CN109919132A - A kind of pedestrian's tumble recognition methods based on skeleton detection - Google Patents
A kind of pedestrian's tumble recognition methods based on skeleton detection Download PDFInfo
- Publication number
- CN109919132A CN109919132A CN201910222523.3A CN201910222523A CN109919132A CN 109919132 A CN109919132 A CN 109919132A CN 201910222523 A CN201910222523 A CN 201910222523A CN 109919132 A CN109919132 A CN 109919132A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- tumble
- coordinate
- human body
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
A kind of pedestrian's tumble recognition methods based on skeleton detection, comprising the following steps: S1 obtains monitoring area image using camera；S2 is split image and obtains pedestrian's human region image, and detects and obtain pedestrian's framework characteristic point distributed intelligence；S3 analyzes the distributed intelligence of pedestrian's framework characteristic point, extracts the body joint point coordinate of pedestrian's human body key position, obtains pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount according to body joint point coordinate, key position is preset position on human body；S4 establishes fall detection model according to pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount；S5 determines that the posture of pedestrian includes normal walking, falls using posture of the fall detection model to pedestrian, realizes that the detection to pedestrian's posture identifies according to judgement result.The present invention pedestrian's abnormal conditions such as fall can improve the monitoring capability of pedestrains safety event in combination with early warning system in active detecting monitor video.
Description
Technical field
The present invention relates to field of machine vision, and in particular to it is a kind of by combination features judge based on skeleton detection
Pedestrian's tumble recognition methods.
Background technique
In recent years, China human mortality Aging Problem is on the rise.Old man's quantity increases year by year, and falling is always to perplex always
One of big problem of the one of people.Falls Among Old People incidence is high, and problem is often very serious, this has become one of current era sternly
The medical care problem and social concern of weight.By scientific and effective method detect Falls Among Old People, monitor video position tumble position from
And reduce the time that old man is given treatment to.Using the feature of tumble behavior, distinguished with behavior common in life.However it is right at present
Accurate model can not be provided in the research of Falls Among Old People behavior, is had for the identification fallen with some other similar movement behavior
More serious issue of false assessments.
Currently, for tumble behavior detection method there are mainly two types of.One is the tumble inspections based on wearable sensor
Survey technology；It is another then be the detection technique based on video.Fall detection technology accuracy based on wearable sensor is high, but
It is that cost is excessively high, and dresses uncomfortable.The detection technique of tumble based on video is extracted using one or more cameras
Human body contour outline motion feature identified, but the influence of intensity of illumination and observation visual angle is susceptible to, so discrimination
It is very low.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of pedestrian's tumble identification sides detected based on skeleton
Method.
In order to solve the above-mentioned technical problem, the present invention takes following technical scheme:
A kind of pedestrian's tumble recognition methods based on skeleton detection, comprising the following steps:
S1 obtains monitoring area image using camera；
S2 is split image and obtains pedestrian's human region image, and detects and obtain pedestrian's framework characteristic point distribution letter
Breath；
S3 analyzes the distributed intelligence of pedestrian's framework characteristic point, the body joint point coordinate of pedestrian's human body key position is extracted, according to pass
Node coordinate obtains pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount, key position include left eye, right eye,
Left ear, auris dextra, mouth, at chest neck, left shoulder, left elbow, left hand, right shoulder, right elbow, the right hand, left hip, left knee, left foot, right hip, right knee
And right crus of diaphragm；
S4 establishes fall detection model according to pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount；
S5 determines that the posture of pedestrian includes normal walking, falls using posture of the fall detection model to pedestrian,
Realize that the detection to pedestrian's posture identifies according to judgement result.
The step S2, which is still further comprised, establishes pedestrian's tumble identification image coordinate system:
The top left co-ordinate of the monitoring area image obtained using camera is coordinate origin (0,0), to the right along image level
Direction is positive direction of the x-axis, is positive direction of the y-axis along image vertically downward direction；
In conjunction with current frame image acquisition time t and image coordinate (x, y), formed continuous videos space-time characteristic coordinate system (x,
Y, t), by the point distributed intelligence of pedestrian's framework characteristic and association in time, form framework characteristic point Spatio-temporal Data collection.
The fall detection model has following tumble decision condition:
Wherein i is pedestrian's framework characteristic point number, and t is current frame image acquisition time, yi(t) be frame time t when pedestrian
The Y axis coordinate of framework characteristic point i,For human body perpendicular bisector deviation angle, ktFor the inclined slope of human body perpendicular bisector, ∈tFor frame
The human body length variation range that camera captures when time t, δ is pre-set length threshold, if meeting decision condition 1 or determining item
Part 2 is then determined as doubtful tumble.
The fall detection model includes following tumble determination method:
Location of general gravity and human body lower limbs geometric center position are found, two o'clock co-ordinate position information principium identification pedestrian is passed through
Doubtful tumble situation, position of human center coordinate are as follows:
Human body lower limbs geometric center position coordinates are as follows:
xi(t) when being frame time t pedestrian's framework characteristic point i X axis coordinate, if Pf(t) X-coordinate is greater than Pl(t) X
Coordinate, ifThen it is determined as doubtful tumble.
The fall detection model further includes following tumble determination method:
Using the line at midpoint between the left shoulder of human body, right shoulder and left hip, right hip as the perpendicular bisector of pedestrian's human body, and detect
Angle between the perpendicular bisector and groundComparison threshold value is set, the relationship between angle and comparison threshold value is judged, if angle
More than or equal to comparison threshold value, then it is determined as doubtful tumble；
Angle formulae between the perpendicular bisector and ground of human body are as follows:
Wherein ktIt is found out by left shoulder, right shoulder, left hip, right hip this 4 artis position coordinates, specific formula are as follows:
Wherein i=5,6,11,12 respectively indicate the artis number of right shoulder, left shoulder, left hip, right hip, ifOrThen it is determined as doubtful tumble, wherein α, β are the comparison threshold value of setting.
The angle when between human body perpendicular bisector and groundWhen, Δ is setting
Angle value calculates pedestrian's human skeleton height in image, calculates camera and joint of head point is formed by pedestrian's inverted image distance:
Wherein HtFor the distance between joint of head point and foot's artis, d is camera to the height on ground, and w is human body
Horizontal distance between camera, HtCalculation formula are as follows:
Wherein xhWith xfFor the x coordinate of joint of head point and foot's artis, yhWith yfFor joint of head point and foot joint
The y-coordinate of point, if ∈t=Ht-λt, it may be assumed that
If ∈t> δ is then determined as doubtful tumble.
During the acquisition monitoring area image, if in t1Moment starts to detect to meet the judgement of doubtful tumble
Condition reads continuous several frames to t2Until moment, and the decision condition whether each frame meets doubtful tumble is detected, if full
The frame number of the doubtful tumble of foot like number of falls threshold value, then is judged to falling greater than setting, formula are as follows:
Wherein K is moment t1To t2Detecting the frame number of tumble, N is the doubtful number of falls threshold value of setting, if μ < 0,
It is judged to falling.
In the fall detection model of the foundation, the priority level of decision condition 1 is higher than decision condition 2, is sentenced first
The judgement of fixed condition 1, the calculating if meeting decision condition 1 without decision condition 2 carry out if being unsatisfactory for decision condition 1
The calculating of decision condition 2.
The present invention can monitor pedestrian in real time, and identify to pedestrian movement's posture, can quickly, be accurately detected pedestrian
It falls.It is especially adapted for use in the Indoor Monitoring System of old man, it is long-range by being sent to when acquisition data-analysis and distinguishing fructufy
Terminal, providing convenient to guardian is also that old man's life security provides safeguard.
Detailed description of the invention
Fig. 1 is processing method flow chart of the present invention；
Fig. 2 is human skeleton structure chart；
Fig. 3 is tumble schematic diagram；
Fig. 4 is body perpendicular bisector structure chart；
Fig. 5 is camera and position of human body information relationship schematic diagram.
Specific embodiment
To further understand the features of the present invention, technological means and specific purposes achieved, function, below with reference to
The present invention is described in further detail with specific embodiment for attached drawing.
It is including following present invention discloses a kind of pedestrian's tumble recognition methods based on skeleton detection as shown in attached drawing 1-5
Step:
S1 obtains monitoring area image using camera.The camera type and without concrete restriction used, meets camera function i.e.
Can, the higher camera of preferred pixel.
S2 is split image and obtains pedestrian's human region image, and detects and obtain pedestrian's framework characteristic point distribution letter
Breath.
S3 analyzes the distributed intelligence of pedestrian's framework characteristic point, the body joint point coordinate of pedestrian's human body key position is extracted, according to pass
Node coordinate obtains pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount, key position include left eye, right eye,
Left ear, auris dextra, mouth, at chest neck, left shoulder, left elbow, left hand, right shoulder, right elbow, the right hand, left hip, left knee, left foot, right hip, right knee
And right crus of diaphragm.Wherein, it is illustrated in figure 2 the human skeleton information for obtaining image zooming-out, specifically includes 18 artis P of human bodyi
(t)={ (xi(t), yi(t)) | i=0,1,2 ..., 17 }, structured features joint dot position information is by this 18 key point groups
At, corresponding label be respectively left eye 1, right eye 2, left ear 3, auris dextra 4, mouth 0,17, left shoulder 6 at chest neck, left elbow 8, left hand 10,
Right shoulder 5, right elbow 7, the right hand 9, left hip 11, left knee 13, left foot 15, right hip 12, right knee 14 and right crus of diaphragm 16.Human skeleton information is by rolling up
Product neural network detects to obtain, and estimates that AlphaPose method establishes skeleton pattern by human body attitude.It is examined by above method
The human skeleton model measured has the advantages that not to be illuminated by the light condition and blocks influence, provides for the further implementation of this method
Reliable basis.
S4 establishes fall detection model according to pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount
S5 determines that the posture of pedestrian includes normal walking, falls using posture of the fall detection model to pedestrian,
Realize that the detection to pedestrian's posture identifies according to judgement result.
The fall detection model has following tumble decision condition:
Wherein i is pedestrian's framework characteristic point number, and t is current frame image acquisition time, yi(t) be frame time t when pedestrian
The Y axis coordinate of framework characteristic point i,For human body perpendicular bisector deviation angle, ktFor the inclined slope of human body perpendicular bisector, ∈tFor frame
The human body length variation range that camera captures when time t, δ is pre-set length threshold, if meeting decision condition 1 or determining item
Part 2 is then determined as doubtful tumble.In addition, the priority level of decision condition 1 is higher than decision condition 2, decision condition 1 is carried out first
Judgement, the calculating if meeting decision condition 1 without decision condition 2 carries out judgement item if being unsatisfactory for decision condition 1
The calculating of part 2.
As further embodiment, the fall detection model includes following tumble determination method:
(1) pedestrian's tumble identification image coordinate system is established: with the top left co-ordinate for the monitoring area image that camera obtains
It is positive direction of the x-axis along image level right direction for coordinate origin (0,0), is positive direction of the y-axis along image vertically downward direction.
(2) current frame image acquisition time t and image coordinate (x, y) are combined, continuous videos space-time characteristic coordinate system is formed
The point distributed intelligence of pedestrian's framework characteristic and association in time are formed framework characteristic point Spatio-temporal Data collection by (x, y, t).
(3) location of general gravity and human body lower limbs geometric center position are found, two o'clock co-ordinate position information principium identification is passed through
The doubtful tumble situation of pedestrian, position of human center coordinate are as follows:
Human body lower limbs geometric center position coordinates are as follows:
xi(t) when being frame time t pedestrian's framework characteristic point i X axis coordinate, if Pf(t) X-coordinate is greater than Pl(t) X
Coordinate, ifThen it is determined as doubtful tumble；IfIt is less than or equal toThen after
Continuous following (4), (5) step carry out judging tumble situation.It is illustrated in figure 3 tumble schematic diagram, in monitoring image, normal stand
Or position of human center is in the top of lower limb geometric center position in the case of walking, so when pedestrian's position of human center in image
Y-coordinate if it is greater than the y-coordinate of pedestrian's human body lower limbs geometric center, i.e., position of human center is in lower limb geometric center position
Lower section, it is determined that doubtful tumble.
(4) as shown in Fig. 4, using the line at midpoint between the left shoulder of human body, right shoulder and left hip, right hip as pedestrian's human body
Perpendicular bisector AB, and detect the angle between the perpendicular bisector and groundSet comparison threshold value, judge angle and comparison threshold value it
Between relationship, if angle be more than or equal to comparison threshold value, be determined as doubtful tumble；If angle is less than comparison threshold value, for
Normal walking.
Angle formulae between the perpendicular bisector and ground of human body are as follows:
Wherein ktIt is found out by left shoulder, right shoulder, left hip, right hip this 4 artis position coordinates, specific formula are as follows:
Wherein i=5,6,11,12 respectively indicate the artis number of right shoulder, left shoulder, left hip, right hip, ifOrThen it is determined as doubtful tumble, wherein α, β are the comparison threshold value of setting.If horizontal direction is 0 °, when people is in standing appearance
It is 90 ° when state, angled relationships meet When, i.e.,OrThen it is determined as doubtful
It falls.
The angle when between human body perpendicular bisector and groundWhen, Δ is setting
Angle value calculates pedestrian's human skeleton height in image, calculates camera and joint of head point is formed by pedestrian's inverted image distance:
Wherein HtFor the distance between joint of head point and foot's artis, d is camera to the height on ground, and w is human body
Horizontal distance between camera, HtCalculation formula are as follows:
Wherein xhWith xfFor the x coordinate of joint of head point and foot's artis, yhWith yfFor joint of head point and foot joint
The y-coordinate of point, if ∈t=Ht-λt, it may be assumed that
If ∈t> δ is then determined as doubtful tumble.
During the acquisition monitoring area image, if in t1Moment starts to detect to meet the judgement of doubtful tumble
Condition reads continuous several frames to t2Until moment, and the decision condition whether each frame meets doubtful tumble is detected, if full
The frame number of the doubtful tumble of foot like number of falls threshold value, then is judged to falling greater than setting, formula are as follows:
Wherein K is moment t1To t2Detecting the frame number of tumble, N is the doubtful number of falls threshold value of setting, if μ < 0,
It is judged to falling.Due to the complexity of human body motion feature, such as the generation for the behaviors such as squat down and tie the shoelace, sit down and lie down, it is
System solves this problem by above method there may be judging by accident.
It should be noted that these are only the preferred embodiment of the present invention, it is not intended to restrict the invention, although ginseng
According to embodiment, invention is explained in detail, for those skilled in the art, still can be to aforementioned reality
Technical solution documented by example is applied to modify or equivalent replacement of some of the technical features, but it is all in this hair
Within bright spirit and principle, any modification, equivalent replacement, improvement and so on should be included in protection scope of the present invention
Within.
Claims (8)
1. a kind of pedestrian's tumble recognition methods based on skeleton detection, comprising the following steps:
S1 obtains monitoring area image using camera；
S2 is split image and obtains pedestrian's human region image, and detects and obtain pedestrian's framework characteristic point distributed intelligence；
S3 analyzes the distributed intelligence of pedestrian's framework characteristic point, the body joint point coordinate of pedestrian's human body key position is extracted, according to artis
Coordinate obtains pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount, and key position includes left eye, right eye, a left side
Ear, auris dextra, mouth, at chest neck, left shoulder, left elbow, left hand, right shoulder, right elbow, the right hand, left hip, left knee, left foot, right hip, right knee and
Right crus of diaphragm；
S4 establishes fall detection model according to pedestrian's human joint points spatial position feature and pedestrian's attitude geometry amount；
S5 determines that the posture of pedestrian includes normal walking, falls using posture of the fall detection model to pedestrian, according to
Determine that result realizes that the detection to pedestrian's posture identifies.
2. pedestrian's tumble recognition methods according to claim 1 based on skeleton detection, which is characterized in that the step S2
It still further comprises and establishes pedestrian's tumble identification image coordinate system:
The top left co-ordinate of the monitoring area image obtained using camera is coordinate origin (0,0), along image level right direction
It is positive direction of the y-axis along image vertically downward direction for positive direction of the x-axis；
In conjunction with current frame image acquisition time t and image coordinate (x, y), formed continuous videos space-time characteristic coordinate system (x, y, t),
By the point distributed intelligence of pedestrian's framework characteristic and association in time, framework characteristic point Spatio-temporal Data collection is formed.
3. pedestrian's tumble recognition methods according to claim 2 based on skeleton detection, which is characterized in that the tumble inspection
Surveying model has following tumble decision condition:
Wherein i is pedestrian's framework characteristic point number, and t is current frame image acquisition time, yi(t) pedestrian skeleton is special when being frame time t
The Y axis coordinate of point i is levied,For human body perpendicular bisector deviation angle, ktFor the inclined slope of human body perpendicular bisector, ∈tWhen for frame time t
The human body length variation range that camera captures, δ is pre-set length threshold, if meeting decision condition 1 or decision condition 2,
It is determined as doubtful tumble.
4. pedestrian's tumble recognition methods according to claim 3 based on skeleton detection, which is characterized in that the tumble inspection
Surveying model includes following tumble determination method:
Location of general gravity and human body lower limbs geometric center position are found, co-ordinate position information principium identification pedestrian is doubtful by two o'clock
Tumble situation, position of human center coordinate are as follows:
Human body lower limbs geometric center position coordinates are as follows:
xi(t) when being frame time t pedestrian's framework characteristic point i X axis coordinate, if Pf(t) X-coordinate is greater than Pl(t) X-coordinate,
IfThen it is determined as doubtful tumble.
5. pedestrian's tumble recognition methods according to claim 4 based on skeleton detection, which is characterized in that the tumble inspection
Surveying model further includes following tumble determination method:
Using the line at midpoint between the left shoulder of human body, right shoulder and left hip, right hip as the perpendicular bisector of pedestrian's human body, and detect in this
Angle between vertical line and groundComparison threshold value is set, the relationship between angle and comparison threshold value is judged, if angle is greater than
Equal to comparison threshold value, then it is determined as doubtful tumble；
Angle formulae between the perpendicular bisector and ground of human body are as follows:
Wherein ktIt is found out by left shoulder, right shoulder, left hip, right hip this 4 artis position coordinates, specific formula are as follows:
Wherein i=5,6,11,12 respectively indicate the artis number of right shoulder, left shoulder, left hip, right hip, ifOrThen it is determined as doubtful tumble, wherein α, β are the comparison threshold value of setting.
6. pedestrian's tumble recognition methods according to claim 5 based on skeleton detection, which is characterized in that described to work as human body
Angle between perpendicular bisector and groundWhen, Δ is set angle angle value, is calculated in image
Pedestrian's human skeleton height calculates camera and joint of head point is formed by pedestrian's inverted image distance:
Wherein HtFor the distance between joint of head point and foot's artis, d is height of the camera to ground, and w is human body and camera
Between horizontal distance, HtCalculation formula are as follows:
Wherein xhWith xfFor the x coordinate of joint of head point and foot's artis, yhWith yfFor the y of joint of head point and foot's artis
Coordinate, if ∈t=Ht-λt, it may be assumed that
If ∈t> δ is then determined as doubtful tumble.
7. pedestrian's tumble recognition methods according to claim 6 based on skeleton detection, which is characterized in that the acquisition prison
During controlling area image, if in t1Moment starts to detect to meet the decision condition of doubtful tumble, if reading continuous
Dry frame is to t2It until moment, and detects each frame and whether meets the decision condition of doubtful tumble, if meeting the frame number of doubtful tumble
Greater than setting like number of falls threshold value, then it is judged to falling, formula are as follows:
Wherein K is moment t1To t2Detect that the frame number of tumble, N are that the doubtful number of falls threshold value of setting determines if μ < 0
To fall.
8. a kind of pedestrian's tumble recognition methods based on skeleton detection according to claim 7, which is characterized in that described to build
In vertical fall detection model, the priority level of decision condition 1 is higher than decision condition 2, carries out the judgement of decision condition 1 first,
Calculating if meeting decision condition 1 without decision condition 2 carries out the meter of decision condition 2 if being unsatisfactory for decision condition 1
It calculates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910222523.3A CN109919132B (en) | 2019-03-22 | 2019-03-22 | Pedestrian falling identification method based on skeleton detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910222523.3A CN109919132B (en) | 2019-03-22 | 2019-03-22 | Pedestrian falling identification method based on skeleton detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919132A true CN109919132A (en) | 2019-06-21 |
| CN109919132B CN109919132B (en) | 2021-04-23 |
Family
ID=66966467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910222523.3A Active CN109919132B (en) | 2019-03-22 | 2019-03-22 | Pedestrian falling identification method based on skeleton detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919132B (en) |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287923A (en) * | 2019-06-29 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Human body attitude acquisition methods, device, computer equipment and storage medium |
| CN110378244A (en) * | 2019-05-31 | 2019-10-25 | 曹凯 | The detection method and device of abnormal posture |
| CN110458061A (en) * | 2019-07-30 | 2019-11-15 | 四川工商学院 | A kind of method and company robot of identification Falls in Old People |
| CN110490080A (en) * | 2019-07-22 | 2019-11-22 | 西安理工大学 | A kind of human body tumble method of discrimination based on image |
| CN110490070A (en) * | 2019-07-12 | 2019-11-22 | 浙江省北大信息技术高等研究院 | A kind of fall detection method based on human body attitude estimation |
| CN110477925A (en) * | 2019-08-23 | 2019-11-22 | 广东省智能制造研究所 | A kind of fall detection for home for the aged old man and method for early warning and system |
| CN110532966A (en) * | 2019-08-30 | 2019-12-03 | 深兰科技（上海）有限公司 | A kind of method and apparatus carrying out tumble identification based on disaggregated model |
| CN110598536A (en) * | 2019-07-31 | 2019-12-20 | 杭州连帆科技有限公司 | Falling detection method and system based on human skeleton motion model |
| CN110688969A (en) * | 2019-09-30 | 2020-01-14 | 上海依图网络科技有限公司 | Video frame human behavior identification method |
| CN111046749A (en) * | 2019-11-25 | 2020-04-21 | 西安建筑科技大学 | Human body falling behavior detection method based on depth data |
| CN111179281A (en) * | 2019-12-24 | 2020-05-19 | 广东省智能制造研究所 | Human body image extraction method and human body action video extraction method |
| CN111191511A (en) * | 2019-12-03 | 2020-05-22 | 北京联合大学 | Method and system for identifying dynamic real-time behaviors of prisons |
| CN111243229A (en) * | 2019-12-31 | 2020-06-05 | 浙江大学 | Old people falling risk assessment method and system |
| CN111460908A (en) * | 2020-03-05 | 2020-07-28 | 中国地质大学（武汉） | Human body tumbling identification method and system based on OpenPose |
| CN111582158A (en) * | 2020-05-07 | 2020-08-25 | 济南浪潮高新科技投资发展有限公司 | Tumbling detection method based on human body posture estimation |
| CN111783702A (en) * | 2020-07-20 | 2020-10-16 | 杭州叙简科技股份有限公司 | Efficient pedestrian tumble detection method based on image enhancement algorithm and human body key point positioning |
| CN111881898A (en) * | 2020-09-27 | 2020-11-03 | 西南交通大学 | Human body posture detection method based on monocular RGB image |
| CN111931733A (en) * | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN111967307A (en) * | 2020-07-02 | 2020-11-20 | 广东技术师范大学 | Target exception handling method and device, computer equipment and storage medium |
| CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
| CN112036299A (en) * | 2020-08-31 | 2020-12-04 | 山东科技大学 | Examination cheating behavior detection method and system under standard examination room environment |
| CN112120703A (en) * | 2019-06-25 | 2020-12-25 | 株式会社日立制作所 | Fall risk assessment method and device |
| CN112164091A (en) * | 2020-08-25 | 2021-01-01 | 南京邮电大学 | Mobile device human body pose estimation method based on three-dimensional skeleton extraction |
| CN112287758A (en) * | 2020-09-26 | 2021-01-29 | 浙江汉德瑞智能科技有限公司 | Climbing identification method based on key point detection |
| CN112287759A (en) * | 2020-09-26 | 2021-01-29 | 浙江汉德瑞智能科技有限公司 | Tumble detection method based on key points |
| CN112686211A (en) * | 2021-01-25 | 2021-04-20 | 广东工业大学 | Fall detection method and device based on attitude estimation |
| CN112699706A (en) * | 2019-10-22 | 2021-04-23 | 广州弘度信息科技有限公司 | Fall detection method, system and storage medium |
| CN112749642A (en) * | 2020-12-30 | 2021-05-04 | 苏州涟漪信息科技有限公司 | Method and device for identifying falling |
| CN112766129A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Power grid worker behavior real-time monitoring method and device |
| CN112861686A (en) * | 2021-02-01 | 2021-05-28 | 内蒙古大学 | SVM-based image target detection method |
| CN112906599A (en) * | 2021-03-04 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Gait-based personnel identity identification method and device and electronic equipment |
| CN112907892A (en) * | 2021-01-28 | 2021-06-04 | 上海电机学院 | Human body falling alarm method based on multiple views |
| CN112906548A (en) * | 2021-02-07 | 2021-06-04 | 广东省科学院智能制造研究所 | Fall detection method and system based on edge calculation |
| CN112949569A (en) * | 2021-03-25 | 2021-06-11 | 南京邮电大学 | Effective extraction method of human body posture points for tumble analysis |
| CN112966597A (en) * | 2021-03-04 | 2021-06-15 | 山东云缦智能科技有限公司 | Human motion action counting method based on skeleton key points |
| CN113204989A (en) * | 2021-03-19 | 2021-08-03 | 南京邮电大学 | Human body posture space-time feature extraction method for tumble analysis |
| CN113450538A (en) * | 2021-06-28 | 2021-09-28 | 杭州电子科技大学 | Warning system based on painful expression discernment and fall action detection |
| CN113470310A (en) * | 2020-04-26 | 2021-10-01 | 海信集团有限公司 | Intelligent household equipment and anti-falling early warning method |
| CN113537005A (en) * | 2021-07-02 | 2021-10-22 | 福州大学 | On-line examination student behavior analysis method based on attitude estimation |
| WO2021227874A1 (en) * | 2020-05-11 | 2021-11-18 | 杭州萤石软件有限公司 | Falling behaviour detection method and device |
| CN113705274A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Climbing behavior detection method and device, electronic equipment and storage medium |
| CN113792700A (en) * | 2021-09-24 | 2021-12-14 | 成都新潮传媒集团有限公司 | Storage battery car boxing detection method and device, computer equipment and storage medium |
| CN113822250A (en) * | 2021-11-23 | 2021-12-21 | 中船（浙江）海洋科技有限公司 | Ship driving abnormal behavior detection method |
| CN114694252A (en) * | 2022-03-30 | 2022-07-01 | 电子科技大学 | Old people falling risk prediction method |
| KR20220106580A (en) * | 2021-01-22 | 2022-07-29 | 동의대학교 산학협력단 | Method and System for detecting fall situation by using deep learning model |
| CN115273243A (en) * | 2022-09-27 | 2022-11-01 | 深圳比特微电子科技有限公司 | Fall detection method and device, electronic equipment and computer readable storage medium |
| CN117278837A (en) * | 2023-11-16 | 2023-12-22 | 新乡天辅电子科技有限公司 | Emergency rescue-oriented imaging equipment control method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598896A (en) * | 2015-02-12 | 2015-05-06 | 南通大学 | Automatic human tumble detecting method based on Kinect skeleton tracking |
| US20150186713A1 (en) * | 2013-12-31 | 2015-07-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for emotion and behavior recognition |
| CN104794463A (en) * | 2015-05-11 | 2015-07-22 | 华东理工大学 | System and method for achieving indoor human body falling detection based on Kinect |
| CN107194967A (en) * | 2017-06-09 | 2017-09-22 | 南昌大学 | Human fall detection method and device based on Kinect depth image |
| CN107220604A (en) * | 2017-05-18 | 2017-09-29 | 清华大学深圳研究生院 | A kind of fall detection method based on video |
| CN107578036A (en) * | 2017-09-28 | 2018-01-12 | 南通大学 | A kind of depth image tumble recognizer based on wavelet moment |
| US20180068545A1 (en) * | 2015-06-01 | 2018-03-08 | Cerner Innovation, Inc. | Method for Determining Whether an Individual Enters a Prescribed Virtual Zone Using Skeletal Tracking and 3D Blob Detection |
| CN108664887A (en) * | 2018-03-20 | 2018-10-16 | 重庆邮电大学 | Prior-warning device and method are fallen down in a kind of virtual reality experience |
| CN108734141A (en) * | 2018-05-28 | 2018-11-02 | 南京邮电大学 | A kind of intelligent carpet tumble method of discrimination based on machine learning |
| CN109389041A (en) * | 2018-09-07 | 2019-02-26 | 南京航空航天大学 | A kind of fall detection method based on joint point feature |
| CN109460702A (en) * | 2018-09-14 | 2019-03-12 | 华南理工大学 | Passenger's abnormal behaviour recognition methods based on human skeleton sequence |
-
2019
- 2019-03-22 CN CN201910222523.3A patent/CN109919132B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186713A1 (en) * | 2013-12-31 | 2015-07-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for emotion and behavior recognition |
| CN104598896A (en) * | 2015-02-12 | 2015-05-06 | 南通大学 | Automatic human tumble detecting method based on Kinect skeleton tracking |
| CN104794463A (en) * | 2015-05-11 | 2015-07-22 | 华东理工大学 | System and method for achieving indoor human body falling detection based on Kinect |
| US20180068545A1 (en) * | 2015-06-01 | 2018-03-08 | Cerner Innovation, Inc. | Method for Determining Whether an Individual Enters a Prescribed Virtual Zone Using Skeletal Tracking and 3D Blob Detection |
| CN107220604A (en) * | 2017-05-18 | 2017-09-29 | 清华大学深圳研究生院 | A kind of fall detection method based on video |
| CN107194967A (en) * | 2017-06-09 | 2017-09-22 | 南昌大学 | Human fall detection method and device based on Kinect depth image |
| CN107578036A (en) * | 2017-09-28 | 2018-01-12 | 南通大学 | A kind of depth image tumble recognizer based on wavelet moment |
| CN108664887A (en) * | 2018-03-20 | 2018-10-16 | 重庆邮电大学 | Prior-warning device and method are fallen down in a kind of virtual reality experience |
| CN108734141A (en) * | 2018-05-28 | 2018-11-02 | 南京邮电大学 | A kind of intelligent carpet tumble method of discrimination based on machine learning |
| CN109389041A (en) * | 2018-09-07 | 2019-02-26 | 南京航空航天大学 | A kind of fall detection method based on joint point feature |
| CN109460702A (en) * | 2018-09-14 | 2019-03-12 | 华南理工大学 | Passenger's abnormal behaviour recognition methods based on human skeleton sequence |
Non-Patent Citations (2)
| Title |
|---|
| CHEN, YL 等: "An Upper Extremity Rehabilitation System Using Efficient Vision-Based Action Identification Techniques", 《APPLIED SCIENCES-BASEL》 * |
| 瞿畅 等: "基于Kinect体感传感器的老年人跌倒自动检测", 《传感技术学报》 * |
Cited By (64)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378244A (en) * | 2019-05-31 | 2019-10-25 | 曹凯 | The detection method and device of abnormal posture |
| CN112120703A (en) * | 2019-06-25 | 2020-12-25 | 株式会社日立制作所 | Fall risk assessment method and device |
| CN110287923B (en) * | 2019-06-29 | 2023-09-15 | 腾讯科技（深圳）有限公司 | Human body posture acquisition method, device, computer equipment and storage medium |
| CN110287923A (en) * | 2019-06-29 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Human body attitude acquisition methods, device, computer equipment and storage medium |
| CN110490070A (en) * | 2019-07-12 | 2019-11-22 | 浙江省北大信息技术高等研究院 | A kind of fall detection method based on human body attitude estimation |
| CN110490080A (en) * | 2019-07-22 | 2019-11-22 | 西安理工大学 | A kind of human body tumble method of discrimination based on image |
| CN110458061B (en) * | 2019-07-30 | 2022-04-05 | 四川工商学院 | Method for identifying old people falling down and accompanying robot |
| CN110458061A (en) * | 2019-07-30 | 2019-11-15 | 四川工商学院 | A kind of method and company robot of identification Falls in Old People |
| CN110598536A (en) * | 2019-07-31 | 2019-12-20 | 杭州连帆科技有限公司 | Falling detection method and system based on human skeleton motion model |
| CN110477925A (en) * | 2019-08-23 | 2019-11-22 | 广东省智能制造研究所 | A kind of fall detection for home for the aged old man and method for early warning and system |
| CN110532966A (en) * | 2019-08-30 | 2019-12-03 | 深兰科技（上海）有限公司 | A kind of method and apparatus carrying out tumble identification based on disaggregated model |
| CN110688969A (en) * | 2019-09-30 | 2020-01-14 | 上海依图网络科技有限公司 | Video frame human behavior identification method |
| CN112699706A (en) * | 2019-10-22 | 2021-04-23 | 广州弘度信息科技有限公司 | Fall detection method, system and storage medium |
| CN111046749A (en) * | 2019-11-25 | 2020-04-21 | 西安建筑科技大学 | Human body falling behavior detection method based on depth data |
| CN111191511A (en) * | 2019-12-03 | 2020-05-22 | 北京联合大学 | Method and system for identifying dynamic real-time behaviors of prisons |
| CN111191511B (en) * | 2019-12-03 | 2023-08-18 | 北京联合大学 | Dynamic real-time behavior recognition method and system for prison |
| CN111179281A (en) * | 2019-12-24 | 2020-05-19 | 广东省智能制造研究所 | Human body image extraction method and human body action video extraction method |
| CN111243229A (en) * | 2019-12-31 | 2020-06-05 | 浙江大学 | Old people falling risk assessment method and system |
| CN111460908A (en) * | 2020-03-05 | 2020-07-28 | 中国地质大学（武汉） | Human body tumbling identification method and system based on OpenPose |
| CN111460908B (en) * | 2020-03-05 | 2023-09-01 | 中国地质大学（武汉） | Human body fall recognition method and system based on OpenPose |
| CN113470310A (en) * | 2020-04-26 | 2021-10-01 | 海信集团有限公司 | Intelligent household equipment and anti-falling early warning method |
| CN111582158A (en) * | 2020-05-07 | 2020-08-25 | 济南浪潮高新科技投资发展有限公司 | Tumbling detection method based on human body posture estimation |
| WO2021227874A1 (en) * | 2020-05-11 | 2021-11-18 | 杭州萤石软件有限公司 | Falling behaviour detection method and device |
| CN113705274A (en) * | 2020-05-20 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Climbing behavior detection method and device, electronic equipment and storage medium |
| CN113705274B (en) * | 2020-05-20 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Climbing behavior detection method and device, electronic equipment and storage medium |
| CN111967307A (en) * | 2020-07-02 | 2020-11-20 | 广东技术师范大学 | Target exception handling method and device, computer equipment and storage medium |
| CN111783702A (en) * | 2020-07-20 | 2020-10-16 | 杭州叙简科技股份有限公司 | Efficient pedestrian tumble detection method based on image enhancement algorithm and human body key point positioning |
| CN112164091A (en) * | 2020-08-25 | 2021-01-01 | 南京邮电大学 | Mobile device human body pose estimation method based on three-dimensional skeleton extraction |
| CN112164091B (en) * | 2020-08-25 | 2022-08-16 | 南京邮电大学 | Mobile device human body pose estimation method based on three-dimensional skeleton extraction |
| CN112036299A (en) * | 2020-08-31 | 2020-12-04 | 山东科技大学 | Examination cheating behavior detection method and system under standard examination room environment |
| CN112036299B (en) * | 2020-08-31 | 2022-12-13 | 山东科技大学 | Examination cheating behavior detection method and system under standard examination room environment |
| CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
| CN111931733A (en) * | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN112287758A (en) * | 2020-09-26 | 2021-01-29 | 浙江汉德瑞智能科技有限公司 | Climbing identification method based on key point detection |
| CN112287759A (en) * | 2020-09-26 | 2021-01-29 | 浙江汉德瑞智能科技有限公司 | Tumble detection method based on key points |
| CN112287758B (en) * | 2020-09-26 | 2022-08-26 | 浙江汉德瑞智能科技有限公司 | Climbing identification method based on key point detection |
| CN111881898B (en) * | 2020-09-27 | 2021-02-26 | 西南交通大学 | Human body posture detection method based on monocular RGB image |
| CN111881898A (en) * | 2020-09-27 | 2020-11-03 | 西南交通大学 | Human body posture detection method based on monocular RGB image |
| CN112749642A (en) * | 2020-12-30 | 2021-05-04 | 苏州涟漪信息科技有限公司 | Method and device for identifying falling |
| CN112766129A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Power grid worker behavior real-time monitoring method and device |
| KR102558054B1 (en) * | 2021-01-22 | 2023-07-19 | 동의대학교 산학협력단 | Method and System for detecting fall situation by using deep learning model |
| KR20220106580A (en) * | 2021-01-22 | 2022-07-29 | 동의대학교 산학협력단 | Method and System for detecting fall situation by using deep learning model |
| CN112686211A (en) * | 2021-01-25 | 2021-04-20 | 广东工业大学 | Fall detection method and device based on attitude estimation |
| CN112907892A (en) * | 2021-01-28 | 2021-06-04 | 上海电机学院 | Human body falling alarm method based on multiple views |
| CN112861686A (en) * | 2021-02-01 | 2021-05-28 | 内蒙古大学 | SVM-based image target detection method |
| CN112906548A (en) * | 2021-02-07 | 2021-06-04 | 广东省科学院智能制造研究所 | Fall detection method and system based on edge calculation |
| CN112906599A (en) * | 2021-03-04 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Gait-based personnel identity identification method and device and electronic equipment |
| CN112966597A (en) * | 2021-03-04 | 2021-06-15 | 山东云缦智能科技有限公司 | Human motion action counting method based on skeleton key points |
| CN113204989B (en) * | 2021-03-19 | 2022-07-29 | 南京邮电大学 | Human body posture space-time feature extraction method for tumble analysis |
| CN113204989A (en) * | 2021-03-19 | 2021-08-03 | 南京邮电大学 | Human body posture space-time feature extraction method for tumble analysis |
| CN112949569B (en) * | 2021-03-25 | 2022-07-29 | 南京邮电大学 | Falling analysis-oriented human body posture point effective extraction method |
| CN112949569A (en) * | 2021-03-25 | 2021-06-11 | 南京邮电大学 | Effective extraction method of human body posture points for tumble analysis |
| CN113450538A (en) * | 2021-06-28 | 2021-09-28 | 杭州电子科技大学 | Warning system based on painful expression discernment and fall action detection |
| CN113537005A (en) * | 2021-07-02 | 2021-10-22 | 福州大学 | On-line examination student behavior analysis method based on attitude estimation |
| CN113537005B (en) * | 2021-07-02 | 2023-08-11 | 福州大学 | Online examination student behavior analysis method based on attitude estimation |
| CN113792700A (en) * | 2021-09-24 | 2021-12-14 | 成都新潮传媒集团有限公司 | Storage battery car boxing detection method and device, computer equipment and storage medium |
| CN113792700B (en) * | 2021-09-24 | 2024-02-27 | 成都新潮传媒集团有限公司 | Storage battery car in-box detection method and device, computer equipment and storage medium |
| CN113822250A (en) * | 2021-11-23 | 2021-12-21 | 中船（浙江）海洋科技有限公司 | Ship driving abnormal behavior detection method |
| CN114694252B (en) * | 2022-03-30 | 2023-04-28 | 电子科技大学 | Old people falling risk prediction method |
| CN114694252A (en) * | 2022-03-30 | 2022-07-01 | 电子科技大学 | Old people falling risk prediction method |
| CN115273243B (en) * | 2022-09-27 | 2023-03-28 | 深圳比特微电子科技有限公司 | Fall detection method, device, electronic equipment and computer readable storage medium |
| CN115273243A (en) * | 2022-09-27 | 2022-11-01 | 深圳比特微电子科技有限公司 | Fall detection method and device, electronic equipment and computer readable storage medium |
| CN117278837A (en) * | 2023-11-16 | 2023-12-22 | 新乡天辅电子科技有限公司 | Emergency rescue-oriented imaging equipment control method |
| CN117278837B (en) * | 2023-11-16 | 2024-01-26 | 新乡天辅电子科技有限公司 | Emergency rescue-oriented imaging equipment control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919132B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919132A (en) | A kind of pedestrian's tumble recognition methods based on skeleton detection | |
| CN109558865A (en) | A kind of abnormal state detection method to the special caregiver of need based on human body key point | |
| CN104598896B (en) | The falling over of human body automatic testing method followed the trail of based on Kinect skeletons | |
| CN107194967A (en) | Human fall detection method and device based on Kinect depth image | |
| CN109670396A (en) | A kind of interior Falls Among Old People detection method | |
| Li et al. | Pre-impact fall detection based on a modified zero moment point criterion using data from Kinect sensors | |
| CN112287759A (en) | Tumble detection method based on key points | |
| CN110472473A (en) | The method fallen based on people on Attitude estimation detection staircase | |
| CN110706255A (en) | Fall detection method based on self-adaptive following | |
| CN111931733B (en) | Human body posture detection method based on depth camera | |
| CN111783702A (en) | Efficient pedestrian tumble detection method based on image enhancement algorithm and human body key point positioning | |
| CN110598536A (en) | Falling detection method and system based on human skeleton motion model | |
| CN111881898B (en) | Human body posture detection method based on monocular RGB image | |
| CN111144174A (en) | System for identifying falling behavior of old people in video by using neural network and traditional algorithm | |
| KR20140110484A (en) | Risk behavior detection method using image information | |
| CN110046557A (en) | Safety cap, Safe belt detection method based on deep neural network differentiation | |
| CN112115827A (en) | Falling behavior identification method based on human body posture dynamic characteristics | |
| CN112597898B (en) | Real-time step counting-based intelligent identification method and medium for safety state of electric power personnel | |
| CN112597903B (en) | Electric power personnel safety state intelligent identification method and medium based on stride measurement | |
| CN113384267A (en) | Fall real-time detection method, system, terminal equipment and storage medium | |
| JP2021189587A (en) | Display device, display method, and display program | |
| Nizam et al. | Classification of human fall from activities of daily life using joint measurements | |
| Nizam et al. | Development of human fall detection system using joint height, joint velocity, and joint position from depth maps | |
| CN109492613A (en) | A kind of falling over of human body detection system and method with separate space | |
| WO2021225249A1 (en) | Gait analysis system and method |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 510000 13 building, 100 martyrs Road, Yuexiu District, Guangzhou, Guangdong. Patentee after: Institute of intelligent manufacturing, Guangdong Academy of Sciences Address before: 510000 13 building, 100 martyrs Road, Yuexiu District, Guangzhou, Guangdong. Patentee before: GUANGDONG INSTITUTE OF INTELLIGENT MANUFACTURING |
|
| CP01 | Change in the name or title of a patent holder |