 黄森 | Detection method and device for flat plate support |
| CN113065474A (en) * | 2021-04-07 | 2021-07-02 | 泰豪软件股份有限公司 | Behavior recognition method and device and computer equipment |
| CN113505752A (en) * | 2021-07-29 | 2021-10-15 | 中移（杭州）信息技术有限公司 | Fall detection method, device, equipment and computer readable storage medium |
| CN114011026A (en) * | 2021-10-29 | 2022-02-08 | 北京林业大学 | Non-contact physical ability test system and method |
| CN114191803A (en) * | 2021-12-08 | 2022-03-18 | 上海影谱科技有限公司 | Method and device for judging whether flat plate supporting posture is standard or not based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964047A (en) * | 2009-07-22 | 2011-02-02 | 深圳泰山在线科技有限公司 | Multiple trace point-based human body action recognition method |
| CN109200562A (en) * | 2017-06-29 | 2019-01-15 | 深圳泰山体育科技股份有限公司 | Body-sensing yoga realization method and system |
| CN109621332A (en) * | 2018-12-29 | 2019-04-16 | 北京卡路里信息技术有限公司 | A kind of attribute determining method, device, equipment and the storage medium of body-building movement |
| CN110490173A (en) * | 2019-08-28 | 2019-11-22 | 深圳市数字星河科技有限公司 | A kind of intelligent behaviour scoring system based on 3D body-sensing model |
| CN110941990A (en) * | 2019-10-22 | 2020-03-31 | 泰康保险集团股份有限公司 | Method and device for evaluating human body actions based on skeleton key points |
| CN111104816A (en) * | 2018-10-25 | 2020-05-05 | 杭州海康威视数字技术股份有限公司 | Target object posture recognition method and device and camera |
-
2020
- 2020-05-07 CN CN202010377362.8A patent/CN111275031B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964047A (en) * | 2009-07-22 | 2011-02-02 | 深圳泰山在线科技有限公司 | Multiple trace point-based human body action recognition method |
| CN109200562A (en) * | 2017-06-29 | 2019-01-15 | 深圳泰山体育科技股份有限公司 | Body-sensing yoga realization method and system |
| CN111104816A (en) * | 2018-10-25 | 2020-05-05 | 杭州海康威视数字技术股份有限公司 | Target object posture recognition method and device and camera |
| CN109621332A (en) * | 2018-12-29 | 2019-04-16 | 北京卡路里信息技术有限公司 | A kind of attribute determining method, device, equipment and the storage medium of body-building movement |
| CN110490173A (en) * | 2019-08-28 | 2019-11-22 | 深圳市数字星河科技有限公司 | A kind of intelligent behaviour scoring system based on 3D body-sensing model |
| CN110941990A (en) * | 2019-10-22 | 2020-03-31 | 泰康保险集团股份有限公司 | Method and device for evaluating human body actions based on skeleton key points |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560817A (en) * | 2021-02-22 | 2021-03-26 | 西南交通大学 | Human body action recognition method and device, electronic equipment and storage medium |
| CN112560817B (en) * | 2021-02-22 | 2021-07-06 | 西南交通大学 | Human body action recognition method and device, electronic equipment and storage medium |
| CN112973097A (en) * | 2021-03-18 | 2021-06-18 | 黄森 | Detection method and device for flat plate support |
| CN112973097B (en) * | 2021-03-18 | 2022-06-03 | 黄森 | Detection method and device for flat plate support |
| CN113065474A (en) * | 2021-04-07 | 2021-07-02 | 泰豪软件股份有限公司 | Behavior recognition method and device and computer equipment |
| CN113065474B (en) * | 2021-04-07 | 2023-06-27 | 泰豪软件股份有限公司 | Behavior recognition method and device and computer equipment |
| CN113505752A (en) * | 2021-07-29 | 2021-10-15 | 中移（杭州）信息技术有限公司 | Fall detection method, device, equipment and computer readable storage medium |
| CN113505752B (en) * | 2021-07-29 | 2024-04-23 | 中移（杭州）信息技术有限公司 | Tumble detection method, device, equipment and computer readable storage medium |
| CN114011026A (en) * | 2021-10-29 | 2022-02-08 | 北京林业大学 | Non-contact physical ability test system and method |
| CN114191803A (en) * | 2021-12-08 | 2022-03-18 | 上海影谱科技有限公司 | Method and device for judging whether flat plate supporting posture is standard or not based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111275031B (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111275031B (en) | Flat plate support detection method, device, equipment and medium based on human body key points | |
| CN111275032B (en) | Deep squatting detection method, device, equipment and medium based on human body key points | |
| CN110495889B (en) | Posture evaluation method, electronic device, computer device, and storage medium | |
| CN109472213B (en) | Palm print recognition method and device, computer equipment and storage medium | |
| CN108205654B (en) | Action detection method and device based on video | |
| CN111563487A (en) | Dance scoring method based on gesture recognition model and related equipment | |
| CN111897430B (en) | Application control method, display terminal and computer readable storage medium | |
| CN109063584B (en) | Facial feature point positioning method, device, equipment and medium based on cascade regression | |
| CN112633196A (en) | Human body posture detection method and device and computer equipment | |
| CN110472594A (en) | Method for tracking target, information insertion method and equipment | |
| Kristan et al. | The tenth visual object tracking vot2022 challenge results | |
| US20220139061A1 (en) | Model training method and apparatus, keypoint positioning method and apparatus, device and medium | |
| US20210097268A1 (en) | Image processing method and apparatus, and computer storage medium | |
| CN103785158A (en) | Method and system for motion guidance of motion sensing game | |
| CN111178128A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN111832581A (en) | Lung feature recognition method and device, computer equipment and storage medium | |
| CN112434556A (en) | Pet nose print recognition method and device, computer equipment and storage medium | |
| CN114022512A (en) | Exercise assisting method, apparatus and medium | |
| Goyal et al. | Yoga pose perfection using deep learning: An algorithm to estimate the error in yogic poses | |
| CN115035037A (en) | Limb rehabilitation training method and system based on image processing and multi-feature fusion | |
| CN113191200A (en) | Push-up test counting method, device, equipment and medium | |
| CN113436736A (en) | Rehabilitation assessment method, system, device and storage medium | |
| CN113392741A (en) | Video clip extraction method and device, electronic equipment and storage medium | |
| CN117173337A (en) | Method, system, equipment and medium for updating virtual fitting model | |
| CN112257642B (en) | Human body continuous motion similarity evaluation method and evaluation device |
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 |