CN116647643B - Intelligent security monitoring system - Google Patents
Intelligent security monitoring system Download PDFInfo
- Publication number
- CN116647643B CN116647643B CN202310637350.8A CN202310637350A CN116647643B CN 116647643 B CN116647643 B CN 116647643B CN 202310637350 A CN202310637350 A CN 202310637350A CN 116647643 B CN116647643 B CN 116647643B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- security
- video
- patrol
- area
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 198
- 238000012163 sequencing technique Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims description 27
- 230000003340 mental effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 230000006996 mental state Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D63/00—Motor vehicles or trailers not otherwise provided for
- B62D63/02—Motor vehicles
-
- 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
- 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
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention belongs to the field of monitoring and discloses an intelligent security monitoring system which comprises a monitoring camera, a security monitoring terminal, a grid division terminal, a patrol car control terminal and an unmanned patrol car; the monitoring camera is used for acquiring a monitoring video of the area where the monitoring camera is located; the security monitoring terminal is used for identifying the monitoring video and obtaining security coefficients of the area where the monitoring camera is located; the grid division terminal is used for dividing the area needing security monitoring into a plurality of grids according to the security coefficient; the patrol car control terminal is used for sequencing the grids to obtain a patrol sequence and sending the patrol sequence to the unmanned patrol car; the unmanned patrol car is used for patrol the area needing security monitoring according to the patrol sequence, obtains patrol video and sends the patrol video to the security monitoring terminal. According to the invention, patrol is performed by the unmanned patrol car, so that the walking distance of security personnel is reduced, and the security quality is ensured.
Description
Technical Field
The invention relates to the field of monitoring, in particular to an intelligent security monitoring system.
Background
The existing security monitoring system generally adopts a camera to monitor an area needing security monitoring, but because the condition that the visual field range of the camera is blocked exists, security personnel are required to patrol the area needing security monitoring so as to avoid the occurrence of a monitoring blind area. However, in the night patrol process, security personnel need to walk around to patrol, the walking distance is long, and fatigue is easy to occur, so that the security quality is not guaranteed.
Disclosure of Invention
The invention aims to disclose an intelligent security monitoring system, which solves the problems of reducing the walking distance of security personnel and ensuring the security quality when patrol is carried out on a security area at night.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an intelligent security monitoring system comprises a monitoring camera, a security monitoring terminal, a grid division terminal, a patrol car control terminal and an unmanned patrol car;
the monitoring camera is used for acquiring a monitoring video of the area where the monitoring camera is located and transmitting the monitoring video to the security monitoring terminal;
the security monitoring terminal is used for identifying the monitoring video and obtaining security coefficients of the area where the monitoring camera is located;
the grid division terminal is used for dividing the area needing security monitoring into a plurality of grids according to the security coefficient;
the patrol car control terminal is used for sequencing the grids to obtain a patrol sequence and sending the patrol sequence to the unmanned patrol car;
the unmanned patrol car is used for patrol the area needing security monitoring according to the patrol sequence, obtains patrol video and sends the patrol video to the security monitoring terminal.
Preferably, the monitoring camera and the security monitoring terminal are in communication connection in a wired connection mode.
Preferably, the security monitoring terminal comprises a video identification module and a display module;
the video identification module is used for identifying the monitoring video and acquiring security coefficients contained in the monitoring video;
the display module is used for displaying the monitoring video and/or the patrol video.
Preferably, the identifying the monitoring video to obtain the security coefficient of the area where the monitoring camera is located includes:
and identifying the monitoring video obtained by the monitoring camera by adopting a fixed identification period to obtain the security coefficient of the area where the monitoring camera is located.
Preferably, a fixed recognition period is adopted to recognize a surveillance video obtained by a surveillance camera, and a security coefficient of an area where the surveillance camera is located is obtained, including:
for the T-th identification period, T is used t,str Indicating the starting time of the T-th identification period, wherein the video segment to be identified in the monitoring video is the shooting time at [ T ] t,str -P,T t,str +P]Video clips composed of video frames within a range; p is a set range parameter, and P is greater than 0;
and identifying the obtained video clips to obtain the security coefficient of the area where the monitoring camera is located.
Preferably, the identifying the obtained video clip to obtain the security coefficient of the area where the monitoring camera is located includes:
inputting each video frame in the video clip into a pre-trained neural network model for identification, and acquiring the number of people in the video frame, the number of vehicles and the invalid visual field parameters of the video frame;
calculating a monitoring coefficient of the video frame based on the number of people in the video frame, the number of vehicles and the invalid view parameter of the video frame;
and obtaining the security coefficient of the area where the monitoring camera is located based on the monitoring coefficient.
Preferably, the calculation function of the monitoring coefficient is:
eftiv represents the monitoring coefficient, mu, of a video frame 1 、μ 2 、μ 3 The weight of the number of persons, the number of vehicles and the invalid view parameter is represented respectively, numpeo represents the number of persons in the video frame, stdpeo represents a standard value of the number of preset persons, numcar represents the number of vehicles in the video frame, stdcar represents a standard value of the number of preset vehicles, eftview represents the invalid view parameter of the video frame, and stdview represents a standard value of the preset invalid view parameter.
Preferably, obtaining the security coefficient of the area where the monitoring camera is located based on the monitoring coefficient includes:
using distmi to represent the shortest linear distance between the monitoring camera and the edge of the area needing security monitoring;
the calculation function of the security coefficient is as follows:
seccoef represents a security coefficient, ζ represents a proportional value, ζ is greater than 0 and less than 1, and mid (eftiv) represents a median value of monitoring coefficients of video frames in the video clips; aveeftiv represents the average value of the monitoring coefficients of video frames in a video clip, and distmid represents the shortest linear distance between the center of an area needing security monitoring and the edge of the area needing security monitoring.
Preferably, the unmanned patrol car comprises a shooting module and a communication module;
the communication module is used for communicating with the patrol car control terminal and communicating with the security monitoring terminal;
the shooting module is used for acquiring patrol videos in the patrol process.
Preferably, the communication module and the patrol car control terminal communicate in a wireless communication mode, and the communication module and the security monitoring terminal communicate in a wireless communication mode.
Compared with the prior art, the invention sets up the monitoring camera in the area needing security monitoring, and sets up the unmanned patrol car to patrol, thus do not need security personnel to walk around to patrol, reduce the probability of fatigue when security personnel is on duty at night, security personnel only need patrol the area needing security monitoring through patrol video in the monitoring room, so that security personnel can keep better mental state to carry out security monitoring, thereby guaranteeing the quality of security.
Drawings
The present disclosure will become more fully understood from the detailed description given herein below and the accompanying drawings, which are given by way of illustration only, and thus are not limiting of the present disclosure, and wherein:
FIG. 1 is a schematic diagram of an intelligent security monitoring system of the present invention.
FIG. 2 is a schematic diagram of a calculation process of invalid view parameters according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
The invention provides an intelligent security monitoring system, which is shown in an embodiment in fig. 1, and comprises a monitoring camera, a security monitoring terminal, a grid division terminal, a patrol car control terminal and an unmanned patrol car;
the monitoring camera is used for acquiring a monitoring video of the area where the monitoring camera is located and transmitting the monitoring video to the security monitoring terminal;
the security monitoring terminal is used for identifying the monitoring video and obtaining security coefficients of the area where the monitoring camera is located;
the grid division terminal is used for dividing the area needing security monitoring into a plurality of grids according to the security coefficient;
the patrol car control terminal is used for sequencing the grids to obtain a patrol sequence and sending the patrol sequence to the unmanned patrol car;
the unmanned patrol car is used for patrol the area needing security monitoring according to the patrol sequence, obtains patrol video and sends the patrol video to the security monitoring terminal.
Compared with the prior art, the invention sets up the monitoring camera in the area needing security monitoring, and sets up the unmanned patrol car to patrol, thus do not need security personnel to walk around to patrol, reduce the probability of fatigue when security personnel is on duty at night, security personnel only need patrol the area needing security monitoring through patrol video in the monitoring room, so that security personnel can keep better mental state to carry out security monitoring, thereby guaranteeing the quality of security.
Preferably, the monitoring camera and the security monitoring terminal are in communication connection in a wired connection mode.
For example, the communication connection may be made by hardware such as coaxial cable, twisted pair, optical fiber, etc.
Preferably, the monitoring camera and the security monitoring terminal can be in communication connection in a wireless connection mode.
For example, the communication connection may be performed by WiFi communication, 4G communication, 5G communication, or the like.
Preferably, the security monitoring terminal comprises a video identification module and a display module;
the video identification module is used for identifying the monitoring video and acquiring security coefficients contained in the monitoring video;
the display module is used for displaying the monitoring video and/or the patrol video.
Specifically, the security monitoring terminal can be arranged in a security room, and security personnel can check the monitoring video and patrol video displayed by the display module in the security room, so that the security personnel do not need to walk around to patrol, and the walking distance of the security personnel during security monitoring at night is effectively reduced.
Preferably, the identifying the monitoring video to obtain the security coefficient of the area where the monitoring camera is located includes:
and identifying the monitoring video obtained by the monitoring camera by adopting a fixed identification period to obtain the security coefficient of the area where the monitoring camera is located.
Specifically, the identification periods of the monitoring videos obtained by all the monitoring cameras are the same.
Preferably, a fixed recognition period is adopted to recognize a surveillance video obtained by a surveillance camera, and a security coefficient of an area where the surveillance camera is located is obtained, including:
for the T-th identification period, T is used t,str Indicating the starting time of the T-th identification period, wherein the video segment to be identified in the monitoring video is the shooting time at [ T ] t,str -P,T t,str +P]Video clips composed of video frames within a range; p is a set range parameter, and P is greater than 0;
and identifying the obtained video clips to obtain the security coefficient of the area where the monitoring camera is located.
Specifically, because the monitoring camera transmits a video stream, that is, new video frames are continuously transmitted to the security monitoring terminal, the video segments are obtained by cutting the monitoring video segments based on the identification period, and the security coefficient is calculated based on the video segments, so that all video frames can be prevented from being identified, and the calculation pressure of the security monitoring terminal can be effectively reduced.
Preferably, the identifying the obtained video clip to obtain the security coefficient of the area where the monitoring camera is located includes:
inputting each video frame in the video clip into a pre-trained neural network model for identification, and acquiring the number of people in the video frame, the number of vehicles and the invalid visual field parameters of the video frame;
calculating a monitoring coefficient of the video frame based on the number of people in the video frame, the number of vehicles and the invalid view parameter of the video frame;
and obtaining the security coefficient of the area where the monitoring camera is located based on the monitoring coefficient.
Specifically, the neural network model may employ a HACNN model, a Siamese model, or the like.
Preferably, as shown in fig. 2, the calculation function of the invalid view parameter is:
partitioning the video frame, and dividing the video frame into a plurality of subareas with the same area;
respectively calculating the image entropy of each sub-region;
taking the image entropy as a pixel value of a sub-region, taking each sub-region as a pixel point, and calculating the sub-region by using an otsu algorithm to obtain a segmentation threshold;
acquiring the number smlnum of sub-areas with pixel values smaller than a segmentation threshold value;
calculating invalid view parameters:
eftview represents an invalid view parameter, and subemm represents the total number of subregions.
In the invention, the invalid view parameters are used for representing the shielding condition of the monitoring camera, and the more serious the shielding is, the smaller the corresponding invalid view parameters are. The traditional recognition method generally directly calculates the proportion of the foreground to judge the shielding condition, and the larger the proportion of the foreground is, the smaller the shielding is, but when the camera is shielded, the region of the shielding part in the image frame can be mistakenly regarded as the foreground, and obviously, the region is incorrect.
Therefore, the invention calculates the segmentation threshold by taking each sub-region as a pixel point and taking the image entropy as a pixel value and adopting the otsu algorithm, and then calculates the invalid visual field parameter based on the segmentation threshold. The method has the advantages that the threshold value used for judging the effective area and the ineffective area does not need to be appointed in advance, so that the threshold value can be adaptively changed along with the change of information in the video frame, more accurate ineffective visual field parameters can be obtained, and the effective area and the ineffective area are divided according to the image entropy.
Preferably, the calculation function of the monitoring coefficient is:
eftiv represents the monitoring coefficient, mu, of a video frame 1 、μ 2 、μ 3 The weight of the number of persons, the number of vehicles and the invalid view parameter is represented respectively, numpeo represents the number of persons in the video frame, stdpeo represents a standard value of the number of preset persons, numcar represents the number of vehicles in the video frame, stdcar represents a standard value of the number of preset vehicles, eftview represents the invalid view parameter of the video frame, and stdview represents a standard value of the preset invalid view parameter.
In the invention, the monitoring coefficient is obtained by weighted summation of the number of people, the number of vehicles and the invalid visual field parameters, and the smaller the number of people is, the larger the number of vehicles is, the larger the invalid visual field parameters are, and the larger the monitoring coefficient is. Therefore, the more serious the shielding condition is, the fewer the number of people is, the earlier the time for carrying out security monitoring patrol in the area with more vehicles is, and the quality of the security monitoring patrol is improved. Because when the number of people is small, the probability of illegal actions is larger, and the more vehicles are, the more serious the shielding is, the smaller the effective monitoring range is, and at this time, the more urgent is the need for the unmanned patrol car to patrol preferentially.
Preferably, obtaining the security coefficient of the area where the monitoring camera is located based on the monitoring coefficient includes:
using distmi to represent the shortest linear distance between the monitoring camera and the edge of the area needing security monitoring;
the calculation function of the security coefficient is as follows:
seccoef represents a security coefficient, ζ represents a proportional value, ζ is greater than 0 and less than 1, and mid (eftiv) represents a median value of monitoring coefficients of video frames in the video clips; aveeftiv represents the average value of the monitoring coefficients of video frames in a video clip, and distmid represents the shortest linear distance between the center of an area needing security monitoring and the edge of the area needing security monitoring.
The security coefficient is calculated on the basis of the monitoring coefficient, and the greater the security coefficient is, the invention does not directly use the maximum value of the monitoring coefficient of the video frame in the video segment to calculate the security coefficient, but calculates the security coefficient by acquiring the median value, so that the influence of sudden errors on the accuracy degree of the security coefficient can be effectively reduced, for example, when the monitoring camera is just blocked by a floating balloon, if the maximum value is directly adopted to calculate, the value of the security coefficient is very large, but the balloon does not always block the monitoring camera, thus leading to preferentially patrol such areas which do not need to be patrol, and further reducing the quality of security patrol. In addition, in the process of calculating the security coefficient, the numerical value of distmi is also considered, and the smaller the distmi is, the larger the security coefficient is, so that the closer to the edge of the area needing patrol is, the earlier patrol can be performed, and the patrol quality is improved. Because the closer to the edge, the greater the probability of representing an illegal intrusion.
Preferably, the area needing security monitoring is divided into a plurality of grids according to the security coefficient, including:
every other identification period, the area needing security monitoring is divided into grids, and the dividing process is as follows:
saving security coefficients belonging to the same identification period to the set security;
the size of the grid is calculated:
the area represents the size of the grid, stdarea represents the standard area of the grid set in advance, secoefma represents the maximum value of the elements in the securset, mid (securset) represents the median value of the elements in the securset, and timeyc represents the mental grade of the time period in which the identification period is located; cynnum tableMaximum value of mental grade, Ω 1 And omega 2 The weights of the security coefficient and the time period are respectively represented, and the mental level is set as follows:
the mental grade of the time period from 0 point to 6 points is 1 grade, the mental grade of the time period from 6 points to 12 points is 4 grade, the mental grade of the time period from 12 points to 18 points is 3 grade, and the mental grade of the time period from 18 points to 0 point is 2 grade;
the area needing security monitoring is divided into a plurality of grids with the size of area grid.
In the invention, the size of the grid is not fixed, but is adaptively changed along with different time periods, specifically, in the time period which is easier to fatigue, the mental level is lower, so that the area of the grid is smaller, the subdivision degree of patrol areas is higher, but the number of patrol areas is not larger, because the invention sorts the patrol areas according to the security coefficients, the security coefficients are close, but the probability of the grid with a longer distance is larger, obviously, because the time is spent on the path between the round-trip grids, and the patrol efficiency is seriously affected by the patrol sequence. In addition, when the time periods are the same, the median value of the security coefficient is larger, the situation of security is more severe, at the moment, the area of the grid is smaller, the smaller the grid area is, the security patrol is facilitated to be performed on the area needing urgent patrol, and when the area of the grid is larger, most of the area needing no urgent patrol is possibly contained in the area needing no urgent patrol.
Therefore, the invention carries out comprehensive calculation through the median value and the spirit level of the security coefficient, can avoid the condition that patrol quality is easy to be reduced when the size of the grid is directly fixed, and can improve the patrol quality.
Preferably, ordering the grids to obtain a patrol order includes:
acquiring a security coefficient nearest to the sorting moment;
acquiring a set of cameras contained in a grid;
taking the maximum value of security coefficients of the areas where all the monitoring cameras in the camset are located as a sequencing parameter;
and ordering the grids according to the order of the ordering parameters from large to small to obtain a patrol order.
Specifically, the invention does not limit the sequencing period, so when the sequencing period is inconsistent with the identification period, the nearest security coefficient from the sequencing moment can be used as the basis for sequencing, thereby realizing correct sequencing.
Preferably, the unmanned patrol car comprises a shooting module and a communication module;
the communication module is used for communicating with the patrol car control terminal and communicating with the security monitoring terminal;
the shooting module is used for acquiring patrol videos in the patrol process.
Preferably, the communication module and the patrol car control terminal communicate in a wireless communication mode, and the communication module and the security monitoring terminal communicate in a wireless communication mode.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. The intelligent security monitoring system is characterized by comprising a monitoring camera, a security monitoring terminal, a grid division terminal, a patrol car control terminal and an unmanned patrol car;
the monitoring camera is used for acquiring a monitoring video of the area where the monitoring camera is located and transmitting the monitoring video to the security monitoring terminal;
the security monitoring terminal is used for identifying the monitoring video and obtaining security coefficients of the area where the monitoring camera is located;
the grid division terminal is used for dividing the area needing security monitoring into a plurality of grids according to the security coefficient;
the patrol car control terminal is used for sequencing the grids to obtain a patrol sequence and sending the patrol sequence to the unmanned patrol car;
the unmanned patrol car is used for patrol the area needing security monitoring according to the patrol sequence, obtaining patrol video and sending the patrol video to the security monitoring terminal;
identifying the monitoring video to obtain the security coefficient of the area where the monitoring camera is located, comprising:
identifying a monitoring video obtained by a monitoring camera by adopting a fixed identification period to obtain a security coefficient of an area where the monitoring camera is positioned;
the monitoring video obtained by the monitoring camera is identified by adopting a fixed identification period, and the security coefficient of the area where the monitoring camera is located is obtained, comprising the following steps:
for the T-th identification period, T is used t,str Indicating the starting time of the t-th identification period, wherein the video segment to be identified in the monitoring video is the shooting timeVideo clips composed of video frames within a range; p is a set range parameter, and P is greater than 0;
identifying the obtained video clips to obtain security coefficients of the area where the monitoring camera is located;
identifying the obtained video clip to obtain the security coefficient of the area where the monitoring camera is located, including:
inputting each video frame in the video clip into a pre-trained neural network model for identification, and acquiring the number of people in the video frame, the number of vehicles and the invalid visual field parameters of the video frame;
calculating a monitoring coefficient of the video frame based on the number of people in the video frame, the number of vehicles and the invalid view parameter of the video frame;
acquiring a security coefficient of an area where the monitoring camera is located based on the monitoring coefficient;
the calculation function of the monitoring coefficient is as follows:
eftiv represents the monitoring coefficient, mu, of a video frame 1 、μ 2 、μ 3 The method comprises the steps of respectively representing the number of people, the number of vehicles and the weight of an invalid view parameter, wherein numpeo represents the number of people in a video frame, stdpeo represents the standard value of the preset number of people, numcar represents the number of vehicles in the video frame, stdcar represents the standard value of the preset number of vehicles, eftview represents the invalid view parameter of the video frame, and stdview represents the standard value of the preset invalid view parameter;
based on the monitoring coefficient, obtaining the security coefficient of the area where the monitoring camera is located, comprising:
using distmi to represent the shortest linear distance between the monitoring camera and the edge of the area needing security monitoring;
the calculation function of the security coefficient is as follows:
seccoef represents a security coefficient, ζ represents a proportional value, ζ is greater than 0 and less than 1, and mid (eftiv) represents a median value of monitoring coefficients of video frames in the video clips; aveeftiv represents the average value of the monitoring coefficients of video frames in a video clip, and distmid represents the shortest linear distance between the center of an area needing security monitoring and the edge of the area needing security monitoring;
the calculation function of the invalid view parameter is:
partitioning the video frame, and dividing the video frame into a plurality of subareas with the same area;
respectively calculating the image entropy of each sub-region;
taking the image entropy as a pixel value of a sub-region, taking each sub-region as a pixel point, and calculating the sub-region by using an otsu algorithm to obtain a segmentation threshold;
acquiring the number smlnum of sub-areas with pixel values smaller than a segmentation threshold value;
calculating invalid view parameters:
eftview represents an invalid view parameter, and subemm represents the total number of subregions;
the area that needs to carry out security monitoring is divided into a plurality of grids according to security coefficient to carry out the meshing, including:
every other identification period, the area needing security monitoring is divided into grids, and the dividing process is as follows:
saving security coefficients belonging to the same identification period to the set security;
the size of the grid is calculated:
the area represents the size of the grid, stdarea represents the standard area of the grid set in advance, secoefma represents the maximum value of the elements in the securset, mid (securset) represents the median value of the elements in the securset, and timeyc represents the mental grade of the time period in which the identification period is located; cynnum represents the maximum value of mental grade, Ω 1 And omega 2 The weights of the security coefficient and the time period are respectively represented, and the mental level is set as follows:
the mental grade of the time period from 0 point to 6 points is 1 grade, the mental grade of the time period from 6 points to 12 points is 4 grade, the mental grade of the time period from 12 points to 18 points is 3 grade, and the mental grade of the time period from 18 points to 0 point is 2 grade;
dividing an area needing security monitoring into a plurality of grids with the size of area;
ordering the grids to obtain patrol orders, including:
acquiring a security coefficient nearest to the sorting moment;
acquiring a set of cameras contained in a grid;
taking the maximum value of security coefficients of the areas where all the monitoring cameras in the camset are located as a sequencing parameter;
and ordering the grids according to the order of the ordering parameters from large to small to obtain a patrol order.
2. The intelligent security monitoring system of claim 1, wherein the monitoring camera is in communication connection with the security monitoring terminal by means of wired connection.
3. The intelligent security monitoring system of claim 1, wherein the security monitoring terminal comprises a video identification module and a display module;
the video identification module is used for identifying the monitoring video and acquiring security coefficients contained in the monitoring video;
the display module is used for displaying the monitoring video and/or the patrol video.
4. The intelligent security monitoring system of claim 1, wherein the unmanned patrol car comprises a shooting module and a communication module;
the communication module is used for communicating with the patrol car control terminal and communicating with the security monitoring terminal;
the shooting module is used for acquiring patrol videos in the patrol process.
5. The intelligent security monitoring system of claim 4, wherein the communication module communicates with the patrol car control terminal in a wireless communication manner, and the communication module communicates with the security monitoring terminal in a wireless communication manner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310637350.8A CN116647643B (en) | 2023-06-01 | 2023-06-01 | Intelligent security monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310637350.8A CN116647643B (en) | 2023-06-01 | 2023-06-01 | Intelligent security monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116647643A CN116647643A (en) | 2023-08-25 |
| CN116647643B true CN116647643B (en) | 2024-03-26 |
Family
ID=87643130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310637350.8A Active CN116647643B (en) | 2023-06-01 | 2023-06-01 | Intelligent security monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116647643B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117528028B (en) * | 2023-11-08 | 2024-04-19 | 广州雄风信息技术有限公司 | Security video monitoring system based on Internet of things |
| CN117319809B (en) * | 2023-11-24 | 2024-03-01 | 广州劲源科技发展股份有限公司 | Intelligent adjusting method for monitoring visual field |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017027246A (en) * | 2015-07-17 | 2017-02-02 | 株式会社日立製作所 | Monitoring system and monitoring method |
| WO2017084008A1 (en) * | 2015-11-16 | 2017-05-26 | 深圳市赛亿科技开发有限公司 | Security protection robot |
| CN108769611A (en) * | 2018-06-14 | 2018-11-06 | 安徽宜介科技有限公司 | A kind of robot video security monitoring system based on mobile Internet |
| CN109270931A (en) * | 2018-08-15 | 2019-01-25 | 深圳市烽焌信息科技有限公司 | Control the method and device of robot patrol |
| CN110290347A (en) * | 2019-05-28 | 2019-09-27 | 安徽安科智能有限公司 | A kind of intelligent security guard network video cooperative monitoring system and method |
| CN112437272A (en) * | 2020-11-13 | 2021-03-02 | 珠海大横琴科技发展有限公司 | Method and device for monitoring area |
| CN112437280A (en) * | 2020-11-23 | 2021-03-02 | 单昂 | Intelligent monitoring security data processing management system based on big data analysis |
| CN112565696A (en) * | 2020-12-04 | 2021-03-26 | 盐城中科高通量计算研究院有限公司 | Auxiliary monitoring method for patrol vehicle |
| CN113359751A (en) * | 2021-06-23 | 2021-09-07 | 武汉理工大学 | Unmanned security patrol system |
| CN113467447A (en) * | 2021-06-24 | 2021-10-01 | 武汉虹信技术服务有限责任公司 | Illegal person intrusion monitoring system and method based on patrol robot |
| CN115079589A (en) * | 2022-08-24 | 2022-09-20 | 深圳泛和科技有限公司 | Park management method, device, system, electronic equipment and computer readable medium |
| CN115146878A (en) * | 2022-09-05 | 2022-10-04 | 深圳市海邻科信息技术有限公司 | Commanding and scheduling method, system, vehicle-mounted equipment and computer readable storage medium |
| CN115273459A (en) * | 2022-06-25 | 2022-11-01 | 河南机电职业学院 | Unmanned safety cruiser |
| CN115366935A (en) * | 2022-08-31 | 2022-11-22 | 钱盼婷 | Community's security is with track cruiser |
-
2023
- 2023-06-01 CN CN202310637350.8A patent/CN116647643B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017027246A (en) * | 2015-07-17 | 2017-02-02 | 株式会社日立製作所 | Monitoring system and monitoring method |
| WO2017084008A1 (en) * | 2015-11-16 | 2017-05-26 | 深圳市赛亿科技开发有限公司 | Security protection robot |
| CN108769611A (en) * | 2018-06-14 | 2018-11-06 | 安徽宜介科技有限公司 | A kind of robot video security monitoring system based on mobile Internet |
| CN109270931A (en) * | 2018-08-15 | 2019-01-25 | 深圳市烽焌信息科技有限公司 | Control the method and device of robot patrol |
| CN110290347A (en) * | 2019-05-28 | 2019-09-27 | 安徽安科智能有限公司 | A kind of intelligent security guard network video cooperative monitoring system and method |
| CN112437272A (en) * | 2020-11-13 | 2021-03-02 | 珠海大横琴科技发展有限公司 | Method and device for monitoring area |
| CN112437280A (en) * | 2020-11-23 | 2021-03-02 | 单昂 | Intelligent monitoring security data processing management system based on big data analysis |
| CN112565696A (en) * | 2020-12-04 | 2021-03-26 | 盐城中科高通量计算研究院有限公司 | Auxiliary monitoring method for patrol vehicle |
| CN113359751A (en) * | 2021-06-23 | 2021-09-07 | 武汉理工大学 | Unmanned security patrol system |
| CN113467447A (en) * | 2021-06-24 | 2021-10-01 | 武汉虹信技术服务有限责任公司 | Illegal person intrusion monitoring system and method based on patrol robot |
| CN115273459A (en) * | 2022-06-25 | 2022-11-01 | 河南机电职业学院 | Unmanned safety cruiser |
| CN115079589A (en) * | 2022-08-24 | 2022-09-20 | 深圳泛和科技有限公司 | Park management method, device, system, electronic equipment and computer readable medium |
| CN115366935A (en) * | 2022-08-31 | 2022-11-22 | 钱盼婷 | Community's security is with track cruiser |
| CN115146878A (en) * | 2022-09-05 | 2022-10-04 | 深圳市海邻科信息技术有限公司 | Commanding and scheduling method, system, vehicle-mounted equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116647643A (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116647643B (en) | Intelligent security monitoring system | |
| WO2022011828A1 (en) | System and method for detecting object that gets in and out of elevator, object detection system, elevator light curtain, and elevator device | |
| CN108205891B (en) | A kind of vehicle monitoring method of monitoring area | |
| CN112437280A (en) | Intelligent monitoring security data processing management system based on big data analysis | |
| CN110458157A (en) | A kind of power cable production process intelligent monitor system | |
| CN116071657B (en) | Intelligent early warning system for building construction video monitoring big data | |
| US20220148316A1 (en) | Method and device for determining road operation condition, and storage medium | |
| CN111488803A (en) | Airport target behavior understanding system integrating target detection and target tracking | |
| CN111460988A (en) | Illegal behavior identification method and device | |
| CN115358951B (en) | Intelligent ring main unit monitoring system based on image recognition | |
| CN111815951A (en) | Road vehicle monitoring system and method based on intelligent vision Internet of things | |
| CN115797856A (en) | Intelligent construction scene safety monitoring method based on machine vision | |
| CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
| JP7199645B2 (en) | Object recognition system and object recognition method | |
| CN113705504A (en) | Marine fishery safety production management system based on video processing technology | |
| KR101357721B1 (en) | Apparatus for detecting of single elderly persons’ abnormal situation using image and method thereof | |
| CN105262984B (en) | A kind of detector with fixing device | |
| CN110407045A (en) | A kind of method and Intelligent lift system showing elevator interior personnel distributed intelligence | |
| CN113674271B (en) | Transformer monitoring system based on cloud computing | |
| CN107609498B (en) | Data processing method of computer monitoring system | |
| CN117560470B (en) | Cloud edge end cooperative distributed industrial television monitoring and identifying system and method | |
| CN114436086B (en) | Method and system for identifying and alarming darkness of elevator car | |
| CN117902415B (en) | Intelligent elevator monitoring method and device based on Internet of things | |
| CN113800348B (en) | Intelligent community elevator management system | |
| CN116229389B (en) | Vehicle collision early warning method, system, electronic equipment and storage medium |
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 |