CN113392751A - Tumbling detection method based on human body skeleton nodes and related device - Google Patents
Tumbling detection method based on human body skeleton nodes and related device Download PDFInfo
- Publication number
- CN113392751A CN113392751A CN202110648819.9A CN202110648819A CN113392751A CN 113392751 A CN113392751 A CN 113392751A CN 202110648819 A CN202110648819 A CN 202110648819A CN 113392751 A CN113392751 A CN 113392751A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- ground
- human body
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physiology (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a human skeleton node-based fall detection method and a related device, wherein after the position coordinate and the ground equation of a human skeleton node in an image to be detected are obtained, the distance between the human skeleton node and the ground in the image to be detected is obtained based on the position coordinate and the ground equation of the human skeleton node, and finally whether the human body in the image to be detected falls or not is judged based on the distance between the human skeleton node and the ground in the image to be detected, the method is designed based on a conventional strategy method, is favorable for meeting the actual engineering requirements, does not need to design a complicated deep learning model, does not need a large amount of data support, is favorable for reducing the algorithm complexity of the fall detection method based on the human skeleton node, and reduces the time cost of algorithm operation, is favorable for realizing real-time tumble detection.
Description
Technical Field
The application relates to the technical field of computer application, in particular to a human skeleton node-based tumble detection method and a related device.
Background
The detection of human body falls based on images is a new demand that appears with the continuous development of machine vision technology and artificial intelligence technology. The human body falling detection method can be used for detecting the old, the children and the crowd with inconvenient actions in real time so as to avoid accidents, and when the falling event of the old, the children and the crowd with inconvenient actions is detected, the system can give an alarm to bring the attention of accompanying personnel conveniently.
At present, the algorithm complexity of the human body tumble detection method is high, higher requirements are provided for equipment carrying the human body tumble detection method, and how to reduce the algorithm complexity of the human body tumble detection method becomes one of the efforts of related researchers.
Disclosure of Invention
In order to solve the technical problems, the application provides a human body skeleton node-based fall detection method and a related device, so as to achieve the purpose of reducing the algorithm complexity of the human body skeleton node-based fall detection method.
In order to achieve the technical purpose, the embodiment of the application provides the following technical scheme:
a human body skeleton node-based fall detection method comprises the following steps:
acquiring position coordinates of human skeleton nodes in an image to be detected;
acquiring a ground equation of the image to be detected;
acquiring the distance between the human body skeleton node and the ground in the image to be detected based on the position coordinate of the human body skeleton node and the ground equation;
and judging whether the human body in the image to be detected falls down or not based on the distance between the human body skeleton node and the ground in the image to be detected.
Optionally, the obtaining the distance between the human skeleton node and the ground in the image to be detected based on the position coordinate of the human skeleton node and the ground equation includes:
calculating the distance between each human body skeleton node and the ground in the image to be detected according to the position coordinates of the human body skeleton nodes and the ground equation;
putting the distance between a human body skeleton node positioned on a first side of a human body and the ground in the image to be detected into a first distance set;
and putting the distance between the human body skeleton node positioned on the second side of the human body and the ground in the image to be detected into a second distance set.
Optionally, the calculating, according to the position coordinates of the human skeleton nodes and the ground equation, a distance between each human skeleton node and the ground in the image to be detected includes:
substituting the position coordinates of the human body skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human body skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
Optionally, based on the distance between the human skeleton node and the ground in the image to be detected, judging whether the human body in the image to be detected falls down includes:
counting the number of elements smaller than a first preset threshold in the first distance set to obtain a first numerical value;
counting the number of elements smaller than a second preset threshold in the second distance set to obtain a second numerical value;
and judging whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than a preset number threshold, if so, judging that the human body in the image to be detected is in a falling state, and if not, judging that the human body in the image to be detected is not in the falling state.
A fall detection system based on human skeleton nodes includes:
the coordinate acquisition module is used for acquiring the position coordinates of the human skeleton nodes in the image to be detected;
the ground acquisition module is used for acquiring a ground equation of the image to be detected;
the distance acquisition module is used for acquiring the distance between the human body skeleton node and the ground in the image to be detected based on the position coordinate of the human body skeleton node and the ground equation;
and the fall detection module is used for judging whether the human body in the image to be detected falls or not based on the human body skeleton node and the distance between the ground in the image to be detected.
Optionally, the distance obtaining module includes:
the distance calculation unit is used for calculating the distance between each human body skeleton node and the ground in the image to be detected according to the position coordinates of the human body skeleton nodes and the ground equation;
the first set establishing unit is used for putting the distance between the human body skeleton node positioned on the first side of the human body and the ground in the image to be detected into a first distance set;
and the second set establishing unit is used for putting the distance between the human body framework node positioned on the second side of the human body and the ground in the image to be detected into a second distance set.
Optionally, the distance calculation unit is specifically configured to substitute the position coordinates of the human skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
Optionally, the fall detection module comprises:
the first counting unit is used for counting the number of elements smaller than a first preset threshold value in the first distance set to obtain a first numerical value;
a second counting unit, configured to count the number of elements in the second distance set, where the number of elements is smaller than a second preset threshold, so as to obtain a second numerical value;
and the threshold judging unit is used for judging whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than a preset number threshold, if so, judging that the human body in the image to be detected is in a falling state, and if not, judging that the human body in the image to be detected is not in a falling state.
A fall detection system based on human skeleton nodes includes: a memory and a processor; wherein the content of the first and second substances,
the memory is stored with a program code, the processor is used for calling the program code, and the program code is called to execute any one of the human skeleton node-based fall detection methods.
A storage medium having stored therein program code for implementing the steps of the human body skeleton node-based fall detection method of any one of the above.
It can be seen from the above technical solutions that the embodiments of the present application provide a fall detection method based on human skeleton nodes and a related device, wherein after obtaining position coordinates and a ground equation of human skeleton nodes in an image to be detected, the fall detection method based on human skeleton nodes obtains a distance between the human skeleton nodes and the ground in the image to be detected based on the position coordinates of the human skeleton nodes and the ground equation, and finally determines whether a human body in the image to be detected falls based on the distance between the human skeleton nodes and the ground in the image to be detected, the method is designed based on a conventional strategy method, is beneficial to meeting engineering practical requirements, does not need to design a complex deep learning model, does not need to support a large amount of data, and is beneficial to reducing algorithm complexity of the fall detection method based on human skeleton nodes, the time cost of algorithm operation is reduced, and real-time tumble detection is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a fall detection method based on human skeleton nodes according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a fall detection method based on human skeleton nodes according to another embodiment of the present application;
fig. 3 is a schematic flow chart of a fall detection method based on human skeleton nodes according to another embodiment of the present application;
fig. 4 is a schematic structural diagram of a human skeleton node-based fall detection system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a human skeleton node-based fall detection system according to another embodiment of the present application;
fig. 6 is a schematic structural diagram of a fall detection system based on human skeleton nodes according to another embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a fall detection method based on human body skeleton nodes, as shown in fig. 1, the fall detection method based on the human body skeleton nodes comprises the following steps:
s101: and acquiring the position coordinates of the human body skeleton nodes in the image to be detected.
The body skeleton nodes include, but are not limited to, left wrist, left elbow, left crotch, left knee, right wrist, right elbow, right crotch, and right knee.
S102: and acquiring a ground equation of the image to be detected.
The steps S101 and S102 can be implemented by using a device capable of acquiring the node position of the deep 3D human skeleton and the ground equation parameters, such as a motion sensing camera or a body sensor.
The expression of the ground equation may be: ax + By + Cz + D ═ 0; where A, B, C and D represent the coefficients of the ground equation, respectively. x, y, z are depth map 3D position coordinates.
S103: and acquiring the distance between the human body skeleton node and the ground in the image to be detected based on the position coordinate of the human body skeleton node and the ground equation.
S104: and judging whether the human body in the image to be detected falls down or not based on the distance between the human body skeleton node and the ground in the image to be detected.
In step S104, the number of the distances between each human skeleton node and the ground in the image to be detected that are smaller than the set threshold distance may be counted, and fall detection may be implemented by using a small number of principles that comply with the majority, or by using the relationship between the distance between a single human skeleton node and the ground in the image to be detected and the set threshold distance. The present application does not limit this, which is determined by the actual situation.
The following describes feasible implementation processes of each step of the human skeleton node-based fall detection method provided by the embodiment of the application.
Optionally, as shown in fig. 2, the obtaining the distance between the human skeleton node and the ground in the image to be detected based on the position coordinate of the human skeleton node and the ground equation includes:
s1031: and calculating the distance between each human body skeleton node and the ground in the image to be detected according to the position coordinates of the human body skeleton nodes and the ground equation.
S1032: and putting the distance between the human body skeleton node positioned on the first side of the human body and the ground in the image to be detected into a first distance set.
S1033: and putting the distance between the human body skeleton node positioned on the second side of the human body and the ground in the image to be detected into a second distance set.
The first side of the body may be the left side of the body and the second book of bodies may be the right side of the body, for example, body skeleton nodes located on the first side of the body include, but are not limited to, left knee, left wrist, left elbow and left crotch, and body skeleton nodes located on the second book of bodies include, but are not limited to, right knee, right wrist, right elbow and right crotch.
More specifically, the calculating the distance between each human skeleton node and the ground in the image to be detected according to the position coordinates of the human skeleton nodes and the ground equation includes:
substituting the position coordinates of the human body skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human body skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
Optionally, as shown in fig. 3, the determining whether the human body in the image to be detected falls down based on the distance between the human body skeleton node and the ground in the image to be detected includes:
s1041: and counting the number of elements smaller than a first preset threshold value in the first distance set to obtain a first numerical value.
S1042: and counting the number of elements smaller than a second preset threshold value in the second distance set to obtain a second numerical value.
S1043: and judging whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than a preset number threshold, if so, judging that the human body in the image to be detected is in a falling state, and if not, judging that the human body in the image to be detected is not in the falling state.
The value range of the first preset threshold is 0.25 +/-0.05 m, and the value range of the second preset threshold is 0.25 +/-0.05 m. The first preset threshold may be equal to the second preset threshold.
Optionally, the preset number threshold may be an integer greater than or equal to half of the total number of elements in the first distance set (or the second distance set), and less than the total number of elements in the first distance set (or the second distance set). For example, when the total number of elements in the first distance set (or the second distance set) is 4, the value of the preset number threshold may be 2 or 3. The present application does not limit this, which is determined by the actual situation.
The following describes the human body skeleton node-based fall detection system provided in the embodiment of the present application, and the following described human body skeleton node-based fall detection system may be referred to in correspondence with the above described human body skeleton node-based fall detection method.
Correspondingly, the embodiment of the present application provides a fall detection system based on human skeleton node, as shown in fig. 4, includes:
the coordinate acquisition module 100 is used for acquiring position coordinates of human skeleton nodes in an image to be detected;
a ground acquisition module 200, configured to acquire a ground equation of the image to be detected;
a distance obtaining module 300, configured to obtain a distance between the human skeleton node and the ground in the image to be detected based on the position coordinate of the human skeleton node and the ground equation;
and the fall detection module 400 is used for judging whether the human body in the image to be detected falls or not based on the human body skeleton node and the distance between the ground in the image to be detected.
Optionally, as shown in fig. 5, the distance obtaining module 300 includes:
a distance calculating unit 310, configured to calculate a distance between each human skeleton node and the ground in the image to be detected according to the position coordinates of the human skeleton node and the ground equation;
a first set establishing unit 320, configured to put a distance between a human skeleton node located on a first side of a human body and a ground in the image to be detected into a first distance set;
a second set establishing unit 330, configured to put the distance between the human skeleton node located on the second side of the human body and the ground in the image to be detected into a second distance set.
Optionally, the distance calculating unit 310 is specifically configured to substitute the position coordinates of the human skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
Optionally, as shown in fig. 6, the fall detection module 400 includes:
a first statistical unit 410, configured to count the number of elements in the first distance set that is smaller than a first preset threshold to obtain a first numerical value;
a second counting unit 420, configured to count the number of elements in the second distance set that is smaller than a second preset threshold, so as to obtain a second value;
a threshold determining unit 430, configured to determine whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than the preset number threshold, if so, determine that the human body in the image to be detected is in a falling state, and if not, determine that the human body in the image to be detected is not in the falling state.
Correspondingly, this application embodiment still provides a fall detecting system based on human skeleton node, includes: a memory and a processor; wherein the content of the first and second substances,
the memory stores a program code, the processor is used for calling the program code, and the program code is called to execute the human skeleton node-based fall detection method of any embodiment.
Accordingly, an embodiment of the present application further provides a storage medium, in which program codes are stored, and when the program codes are executed, the program codes are used to implement the steps of the human skeleton node-based fall detection method according to any one of the embodiments.
In summary, the embodiments of the present application provide a fall detection method based on human skeleton nodes and a related device, wherein after obtaining position coordinates and a ground equation of human skeleton nodes in an image to be detected, the fall detection method based on human skeleton nodes obtains a distance between the human skeleton nodes and the ground in the image to be detected based on the position coordinates and the ground equation of the human skeleton nodes, and finally determines whether a human body in the image to be detected falls based on the distance between the human skeleton nodes and the ground in the image to be detected, the method is designed based on a conventional strategy method, is beneficial to meeting engineering practical requirements, does not need to design a complex deep learning model, does not need to support a large amount of data, and is beneficial to reducing algorithm complexity of the fall detection method based on human skeleton nodes, the time cost of algorithm operation is reduced, and real-time tumble detection is facilitated.
Features described in the embodiments in the present specification may be replaced with or combined with each other, each embodiment is described with a focus on differences from other embodiments, and the same and similar portions among the embodiments may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A fall detection method based on human body skeleton nodes is characterized by comprising the following steps:
acquiring position coordinates of human skeleton nodes in an image to be detected;
acquiring a ground equation of the image to be detected;
acquiring the distance between the human body skeleton node and the ground in the image to be detected based on the position coordinate of the human body skeleton node and the ground equation;
and judging whether the human body in the image to be detected falls down or not based on the distance between the human body skeleton node and the ground in the image to be detected.
2. The human skeleton node-based fall detection method according to claim 1, wherein the obtaining of the distance between the human skeleton node and the ground in the image to be detected based on the position coordinates of the human skeleton node and the ground equation comprises:
calculating the distance between each human body skeleton node and the ground in the image to be detected according to the position coordinates of the human body skeleton nodes and the ground equation;
putting the distance between a human body skeleton node positioned on a first side of a human body and the ground in the image to be detected into a first distance set;
and putting the distance between the human body skeleton node positioned on the second side of the human body and the ground in the image to be detected into a second distance set.
3. The human skeleton node-based fall detection method according to claim 2, wherein the calculating the distance between each human skeleton node and the ground in the image to be detected according to the position coordinates of the human skeleton nodes and the ground equation comprises:
substituting the position coordinates of the human body skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human body skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
4. The human skeleton node-based fall detection method according to claim 2, wherein the determining whether the human body in the image to be detected falls based on the distance between the human skeleton node and the ground in the image to be detected comprises:
counting the number of elements smaller than a first preset threshold in the first distance set to obtain a first numerical value;
counting the number of elements smaller than a second preset threshold in the second distance set to obtain a second numerical value;
and judging whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than a preset number threshold, if so, judging that the human body in the image to be detected is in a falling state, and if not, judging that the human body in the image to be detected is not in the falling state.
5. A fall detection system based on human skeleton node, its characterized in that includes:
the coordinate acquisition module is used for acquiring the position coordinates of the human skeleton nodes in the image to be detected;
the ground acquisition module is used for acquiring a ground equation of the image to be detected;
the distance acquisition module is used for acquiring the distance between the human body skeleton node and the ground in the image to be detected based on the position coordinate of the human body skeleton node and the ground equation;
and the fall detection module is used for judging whether the human body in the image to be detected falls or not based on the human body skeleton node and the distance between the ground in the image to be detected.
6. The human skeleton node-based fall detection system of claim 5, wherein the distance acquisition module comprises:
the distance calculation unit is used for calculating the distance between each human body skeleton node and the ground in the image to be detected according to the position coordinates of the human body skeleton nodes and the ground equation;
the first set establishing unit is used for putting the distance between the human body skeleton node positioned on the first side of the human body and the ground in the image to be detected into a first distance set;
and the second set establishing unit is used for putting the distance between the human body framework node positioned on the second side of the human body and the ground in the image to be detected into a second distance set.
7. The human skeleton node-based fall detection system according to claim 6, wherein the distance calculation unit is specifically configured to substitute the position coordinates of the human skeleton nodes and the ground equation into a first preset formula to calculate and obtain the distance between the human skeleton nodes and the ground in the image to be detected;
the first preset formula includes:
wherein L represents the distance between the human skeleton node and the ground in the image to be detected, (x)i，yi，zi) Position coordinates representing the human skeleton nodes, A, B, C and D respectively represent coefficients of the ground equation.
8. The human skeleton node-based fall detection system of claim 6, wherein the fall detection module comprises:
the first counting unit is used for counting the number of elements smaller than a first preset threshold value in the first distance set to obtain a first numerical value;
a second counting unit, configured to count the number of elements in the second distance set, where the number of elements is smaller than a second preset threshold, so as to obtain a second numerical value;
and the threshold judging unit is used for judging whether the first numerical value is greater than a preset number threshold or whether the second numerical value is greater than a preset number threshold, if so, judging that the human body in the image to be detected is in a falling state, and if not, judging that the human body in the image to be detected is not in a falling state.
9. A fall detection system based on human skeleton node, its characterized in that includes: a memory and a processor; wherein the content of the first and second substances,
the memory is stored with program code, and the processor is used for calling the program code, and when the program code is called, the human body skeleton node-based fall detection method of any one of claims 1 to 4 is executed.
10. A storage medium, characterized in that the storage medium has stored therein a program code, which when executed, is used for implementing the steps of the human skeleton node-based fall detection method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110648819.9A CN113392751A (en) | 2021-06-10 | 2021-06-10 | Tumbling detection method based on human body skeleton nodes and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110648819.9A CN113392751A (en) | 2021-06-10 | 2021-06-10 | Tumbling detection method based on human body skeleton nodes and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113392751A true CN113392751A (en) | 2021-09-14 |
Family
ID=77620388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110648819.9A Pending CN113392751A (en) | 2021-06-10 | 2021-06-10 | Tumbling detection method based on human body skeleton nodes and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392751A (en) |
Citations (9)
| 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 |
| CN106384481A (en) * | 2016-11-01 | 2017-02-08 | 西安培华学院 | Remote Internet-based first-aid alarm device with fall posture judgment function |
| CN109325476A (en) * | 2018-11-20 | 2019-02-12 | 齐鲁工业大学 | A kind of human body exception attitude detection system and method based on 3D vision |
| 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 |
| CN109920208A (en) * | 2019-01-31 | 2019-06-21 | 深圳绿米联创科技有限公司 | Tumble prediction technique, device, electronic equipment and system |
| CN110176126A (en) * | 2019-06-03 | 2019-08-27 | 珠海格力电器股份有限公司 | A kind of human body fall monitoring device and method |
| CN111241913A (en) * | 2019-12-19 | 2020-06-05 | 北京文安智能技术股份有限公司 | Method, device and system for detecting falling of personnel |
| CN112163564A (en) * | 2020-10-26 | 2021-01-01 | 燕山大学 | Tumble prejudging method based on human body key point behavior identification and LSTM (least Square TM) |
| 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 |
-
2021
- 2021-06-10 CN CN202110648819.9A patent/CN113392751A/en active Pending
Patent Citations (9)
| 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 |
| CN106384481A (en) * | 2016-11-01 | 2017-02-08 | 西安培华学院 | Remote Internet-based first-aid alarm device with fall posture judgment function |
| 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 |
| CN109325476A (en) * | 2018-11-20 | 2019-02-12 | 齐鲁工业大学 | A kind of human body exception attitude detection system and method based on 3D vision |
| CN109920208A (en) * | 2019-01-31 | 2019-06-21 | 深圳绿米联创科技有限公司 | Tumble prediction technique, device, electronic equipment and system |
| CN110176126A (en) * | 2019-06-03 | 2019-08-27 | 珠海格力电器股份有限公司 | A kind of human body fall monitoring device and method |
| CN111241913A (en) * | 2019-12-19 | 2020-06-05 | 北京文安智能技术股份有限公司 | Method, device and system for detecting falling of personnel |
| 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 |
| CN112163564A (en) * | 2020-10-26 | 2021-01-01 | 燕山大学 | Tumble prejudging method based on human body key point behavior identification and LSTM (least Square TM) |
Non-Patent Citations (3)
| Title |
|---|
| CHRISTOPHER KAWATSU 等: "Development of a Fall Detection System with Microsoft Kinect", ROBOT INTELLIGENCE TECHNOL. & APPL., pages 623 - 630 * |
| MONA SALEH ALZAHRANI等: "Comprehensive evaluation of skeleton features-based fall detection from Microsoft Kinect v2", SIGNAL, IMAGE AND VIDEO PROCESSING, vol. 13, no. 7, pages 1431 - 1439, XP036909169, DOI: 10.1007/s11760-019-01490-9 * |
| 李旋旋;张仁杰;: "一种基于Kinect的人体摔倒检测方法", 软件导刊, no. 07, pages 128 - 130 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111598998B (en) | Three-dimensional virtual model reconstruction method, three-dimensional virtual model reconstruction device, computer equipment and storage medium | |
| KR102437456B1 (en) | Event camera-based deformable object tracking | |
| WO2022241874A1 (en) | Infrared thermal imaging monocular vision ranging method and related assembly | |
| CN108875533B (en) | Face recognition method, device, system and computer storage medium | |
| CN110827342A (en) | Three-dimensional human body model reconstruction method, storage device and control device | |
| CN111524233B (en) | Three-dimensional reconstruction method of static scene dynamic target | |
| CN109934065A (en) | A kind of method and apparatus for gesture identification | |
| CN113111767A (en) | Fall detection method based on deep learning 3D posture assessment | |
| CN111680573B (en) | Face recognition method, device, electronic equipment and storage medium | |
| CN115546442A (en) | Multi-view stereo matching reconstruction method and system based on perception consistency loss | |
| CN108986210B (en) | Method and device for reconstructing three-dimensional scene | |
| JPWO2023112083A5 (en) | ||
| CN113392751A (en) | Tumbling detection method based on human body skeleton nodes and related device | |
| CN111507304B (en) | Self-adaptive rigidity priori model training method, face tracking method and related devices | |
| CN116129361B (en) | Crowd gathering identification method and device based on distance measurement | |
| CN113177564A (en) | Computer vision pig key point identification method | |
| CN111814731A (en) | Sitting posture detection method, device, equipment and storage medium | |
| CN110490165A (en) | A kind of dynamic hand tracking method based on convolutional neural networks | |
| CN113724378B (en) | Three-dimensional modeling method and apparatus, computer-readable storage medium, and computer device | |
| CN115035188A (en) | Target-based distance measurement method and device and terminal equipment | |
| CN110675311A (en) | Sketch generation method and device under sketch order constraint and storage medium | |
| CN111814679A (en) | FPGA-based realization algorithm for voxel-encoder and VFE of voxel 3D network | |
| CN107027019B (en) | Image parallactic acquisition methods and device | |
| CN111967579A (en) | Method and apparatus for performing convolution calculation on image using convolution neural network | |
| Chen et al. | An integrated sensor network method for safety management of construction workers |
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 |