CN112437280A - Intelligent monitoring security data processing management system based on big data analysis - Google Patents
Intelligent monitoring security data processing management system based on big data analysis Download PDFInfo
- Publication number
- CN112437280A CN112437280A CN202011321019.8A CN202011321019A CN112437280A CN 112437280 A CN112437280 A CN 112437280A CN 202011321019 A CN202011321019 A CN 202011321019A CN 112437280 A CN112437280 A CN 112437280A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- time period
- dangerous
- module
- sub
- 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.)
- Withdrawn
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 240
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 5
- 230000007774 longterm Effects 0.000 abstract description 5
- 230000002354 daily effect Effects 0.000 description 11
- 239000000284 extract Substances 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Library & Information Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a big data analysis-based intelligent monitoring security data processing and management system which comprises a region dividing module, an image acquisition module, a time period dividing module, a feature extraction module, a storage database, an image preprocessing module, a dangerous feature database, an analysis cloud platform, a video retrieval module, an early warning module and a display terminal. According to the invention, a large amount of useless video image data is removed through the image preprocessing module, and the dangerous behavior type characteristics are contrastingly extracted from the reserved video image data through the characteristic extraction module and the dangerous characteristic database, so that the problems that the existing video monitoring resource data is massive and complicated, occupies a large amount of storage, and is high in construction capital of monitoring hardware are solved, the contrast analysis operation speed of effective data is improved, the method is suitable for monitoring and using in some long-term monitoring areas, the hardware cost is reduced, a large amount of time is saved, and the normal development of security monitoring work of monitoring personnel is promoted.
Description
Technical Field
The invention belongs to the field of monitoring video data processing and analysis, and relates to an intelligent monitoring security data processing and management system based on big data analysis.
Background
With the development of modern information society, the living standard of people is also continuously improved, so the requirement on safety is more and more urgent, and in recent years, a batch of intelligent security monitoring systems or products with different degrees emerge successively at home and abroad, so that the visible security monitoring system gradually becomes intelligent from digitalization and networking. In the security monitoring industry, the original and lagged manual comparison mode is basically used for real-time video monitoring and later-stage query for specific events, the existing video monitoring resource data are massive and complicated, invalid data is up to more than 70%, a large amount of storage is occupied, the construction capital of monitoring hardware is high, meanwhile, the comparison analysis and operation speed of the valid data is low, the method cannot be applied to monitoring in some long-term monitoring areas, the data comparison and analysis speed cannot be improved, the hardware cost is reduced, the purpose of saving a large amount of time while the data analysis capability is improved cannot be achieved, the monitoring security system cannot be guaranteed to have high timeliness, and therefore, the method is very unfavorable for the normal security monitoring work of monitoring personnel.
Disclosure of Invention
Aiming at the problems, the invention provides an intelligent monitoring security data processing management system based on big data analysis, which removes a large amount of useless video image data through an image preprocessing module, and contrasts and extracts dangerous behavior type characteristics from the retained video image data through a characteristic extraction module and a dangerous characteristic database, thereby solving the problems that the existing video monitoring resource data is massive and complicated, occupies a large amount of storage, and has higher occupation ratio on the construction capital of monitoring hardware, improving the contrast analysis operation speed of effective data, being suitable for monitoring and using in some long-term monitoring areas, reducing the hardware cost, achieving the purpose of saving a large amount of time while improving the data analysis capability, and further promoting the normal development of security monitoring work of monitoring personnel.
The purpose of the invention can be realized by the following technical scheme:
a smart monitoring security data processing management system based on big data analysis comprises a region dividing module, an image acquisition module, a time period dividing module, a feature extraction module, a storage database, an image preprocessing module, a dangerous feature database, an analysis cloud platform, a video retrieval module, an early warning module and a display terminal;
the image acquisition module is respectively connected with the region division module and the time period division module, the storage database is respectively connected with the time period division module, the feature extraction module and the video retrieval module, the image preprocessing module is respectively connected with the time period division module and the feature extraction module, the feature extraction module is respectively connected with the dangerous feature database, the analysis cloud platform and the display terminal, and the analysis cloud platform is respectively connected with the dangerous feature database and the early warning module;
the area division module is used for carrying out area division on the monitoring area, dividing the monitoring area into a plurality of monitoring sub-areas which are the same in area and are connected with each other in a gridding division mode, numbering the monitoring sub-areas according to a set sequence, and sequentially marking the monitoring sub-areas as 1,2,. once, m,. once, n;
the image acquisition module comprises a plurality of high-definition cameras which are respectively used for monitoring each monitoring subarea in real time, acquiring a monitoring video of each monitoring subarea and sending the monitoring video of each monitoring subarea to the time period division module;
the time period dividing module receives the monitoring videos of each monitoring subarea sent by the image acquisition module, is used for dividing the time periods of the received monitoring videos of each monitoring subarea, can divide the monitoring videos into a plurality of time periods according to a time interval value preset by a monitoring person, numbers the divided time periods according to the time sequence, and sequentially marks the time periods as 1,2,m(am1,am2,...,amt,...,amh)，amt represents a monitoring video in a corresponding t time period in the mth monitoring sub-area, and sends a monitoring video set of each day time period to the image preprocessing module and the storage database;
the image preprocessing module receives the daily time period monitoring video set sent by the time period dividing module and performs image preprocessing on the daily time period monitoring video, and the specific processing process comprises the following steps:
s1: extracting the monitoring video of each time period in each monitoring subregion in a daily time period monitoring video set;
s2: acquiring video time of monitoring videos of each time period in each monitoring sub-area, decomposing the monitoring videos of each time period in each monitoring sub-area into a plurality of images according to the number of video frames of the video time, numbering the decomposed images according to a preset sequence, and sequentially marking the images as 1,2,. once, j,. once, k;
s3, extracting the outline characteristics of the person from each image decomposed by the monitoring video in each time period in each monitoring sub-area, if the outline characteristics of the person can not be extracted from a certain image, then indicating that no human body exists on the image, removing the image, if the outline characteristics of the person can be extracted from a certain image, indicating that the human body exists on the image, reserving the image, and further obtaining each image reserved in each time period in each monitoring sub-area, wherein the image is marked as a target image;
s4: carrying out image enhancement preprocessing operation on each target image reserved in each time period in each monitoring sub-area;
s5: the target images after the image enhancement preprocessing obtained in the step S4 are formed into a time-period target image set B of each daymt(bmt1,bmt2,...,bmtj,...,bmtk)，bmtj represents the jth target image in the tth time period in the mth monitoring sub-area, and sends the target image set of each day time period to the feature extraction module;
the characteristic extraction module receives the target image set of each time period sent by the image preprocessing module, is used for analyzing and processing the target images in each time period in each monitoring sub-area in the target image set of each time period, identifies and extracts the behavior type characteristics existing in the target images, extracts the characteristics corresponding to different dangerous behavior types in the dangerous characteristic database, and combines the behavior type characteristics of the target images in each time period in each monitoring sub-area with the characteristics not existing in the dangerous characteristic databaseComparing the characteristics corresponding to the dangerous behavior types to form a time slot target image characteristic comparison set B 'of each day'mt(b′mt1,b′mt2,...,b′mtj,...,b′mtk)，b′mtj is a comparison value of behavior type features in the jth target image in the tth time period in the mth monitoring sub-area and features corresponding to a certain dangerous behavior type, and b 'is obtained if the behavior type features in the jth target image in the tth time period in the mth monitoring sub-area are successfully compared with the features corresponding to the certain dangerous behavior type in the dangerous feature database'mtj is equal to a fixed value R, R>0, if the comparison between the behavior type feature in the jth target image in the jth time period in the mth monitoring sub-area and the feature corresponding to a certain dangerous behavior type in the dangerous feature database fails, b'mtj is equal to 0, the dangerous behavior types, the time period numbers and the monitored sub-region numbers corresponding to all the successfully-compared monitored sub-regions are recorded at the same time, the successfully-compared monitored sub-regions are marked as dangerous sub-regions, the numbers of the dangerous sub-regions are counted, the dangerous sub-regions are marked as 1,2, asi(csi1,csi2,...,csip,...,csiq)，csip represents the p-th dangerous behavior type in the ith dangerous time period in the s-th dangerous subarea, the dangerous behavior type set of each day time period is sent to a storage database, the numbers of all dangerous subareas, different dangerous behavior types and dangerous time period numbers corresponding to the dangerous subareas are sent to a display terminal, and the formed time period target image feature comparison set is sent to an analysis cloud platform;
analyzing a time period target image feature comparison set sent by a feature extraction module received by the cloud platform to count the risk coefficient values of all monitoring sub-regions, extracting the risk coefficient thresholds corresponding to the first-level, second-level and third-level risk levels stored in the risk feature database, if the risk coefficient value of a certain monitoring sub-region is smaller than the risk coefficient threshold corresponding to the first-level risk level, the monitoring sub-region is a first-level risk level, if the risk coefficient value of a certain monitoring sub-region is greater than the risk coefficient threshold value corresponding to the first-level risk level and is less than the risk coefficient threshold value corresponding to the second-level risk level, the monitoring sub-region is a secondary risk level, if the risk coefficient value corresponding to a certain monitoring sub-region is greater than the risk coefficient threshold value corresponding to the secondary risk level, the monitoring sub-regions are in three-level danger levels, and the danger levels corresponding to the monitoring sub-regions are respectively sent to the early warning module;
the storage database receives the dangerous behavior category set of each day time period sent by the characteristic extraction module and the monitoring video set of each day time period sent by the time period division module, and stores the dangerous behavior category set of each day time period and the monitoring video set of each day time period;
the danger characteristic database stores danger coefficient threshold values corresponding to first-level, second-level and third-level danger grades, and stores characteristics corresponding to different dangerous behavior types;
the early warning module receives and analyzes the danger levels corresponding to the monitoring sub-areas sent by the cloud platform and gives early warnings of different levels;
the display terminal receives the serial numbers of all the dangerous subregions sent by the characteristic extraction module and the serial numbers of different dangerous behavior types and dangerous time periods corresponding to the dangerous subregions and displays the serial numbers;
the video retrieval module is used for inquiring all dangerous behavior types meeting the corresponding retrieval conditions from the dangerous behavior type set of the time period every day stored in the storage database according to the retrieval conditions input by the user, and providing the dangerous behavior types for further analysis and discrimination of monitoring personnel.
Furthermore, the number of the high-definition cameras and the number of each monitoring subarea are kept consistent.
Further, the image preprocessing module includes a median filtering unit.
Furthermore, the middle finger filtering unit is used for performing noise interference removing processing on the video frame images in the monitoring videos of all time periods in all monitoring sub-areas, and removing a large amount of useless information doped by the external environment in the video frame images.
Further, the retrieval condition includes a risk time period, a risk detection sub-region number, and one or more risk behavior categories.
Further, the magnitude sequence of the risk coefficient threshold values corresponding to the first-level, second-level and third-level risk levels is that xi 1 is less than xi 2 and less than xi 3.
Further, the risk factor value of the monitoring sub-area is calculated as
θmRisk coefficient value, b ', expressed as m-th monitoring sub-region'mtj is expressed as a contrast value of behavior type characteristics in the jth target image in the tth time period in the mth monitoring sub-area and characteristics corresponding to different dangerous behavior types.
Further, a larger hazard coefficient value for a monitored sub-region indicates that the monitored sub-region is more hazardous, and a smaller hazard coefficient value for the monitored sub-region indicates that the monitored sub-region is safer.
Has the advantages that:
(1) according to the invention, through the image preprocessing module, the feature extraction module and the dangerous feature database, dangerous behavior type features in video image data are contrastingly extracted, a large amount of useless video image data are removed, the problems that the existing video monitoring resource data are massive and complicated, occupy a large amount of storage and are high in construction capital of monitoring hardware are solved, the contrast analysis operation speed of effective data is improved, the method is suitable for monitoring and using in some long-term monitoring areas, the hardware cost is reduced, the purpose of saving a large amount of time while improving the data analysis capability is achieved, and the normal development of security monitoring work of monitoring personnel is promoted.
(2) According to the invention, in the analysis cloud platform, the risk coefficient of each monitoring sub-region is calculated, and the corresponding risk level of each monitoring sub-region is counted, so that the safety condition of each monitoring sub-region is visually and quantitatively displayed, and monitoring personnel can take corresponding countermeasures according to the safety condition, thereby protecting the property safety and the personal safety of people in various aspects and in various ranges.
(3) In the image preprocessing module, a large amount of useless information doped by the external environment in the image is removed by extracting the video frame image in the monitoring video, and the interference of the useless information on the image is reduced, so that a target image containing a large amount of useful information is obtained, the quality of the video is improved, and the identification of important things in the video is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a smart monitoring security data processing and management system based on big data analysis includes a region division module, an image acquisition module, a time period division module, a feature extraction module, a storage database, an image preprocessing module, a dangerous feature database, an analysis cloud platform, a video retrieval module, an early warning module and a display terminal;
the image acquisition module is respectively connected with the region division module and the time period division module, the storage database is respectively connected with the time period division module, the feature extraction module and the video retrieval module, the image preprocessing module is respectively connected with the time period division module and the feature extraction module, the feature extraction module is respectively connected with the dangerous feature database, the analysis cloud platform and the display terminal, and the analysis cloud platform is respectively connected with the dangerous feature database and the early warning module;
the area division module is used for carrying out area division on the monitoring area, dividing the monitoring area into a plurality of monitoring sub-areas which are the same in area and are connected with each other in a gridding division mode, numbering the monitoring sub-areas according to a set sequence, and sequentially marking the monitoring sub-areas as 1,2,. once, m,. once, n;
the image acquisition module comprises a plurality of high-definition cameras, the number of the high-definition cameras is consistent with that of each monitoring subarea, the high-definition cameras are respectively used for monitoring each monitoring subarea in real time to obtain monitoring videos of each monitoring subarea and send the monitoring videos of each monitoring subarea to the time period division module, and the high-definition cameras are arranged in each monitoring subarea to prevent a dead angle area in the monitoring area from being monitored, so that the whole area is monitored in multiple angles and multiple directions, and the accuracy and reliability of video image data are improved;
the time period dividing module receives the monitoring videos of each monitoring subarea sent by the image acquisition module, is used for dividing the time periods of the received monitoring videos of each monitoring subarea, can divide the monitoring videos into a plurality of time periods according to a time interval value preset by a monitoring person, numbers the divided time periods according to the time sequence, and sequentially marks the time periods as 1,2,m(am1,am2,...,amt,...,amh)，amt represents a monitoring video in a corresponding t time period in the mth monitoring sub-area, and sends a monitoring video set of each day time period to the image preprocessing module and the storage database;
the image preprocessing module comprises a median filtering unit and is used for performing denoising and interference processing on video frame images in the monitoring videos of all time periods in all monitoring sub-areas, removing a large amount of useless information doped by the external environment in the video frame images, reducing the interference of the useless information on the video frame images, facilitating subsequent image processing, receiving a time period monitoring video set of each day sent by the time period dividing module, and performing image preprocessing on the monitoring videos of each day time period, wherein the specific processing process comprises the following steps:
s1: extracting the monitoring video of each time period in each monitoring subregion in a daily time period monitoring video set;
s2: acquiring video time of monitoring videos of each time period in each monitoring sub-area, decomposing the monitoring videos of each time period in each monitoring sub-area into a plurality of images according to the number of video frames of the video time, numbering the decomposed images according to a preset sequence, and sequentially marking the images as 1,2,. once, j,. once, k;
s3, extracting the outline characteristics of the person from each image decomposed by the monitoring video in each time period in each monitoring sub-area, if the outline characteristics of the person can not be extracted from a certain image, then indicating that no human body exists on the image, removing the image, if the outline characteristics of the person can be extracted from a certain image, indicating that the human body exists on the image, reserving the image, and further obtaining each image reserved in each time period in each monitoring sub-area, wherein the image is marked as a target image;
s4: carrying out image enhancement preprocessing operation on each target image reserved in each time period in each monitoring sub-area;
s5: the target images after the image enhancement preprocessing obtained in the step S4 are formed into a time-period target image set B of each daymt(bmt1,bmt2,...,bmtj,...,bmtk)，bmtj represents the jth target image in the tth time period in the mth monitoring sub-area, and sends the target image set of each day time period to the feature extraction module;
according to the embodiment, the video frame images in the monitoring video are extracted, a large amount of useless information doped by the external environment in the images is removed, and the interference of the useless information on the images is reduced, so that the target images containing a large amount of useful information are obtained, the quality of the video is improved, and the identification of important objects in the video is facilitated.
Feature extraction module receives image preprocessingThe module is used for sending a daily time period target image set, analyzing and processing target images in each time period in each monitoring sub-area in the daily time period target image set, identifying and extracting behavior type features existing in the target images, extracting features corresponding to different dangerous behavior types in a dangerous feature database, comparing the behavior type features of the target images in each time period in each monitoring sub-area with the features corresponding to different dangerous behavior types in the dangerous feature database, and forming a daily time period target image feature comparison set B'mt(b′mt1,b′mt2,...,b′mtj,...,b′mtk)，b′mtj is a comparison value of behavior type features in the jth target image in the tth time period in the mth monitoring sub-area and features corresponding to a certain dangerous behavior type, and b 'is obtained if the behavior type features in the jth target image in the tth time period in the mth monitoring sub-area are successfully compared with the features corresponding to the certain dangerous behavior type in the dangerous feature database'mtj is equal to a fixed value R, R>0, if the comparison between the behavior type feature in the jth target image in the jth time period in the mth monitoring sub-area and the feature corresponding to a certain dangerous behavior type in the dangerous feature database fails, b'mtj is equal to 0, the dangerous behavior types, the time period numbers and the monitored sub-region numbers corresponding to all the successfully-compared monitored sub-regions are recorded at the same time, the successfully-compared monitored sub-regions are marked as dangerous sub-regions, the numbers of the dangerous sub-regions are counted, the dangerous sub-regions are marked as 1,2, asi(csi1,csi2,...,csip,...,csiq)，csip represents the p-th dangerous behavior type in the ith dangerous time period in the s-th dangerous subarea, the dangerous behavior type set of each day time period is sent to a storage database, and the serial numbers of all dangerous subareas and different dangerous lines corresponding to the dangerous subareasThe type and danger time period numbers are sent to a display terminal, and a formed time period target image feature comparison set is sent to an analysis cloud platform;
analyzing a time period target image feature comparison set sent by a cloud platform receiving feature extraction module to count the risk coefficient value of each monitoring sub-region, wherein the risk coefficient value calculation formula of the monitoring sub-region is
θmRisk coefficient value, b ', expressed as m-th monitoring sub-region'mtj represents a comparison value of behavior type characteristics in a jth target image in a tth time period in the mth monitoring sub-area and characteristics corresponding to different dangerous behavior types, the larger the danger coefficient value of the monitoring sub-area is, the more dangerous the monitoring sub-area is, the smaller the danger coefficient value of the monitoring sub-area is, the more safe the monitoring sub-area is, the danger coefficient threshold values corresponding to the first-level, second-level and third-level danger levels stored in the danger characteristic database are extracted, if the danger coefficient value of a certain monitoring sub-area is smaller than the danger coefficient threshold value corresponding to the first-level danger level, the monitoring sub-area is the first-level danger level, if the danger coefficient value of a certain monitoring sub-area is larger than the danger coefficient threshold value corresponding to the first-level danger level and smaller than the danger coefficient threshold value corresponding to the second-level danger level, the monitoring sub-area is the second-level danger level, the monitoring sub-regions are in three-level danger levels, and the danger levels corresponding to the monitoring sub-regions are respectively sent to the early warning module;
according to the embodiment, the danger coefficient of each monitoring sub-region is calculated, the danger level corresponding to each monitoring sub-region is counted, the safety condition of each monitoring sub-region is visually and quantitatively displayed, and monitoring personnel can take corresponding countermeasures according to the safety condition of the monitoring personnel, so that the property safety and the personal safety of people are protected in multiple aspects and multiple ranges.
The storage database receives the daily time period dangerous category set sent by the characteristic extraction module and the daily time period monitoring video set sent by the time period division module, and stores the daily time period dangerous category set and the daily time period monitoring video set;
the danger characteristic database stores danger coefficient thresholds corresponding to first-level, second-level and third-level danger levels, the magnitude sequence of the danger coefficient thresholds corresponding to the first-level, second-level and third-level danger levels is xi 1 < xi 2 < xi 3, and characteristics corresponding to different dangerous behavior types are stored;
the early warning module receives and analyzes the danger levels corresponding to the monitoring sub-areas sent by the cloud platform and gives early warnings of different levels;
the display terminal receives the serial numbers of all the dangerous subregions sent by the characteristic extraction module and the serial numbers of different dangerous behavior types and dangerous time periods corresponding to the dangerous subregions and displays the serial numbers;
the video retrieval module is used for inquiring all dangerous behavior types meeting the corresponding retrieval conditions from a dangerous type set in a time period every day stored in the storage database according to retrieval conditions input by a user, including dangerous time periods, dangerous detection sub-region numbers and one or more dangerous behavior types, and providing the dangerous behavior types for further analysis and discrimination of monitoring personnel.
According to the invention, a large amount of useless video image data is removed through the image preprocessing module, and dangerous behavior type characteristics are contrastingly extracted from the reserved video image data through the characteristic extraction module and the dangerous characteristic database, so that the problems that the existing video monitoring resource data is massive and complicated, occupies a large amount of storage, and is high in construction capital of monitoring hardware are solved, the contrast analysis operation speed of effective data is improved, the method is suitable for monitoring and using in some long-term monitoring areas, the hardware cost is reduced, the purpose of saving a large amount of time while improving the data analysis capacity is achieved, and the normal development of security monitoring work of monitoring personnel is promoted.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
Claims (8)
1. The utility model provides an wisdom control security protection data processing management system based on big data analysis which characterized in that: the system comprises a region dividing module, an image acquisition module, a time period dividing module, a feature extraction module, a storage database, an image preprocessing module, a dangerous feature database, an analysis cloud platform, a video retrieval module, an early warning module and a display terminal;
the image acquisition module is respectively connected with the region division module and the time period division module, the storage database is respectively connected with the time period division module, the feature extraction module and the video retrieval module, the image preprocessing module is respectively connected with the time period division module and the feature extraction module, the feature extraction module is respectively connected with the dangerous feature database, the analysis cloud platform and the display terminal, and the analysis cloud platform is respectively connected with the dangerous feature database and the early warning module;
the area division module is used for carrying out area division on the monitoring area, dividing the monitoring area into a plurality of monitoring sub-areas which are the same in area and are connected with each other in a gridding division mode, numbering the monitoring sub-areas according to a set sequence, and sequentially marking the monitoring sub-areas as 1,2,. once, m,. once, n;
the image acquisition module comprises a plurality of high-definition cameras which are respectively used for monitoring each monitoring subarea in real time, acquiring a monitoring video of each monitoring subarea and sending the monitoring video of each monitoring subarea to the time period division module;
the time period dividing module receives the monitoring videos of each monitoring sub-region sent by the image acquisition module, is used for dividing the time periods of the received monitoring videos of each monitoring sub-region, can divide the monitoring videos into a plurality of time periods according to a time interval value preset by a monitoring person, numbers the divided time periods according to the time sequence, and sequentially marks the time periods as 1,2,m(am1,am2,...,amt,...,amh)，amt represents a monitoring video in a corresponding t time period in the mth monitoring sub-area, and sends a monitoring video set of each day time period to the image preprocessing module and the storage database;
the image preprocessing module receives the daily time period monitoring video set sent by the time period dividing module and performs image preprocessing on the daily time period monitoring video, and the specific processing process comprises the following steps:
s1: extracting the monitoring video of each time period in each monitoring subregion in a daily time period monitoring video set;
s2: acquiring video time of monitoring videos of each time period in each monitoring sub-area, decomposing the monitoring videos of each time period in each monitoring sub-area into a plurality of images according to the number of video frames of the video time, numbering the decomposed images according to a preset sequence, and sequentially marking the images as 1,2,. once, j,. once, k;
s3, extracting the outline characteristics of the person from each image decomposed by the monitoring video in each time period in each monitoring sub-area, if the outline characteristics of the person can not be extracted from a certain image, then indicating that no human body exists on the image, removing the image, if the outline characteristics of the person can be extracted from a certain image, indicating that the human body exists on the image, reserving the image, and further obtaining each image reserved in each time period in each monitoring sub-area, wherein the image is marked as a target image;
s4: carrying out image enhancement preprocessing operation on each target image reserved in each time period in each monitoring sub-area;
s5: the target images after the image enhancement preprocessing obtained in the step S4 are formed into a time-period target image set B of each daymt(bmt1,bmt2,...,bmtj,...,bmtk)，bmtj represents the jth target image in the tth time period in the mth monitoring sub-area, and sends the target image set of each day time period to the feature extraction module;
the characteristic extraction module receives the time period target image set of each day sent by the image preprocessing moduleAnd the system is used for analyzing and processing the target images in each time period in each monitoring subregion in the time period target image set of each day, identifying and extracting the behavior type characteristics existing in the target images, extracting the characteristics corresponding to different dangerous behavior types in the dangerous characteristic database, comparing the behavior type characteristics of the target images in each time period in each monitoring subregion with the characteristics corresponding to different dangerous behavior types in the dangerous characteristic database, and forming a time period target image characteristic comparison set B 'of each day'mt(b′mt1,b′mt2,...,b′mtj,...,b′mtk)，b′mtj is a comparison value of behavior type features in the jth target image in the tth time period in the mth monitoring sub-area and features corresponding to a certain dangerous behavior type, and b 'is obtained if the behavior type features in the jth target image in the tth time period in the mth monitoring sub-area are successfully compared with the features corresponding to the certain dangerous behavior type in the dangerous feature database'mtj is equal to a fixed value R, R>0, if the comparison between the behavior type feature in the jth target image in the jth time period in the mth monitoring sub-area and the feature corresponding to a certain dangerous behavior type in the dangerous feature database fails, b'mtj is equal to 0, the dangerous behavior types, the time period numbers and the monitored sub-region numbers corresponding to all the successfully-compared monitored sub-regions are recorded at the same time, the successfully-compared monitored sub-regions are marked as dangerous sub-regions, the numbers of the dangerous sub-regions are counted, the dangerous sub-regions are marked as 1,2, asi(csi1,csi2,...,csip,...,csiq)，csip represents the p-th dangerous behavior type in the ith dangerous time period in the s-th dangerous subarea, the dangerous behavior type set of each day time period is sent to a storage database, and the numbers of all dangerous subareas, different dangerous behavior types corresponding to the dangerous subareas and the numbers of the dangerous time periods are sent to a displayThe terminal sends the formed time period target image feature comparison set to an analysis cloud platform;
the analysis cloud platform receives a time period target image feature comparison set sent by the feature extraction module, the risk coefficient values of all the monitoring sub-areas are counted, the risk coefficient threshold values corresponding to the first-level, second-level and third-level risk levels stored in the risk characteristic database are extracted, if the risk coefficient value of a certain monitoring sub-area is smaller than the risk coefficient threshold value corresponding to the first-level risk level, the monitoring sub-region is a first-level risk level, if the risk coefficient value of a certain monitoring sub-region is greater than the risk coefficient threshold value corresponding to the first-level risk level and is less than the risk coefficient threshold value corresponding to the second-level risk level, the monitoring sub-region is a secondary risk level, if the risk coefficient value corresponding to a certain monitoring sub-region is greater than the risk coefficient threshold value corresponding to the secondary risk level, the monitoring sub-regions are in three-level danger levels, and the danger levels corresponding to the monitoring sub-regions are respectively sent to the early warning module;
the storage database receives the dangerous behavior category set of each day time period sent by the characteristic extraction module and the monitoring video set of each day time period sent by the time period division module, and stores the dangerous behavior category set of each day time period and the monitoring video set of each day time period;
the danger characteristic database stores danger coefficient thresholds corresponding to first-level, second-level and third-level danger grades, and stores characteristics corresponding to different dangerous behavior types;
the early warning module receives and analyzes the danger levels corresponding to the monitoring sub-areas sent by the cloud platform and gives early warnings of different levels;
the display terminal receives and displays the numbers of all the dangerous subregions sent by the characteristic extraction module and the different dangerous behavior types and the dangerous time period numbers corresponding to the dangerous subregions;
the video retrieval module is used for inquiring all dangerous behavior types meeting the corresponding retrieval conditions from the dangerous behavior type set in the time period of each day stored in the storage database according to the retrieval conditions input by the user, and providing the dangerous behavior types for further analysis and discrimination of monitoring personnel.
2. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the number of the high-definition cameras is consistent with that of each monitoring subarea.
3. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the image preprocessing module comprises a median filtering unit.
4. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 3, wherein: the middle finger filtering unit is used for carrying out noise interference removing processing on video frame images in the monitoring videos of all time periods in all monitoring sub-areas and removing a large amount of useless information mixed by the external environment in the video frame images.
5. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the retrieval conditions include a risk time period, a risk detection sub-region number, and one or more risk behavior categories.
6. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the magnitude sequence of the risk coefficient threshold values corresponding to the first-level, second-level and third-level risk levels is that xi 1 is more than xi 2 and less than xi 3.
7. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the risk coefficient value of the monitoring subarea is calculated by the formula
θmIs expressed as the m < th > oneMonitoring hazard coefficient values, b 'of sub-regions'mtj is expressed as a contrast value of behavior type characteristics in the jth target image in the tth time period in the mth monitoring sub-area and characteristics corresponding to different dangerous behavior types.
8. The intelligent monitoring and security data processing and management system based on big data analysis as claimed in claim 1, wherein: the larger the danger coefficient value of the monitoring sub-area is, the more dangerous the monitoring sub-area is, and the smaller the danger coefficient value of the monitoring sub-area is, the safer the monitoring sub-area is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011321019.8A CN112437280A (en) | 2020-11-23 | 2020-11-23 | Intelligent monitoring security data processing management system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011321019.8A CN112437280A (en) | 2020-11-23 | 2020-11-23 | Intelligent monitoring security data processing management system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112437280A true CN112437280A (en) | 2021-03-02 |
Family
ID=74692895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011321019.8A Withdrawn CN112437280A (en) | 2020-11-23 | 2020-11-23 | Intelligent monitoring security data processing management system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112437280A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113099178A (en) * | 2021-04-01 | 2021-07-09 | 武汉拥钟智能科技有限公司 | Intelligent community safety online real-time monitoring and early warning method based on video remote monitoring |
| CN113359651A (en) * | 2021-07-06 | 2021-09-07 | 隆升量化(武汉)大数据科技有限公司 | Digital intelligent manufacturing industrial workshop production safety real-time online monitoring cloud platform |
| CN113573026A (en) * | 2021-08-11 | 2021-10-29 | 江西志宏安防科技有限公司 | Building security protection monitored control system of many monitoring points |
| CN114021969A (en) * | 2021-11-04 | 2022-02-08 | 中国安全生产科学研究院 | Agricultural enterprise safety production risk index analysis system |
| CN114996518A (en) * | 2022-08-04 | 2022-09-02 | 深圳市稻兴实业有限公司 | Ultra-high-definition video data storage and classification management system based on cloud platform |
| CN115375687A (en) * | 2022-10-25 | 2022-11-22 | 江苏博惠新材料科技有限公司 | Plastic sheet production plastic raw material mixing uniformity monitoring and analyzing system |
| CN116088399A (en) * | 2023-04-10 | 2023-05-09 | 中国电力工程顾问集团西南电力设计院有限公司 | Intelligent power plant factory monitoring system and monitoring method thereof |
| CN116647643A (en) * | 2023-06-01 | 2023-08-25 | 西藏康发电子工程有限公司 | Intelligent security monitoring system |
| CN116916050A (en) * | 2022-12-20 | 2023-10-20 | 哈尔滨商业大学 | Method and device for transmitting road monitoring image to terminal |
-
2020
- 2020-11-23 CN CN202011321019.8A patent/CN112437280A/en not_active Withdrawn
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113099178A (en) * | 2021-04-01 | 2021-07-09 | 武汉拥钟智能科技有限公司 | Intelligent community safety online real-time monitoring and early warning method based on video remote monitoring |
| CN113099178B (en) * | 2021-04-01 | 2021-12-03 | 广州市宁葳信息科技有限公司 | Intelligent community safety online real-time monitoring and early warning method based on video remote monitoring |
| CN113359651A (en) * | 2021-07-06 | 2021-09-07 | 隆升量化(武汉)大数据科技有限公司 | Digital intelligent manufacturing industrial workshop production safety real-time online monitoring cloud platform |
| CN113573026A (en) * | 2021-08-11 | 2021-10-29 | 江西志宏安防科技有限公司 | Building security protection monitored control system of many monitoring points |
| CN114021969A (en) * | 2021-11-04 | 2022-02-08 | 中国安全生产科学研究院 | Agricultural enterprise safety production risk index analysis system |
| CN114021969B (en) * | 2021-11-04 | 2022-06-07 | 中国安全生产科学研究院 | Agricultural enterprise safety production risk index analysis system |
| CN114996518A (en) * | 2022-08-04 | 2022-09-02 | 深圳市稻兴实业有限公司 | Ultra-high-definition video data storage and classification management system based on cloud platform |
| CN114996518B (en) * | 2022-08-04 | 2022-10-21 | 深圳市稻兴实业有限公司 | Ultra-high-definition video data storage and classification management system based on cloud platform |
| CN115375687A (en) * | 2022-10-25 | 2022-11-22 | 江苏博惠新材料科技有限公司 | Plastic sheet production plastic raw material mixing uniformity monitoring and analyzing system |
| CN115375687B (en) * | 2022-10-25 | 2023-03-24 | 江苏博惠新材料科技有限公司 | Monitoring and analyzing system for mixing uniformity of plastic raw materials in plastic sheet production |
| CN116916050A (en) * | 2022-12-20 | 2023-10-20 | 哈尔滨商业大学 | Method and device for transmitting road monitoring image to terminal |
| CN116916050B (en) * | 2022-12-20 | 2024-03-19 | 哈尔滨商业大学 | Method and device for transmitting road monitoring image to terminal |
| CN116088399A (en) * | 2023-04-10 | 2023-05-09 | 中国电力工程顾问集团西南电力设计院有限公司 | Intelligent power plant factory monitoring system and monitoring method thereof |
| CN116647643A (en) * | 2023-06-01 | 2023-08-25 | 西藏康发电子工程有限公司 | Intelligent security monitoring system |
| CN116647643B (en) * | 2023-06-01 | 2024-03-26 | 西藏康发电子工程有限公司 | Intelligent security monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112437280A (en) | Intelligent monitoring security data processing management system based on big data analysis | |
| Huang et al. | Detection algorithm of safety helmet wearing based on deep learning | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| CN105139016B (en) | The Interference Detection system and its application process of monitoring camera | |
| CN111522995B (en) | Target object analysis method and device and electronic equipment | |
| CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
| CN103826108B (en) | Monitoring method and system after loan based on video image | |
| CN113297926B (en) | Behavior detection and recognition method and system | |
| CN111460988A (en) | Illegal behavior identification method and device | |
| CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
| CN112183219A (en) | Public safety video monitoring method and system based on face recognition | |
| CN111510675A (en) | Intelligent security system based on face recognition and big data analysis | |
| CN111753642B (en) | Method and device for determining key frame | |
| CN115691034A (en) | Intelligent household abnormal condition warning method, system and storage medium | |
| CN113179389A (en) | System and method for identifying crane jib of power transmission line dangerous vehicle | |
| CN115083004A (en) | Identity recognition method and device and computer readable storage medium | |
| CN111461655A (en) | Personnel management system | |
| CN117523503B (en) | Preparation equipment safety monitoring method and system based on thick film circuit board | |
| CN111597919A (en) | Human body tracking method in video monitoring scene | |
| CN117953571A (en) | Intelligent digital refrigerator face detection method and system | |
| CN115346170B (en) | Intelligent monitoring method and device for gas facility area | |
| CN116682162A (en) | Robot detection algorithm based on real-time video stream | |
| CN111666780A (en) | Intelligent door control security method based on emotion recognition technology | |
| CN111723761B (en) | Method, device and storage medium for determining abnormal face image | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210302 |
|
| WW01 | Invention patent application withdrawn after publication |