CN111178241A - Intelligent monitoring system and method based on video analysis - Google Patents
Intelligent monitoring system and method based on video analysis Download PDFInfo
- Publication number
- CN111178241A CN111178241A CN201911376466.0A CN201911376466A CN111178241A CN 111178241 A CN111178241 A CN 111178241A CN 201911376466 A CN201911376466 A CN 201911376466A CN 111178241 A CN111178241 A CN 111178241A
- Authority
- CN
- China
- Prior art keywords
- data
- image frame
- sensitive
- behavior
- frame data
- 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
-
- 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
-
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- 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
-
- 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
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to an intelligent monitoring system and method based on video analysis, which comprises the following steps: the data acquisition module is used for acquiring video data acquired by the monitoring equipment in real time and historical video data; the data preprocessing module is used for decoding and framing the acquired video data through openCV and ffmpeg to acquire a picture frame queue; the data analysis module is used for analyzing whether the image frame data has the sensitive behaviors or not by utilizing a sensitive behavior analysis model determined based on the sensitive behavior rule; and the alarm module is connected with the main control platform and used for determining an alarm mode according to the corresponding relation between the preset sensitive behavior and the alarm mode when the sensitive behavior in the image frame data is determined, and sending alarm information to the main control platform according to the determined alarm mode. The invention enhances the online video transmission speed while improving the real-time control of kitchen sanitation by catering merchants, assists governments in completing online intelligent supervision, and effectively improves the targeted supervision capability of market supervision departments.
Description
Technical Field
The present invention relates to the field of video data analysis technology, and more particularly, to an intelligent monitoring system and method based on video analysis.
Background
Some terminals such as the existing hard disk video recorder have relatively wide application in security protection fields such as public security, traffic and the like, wherein similar video monitoring terminals are also arranged in bright kitchen ranges in catering enterprises governed by a market supervision and management bureau, and the video integration and live broadcast of cameras of the enterprises are realized. As the number of cameras of a supervision enterprise increases, it becomes difficult to integrate various categories of cameras; and the problem that the operation specification of the operator is identified manually by a supervisor becomes difficult.
Therefore, an intelligent monitoring method based on video analysis is needed.
Disclosure of Invention
The invention provides an intelligent monitoring system and method based on video analysis, and aims to solve the problem of how to analyze and monitor video data.
In order to solve the above problems, according to an aspect of the present invention, there is provided an intelligent monitoring system based on video analysis, the system including:
the data acquisition module is respectively connected with the monitoring equipment and the data storage module and is used for acquiring video data acquired by the monitoring equipment in real time and historical video data stored in the data storage module;
the data preprocessing module is connected with the data analysis module and is used for decoding and framing the acquired video data through openCV and ffmpeg to acquire a picture frame queue;
the data analysis module is connected with the alarm module and used for carrying out image analysis on image frame data in the image frame queue by utilizing a sensitive behavior analysis model determined based on a sensitive behavior rule so as to analyze whether the image frame data has sensitive behaviors or not;
and the alarm module is connected with the main control platform and used for determining an alarm mode according to the corresponding relation between the preset sensitive behavior and the alarm mode when the sensitive behavior in the image frame data is determined, and sending alarm information to the main control platform according to the determined alarm mode.
Preferably, the data preprocessing module is further configured to:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
Preferably, the data analysis module performs image analysis on the image frame data in the image frame queue by using a sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether an attention target exists in the image frame data, and the method includes:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
Preferably, the data analysis module is further configured to:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
Preferably, wherein the system further comprises:
the monitoring equipment management module is used for remotely configuring and maintaining the monitoring equipment at the front end;
and the alarm video extraction module is used for extracting and storing video data containing the sensitive behaviors according to a preset time rule when the sensitive behaviors are determined to be identified.
According to another aspect of the present invention, there is provided an intelligent monitoring method based on video analysis, the method comprising:
acquiring video data acquired by monitoring equipment in real time and historical video data stored in a data storage module;
decoding and framing the acquired video data through openCV and ffmpeg to acquire a picture frame queue;
carrying out image analysis on image frame data in an image frame queue by using a sensitive behavior analysis model determined based on a sensitive behavior rule so as to analyze whether sensitive behaviors exist in the image frame data or not;
and when the sensitive behavior exists in the image frame data, determining an alarm mode according to the corresponding relation between the preset sensitive behavior and the alarm mode, and sending alarm information according to the determined alarm mode.
Preferably, wherein the method further comprises:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
Preferably, the performing image analysis on the image frame data in the image frame queue by using the sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether the target of interest exists in the image frame data includes:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
Preferably, wherein the method further comprises:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
Preferably, wherein the method further comprises:
remotely configuring and maintaining the monitoring equipment at the front end;
and when the sensitive behavior is determined to be identified, extracting the video data containing the sensitive behavior according to a preset time rule and storing the video data.
The invention provides an intelligent monitoring system and method based on video analysis, which decode and frame-divide the acquired video data through openCV and ffmpeg to acquire a picture frame queue; carrying out image analysis on image frame data in the image frame queue by using a sensitive behavior analysis model determined based on a sensitive behavior rule; and sending alarm information when the sensitive behavior exists in the image frame data. The invention can integrate video data of different types of cameras, simultaneously utilizes technologies such as video calculation, face recognition and the like to realize the analysis and calculation of the operation specification of catering operators, comprehensively improves the management capability of a supervision department on a kitchen, enhances the interactivity and the intellectualization of equipment, enhances the online video transmission speed, enhances the data analysis capability, strengthens the output of data and information, assists a government to complete online intelligent supervision, provides data required by supervision for the supervision department, provides a monitoring and alarming function, and effectively improves the targeted supervision capability of a market supervision department while promoting the real-time control of the catering department on the kitchen sanitation.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a schematic diagram of an intelligent monitoring system 100 based on video analysis according to an embodiment of the present invention;
FIG. 2 is a diagram of the physical architecture of an intelligent monitoring system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the processing power of an intelligent monitoring system according to an embodiment of the invention; and
fig. 4 is a flowchart of an intelligent monitoring method 400 based on video analysis according to an embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Fig. 1 is a schematic structural diagram of an intelligent monitoring system 100 based on video analysis according to an embodiment of the present invention. As shown in fig. 1, the intelligent monitoring system based on video analysis provided by the embodiment of the invention can integrate video data of different types of cameras, and simultaneously utilize technologies such as video calculation and face recognition to realize analysis and calculation of operation specifications of catering practitioners, comprehensively improve the management capability of a supervision department on a kitchen, enhance the interactivity and intelligence of equipment, enhance the online video transmission speed, enhance the data analysis capability, enhance the output of data and information, assist a government to complete online intelligent supervision while improving real-time control of catering merchants on the kitchen sanitation, provide data required by supervision for the supervision department, provide a monitoring and alarming function, and effectively improve the targeted supervision capability of a market supervision department. The intelligent monitoring system 100 based on video analysis provided by the embodiment of the invention comprises: the system comprises a data acquisition module 101, a data preprocessing module 102, a data analysis module 103 and an alarm module 104.
Preferably, the data obtaining module 101 is connected to the monitoring device and the data storage module, respectively, and is configured to obtain video data acquired by the monitoring device in real time and historical video data stored in the data storage module.
In the embodiment of the invention, the system terminal machine is connected with an external camera by a network cable to acquire network video data, or directly acquires historical video data from the data storage module. And after receiving the video data, sending the video data to a CPU connected with the video data, transmitting an instruction by the CPU to control a video computing module to complete video analysis and computation, and transmitting the computed data to background software for display and storage through a network cable on a mainboard.
In the embodiment of the invention, the obtained video data can realize the real-time monitoring image viewing of videos of different manufacturers on the same video interface. For example, a video of a vendor such as A, B and C may be opened on the same interface. In addition, the operations of checking videos connected with the front end, calling video data, downloading, editing, controlling, capturing and the like can be realized in real time through the network. The staff can also check any video resource through the browser of the computer, and can realize browsing images, snapping pictures, controlling the pan-tilt, playing back video data, downloading video data, editing video data and the like.
Preferably, the data preprocessing module 102 is connected to the data analysis module, and is configured to decode and frame the acquired video data through openCV and ffmpeg to acquire the image frame queue.
Preferably, the data preprocessing module 102 is further configured to:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
In the embodiment of the invention, the acquired historical video data is subjected to framing processing into a frame queue through openCV and ffmpeg. The historical data is video data which is recorded by the monitoring equipment or stored in other storage equipment in the local area network and occurs in the past, such as video data in formats of AVI, WMV, MPEG or MP 4. During preprocessing, video format recognition is carried out on historical data, then the historical data are compressed into a frame-by-frame relatively independent picture through openCV and ffmpeg framing, and the frame-by-frame relatively independent picture is stored in a frame queue.
For video data acquired from the monitoring equipment in real time, the real-time data is decoded through ffmpeg and is processed into a frame queue in a framing mode. The monitoring equipment is a video monitoring platform, a camera and the like, and video data can be collected in real time through the monitoring equipment. During preprocessing, video data are received in real time through a network interface, real-time video decoding is carried out on the real-time video data through ffmpeg, the video data are divided into frames, the frames are compressed into one frame and one frame of relatively independent pictures, and the pictures are stored in a frame queue.
In addition, before the frame image data is stored in the frame queue, the video image after decoding and framing needs to be subjected to value filtering processing for denoising.
Preferably, the data analysis module 103 is connected to the alarm module, and configured to perform image analysis on image frame data in an image frame queue by using a sensitive behavior analysis model determined based on a sensitive behavior rule, so as to analyze whether a sensitive behavior exists in the image frame data.
Preferably, the data analysis module 103 performs image analysis on the image frame data in the image frame queue by using a sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether an attention target exists in the image frame data, including:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
Preferably, wherein the data analysis module 103 is further configured to:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
In the implementation mode of the invention, a series of video analysis rules are formulated according to the requirements of the catering enterprise supervision policy, and the main rules comprise:
and (3) personnel intrusion rule: and setting face information of restaurant workers. And the analysis model center gives an alarm when the person is not in the face information list of the person.
The rule of wearing the hat by the person is as follows: and setting rules of hat of restaurant workers, wherein the rules comprise factors such as hat color, type, wearing position and the like. And giving an alarm to the person who does not wear the hat according to the requirement in the analysis model.
The rule of wearing the mask by the person is as follows: setting rules of the mask of restaurant workers, wherein the rules comprise factors such as color, type, wearing position and the like of the mask. And giving an alarm to the person who does not wear the mask according to the requirement in the analysis model.
The smoking behavior rules of the persons are as follows: and setting smoking behavior rules of restaurant workers. And giving an alarm for the smoking condition in the no-smoking area in the analysis model.
The rule of the person playing the mobile phone is as follows: and setting rules of mobile phone playing behaviors of restaurant workers. And giving an alarm for the condition that the mobile phone is played in the operation room in the analysis model.
When the image frame data is analyzed, a face recognition unit, a behavior recognition unit and an event recognition unit of the data analysis module are respectively utilized for analyzing, whether the recognized sensitive behaviors between two adjacent frames are the same or not is judged, if yes, whether the overlapping rate between the two adjacent frames is reasonable or not is judged, if yes, the sensitive behaviors are determined to be recognized, and whether the sensitive behaviors exist in the image frame data or not is determined; otherwise, the identified sensitive behavior is excluded.
Preferably, the alarm module 104 is connected to the main control platform, and configured to determine an alarm mode according to a corresponding relationship between a preset sensitive behavior and the alarm mode when it is determined that the sensitive behavior exists in the image frame data, and send alarm information to the main control platform according to the determined alarm mode.
Preferably, wherein the system further comprises:
the monitoring equipment management module is used for remotely configuring and maintaining the monitoring equipment at the front end;
and the alarm video extraction module is used for extracting and storing video data containing the sensitive behaviors according to a preset time rule when the sensitive behaviors are determined to be identified.
In the embodiment of the invention, the terminal can report the video analysis result by setting an alarm reporting mode through a background management function page. In addition, the system of the invention also provides different remote configuration functions of the front-end equipment, and equipment maintenance can be carried out through a system console, including management functions of addition, modification, deletion and the like, so that the remote configuration function is realized. The system of the invention can monitor the running condition of the front-end equipment in real time and the operations of remote setting, control, shutdown, time correction and the like: put more at the front end to present equipment, it is not very convenient to manage, if efficient, convenient can set up front end equipment, equipment time has gone away and has also had some errors, if carry out the unified management through the platform to equipment timing religion etc. including can long-rangely restart, shut down etc.. The invention can also store the video data into the local hard disk, is convenient for the manager to check the historical video and provides the function of checking the alarm video; the configuration of the background can be followed, and the accessed front-end video data can be locally stored, so that the subsequent historical videos can be conveniently checked; the alarm video data discovered by video analysis and calculation can be stored in a centralized manner according to background configuration, so that the alarm data can be quickly positioned and checked.
Fig. 2 is a diagram of the physical architecture of an intelligent monitoring system according to an embodiment of the present invention. As shown in fig. 2, the video analysis terminal acquires the overall state of the kitchen through the acquisition camera, analyzes the overall state, and sends an analysis result to the supervisory system or the school terminal. The video intelligent analysis and calculation can be carried out on the situations of personnel invasion, cap wearing according to regulations, mask wearing according to regulations, smoking in a smoke-forbidden area, mobile phone playing in a kitchen operation area and the like by configuring the video calculation model rule in the background, and the real-time report of the video analysis result can be realized by configuring the alarm rule in the background. FIG. 3 is a schematic diagram of processing power of an intelligent monitoring system according to an embodiment of the invention. As shown in fig. 3, when the video analysis result indicates that there is a human invasion problem, a dressing problem, an operation violation or a harmful substance invasion, the system can be set off to alarm. And for the kitchens with multiple illegal behaviors, alarm information can be directly sent to a supervision department.
The intelligent monitoring system based on video analysis can integrate video data of different types of cameras, realize standard analysis and calculation of operation of catering practitioners by utilizing technologies such as video calculation, face recognition and the like, and provide functions such as video integration, acquisition, video analysis, monitoring, early warning and the like for catering enterprise managers and supervision departments.
Fig. 4 is a flowchart of an intelligent monitoring method 400 based on video analysis according to an embodiment of the present invention. As shown in fig. 4, the intelligent monitoring method 100 based on video analysis provided by the embodiment of the present invention starts at step 401, and obtains video data collected by a monitoring device in real time and historical video data stored in a data storage module at step 401.
In step 402, the acquired video data is decoded and frame-divided by openCV and ffmpeg to acquire a video frame queue.
Preferably, wherein the method further comprises:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
In step 403, image analysis is performed on the image frame data in the image frame queue by using a sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether a sensitive behavior exists in the image frame data.
Preferably, the performing image analysis on the image frame data in the image frame queue by using the sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether the target of interest exists in the image frame data includes:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
Preferably, wherein the method further comprises:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
In step 404, when it is determined that the image frame data has the sensitive behavior, an alarm mode is determined according to a corresponding relationship between a preset sensitive behavior and the alarm mode, and alarm information is sent according to the determined alarm mode.
Preferably, wherein the method further comprises:
remotely configuring and maintaining the monitoring equipment at the front end;
and when the sensitive behavior is determined to be identified, extracting the video data containing the sensitive behavior according to a preset time rule and storing the video data.
The video analysis-based intelligent monitoring method 400 according to the embodiment of the present invention corresponds to the video analysis-based intelligent monitoring system 100 according to another embodiment of the present invention, and is not described herein again.
The invention has been described with reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [ device, component, etc ]" are to be interpreted openly as referring to at least one instance of said device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. An intelligent monitoring system based on video analysis, the system comprising:
the data acquisition module is respectively connected with the monitoring equipment and the data storage module and is used for acquiring video data acquired by the monitoring equipment in real time and historical video data stored in the data storage module;
the data preprocessing module is connected with the data analysis module and is used for decoding and framing the acquired video data through openCV and ffmpeg to acquire a picture frame queue;
the data analysis module is connected with the alarm module and used for carrying out image analysis on image frame data in the image frame queue by utilizing a sensitive behavior analysis model determined based on a sensitive behavior rule so as to analyze whether the image frame data has sensitive behaviors or not;
and the alarm module is connected with the main control platform and used for determining an alarm mode according to the corresponding relation between the preset sensitive behavior and the alarm mode when the sensitive behavior in the image frame data is determined, and sending alarm information to the main control platform according to the determined alarm mode.
2. The system of claim 1, wherein the data pre-processing module is further configured to:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
3. The system of claim 1, wherein the data analysis module performs image analysis on the image frame data in the image frame queue using a sensitive behavior analysis model determined based on the sensitive behavior rule to analyze whether the target of interest exists in the image frame data, and comprises:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
4. The system of claim 3, wherein the data analysis module is further configured to:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
5. The system of claim 1, further comprising:
the monitoring equipment management module is used for remotely configuring and maintaining the monitoring equipment at the front end;
and the alarm video extraction module is used for extracting and storing video data containing the sensitive behaviors according to a preset time rule when the sensitive behaviors are determined to be identified.
6. An intelligent monitoring method based on video analysis is characterized by comprising the following steps:
acquiring video data acquired by monitoring equipment in real time and historical video data stored in a data storage module;
decoding and framing the acquired video data through openCV and ffmpeg to acquire a picture frame queue;
carrying out image analysis on image frame data in an image frame queue by using a sensitive behavior analysis model determined based on a sensitive behavior rule so as to analyze whether sensitive behaviors exist in the image frame data or not;
and when the sensitive behavior exists in the image frame data, determining an alarm mode according to the corresponding relation between the preset sensitive behavior and the alarm mode, and sending alarm information according to the determined alarm mode.
7. The method of claim 6, further comprising:
and carrying out value filtering on the video image subjected to decoding and framing processing so as to achieve the purpose of denoising.
8. The method of claim 6, wherein performing image analysis on the image frame data in the image frame queue to analyze whether the target of interest exists in the image frame data by using a sensitive behavior analysis model determined based on the sensitive behavior rule comprises:
analyzing and processing the face information in the image frame data by using a face recognition unit; if face information which is not matched with the face image in the target database exists, determining that an attention target exists in the image frame data;
analyzing and processing the behavior characteristic sequence in the image frame data by using a behavior identification unit, and if the behavior is the same as that in a target database, determining that sensitive behavior exists in the image frame data;
and analyzing and processing event image information in the image frame data by using an event identification unit, and determining that sensitive behaviors exist in the image frame data if the same characteristic events exist in a target database.
9. The method of claim 8, further comprising:
analyzing the scene of image frame data, selecting a sensitive behavior analysis model and a target database corresponding to the scene, and filtering the identified sensitive behavior through a time sequence and a continuous multi-frame relationship, wherein the method comprises the following steps:
judging whether the identified sensitive behaviors between two adjacent frames are the same, if so, carrying out the next step, and if not, excluding the identified sensitive behaviors;
and judging whether the overlapping rate between two adjacent frames is reasonable, if so, determining that the sensitive behavior is identified, and if not, excluding the identified sensitive behavior.
10. The method of claim 6, further comprising:
remotely configuring and maintaining the monitoring equipment at the front end;
and when the sensitive behavior is determined to be identified, extracting the video data containing the sensitive behavior according to a preset time rule and storing the video data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911376466.0A CN111178241A (en) | 2019-12-27 | 2019-12-27 | Intelligent monitoring system and method based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911376466.0A CN111178241A (en) | 2019-12-27 | 2019-12-27 | Intelligent monitoring system and method based on video analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178241A true CN111178241A (en) | 2020-05-19 |
Family
ID=70652252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911376466.0A Pending CN111178241A (en) | 2019-12-27 | 2019-12-27 | Intelligent monitoring system and method based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178241A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111698473A (en) * | 2020-06-10 | 2020-09-22 | 中国工商银行股份有限公司 | Method and device for detecting staff on duty |
| CN113037958A (en) * | 2021-01-27 | 2021-06-25 | 湖北盟道信息科技有限公司 | Method and system for analyzing class-taking behaviors of students based on openCv |
| CN113610688A (en) * | 2021-06-25 | 2021-11-05 | 格讯科技(深圳)有限公司 | Food safety supervision method based on big data analysis and storage medium |
| CN116362564A (en) * | 2023-04-04 | 2023-06-30 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633238A (en) * | 2017-10-12 | 2018-01-26 | 深圳市信海通科技有限公司 | A kind of video analysis method and intellectual analysis server |
| CN108205681A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of campus food security intelligent monitoring management system |
| CN109146322A (en) * | 2018-09-12 | 2019-01-04 | 深圳市商汤科技有限公司 | Monitoring method and device and system, electronic equipment and storage medium |
| CN109413369A (en) * | 2017-08-17 | 2019-03-01 | 孟思宏 | A kind of monitor video intellectual analysis early warning platform |
| CN109495727A (en) * | 2019-01-04 | 2019-03-19 | 京东方科技集团股份有限公司 | Intelligent control method and device, system, readable storage medium storing program for executing |
| CN109936721A (en) * | 2017-12-18 | 2019-06-25 | 航天信息股份有限公司 | Monitoring system |
-
2019
- 2019-12-27 CN CN201911376466.0A patent/CN111178241A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108205681A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of campus food security intelligent monitoring management system |
| CN109413369A (en) * | 2017-08-17 | 2019-03-01 | 孟思宏 | A kind of monitor video intellectual analysis early warning platform |
| CN107633238A (en) * | 2017-10-12 | 2018-01-26 | 深圳市信海通科技有限公司 | A kind of video analysis method and intellectual analysis server |
| CN109936721A (en) * | 2017-12-18 | 2019-06-25 | 航天信息股份有限公司 | Monitoring system |
| CN109146322A (en) * | 2018-09-12 | 2019-01-04 | 深圳市商汤科技有限公司 | Monitoring method and device and system, electronic equipment and storage medium |
| CN109495727A (en) * | 2019-01-04 | 2019-03-19 | 京东方科技集团股份有限公司 | Intelligent control method and device, system, readable storage medium storing program for executing |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111698473A (en) * | 2020-06-10 | 2020-09-22 | 中国工商银行股份有限公司 | Method and device for detecting staff on duty |
| CN113037958A (en) * | 2021-01-27 | 2021-06-25 | 湖北盟道信息科技有限公司 | Method and system for analyzing class-taking behaviors of students based on openCv |
| CN113610688A (en) * | 2021-06-25 | 2021-11-05 | 格讯科技(深圳)有限公司 | Food safety supervision method based on big data analysis and storage medium |
| CN113610688B (en) * | 2021-06-25 | 2024-03-12 | 格讯科技(深圳)有限公司 | Based on big food for data analysis Security supervision method and storage medium |
| CN116362564A (en) * | 2023-04-04 | 2023-06-30 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
| CN116362564B (en) * | 2023-04-04 | 2023-09-08 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178241A (en) | Intelligent monitoring system and method based on video analysis | |
| CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
| EP1631073B1 (en) | Apparatus and methods for the detection of abnormal motion in a video stream | |
| CN111223011A (en) | Food safety supervision method and system for catering enterprises based on video analysis | |
| US7428314B2 (en) | Monitoring an environment | |
| US8107680B2 (en) | Monitoring an environment | |
| CN110705482A (en) | Personnel behavior alarm prompt system based on video AI intelligent analysis | |
| CN110147723B (en) | Method and system for processing abnormal behaviors of customers in unmanned store | |
| CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
| US20160210759A1 (en) | System and method of detecting moving objects | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN115103157A (en) | Video analysis method and device based on edge cloud cooperation, electronic equipment and medium | |
| CN110751125A (en) | Wearing detection method and device | |
| CN211184122U (en) | Intelligent video analysis system for linkage of railway operation safety prevention and control and large passenger flow early warning | |
| CN116246416A (en) | Intelligent analysis early warning platform and method for security protection | |
| CN110602453A (en) | Internet of things big data intelligent video security monitoring system | |
| CN109120896B (en) | Security video monitoring guard system | |
| CN116665121A (en) | Safety operation detection alarm method and device in safety operation scene | |
| CN203883934U (en) | Intelligent self-help bank video monitoring system | |
| CN112601054B (en) | Pickup picture acquisition method and device, storage medium and electronic equipment | |
| CN114973135A (en) | Head-shoulder-based sequential video sleep post identification method and system and electronic equipment | |
| CN115860979A (en) | Artificial intelligence management system for field operation of power grid | |
| CN115641608A (en) | Intelligent identification equipment for personal protection articles for distribution network operation based on edge intelligence | |
| CN112419638B (en) | Method and device for acquiring alarm video | |
| CN112804492B (en) | Communication prompting method and device for electronic peepholes |
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 |