CN109657626B - Analysis method for recognizing human body behaviors - Google Patents
Analysis method for recognizing human body behaviors Download PDFInfo
- Publication number
- CN109657626B CN109657626B CN201811576882.0A CN201811576882A CN109657626B CN 109657626 B CN109657626 B CN 109657626B CN 201811576882 A CN201811576882 A CN 201811576882A CN 109657626 B CN109657626 B CN 109657626B
- Authority
- CN
- China
- Prior art keywords
- module
- behavior
- information
- processing unit
- central processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- 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
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of computer vision, and discloses an analysis method for recognizing human body behaviors, which comprises a central processing unit, a camera module, a sensing module, an information transmission module, a receiving module, an information processing module, an information base, a simple behavior analysis module, a behavior comparison module, a behavior information feedback module, terminal equipment and an alarm module, wherein the output end of the camera module is electrically connected with the input end of the sensing module. The method has the characteristics of high speed, stable performance, strong expandability and the like, can detect and position a plurality of bad behaviors of personnel in real time, and provides effective data for a superior management department in time, thereby standardizing window service, continuously improving the service quality of public departments, simultaneously monitoring the behaviors of drivers in real time and reducing traffic accidents.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to an analysis method for recognizing human body behaviors.
Background
The gist of behavior recognition is that enterprises should have a normative criterion in internal coordination and external communication. This criterion is embodied in the consistent daily behavior of all employees. That is, the concerted behavior of the employees should be a business behavior, which reflects the business idea and value orientation of the business, rather than independent and random individual behaviors.
Meanwhile, the behavior criterion is not like the behavior of compliance with the regulations, such as 'arriving no later on duty and leaving no early off duty'. If the operation is carried out according to the established terms, the staff is required to change the operation into the self-conscious action of the enterprise on the basis of understanding the operation idea of the enterprise, and only then, the same idea can be specifically implemented into management behaviors, sales behaviors, service behaviors and public relation behaviors on different occasions and different levels. The behavior recognition of the enterprise is a dynamic operation system of enterprise processing, coordinators, events and objects. The implementation of behavior recognition includes new product development, cadre training, employee education, production management, environmental protection, benefit distribution, civilization and politeness specification and the like. The external application includes market research and sales promotion of goods, various service and official rule, and the rule of interaction with finance, upstream and downstream partners and agent dealers.
In recent years, with the promotion of the construction of safe cities and smart cities and the application and popularization of high-definition video technology, how to analyze video big data and extract effective information becomes a key for the development of next-generation information technology. The method and the device can be used for rapidly and accurately analyzing and processing the actions and behaviors of people serving as video big data cores, so that the abnormal emergencies can be detected in real time, and the judgment can be effectively carried out and the abnormal emergencies can be processed in time.
Disclosure of Invention
Technical problem to be solved
The invention provides an analysis method for recognizing human body behaviors, which has the characteristics of high speed, stable performance, strong expandability and the like, can detect and position various bad behaviors of personnel in real time, and provides effective data for superior management departments in time, thereby standardizing window services, continuously improving the service quality of public departments and the like.
(II) technical scheme
The invention provides the following technical scheme: an analysis method for recognizing human body behaviors comprises a central processing unit, a camera module, a sensing module, an information transmission module, a receiving module, an information processing module, an information base, a simple behavior analysis module, a behavior comparison module, a behavior information feedback module, a terminal device and an alarm module, wherein the output end of the camera module is electrically connected with the input end of the sensing module, the output end of the sensing module is electrically connected with the input end of the information transmission module, the output end of the information transmission module is electrically connected with the input end of the receiving module, the output end of the receiving module is electrically connected with the input end of the information processing module, the output end of the information processing module is electrically connected with the input end of the central processing unit, the output end of the central processing unit is electrically connected with the input end of the information base, the output end of the information base is electrically connected with the input end of the simple behavior analysis module, the output end of the simple behavior analysis module is electrically connected with the input end of the behavior comparison module, the output end of the behavior comparison module is electrically connected with the input end of the behavior information feedback module, the output end of the behavior information feedback module is electrically connected with the input end of the central processing module, the output end of the alarm module is electrically connected with the input end of the alarm module.
Preferably, the central processing unit at least comprises three output interface terminals and four input terminals.
Preferably, the information base includes information about each behavior and action.
Preferably, the camera module is used for combining close-range monitoring and long-range monitoring.
The invention provides an analysis method for recognizing human body behaviors, which comprises the following steps of:
1) Detection of moving objects within range by camera module
(1) When the abnormal behavior is in the monitoring and identifying range, the abnormal behavior of the human body is identified by analyzing the local limb movement of the target through close-range monitoring, namely the abnormal behavior of the moving human body is detected and identified;
(2) when the moving object is out of the monitoring and identifying range, due to the distance relation, the local limb characteristics of the object can be hidden or are difficult to identify, so that whether abnormal behaviors occur or not can be judged only by detecting and tracking the whole moving object in a long-range monitoring mode, namely the moving object wanders and tracks the moving object according to the whole behaviors;
2) At the moment, the video information shot by the step is transmitted through the sensing module and the information transmission module, meanwhile, the receiving module on the information processing module receives the shot information, the information processing module processes and codes the received information, the source location is confirmed according to the transmission IP address, and then detailed position marking is carried out;
3) Judging the behavior property, and setting a human behavior threshold value according to the behavior information in the information base;
5) The information marked by the information processing module is transmitted to the central processing unit, the information is transmitted to the information base by the central processing unit, the shot information is processed and analyzed by the information base, the image is analyzed and identified by simple behavior analysis, and if the shot information can be identified, the shot information is transmitted to the central processing unit;
if the human body behavior information cannot be identified, the behavior comparison module compares the human body behavior information according to various human body behavior information in the information base, processes and analyzes the image, extracts features according to specific behaviors, transmits the features to the central processing unit through the behavior information feedback module, finally judges the behavior property through the central processing unit, and simultaneously transmits the behavior property to the terminal equipment;
5) Alarm judgment, namely finally judging the nature of the behavior through a central processing unit and controlling an alarm module to start;
and judging whether the human behavior threshold value exceeds the preset human behavior threshold value or not according to the preset human behavior threshold value, if the human behavior threshold value exceeds the preset threshold value, displaying alarm information in time to inform monitoring personnel to process, wherein the alarm mode is carried out in the practical application by adopting a ring alarm or short message notification mode, and if not, returning to the step of re-collecting the video sequence to carry out moving target detection.
Compared with the prior art, the invention provides an analysis method for recognizing human body behaviors, which has the following beneficial effects:
1. according to the invention, through the setting of simple behavior analysis, some regions with human body behaviors smaller than a set basic threshold value can be deleted, subsequent processing is not carried out, the detection effect can be greatly improved through foreground images processed through the simple behavior analysis, and meanwhile, behavior judgment can be accurately made by combining artificial intelligence and video big data, so that the basic workload is reduced.
2. The method has the characteristics of high speed, stable performance, strong expandability and the like, can detect and position various bad behaviors of personnel in real time, and provides effective data for a superior management department in time, so that window service is standardized, the service quality of a public department is continuously improved, driver behaviors can be monitored in real time, and traffic accidents are reduced.
Drawings
FIG. 1 is a flow chart of human behavior analysis according to the present invention.
In the figure: the system comprises a central processing unit 1, a camera module 2, a sensing module 3, an information transmission module 4, a receiving module 5, an information processing module 6, an information base 7, a simple behavior analysis module 8, a behavior comparison module 9, a behavior information feedback module 10, a terminal device 11 and an alarm module 12.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
As shown in fig. 1, the present invention provides a technical solution: an analysis method for recognizing human body behaviors comprises a central processing unit 1, a camera module 2, a sensing module 3, an information transmission module 4, a receiving module 5, an information processing module 6, an information base 7, a simple behavior analysis 8, a behavior comparison module 9, a behavior information feedback module 10, a terminal device 11 and an alarm module 12, wherein the output end of the camera module 2 is electrically connected with the input end of the sensing module 3, the output end of the sensing module 3 is electrically connected with the input end of the information transmission module 4, the output end of the information transmission module 4 is electrically connected with the input end of the receiving module 5, the output end of the receiving module 5 is electrically connected with the input end of the information processing module 6, the output end of the information processing module 6 is electrically connected with the input end of the central processing unit 1, the output end of the central processing unit 1 is electrically connected with the input end of the information base 7, the output end of the information base 7 is electrically connected with the input end of the simple behavior analysis 8, the output end of the behavior analysis 8 is electrically connected with the input end of the central processing unit 1, the output end of the simple behavior analysis module 8 is electrically connected with the input end of the behavior comparison module 9, the input end of the behavior feedback module 9 is electrically connected with the input end of the terminal device 12, and the output end of the alarm module 11 is electrically connected with the input end of the central processing module 11.
An analysis method for recognizing human body behaviors comprises the following steps:
1) Detecting a moving target in the range through the camera module 2;
(1) when the abnormal behaviors are in the monitoring and identifying range, the abnormal behaviors of the human body are identified by analyzing the local limb movement of the target through close-range monitoring, namely the abnormal behaviors of the moving human body are detected and identified;
(2) when the moving object is out of the monitoring and identifying range, due to the distance relation, the local limb characteristics of the object can be hidden or are difficult to identify, so that whether abnormal behaviors occur or not can be judged only by detecting and tracking the whole moving object in a long-range monitoring mode, namely the moving object wanders and tracks the moving object according to the whole behaviors;
2) At the moment, the video information shot by the step 1 is transmitted through a sensing module 3 and an information transmission module 4, meanwhile, a receiving module 5 on an information processing module 6 receives the shot information, the information processing module 6 processes and codes the received information, a source location is confirmed according to a transmission IP address, and then detailed position marking is carried out;
3) Judging the behavior property, and setting a human behavior threshold value according to the behavior information in the information base 7;
4) The information marked by the information processing module 6 is transmitted to the central processing unit 1, the information is transmitted to the information base 7 by the central processing unit 1, and the shot information is processed and analyzed by the information base 7 to perform simple behavior analysis and identification, and if the information can be identified, the information is transmitted to the central processing unit 1;
if the behavior cannot be identified, the behavior comparison module 9 compares the behavior information of each human body in the information base 7, processes and analyzes the image, extracts the characteristics according to the specific behavior, transmits the characteristics to the central processing unit 1 through the behavior information feedback module 10, finally judges the behavior property through the central processing unit 1, and simultaneously transmits the behavior property to the terminal device 11;
5) Alarm judgment, namely finally judging the nature of the behavior through the central processing unit 1 and controlling the alarm module 12 to start;
and (2) judging whether the human behavior threshold value exceeds the preset human behavior threshold value or not according to the preset human behavior threshold value, if the human behavior threshold value exceeds the preset threshold value, displaying alarm information in time to inform monitoring personnel to process, wherein the alarm mode is carried out in the practical application by adopting a ring alarm or short message notification mode, and if not, returning to the step 1 to re-acquire the video sequence to carry out moving target detection.
The invention has the beneficial effects that: the invention can delete some areas with human body behaviors smaller than the set basic threshold value through the setting of simple behavior analysis, does not need subsequent processing, can greatly improve the detection effect through the foreground image processed by the simple behavior analysis, and can accurately make behavior judgment by combining artificial intelligence and video big data, thereby reducing the basic workload.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. An analysis method for recognizing human body behaviors comprises a central processing unit (1), a camera module (2), a sensing module (3), an information transmission module (4), a receiving module (5), an information processing module (6), an information base (7), simple behavior analysis (8), a behavior comparison module (9), a behavior information feedback module (10), a terminal device (11) and an alarm module (12), and is characterized in that: the output end of the camera module (2) is electrically connected with the input end of the sensing module (3), the output end of the sensing module (3) is electrically connected with the input end of the information transmission module (4), the output end of the information transmission module (4) is electrically connected with the input end of the receiving module (5), the output end of the receiving module (5) is electrically connected with the input end of the information processing module (6), the output end of the information processing module (6) is electrically connected with the input end of the central processing unit (1), the output end of the central processing unit (1) is electrically connected with the input end of the information base (7), the output end of the information base (7) is electrically connected with the input end of the simple behavior analysis (8), the output end of the simple behavior analysis (8) is electrically connected with the input end of the central processing unit (1), the output end of the simple behavior analysis (8) is electrically connected with the input end of the behavior comparison module (9), the output end of the behavior comparison module (9) is electrically connected with the input end of the behavior information feedback module (10), the output end of the behavior information feedback module (10) is electrically connected with the input end of the central processing unit (1), and the alarm device (11), the input end of the alarm module (12) is electrically connected with the output end of the central processing unit (1);
the method comprises the following steps:
1) Detecting a moving target in the range through the camera module (2);
(1) when the abnormal behavior is in the monitoring and identifying range, the abnormal behavior of the human body is identified by analyzing the local limb movement of the target through close-range monitoring, namely the abnormal behavior of the moving human body is detected and identified;
(2) when the moving object is out of the monitoring and identifying range, due to the distance relation, the local limb characteristics of the object can be hidden or are difficult to identify, so that whether abnormal behaviors occur or not can be judged only by detecting and tracking the whole moving object in a long-range monitoring mode, namely the moving object wanders and tracks the moving object according to the whole behaviors;
2) At the moment, video information shot by the step 1 is transmitted through a sensing module (3) and an information transmission module (4), meanwhile, a receiving module (5) on an information processing module (6) receives the shot information, the information processing module (6) processes and codes the received information, a source location is confirmed according to a transmission IP address, and then detailed position marking is carried out;
3) Judging the behavior property, and setting a human behavior threshold value according to the behavior information in the information base (7);
4) The information marked by the information processing module (6) is transmitted to the central processing unit (1), the information is transmitted to the information base (7) by the central processing unit (1), and the shot information is processed and analyzed by the information base (7) to carry out simple behavior analysis and identification, and if the information can be identified, the information is transmitted to the central processing unit (1);
if the human body behavior information cannot be identified, the behavior comparison module (9) compares the human body behavior information according to various human body behavior information in the information base (7), processes and analyzes the image, extracts features according to specific behaviors, transmits the features to the central processing unit (1) through the behavior information feedback module (10), finally judges the behavior property through the central processing unit (1), and simultaneously transmits the behavior property to the terminal equipment (11);
5) Alarm judgment, namely finally judging the nature of the behavior through the central processing unit (1) and controlling the alarm module (12) to start;
and (2) judging whether the human behavior threshold value exceeds the preset human behavior threshold value or not according to the preset human behavior threshold value, if the human behavior threshold value exceeds the preset threshold value, displaying alarm information in time to inform monitoring personnel to process, wherein the alarm mode is carried out in the practical application by adopting a ring alarm or short message notification mode, and if not, returning to the step 1 to re-acquire the video sequence to carry out moving target detection.
2. The analysis method for recognizing human body behavior according to claim 1, wherein: the central processing unit (1) at least comprises three output interface terminals and four input terminals.
3. The analysis method for recognizing human body behavior according to claim 1, wherein: the information base (7) comprises various behavior and action information.
4. The analysis method for recognizing human body behavior according to claim 1, wherein: the camera module (2) combines close-range monitoring and long-range monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576882.0A CN109657626B (en) | 2018-12-23 | 2018-12-23 | Analysis method for recognizing human body behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576882.0A CN109657626B (en) | 2018-12-23 | 2018-12-23 | Analysis method for recognizing human body behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109657626A CN109657626A (en) | 2019-04-19 |
| CN109657626B true CN109657626B (en) | 2022-11-15 |
Family
ID=66115827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811576882.0A Active CN109657626B (en) | 2018-12-23 | 2018-12-23 | Analysis method for recognizing human body behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109657626B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016363A (en) * | 2019-05-30 | 2020-12-01 | 富泰华工业（深圳）有限公司 | Personnel monitoring method and device, computer device and readable storage medium |
| CN110909684A (en) * | 2019-11-25 | 2020-03-24 | 创新奇智(北京)科技有限公司 | Working state checking system and method based on human body detection |
| CN111079694A (en) * | 2019-12-28 | 2020-04-28 | 神思电子技术股份有限公司 | Counter assistant job function monitoring device and method |
| CN112884955A (en) * | 2021-01-18 | 2021-06-01 | 浙江乐地食品有限公司 | Food production safety management system |
| CN113033361A (en) * | 2021-03-13 | 2021-06-25 | 杭州翔毅科技有限公司 | Intelligent human-computer interaction system based on environment visibility |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110137836A1 (en) * | 2008-09-19 | 2011-06-09 | Hiroyuki Kuriyama | Method and system for generating history of behavior |
| JP2011048547A (en) * | 2009-08-26 | 2011-03-10 | Toshiba Corp | Abnormal-behavior detecting device, monitoring system, and abnormal-behavior detecting method |
| CN102164270A (en) * | 2011-01-24 | 2011-08-24 | 浙江工业大学 | Intelligent video monitoring method and system capable of exploring abnormal events |
| CN106096590A (en) * | 2016-07-16 | 2016-11-09 | 惠州学院 | A kind of multi-mode behavior tracking identification system and method |
| CN107689971A (en) * | 2016-08-04 | 2018-02-13 | 惠州学院 | A kind of human body behavior system for rapidly identifying under multiple-camera |
| CN206460481U (en) * | 2017-01-12 | 2017-09-01 | 刘曼 | One kind recognizes abnormal behaviour video system based on multi-angle |
-
2018
- 2018-12-23 CN CN201811576882.0A patent/CN109657626B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109657626A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657626B (en) | Analysis method for recognizing human body behaviors | |
| US20230316762A1 (en) | Object detection in edge devices for barrier operation and parcel delivery | |
| US11295139B2 (en) | Human presence detection in edge devices | |
| CN105590097B (en) | Dual camera collaboration real-time face identification security system and method under the conditions of noctovision | |
| US20140139633A1 (en) | Method and System for Counting People Using Depth Sensor | |
| CN109376577A (en) | Video synthesis analysis method and system | |
| CN109191829B (en) | road safety monitoring method and system, and computer readable storage medium | |
| CN104881643B (en) | A kind of quick remnant object detection method and system | |
| Beghdadi et al. | Towards the design of smart video-surveillance system | |
| CN112580470A (en) | City visual perception method and device, electronic equipment and storage medium | |
| US20200089965A1 (en) | Predictive Security Camera System | |
| Phule et al. | Abnormal activities detection for security purpose unattainded bag and crowding detection by using image processing | |
| CN111565303B (en) | Video monitoring method, system and readable storage medium based on fog calculation and deep learning | |
| CN113392706A (en) | Device and method for detecting smoking and using mobile phone behaviors | |
| CN113628172A (en) | Intelligent detection algorithm for personnel handheld weapons and smart city security system | |
| CN116993265A (en) | Intelligent warehouse safety management system based on Internet of things | |
| CN116912758A (en) | Target image identification method and device for potential safety hazard monitoring | |
| WO2023045239A1 (en) | Behavior recognition method and apparatus, device, medium, chip, product, and program | |
| CN112804492B (en) | Communication prompting method and device for electronic peepholes | |
| CN113645439B (en) | Event detection method and system, storage medium and electronic device | |
| CN114743157A (en) | Pedestrian monitoring method, device, equipment and medium based on video | |
| KH et al. | Smart CCTV surveillance system for intrusion detection with live streaming | |
| CN113128294A (en) | Road event evidence obtaining method and device, electronic equipment and storage medium | |
| CN113903003B (en) | Event occurrence probability determination method, storage medium, and electronic apparatus | |
| CN112991717B (en) | Vehicle track display method and related product |
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 |