CN115278159A - Person monitoring and alarming method and system - Google Patents
Person monitoring and alarming method and system Download PDFInfo
- Publication number
- CN115278159A CN115278159A CN202210686767.9A CN202210686767A CN115278159A CN 115278159 A CN115278159 A CN 115278159A CN 202210686767 A CN202210686767 A CN 202210686767A CN 115278159 A CN115278159 A CN 115278159A
- Authority
- CN
- China
- Prior art keywords
- human body
- target
- image
- parallel straight
- behaviors
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 230000006399 behavior Effects 0.000 claims abstract description 124
- 238000005516 engineering process Methods 0.000 claims description 37
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 235000019504 cigarettes Nutrition 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000391 smoking effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses a person monitoring and alarming method and a person monitoring and alarming system, a scene is shot through a camera module, a human body target is judged through a human body target judging module, whether the human body target is illegal or not is determined through a human body behavior judging module, the human body target with illegal behaviors is marked, displayed and alarmed through a display module, real-time monitoring of behaviors of workers is achieved, and the illegal behaviors of the workers are effectively avoided.
Description
Technical Field
The invention relates to the technical field of people behavior monitoring, in particular to a people monitoring and alarming method and a people monitoring and alarming system.
Background
In daily production activities, due to different work contents, places where workers work often have special requirements, most places require that smoking and calling are prohibited, in the prior art, in order to enable the workers to match with corresponding requirements of the work places, a plurality of inspectors can patrol the work places, although the work mode can enable the workers to do things to a certain extent according to requirements, when the inspectors check neutral gear, the workers often do not do things according to the requirements, and further certain harm is brought to the production activities, and in order to avoid similar things, a method or a system capable of monitoring the behaviors of the workers in real time is needed.
Disclosure of Invention
The invention aims to provide a method and a system for monitoring a worker in real time so as to monitor the violation of the worker.
The invention discloses a person monitoring and alarming method, which is applied with a camera and further comprises the following steps:
acquiring a video image shot by the camera, and determining a moving target in the video image according to a multi-moving-target detection technology;
according to a face recognition technology, scanning and analyzing the moving target, and screening to determine a human body target;
scanning and analyzing the region of the human body target in the video image to generate a depth image of the human body target;
according to the human body skeleton recognition technology, joint point feature data of the human body target in the depth image are determined, the joint point feature data are compared with a preset behavior recognition library to determine whether the human body target has illegal behaviors, and if the human body target has the illegal behaviors, an alarm is given for the corresponding human body target.
In some embodiments of the present application, in order to determine the behavior of the human target through the joint point of the human target, a method for presetting the behavior recognition library is disclosed, and the method for presetting the behavior recognition library includes:
and according to different behaviors of the human body, dividing a plurality of human body actions of the human body behaviors, and according to the joint point characteristic data corresponding to the human body actions, generating the behavior recognition library related to the human body behaviors and the joint point characteristic data.
In some embodiments of the present application, in order to improve the accuracy of the behavior judgment on the human target, the method further includes:
converting the video image into an edge information graph according to an image edge detection technology;
determining the position of the face of the human body target according to the face recognition technology, and scanning and analyzing whether parallel straight lines exist at the position of the edge information image corresponding to the face according to the position of the face;
if the position of the edge information graph corresponding to the face has parallel straight lines and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body target has violation behaviors, and giving an alarm aiming at the corresponding human body target.
In some embodiments of the present application, a method for determining whether parallel straight lines exist at a position where the edge information graph corresponds to the face is disclosed, and the method for determining whether parallel straight lines exist at a position where the edge information graph corresponds to the face includes:
carrying out smooth denoising processing on the video image to obtain a denoised image, carrying out scanning analysis on the denoised image, and determining high-frequency color characteristics in the denoised image so as to generate an edge information graph;
and carrying out Hough transformation on the edge information graph to obtain edge line segment parameters, and determining parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
In some embodiments of the present application, in order to determine whether parallel straight lines of the position of the face are mobile phones or cigarettes, a preset range of a distance between the parallel straight lines is provided, and the preset range of the distance between the parallel straight lines includes:
length value and width value of the conventional mobile phone;
diameter values for regular cigarettes.
The application discloses a person monitoring and alarming method, a human body target is determined by carrying out multi-target detection on a video image and through a face recognition technology, joint point characteristic data of the human body target is compared with a preset behavior recognition library, if the behavior of the joint point characteristic data of the human body target in the behavior recognition library corresponds to an illegal behavior, alarming is carried out, real-time monitoring on the behavior of a worker is achieved, and the illegal behavior of the worker is effectively avoided.
In some embodiments of the present application, there is also disclosed a people monitoring and warning system, the system comprising:
the camera module is used for shooting a scene;
the display module is used for displaying the video image shot by the camera;
the human body target judgment module is used for determining a moving target in the video image according to a multi-moving target detection technology and screening and determining a human body target according to a face recognition technology;
the image conversion module is used for converting the video image into a depth image;
the human body behavior judgment module determines joint point characteristic data of the human body target in the depth image according to a human body skeleton recognition technology, compares the joint point characteristic data with a preset behavior recognition library to determine whether the human body target has an illegal behavior, and if the human body target has the illegal behavior, enables the display module to carry out mark display alarm on the corresponding human body target.
In some embodiments of the application, in order to enable the human behavior determination module to determine the behavior of the human target through the behavior recognition library, the contents of the behavior recognition library include:
a plurality of human body behaviors and joint point characteristic data corresponding to the human body behaviors;
the correlation relationship between the human body behaviors and the joint point characteristic data is as follows:
the human body behaviors are associated with a plurality of human body actions, and the human body actions correspond to the corresponding joint point characteristic data one by one.
In some embodiments of the present application, in order to improve the accuracy of the behavior of the human target of the human behavior determination module, the method for the human behavior determination module to identify the behavior of the human target further includes:
the image conversion module converts the video image into an edge information graph according to an image edge detection technology;
the human body behavior judging module determines the position of the human face of the human body target according to the human face recognition technology, and scans and analyzes whether parallel straight lines exist at the position of the edge information image corresponding to the human face according to the position of the human face; if the position of the edge information graph corresponding to the face has parallel straight lines and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body target has violation behaviors, and giving an alarm aiming at the corresponding human body target.
In some embodiments of the present application, in order to enable a system to determine whether there is a parallel straight line at a position where the face is located, a determination method is disclosed, where the method for the system to determine whether there is a parallel straight line at a position where the edge information map corresponds to the face includes:
the image conversion module carries out smooth denoising processing on the video image to obtain a denoised image, carries out scanning analysis on the denoised image, and determines high-frequency color characteristics in the denoised image so as to generate an edge information graph;
and the human body behavior judgment module performs Hough transformation on the edge information graph to obtain edge line segment parameters, and determines parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
In some embodiments of the present application, there is disclosed contents of the preset range of the distance between the parallel straight lines, the preset range of the distance between the parallel straight lines including:
length value and width value of the conventional mobile phone;
diameter values for regular cigarettes.
The application discloses personage monitoring alarm system shoots the scene through the camera module, judges human target through human target judgment module, confirms whether human target is the violation of action through human action judgment module to carry out mark display alarm to the human target that has the violation of action through the display module, realized real-time control to the staff action, effectively avoided staff's violation of action.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 illustrates one conceptual step in the practice of the present application for constructing a people monitoring alarm system.
Detailed Description
The technical solution of the present invention is further illustrated by the accompanying drawings and examples.
Unless defined otherwise, technical or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used only to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
The embodiment is as follows:
the invention discloses a person monitoring and alarming method, which is applied with a camera and further comprises the following steps:
step 1, acquiring a video image shot by the camera, and determining a moving target in the video image according to a multi-moving-target detection technology.
And 2, scanning and analyzing the moving target according to a face recognition technology, and screening and determining a human body target.
And 3, scanning and analyzing the region of the human body target in the video image to generate a depth image of the human body target.
And 4, determining joint point characteristic data of the human body target in the depth image according to a human body skeleton recognition technology.
And 5, comparing the joint point characteristic data with a preset behavior recognition library to determine whether the human body target has illegal behaviors, and if the human body target has illegal behaviors, alarming aiming at the corresponding human body target.
In step 5, in order to determine the behavior of the human target through the joint point of the human target, in some embodiments of the present application, a method for presetting the behavior recognition library is disclosed, where the method for presetting the behavior recognition library includes: and according to different behaviors of the human body, dividing a plurality of human body actions of the human body behaviors, and according to the joint point characteristic data corresponding to the human body actions, generating the behavior recognition library related to the human body behaviors and the joint point characteristic data.
In some embodiments of the present application, in order to improve the accuracy of the behavior judgment on the human target, the method further includes:
step 6, converting the video image into an edge information graph according to an image edge detection technology;
step 7, determining the position of the face of the human body target according to the face recognition technology, and scanning and analyzing whether parallel straight lines exist at the position of the edge information image corresponding to the face according to the position of the face;
and step 8, if parallel straight lines exist at positions of the edge information images corresponding to the human faces, and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body targets have illegal behaviors, and giving an alarm aiming at the corresponding human body targets.
In some embodiments of the present application, a method for determining whether there is a parallel straight line at a position where the edge information map corresponds to the face is disclosed, and the method for determining whether there is a parallel straight line at a position where the edge information map corresponds to the face includes:
a. carrying out smooth denoising processing on the video image to obtain a denoised image, carrying out scanning analysis on the denoised image, and determining high-frequency color characteristics in the denoised image so as to generate an edge information graph;
b. and carrying out Hough transformation on the edge information graph to obtain edge line segment parameters, and determining parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
In some embodiments of the present application, in order to determine whether parallel straight lines of the position of the face are mobile phones or cigarettes, a preset range of a distance between the parallel straight lines is provided, and the preset range of the distance between the parallel straight lines includes:
1. the length and width values of a conventional handset.
2. Diameter values for regular cigarettes.
The application discloses a person monitoring and alarming method, a human body target is determined by carrying out multi-target detection on a video image and through a face recognition technology, joint point characteristic data of the human body target is compared with a preset behavior recognition library, if the behavior of the joint point characteristic data of the human body target in the behavior recognition library corresponds to an illegal behavior, alarming is carried out, real-time monitoring on the behavior of a worker is achieved, and the illegal behavior of the worker is effectively avoided.
In order to further explain the technical scheme of the application, the application also discloses a concept step for constructing a person monitoring and alarming system, and firstly, it should be clear that the technical problem to be solved by the person monitoring and alarming system is to monitor whether the staff has illegal behaviors, wherein the illegal behaviors comprise smoking behaviors and mobile phone using behaviors.
The design steps are as follows:
s1, acquiring a video image shot by the camera, and determining a moving target in the video image according to a multi-moving-target detection technology.
And S2, scanning and analyzing the moving target according to a face recognition technology, and screening to determine a human body target.
And S3, scanning and analyzing the region of the human body target in the video image to generate a depth image of the human body target.
And S4, determining joint point characteristic data of the human body target in the depth image according to a human body skeleton recognition technology.
And S5, comparing the joint point characteristic data with a preset behavior recognition library to determine whether the human body target has illegal behaviors.
And S6, if the illegal behavior exists, alarming aiming at the corresponding human body target.
In the step S5, the behaviors recorded by the behavior recognition library are divided into smoking behavior and mobile phone using behavior, and the joint point feature data of the human body target is obtained according to the motion features of the two behaviors, where the joint point feature data includes the position relationship between joint points and the time for maintaining the position relationship. Although smoking behaviors and behaviors using mobile phones are disclosed, many illegal behaviors have own action characteristics, and if other illegal behaviors are monitored, the behavior recognition library can still be set by adopting the measures.
The method for presetting the behavior recognition library comprises the steps of dividing a plurality of human body actions of the human body actions according to different human body actions, and generating the behavior recognition library related to the human body actions and the joint point characteristic data according to the joint point characteristic data corresponding to the human body actions.
In order to improve the accuracy of system monitoring action, can also be to the face of human target scans the monitoring, judges whether there is cell-phone and cigarette, and the cross-section of these two kinds of objects is the rectangle, and for people's face, these two kinds of objects all have parallel edge, and based on this characteristic, still disclose in some embodiments of this application as follows and think the step:
and S7, converting the video image into an edge information graph according to an image edge detection technology.
And S8, determining the position of the human face of the human body target according to the human face recognition technology.
And S8, scanning and analyzing whether parallel straight lines exist at the positions of the edge information images corresponding to the human faces or not according to the positions of the human faces.
And S9, if parallel straight lines exist at positions of the edge information images corresponding to the human faces, and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body targets have illegal behaviors, and alarming aiming at the corresponding human body targets.
In some embodiments of the present application, a person monitoring and alarming system is further disclosed, the system includes a camera module, a display module, a human body target determination module, an image conversion module, and a human body behavior determination module.
The camera module is used for shooting a scene.
And the display module is used for displaying the video image shot by the camera.
The human body target judgment module determines a moving target in the video image according to a multi-moving target detection technology and screens and determines a human body target according to a face recognition technology.
And the image conversion module is used for converting the video image into a depth image.
The human body behavior judging module is used for determining joint point characteristic data of the human body target in the depth image according to a human body skeleton recognition technology, comparing the joint point characteristic data with a preset behavior recognition library to determine whether the human body target has an illegal behavior, and if the human body target has the illegal behavior, enabling the display module to carry out mark display alarm on the corresponding human body target.
In some embodiments of the present application, in order to enable the human behavior determination module to determine the behavior of the human target through the behavior recognition library, the contents of the behavior recognition library include:
a plurality of human body behaviors and joint point characteristic data corresponding to the human body behaviors.
The correlation relationship between the human body behaviors and the joint point characteristic data is as follows:
the human body behaviors are associated with a plurality of human body actions, and the human body actions correspond to the corresponding joint point characteristic data one by one.
In some embodiments of the present application, in order to improve the accuracy of the behavior of the human target of the human behavior determination module, the method for the human behavior determination module to identify the behavior of the human target further includes:
a. the image conversion module converts the video image into an edge information graph according to an image edge detection technology;
b. the human body behavior judging module determines the position of the human face of the human body target according to the human face recognition technology, and scans and analyzes whether parallel straight lines exist at the position of the edge information image corresponding to the human face according to the position of the human face; if the position of the edge information graph corresponding to the face has parallel straight lines and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body target has violation behaviors, and giving an alarm aiming at the corresponding human body target.
In some embodiments of the present application, in order to enable a system to determine whether there is a parallel straight line at a position where the face is located, a determination method is disclosed, where the method for determining whether there is a parallel straight line at a position where the edge information map corresponds to the face by the system includes:
a. the image conversion module carries out smooth denoising processing on the video image to obtain a denoised image, carries out scanning analysis on the denoised image, and determines high-frequency color characteristics in the denoised image so as to generate an edge information graph;
b. the human body behavior judgment module carries out Hough transformation on the edge information graph to obtain edge line segment parameters, and determines parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
In some embodiments of the present application, there is disclosed contents of the preset range of the distance between the parallel straight lines, the preset range of the distance between the parallel straight lines including:
length value and width value of the conventional mobile phone;
diameter values for regular cigarettes.
The application discloses personage monitoring alarm system shoots the scene through the camera module, judges human target through human target judgment module, confirms whether human target is the violation of action through human action judgment module to carry out mark display alarm to the human target that has the violation of action through the display module, realized real-time control to the staff action, effectively avoided staff's violation of action.
Finally, it should be noted that: the above embodiments are only intended to illustrate the technical solution of the present invention and not to limit the same, and although the present invention is described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the invention without departing from the spirit and scope of the invention.
Claims (10)
1. A person monitoring and alarming method is characterized in that a camera is applied, and the method further comprises the following steps:
acquiring a video image shot by the camera, and determining a moving target in the video image according to a multi-moving-target detection technology;
according to a face recognition technology, scanning and analyzing the moving target, and screening to determine a human body target;
scanning and analyzing the region of the human body target in the video image to generate a depth image of the human body target;
according to the human body skeleton recognition technology, joint point feature data of the human body target in the depth image are determined, the joint point feature data are compared with a preset behavior recognition library to determine whether the human body target has illegal behaviors, and if the human body target has the illegal behaviors, an alarm is given for the corresponding human body target.
2. The person monitoring and alarming method as claimed in claim 1, wherein the method for presetting the behavior recognition library comprises:
and according to different behaviors of the human body, dividing a plurality of human body actions of the human body behaviors, and according to the joint point characteristic data corresponding to the human body actions, generating the behavior recognition library related to the human body behaviors and the joint point characteristic data.
3. The people monitoring and alarming method of claim 1, further comprising:
converting the video image into an edge information graph according to an image edge detection technology;
determining the position of the face of the human body target according to the face recognition technology, and scanning and analyzing whether parallel straight lines exist at the position of the edge information image corresponding to the face according to the position of the face;
if the position of the edge information graph corresponding to the face has parallel straight lines and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body target has violation behaviors, and giving an alarm aiming at the corresponding human body target.
4. The method for monitoring and alarming people as claimed in claim 3, wherein the step of judging whether the position of the edge information graph corresponding to the face has a parallel straight line comprises the following steps:
carrying out smooth denoising processing on the video image to obtain a denoised image, carrying out scanning analysis on the denoised image, and determining high-frequency color characteristics in the denoised image so as to generate an edge information graph;
and carrying out Hough transformation on the edge information graph to obtain edge line segment parameters, and determining parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
5. The human monitoring and alarming method as claimed in claim 3, wherein the preset range of the distance between the parallel straight lines comprises:
length value and width value of the conventional mobile phone;
diameter values for regular cigarettes.
6. A people monitoring and alarm system, the system comprising:
the camera module is used for shooting a scene;
the display module is used for displaying the video image shot by the camera;
the human body target judgment module is used for determining a moving target in the video image according to a multi-moving target detection technology and screening and determining a human body target according to a face recognition technology;
the image conversion module is used for converting the video image into a depth image;
the human body behavior judgment module determines joint point feature data of the human body target in the depth image according to a human body skeleton recognition technology, compares the joint point feature data with a preset behavior recognition library to determine whether the human body target has illegal behaviors, and if the human body target has the illegal behaviors, the display module marks, displays and alarms the corresponding human body target.
7. The person monitoring and alarm system of claim 6, wherein the content of the behavior recognition library comprises:
a plurality of human body behaviors and joint point characteristic data corresponding to the human body behaviors;
the correlation relationship between the human body behaviors and the joint point characteristic data is as follows:
the human body behaviors are associated with a plurality of human body actions, and the human body actions correspond to the corresponding joint point characteristic data one by one.
8. The system of claim 6, wherein the method for identifying the target human behavior by the human behavior determination module further comprises:
the image conversion module converts the video image into an edge information graph according to an image edge detection technology;
the human body behavior judging module determines the position of the human face of the human body target according to the human face recognition technology, and scans and analyzes whether parallel straight lines exist at the position of the edge information image corresponding to the human face according to the position of the human face; if the position of the edge information graph corresponding to the face has parallel straight lines and the distance between the parallel straight lines falls into a preset range, determining that the corresponding human body target has violation behaviors, and giving an alarm aiming at the corresponding human body target.
9. The system of claim 8, wherein the method for determining whether the position of the edge information map corresponding to the face has a parallel straight line comprises:
the image conversion module carries out smooth denoising processing on the video image to obtain a denoised image, carries out scanning analysis on the denoised image, and determines high-frequency color characteristics in the denoised image so as to generate an edge information graph;
the human body behavior judgment module carries out Hough transformation on the edge information graph to obtain edge line segment parameters, and determines parallel straight lines and the distance between the parallel straight lines according to the edge line segment parameters.
10. The people monitoring and alarming system of claim 8, wherein the preset range of distances between the parallel straight lines comprises:
length value and width value of the conventional mobile phone;
diameter values for regular cigarettes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210686767.9A CN115278159A (en) | 2022-06-16 | 2022-06-16 | Person monitoring and alarming method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210686767.9A CN115278159A (en) | 2022-06-16 | 2022-06-16 | Person monitoring and alarming method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115278159A true CN115278159A (en) | 2022-11-01 |
Family
ID=83761328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210686767.9A Pending CN115278159A (en) | 2022-06-16 | 2022-06-16 | Person monitoring and alarming method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115278159A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339688A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Intrusion checking method and system |
| KR101113515B1 (en) * | 2011-09-20 | 2012-02-29 | 제주특별자치도 | Video index system using surveillance camera and the method thereof |
| US20150092978A1 (en) * | 2013-09-27 | 2015-04-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for recognition of abnormal behavior |
| CN107545225A (en) * | 2016-06-23 | 2018-01-05 | 杭州海康威视数字技术股份有限公司 | A kind of method, apparatus and electronic equipment for detecting vehicle carried driving person's unlawful practice |
| CN110321852A (en) * | 2019-07-05 | 2019-10-11 | 名创优品（横琴）企业管理有限公司 | A kind of type of action recognition methods, device, storage medium and computer equipment |
| CN111325058A (en) * | 2018-12-14 | 2020-06-23 | 长沙智能驾驶研究院有限公司 | Driving behavior detection method, device and system and storage medium |
| WO2021008039A1 (en) * | 2019-07-17 | 2021-01-21 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for object monitoring |
-
2022
- 2022-06-16 CN CN202210686767.9A patent/CN115278159A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339688A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Intrusion checking method and system |
| KR101113515B1 (en) * | 2011-09-20 | 2012-02-29 | 제주특별자치도 | Video index system using surveillance camera and the method thereof |
| US20150092978A1 (en) * | 2013-09-27 | 2015-04-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for recognition of abnormal behavior |
| CN107545225A (en) * | 2016-06-23 | 2018-01-05 | 杭州海康威视数字技术股份有限公司 | A kind of method, apparatus and electronic equipment for detecting vehicle carried driving person's unlawful practice |
| CN111325058A (en) * | 2018-12-14 | 2020-06-23 | 长沙智能驾驶研究院有限公司 | Driving behavior detection method, device and system and storage medium |
| CN110321852A (en) * | 2019-07-05 | 2019-10-11 | 名创优品（横琴）企业管理有限公司 | A kind of type of action recognition methods, device, storage medium and computer equipment |
| WO2021008039A1 (en) * | 2019-07-17 | 2021-01-21 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for object monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10949657B2 (en) | Person's behavior monitoring device and person's behavior monitoring system | |
| CN110044486B (en) | Method, device and equipment for avoiding repeated alarm of human body inspection and quarantine system | |
| US9536154B2 (en) | Monitoring method and camera | |
| US6928228B2 (en) | System and method for detection and analysis of video recordings | |
| US7868772B2 (en) | Flame detecting method and device | |
| US10691947B2 (en) | Monitoring device | |
| CN110188724A (en) | The method and system of safety cap positioning and color identification based on deep learning | |
| EP3308356B1 (en) | System and method for detecting a dissimilar object in undercarriage of a vehicle | |
| CN109409238B (en) | Obstacle detection method and device and terminal equipment | |
| CN114140832A (en) | Method and device for detecting pedestrian boundary crossing risk in well, electronic equipment and storage medium | |
| CN112070053B (en) | Background image self-updating method, device, equipment and storage medium | |
| JP5718632B2 (en) | Part recognition device, part recognition method, and part recognition program | |
| JP2018169831A (en) | Apparatus for image comparison | |
| EP2000998A2 (en) | Flame detecting method and device | |
| CN113313899A (en) | Security monitoring analysis processing method based on big data | |
| CN115620192A (en) | Method and device for detecting wearing of safety rope in aerial work | |
| Verstockt et al. | Silhouette-based multi-sensor smoke detection: coverage analysis of moving object silhouettes in thermal and visual registered images | |
| JP2007219603A (en) | Person tracking device, person tracking method and person tracking program | |
| CN115278159A (en) | Person monitoring and alarming method and system | |
| CN112104838B (en) | Image distinguishing method, monitoring camera and monitoring camera system thereof | |
| JPH0514891A (en) | Image monitor device | |
| JP2008152586A (en) | Automatic identification monitor system for area surveillance | |
| CN110910379B (en) | Incomplete detection method and device | |
| CN113505760A (en) | Target detection method, device, related equipment and computer readable storage medium | |
| JP3736836B2 (en) | Object detection method, object detection apparatus, and program |
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 |