CN117522017B - Smart city security monitoring system based on image recognition technology - Google Patents
Smart city security monitoring system based on image recognition technology Download PDFInfo
- Publication number
- CN117522017B CN117522017B CN202311457873.0A CN202311457873A CN117522017B CN 117522017 B CN117522017 B CN 117522017B CN 202311457873 A CN202311457873 A CN 202311457873A CN 117522017 B CN117522017 B CN 117522017B
- Authority
- CN
- China
- Prior art keywords
- security
- value
- variation
- interval
- warning
- 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 70
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 31
- 238000012163 sequencing technique Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims 1
- 238000012549 training Methods 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/776—Validation; Performance evaluation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Emergency Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a smart city security monitoring system based on an image recognition technology, which relates to the technical field of monitoring systems, and discloses an image recognition module, a security early warning module and a security preset module.
Description
Technical Field
The invention relates to the technical field of monitoring systems, in particular to a smart city security monitoring system based on an image recognition technology.
Background
The smart city originates in the media field, and is characterized in that key infrastructure components and services formed by cities such as city management, education, medical treatment, real estate, transportation, public utilities, public safety and the like are interconnected, efficient and intelligent through application of intelligent computing technologies such as Internet of things, cloud computing, big data, space geographic information integration and the like in the fields of city planning, design, construction, management, operation and the like, so that better life and working services are provided for citizens, a more favorable business development environment is created for enterprises, and a more efficient operation and management mechanism is provided for governments.
The development of the smart city in various facilities is synchronous, and the security supervision of the smart city is required to be well done. The current smart city security system monitors the security of the smart city through the cooperation of monitoring equipment and security personnel. Corresponding monitoring equipment is arranged in each area to monitor and security personnel patrol, but the configuration can only process security events when security crisis occurs, and early warning can not be carried out on the security events in advance.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a smart city security monitoring system based on an image recognition technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A smart city security monitoring system based on an image recognition technology comprises an image recognition module, a security early warning module and a security preset module;
the image recognition module is used for collecting video data shot by the monitoring equipment and sending the shot video data to the server for storage;
The security early warning module is used for sending security early warning information to security personnel positioned in a security early warning range, and specifically comprises the following steps:
Converting video data into image frames, taking the image frames as input data of a security detection model, obtaining output data of the security detection model, marking the output data as security detection values, sequencing the obtained security detection values according to the time sequence of the corresponding image frames, obtaining security variation values Af, setting one security standard variation value of each security variation value corresponding to the security monitoring type, marking the security variation value as a security optimal variation value when the security variation value is smaller than the security standard variation value, obtaining An Youzhi Bn, and marking the security variation value as security risk variation value when the security variation value is larger than or equal to the security standard variation value, and obtaining security risk value Rc;
Acquiring a security monitoring value Gt, setting a security monitoring threshold value as Dm, when the security monitoring value Gt is more than or equal to the security monitoring threshold value Dm, not performing processing, marking monitoring equipment to which the video data belongs as security early warning equipment when the security monitoring value Gt is less than the security monitoring threshold value Dm, and drawing a circle with a preset radius by taking the position of the security early warning equipment as a circle center to acquire a security early warning range, and sending security early warning information to security personnel positioned in the security early warning range;
the security protection preset module is used for adjusting the number of security protection personnel corresponding to the monitoring equipment in the security protection early warning range, and specifically comprises the following steps:
When the monitoring equipment is marked as security early-warning equipment, marking the marking time as security early-warning time, acquiring all security early-warning time of the monitoring equipment in the current time n days of the system, sequencing the security early-warning time according to the time sequence, performing time difference calculation on two adjacent security early-warning time after sequencing, acquiring to acquire security early-warning intervals, setting each security early-warning interval to correspond to a standard early-warning interval, marking the security early-warning interval as an early-warning low-standard interval when the security early-warning interval is smaller than the standard early-warning interval, acquiring to acquire to a pre-low value Xb, and marking the security early-warning interval as an early-warning high-standard interval when the security early-warning interval is larger than or equal to the standard early-warning interval, and acquiring to acquire to a pre-high value Sa;
Obtaining a security preset value Ty, setting a security preset high value as Hd, setting a security preset low value as Lm, when the security preset value Ty is larger than or equal to the security preset high value Hd, adjusting the number of security personnel of the monitoring equipment in a security early warning range upwards, when the security preset low value Lm is smaller than or equal to the security preset value Ty and smaller than the security preset high value Hd, not adjusting the number of security personnel of the monitoring equipment in the security early warning range, and when the security preset value Ty is smaller than the security preset low value Lm, adjusting the number of security personnel of the monitoring equipment in the security early warning range downwards.
Further, the security change value Af is obtained by the following steps: and marking the next previous security detection value after sequencing as a previous security detection value, marking the next security detection value after sequencing as a next security detection value, performing difference value calculation on the next security detection value and the previous security detection value, obtaining a security change value, and marking the security change value as Af.
Further, the larger the value of the output data of the security detection model is, the higher the security risk is.
Further, an Youzhi Bn is obtained by the following steps: calculating the difference value between the security standard variation value and the security variation value to obtain security variation, summing all security variation values and taking an average value to obtain average variation, marking as Wz, obtaining the shooting time of an image frame to which the security variation value belongs before the security variation is subjected, marking the time as security variation time, sequencing all security variation time according to time sequence, calculating the time difference value between two adjacent security variation time after sequencing to obtain security variation interval, summing all security variation intervals and taking an average value to obtain security variation interval, marking as Mh, and utilizing a formulaAnd obtaining An Youzhi Bn, wherein a1 is an average variable coefficient, and a2 is a security variable uniform coefficient.
Further, the security risk value Rc is obtained through the following steps: performing difference calculation on security risk variation values and security standard variation values to obtain security risk variation, summing all security risk variation values and taking an average value to obtain average security risk variation, marking as Ts, obtaining shooting time of an image frame to which a security check value belongs before the security risk variation is subjected, marking the time as security risk variation time, sequencing all security risk variation time according to time sequence, performing time difference calculation on two adjacent security risk variation time after sequencing to obtain security risk variation intervals, summing all security risk variation intervals and taking an average value to obtain security risk variation intervals, marking as Qz, and utilizing a formulaAnd obtaining an security risk value Rc, wherein b1 is an average risk variation coefficient, and b2 is a security risk variation uniform coefficient.
Further, the security monitoring value Gt is obtained through the following steps: and obtaining a security monitoring value Gt by using a formula Gt=Bn×c1-Rc×c2, wherein c1 is An Youzhi coefficients, and c2 is an security risk value coefficient.
Further, the pre-low value Xb is obtained by the following steps: and calculating the difference value between the standard early warning interval and the early warning low standard interval to obtain a pre-low interval difference, summing all the pre-low interval differences to obtain a pre-low interval total difference, marking the pre-low interval total difference as Dk, obtaining the total number of the early warning low standard intervals marked as the safety warning interval and Wg marked as the safety warning interval, and obtaining a pre-low value Xb by using a formula Xb=Dk×d1+Wg×d2, wherein d1 is a pre-low interval total difference coefficient, and d2 is an early warning low standard quantity coefficient.
Further, the pre-high value Sa is obtained by: and calculating the difference value between the early warning high standard interval and the standard early warning interval to obtain a pre-high interval difference, summing all the pre-high interval differences to obtain a pre-high interval total difference, marking the pre-high interval total difference as Rd, obtaining the total number of the early warning high standard intervals marked as the early warning high standard interval and marking the safety pre-warning interval as Kc, and obtaining the pre-high value Sa by using a formula Sa=Rd×e1+Kc×e2, wherein e1 is a pre-high interval total difference coefficient, and e2 is an early warning high standard quantity coefficient.
Further, the security protection preset value Ty is obtained through the following steps: and obtaining a security preset value Ty by using a formula Uj=Xb×f1-Saxf 2, wherein f1 is a pre-low value coefficient, and f2 is a pre-high value coefficient.
Compared with the prior art, the invention has the following beneficial effects:
1. The security early warning module is arranged, so that whether security early warning information needs to be sent to security personnel positioned in a security early warning range or not can be judged according to the change of security risks, early warning is carried out before security crisis occurs, and the security personnel can timely and efficiently handle security events;
2. The security protection preset module is arranged, the number of security protection personnel corresponding to the monitoring equipment in the security protection early warning range can be adjusted, the reasonable number of security protection personnel nearby each monitoring equipment is guaranteed on the basis of reducing the probability of security protection accidents nearby the monitoring equipment, and the security protection personnel are adjusted in real time according to the security protection conditions.
Drawings
FIG. 1 is a schematic block diagram of a security early warning module of the present invention;
fig. 2 is a schematic block diagram of a security protection preset module according to the present invention.
Detailed Description
Example 1
Referring to fig. 1, a smart city security monitoring system based on an image recognition technology comprises an image recognition module and a security early warning module.
The image recognition module is used for collecting video data shot by the monitoring equipment and sending the shot video data to the server for storage.
The security early warning module is used for sending security early warning information to security personnel positioned in a security early warning range, and specifically comprises the following steps:
Converting video data into image frames, taking the image frames as input data of a security detection model, and obtaining the security detection model through the following steps: obtaining a plurality of image frames, marking the image frames as training images, giving image labels to the training images, dividing the training images into a training set and a verification set according to a set proportion, constructing a neural network model, carrying out iterative training on the neural network model through the training set and the verification set, judging that the neural network model is completed to train when the iterative training times are greater than the iterative times threshold, and marking the trained neural network model as a security detection model. The larger the value of the output data of the security detection model is, the higher the security risk is. Obtaining output data of the security detection model, marking the output data as security detection values, sequencing the obtained security detection values according to the time sequence of corresponding image frames, obtaining a security variation value Af, and obtaining the security variation value Af through the following steps: and marking the next previous security detection value after sequencing as a previous security detection value, marking the next security detection value after sequencing as a next security detection value, performing difference value calculation on the next security detection value and the previous security detection value, obtaining a security change value, and marking the security change value as Af. Setting a security standard change value of each security change value corresponding to the security monitoring type, marking the security change value as a security optimal change value when the security change value is smaller than the security standard change value, and acquiring An Youzhi Bn and An Youzhi Bn through the following steps: calculating the difference value between the security standard variation value and the security variation value to obtain security variation, summing all security variation values and taking an average value to obtain average variation, marking as Wz, obtaining the shooting time of an image frame to which the security variation value belongs before the security variation is subjected, marking the time as security variation time, sequencing all security variation time according to time sequence, calculating the time difference value between two adjacent security variation time after sequencing to obtain security variation interval, summing all security variation intervals and taking an average value to obtain security variation interval, marking as Mh, and utilizing a formula An Youzhi Bn is obtained, wherein a1 is an average variable coefficient, a2 is a security variable uniform coefficient, the value of a1 is 0.65, and the value of a2 is 0.47. When the security change value is more than or equal to the security standard change value, marking the security change value as a security risk change value, and obtaining a security risk value Rc. The security risk value Rc is obtained by the following steps: performing difference calculation on security risk variation values and security standard variation values to obtain security risk variation, summing all security risk variation values and taking an average value to obtain average security risk variation, marking as Ts, obtaining shooting time of an image frame to which a security check value belongs before the security risk variation is subjected, marking the time as security risk variation time, sequencing all security risk variation time according to time sequence, performing time difference calculation on two adjacent security risk variation time after sequencing to obtain security risk variation intervals, summing all security risk variation intervals and taking an average value to obtain security risk variation intervals, marking as Qz, and utilizing a formula/>And obtaining an security risk value Rc, wherein b1 is an average risk variation coefficient, b2 is a security risk variation uniform coefficient, b1 is 0.64, and b2 is 0.48.
The security monitoring value Gt is obtained by the following steps: and obtaining a security monitoring value Gt by using a formula Gt=Bn×c1-Rc×c2, wherein c1 is An Youzhi coefficients, c2 is an security value coefficient, c1 is 0.99, and c2 is 0.98. Setting a security monitoring threshold value as Dm, when the security monitoring value Gt is more than or equal to the security monitoring threshold value Dm, not performing processing, marking the monitoring equipment to which the video data belongs as security early warning equipment when the security monitoring value Gt is less than the security monitoring threshold value Dm, and taking the position of the security early warning equipment as a circle center, drawing a circle with a preset radius to obtain a security early warning range, and sending security early warning information to security personnel positioned in the security early warning range. The security early warning module is arranged, whether security early warning information needs to be sent to security personnel positioned in a security early warning range or not can be judged according to the change of security risks, early warning is carried out before security crisis occurs, and the security personnel can timely and efficiently handle security events.
Example 2
Referring to fig. 2, on the basis of embodiment 1, the system further includes a security protection preset module, where the security protection preset module is used to adjust the number of security protection personnel corresponding to the monitoring device in the security protection early warning range, specifically:
When the monitoring equipment is marked as security early-warning equipment, marking the marking time as security early-warning time, acquiring all security early-warning time of the monitoring equipment at the current time n days of the system, sequencing the security early-warning time according to the time sequence, performing time difference calculation on two adjacent security early-warning time after sequencing, acquiring security early-warning intervals, setting each security early-warning interval to correspond to a standard early-warning interval, and marking the security early-warning interval as early-warning low-standard interval when the security early-warning interval is smaller than the standard early-warning interval, acquiring a pre-low value Xb, wherein the pre-low value Xb is acquired through the following steps: and carrying out difference value calculation on the standard early warning interval and the early warning low standard interval to obtain a pre-low interval difference, carrying out summation treatment on all the pre-low interval differences to obtain a pre-low interval total difference, marking the pre-low interval total difference as Dk, obtaining the total number of the safety protection early warning intervals marked as the early warning low standard interval and marking the safety protection early warning intervals as Wg, and obtaining a pre-low value Xb by using a formula Xb=Dk multiplied by d1+Wg multiplied by d2, wherein d1 is a pre-low interval total difference coefficient, d2 is an early warning low standard quantity coefficient, d1 has a value of 0.72, and d2 has a value of 0.58. When the security early warning interval is more than or equal to the standard early warning interval, marking the security early warning interval as an early warning high-standard interval, and obtaining the pre-high value Sa. The pre-high value Sa is obtained by the following steps: and calculating the difference value between the early warning high standard interval and the standard early warning interval to obtain a pre-high interval difference, summing all the pre-high interval differences to obtain a pre-high interval total difference, marking the pre-high interval total difference as Rd, obtaining the total number of the safety protection early warning intervals marked as the early warning high standard interval and marking the safety protection early warning intervals as Kc, and obtaining the pre-high value Sa by using a formula Sa=Rd×e1+Kc×e2, wherein e1 is a pre-high interval total difference coefficient, e2 is an early warning high standard quantity coefficient, e1 has a value of 0.71, and e2 has a value of 0.59.
The security preset value Ty is obtained by the following steps: obtaining a security preset value Ty by using a formula Uj=Xb×f1-Saxf2, wherein f1 is a pre-low value coefficient, f2 is a pre-high value coefficient, the value of f1 is 1.02, and the value of f2 is 1.01. Setting a security preset high value as Hd, setting a security preset low value as Lm, when the security preset value Ty is greater than or equal to the security preset high value Hd, upwardly adjusting the number of security personnel of the monitoring equipment in a security early warning range, when the security preset low value Lm is less than or equal to the security preset value Ty and less than the security preset high value Hd, not adjusting the number of security personnel of the monitoring equipment in the security early warning range, and when the security preset value Ty is less than the security preset low value Lm, downwardly adjusting the number of security personnel of the monitoring equipment in the security early warning range. The security protection preset module is arranged, the number of security protection personnel corresponding to the monitoring equipment in the security protection early warning range can be adjusted, the reasonable number of security protection personnel nearby each monitoring equipment is guaranteed on the basis of reducing the probability of security protection accidents nearby the monitoring equipment, and the security protection personnel are adjusted in real time according to the security protection conditions.
Working principle:
The security early warning module is arranged, whether security early warning information needs to be sent to security personnel positioned in a security early warning range or not can be judged according to the change of security risks, early warning is carried out before security crisis occurs, and the security personnel can timely and efficiently handle security events. The security protection preset module is arranged, the number of security protection personnel corresponding to the monitoring equipment in the security protection early warning range can be adjusted, the reasonable number of security protection personnel nearby each monitoring equipment is guaranteed on the basis of reducing the probability of security protection accidents nearby the monitoring equipment, and the security protection personnel are adjusted in real time according to the security protection conditions.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to those skilled in the art without departing from the principles of the present invention are intended to be considered as protecting the scope of the present template.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (2)
1. The intelligent city security monitoring system based on the image recognition technology is characterized by comprising an image recognition module, a security early warning module and a security preset module;
the image recognition module is used for collecting video data shot by the monitoring equipment and sending the shot video data to the server for storage;
The security early warning module is used for sending security early warning information to security personnel positioned in a security early warning range, and specifically comprises the following steps:
Converting video data into image frames, taking the image frames as input data of a security detection model, obtaining output data of the security detection model, marking the output data as security detection values, sequencing the obtained security detection values according to the time sequence of the corresponding image frames, obtaining security variation values Af, setting each security variation value to correspond to a security standard variation value, marking the security variation value as a security optimal variation value when the security variation value is smaller than the security standard variation value, obtaining An Youzhi Bn, and marking the security variation value as security risk variation value when the security variation value is larger than or equal to the security standard variation value, and obtaining security risk value Rc;
Acquiring a security monitoring value Gt, setting a security monitoring threshold value as Dm, when the security monitoring value Gt is more than or equal to the security monitoring threshold value Dm, not performing processing, marking monitoring equipment to which the video data belongs as security early warning equipment when the security monitoring value Gt is less than the security monitoring threshold value Dm, and drawing a circle with a preset radius by taking the position of the security early warning equipment as a circle center to acquire a security early warning range, and sending security early warning information to security personnel positioned in the security early warning range;
the security protection preset module is used for adjusting the number of security protection personnel corresponding to the monitoring equipment in the security protection early warning range, and specifically comprises the following steps:
When the monitoring equipment is marked as security early-warning equipment, marking the marking time as security early-warning time, acquiring all security early-warning time of the monitoring equipment n days before the current time of the system, sequencing the security early-warning time according to time sequence, performing time difference calculation on two adjacent security early-warning time after sequencing, acquiring to acquire security early-warning intervals, setting each security early-warning interval to correspond to a standard early-warning interval, marking the security early-warning interval as early-warning low-standard interval when the security early-warning interval is smaller than the standard early-warning interval, acquiring to acquire to obtain a pre-low value Xb, and marking the security early-warning interval as early-warning high-standard interval when the security early-warning interval is larger than or equal to the standard early-warning interval, and acquiring to acquire to a pre-high value Sa;
Obtaining a security preset value Ty, setting a security preset high value Hd and setting a security preset low value Lm, when the security preset value Ty is larger than or equal to the security preset high value Hd, upwardly adjusting the number of security personnel of the monitoring equipment in a security early warning range, when the security preset low value Lm is smaller than or equal to the security preset high value Hd, not adjusting the number of security personnel of the monitoring equipment in the security early warning range, and when the security preset value Ty is smaller than the security preset low value Lm, downwardly adjusting the number of security personnel of the monitoring equipment in the security early warning range;
The security change value Af is obtained through the following steps: marking the sequenced adjacent previous security detection value as a pre-change security value, marking the sequenced adjacent next security detection value as a post-change security value, performing difference value calculation on the post-change security value and the pre-change security value to obtain a security change value, and marking the security change value as Af;
An Youzhi Bn is obtained by the following steps: calculating the difference value between the security standard variation value and the security variation value to obtain security variation, summing all security variation values and taking an average value to obtain average variation, marking as Wz, obtaining the shooting time of an image frame to which the security variation value belongs before the security variation is subjected, marking the time as security variation time, sequencing all security variation time according to time sequence, calculating the time difference value between two adjacent security variation time after sequencing to obtain security variation interval, summing all security variation intervals and taking an average value to obtain security variation interval, marking as Mh, and utilizing a formula An Youzhi Bn is obtained, wherein a1 is an average variable coefficient, and a2 is a security variable uniform coefficient;
the security risk value Rc is obtained by the following steps: performing difference calculation on security risk variation values and security standard variation values to obtain security risk variation, summing all security risk variation values and taking an average value to obtain average security risk variation, marking as Ts, obtaining shooting time of an image frame to which a security check value belongs before the security risk variation is subjected, marking the time as security risk variation time, sequencing all security risk variation time according to time sequence, performing time difference calculation on two adjacent security risk variation time after sequencing to obtain security risk variation intervals, summing all security risk variation intervals and taking an average value to obtain security risk variation intervals, marking as Qz, and utilizing a formula Obtaining an security risk value Rc, wherein b1 is an average risk variation coefficient, and b2 is a security risk variation uniform separation coefficient;
The security monitoring value Gt is obtained through the following steps: obtaining a security monitoring value Gt by using a formula Gt=Bn×c1-Rc×c2, wherein c1 is An Youzhi coefficients, and c2 is an security risk value coefficient;
The pre-low value Xb is obtained by the following steps: calculating the difference value between the standard early warning interval and the early warning low standard interval to obtain a pre-low interval difference, summing all the pre-low interval differences to obtain a pre-low interval total difference, marking the pre-low interval total difference as Dk, obtaining the total number of the early warning low standard intervals marked as the safety warning interval, marking the safety warning interval as Wg, and obtaining a pre-low value Xb by using a formula Xb=Dk×d1+Wg×d2, wherein d1 is a pre-low interval total difference coefficient, and d2 is an early warning low standard quantity coefficient;
The pre-high value Sa is obtained by the following steps: calculating the difference value between the early warning high standard interval and the standard early warning interval to obtain a pre-high interval difference, summing all the pre-high interval differences to obtain a pre-high interval total difference, marking the pre-high interval total difference as Rd, obtaining the total number of the early warning high standard intervals marked as the early warning high standard interval and marking the safety pre-warning interval as Kc, and obtaining the pre-high value Sa by using a formula Sa=Rd×e1+Kc×e2, wherein e1 is a pre-high interval total difference coefficient, and e2 is an early warning high standard quantity coefficient;
The security protection preset value Ty is obtained through the following steps: and obtaining a security preset value Ty by using a formula Uj=Xb×f1-Saxf 2, wherein f1 is a pre-low value coefficient, and f2 is a pre-high value coefficient.
2. The smart city security monitoring system based on the image recognition technology of claim 1, wherein the larger the value of the security detection model output data is, the higher the security risk is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311457873.0A CN117522017B (en) | 2023-11-04 | 2023-11-04 | Smart city security monitoring system based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311457873.0A CN117522017B (en) | 2023-11-04 | 2023-11-04 | Smart city security monitoring system based on image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117522017A CN117522017A (en) | 2024-02-06 |
| CN117522017B true CN117522017B (en) | 2024-06-04 |
Family
ID=89742974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311457873.0A Active CN117522017B (en) | 2023-11-04 | 2023-11-04 | Smart city security monitoring system based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117522017B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040707A (en) * | 2018-09-19 | 2018-12-18 | 信利光电股份有限公司 | A kind of security monitoring device and method |
| CN113066248A (en) * | 2021-03-25 | 2021-07-02 | 武汉畅途网络科技有限公司 | Intelligent community construction security monitoring intelligent management system based on video image processing |
| CN114615471A (en) * | 2022-03-21 | 2022-06-10 | 安徽老品牌智能科技有限公司 | Security protection monitored control system based on intelligent electronic product |
| CN114743141A (en) * | 2022-04-07 | 2022-07-12 | 安徽晶奇网络科技股份有限公司 | Dangerous behavior detection system for intelligent community |
| CN115273413A (en) * | 2022-07-04 | 2022-11-01 | 江苏启智电子工程有限公司 | Building intelligent security system based on Internet of things |
| CN115393140A (en) * | 2022-07-20 | 2022-11-25 | 郑州轻工业大学 | Community fire-fighting management system based on Internet of things |
| KR20230051851A (en) * | 2021-10-12 | 2023-04-19 | (주)비바 | Control system for preventing safety accidents and operation method thereof |
| CN116279519A (en) * | 2023-05-17 | 2023-06-23 | 山东新凌志检测技术有限公司 | Active safety early warning system for automobile |
| CN116844105A (en) * | 2023-06-10 | 2023-10-03 | 广州启盟信息科技有限公司 | Logistics service monitoring system |
| CN116906836A (en) * | 2023-08-30 | 2023-10-20 | 广东胜昌科技有限公司 | Visual management monitoring system and method based on GIS (geographic information system) urban drainage pipe network |
-
2023
- 2023-11-04 CN CN202311457873.0A patent/CN117522017B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040707A (en) * | 2018-09-19 | 2018-12-18 | 信利光电股份有限公司 | A kind of security monitoring device and method |
| CN113066248A (en) * | 2021-03-25 | 2021-07-02 | 武汉畅途网络科技有限公司 | Intelligent community construction security monitoring intelligent management system based on video image processing |
| KR20230051851A (en) * | 2021-10-12 | 2023-04-19 | (주)비바 | Control system for preventing safety accidents and operation method thereof |
| CN114615471A (en) * | 2022-03-21 | 2022-06-10 | 安徽老品牌智能科技有限公司 | Security protection monitored control system based on intelligent electronic product |
| CN114743141A (en) * | 2022-04-07 | 2022-07-12 | 安徽晶奇网络科技股份有限公司 | Dangerous behavior detection system for intelligent community |
| CN115273413A (en) * | 2022-07-04 | 2022-11-01 | 江苏启智电子工程有限公司 | Building intelligent security system based on Internet of things |
| CN115393140A (en) * | 2022-07-20 | 2022-11-25 | 郑州轻工业大学 | Community fire-fighting management system based on Internet of things |
| CN116279519A (en) * | 2023-05-17 | 2023-06-23 | 山东新凌志检测技术有限公司 | Active safety early warning system for automobile |
| CN116844105A (en) * | 2023-06-10 | 2023-10-03 | 广州启盟信息科技有限公司 | Logistics service monitoring system |
| CN116906836A (en) * | 2023-08-30 | 2023-10-20 | 广东胜昌科技有限公司 | Visual management monitoring system and method based on GIS (geographic information system) urban drainage pipe network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117522017A (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256447A (en) | A kind of unmanned plane video analysis method based on deep neural network | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| CN103000029B (en) | Automobile video frequency recognition methods and application thereof | |
| CN108270999A (en) | A kind of object detection method, image recognition server and system | |
| CN108549862A (en) | Abnormal scene detection method and device | |
| CN113569956A (en) | Mountain fire disaster investigation and identification method based on AI algorithm | |
| CN114693053A (en) | AI intelligent analysis and detection-based risk assessment and risk early warning system and method | |
| CN117522017B (en) | Smart city security monitoring system based on image recognition technology | |
| CN113963373A (en) | Video image dynamic detection and tracking algorithm based system and method | |
| Statsenko et al. | Developing software and hardware for automation of ground urban transport traffic management | |
| CN103824074A (en) | Crowd density estimation method based on background subtraction and texture features and system | |
| CN113628172A (en) | Intelligent detection algorithm for personnel handheld weapons and smart city security system | |
| CN117319809A (en) | Intelligent adjusting method for monitoring visual field | |
| CN112270207A (en) | Smoke and fire detection method in community monitoring scene | |
| Choi et al. | Air quality prediction with 1-dimensional convolution and attention on multi-modal features | |
| CN110070344A (en) | The city management system of task quantization | |
| Beiji et al. | Crime hotspot detection and monitoring using video based event modeling and mapping techniques | |
| CN113191170B (en) | Public facility two-dimensional code damage inspection effectiveness prediction method and system | |
| CN117830949B (en) | Smart city management system and method based on image processing | |
| CN115393900A (en) | Intelligent construction site safety supervision method and system based on Internet of things | |
| CN114973704A (en) | Method, device, equipment and storage medium for generating signal control strategy | |
| Prezioso et al. | Integrating Object Detection and Advanced Analytics for Smart City Crowd Management | |
| CN114373145A (en) | Monitoring video scene classification method based on ORB algorithm and capable of obtaining key frames | |
| CN113946464A (en) | Alarm noise reduction method combining model and experience pre-training and parallel deduction | |
| CN113516850A (en) | Pipeline traffic flow data acquisition method based on space syntactic analysis |
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 |