CN117176923B - Intelligent community police service patrol method and system based on data encryption - Google Patents
Intelligent community police service patrol method and system based on data encryption Download PDFInfo
- Publication number
- CN117176923B CN117176923B CN202311456344.9A CN202311456344A CN117176923B CN 117176923 B CN117176923 B CN 117176923B CN 202311456344 A CN202311456344 A CN 202311456344A CN 117176923 B CN117176923 B CN 117176923B
- Authority
- CN
- China
- Prior art keywords
- community
- monitoring video
- video data
- data
- police service
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 95
- 230000000694 effects Effects 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000005856 abnormality Effects 0.000 claims abstract description 3
- 230000033001 locomotion Effects 0.000 claims description 32
- 238000005457 optimization Methods 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 21
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 8
- 230000035772 mutation Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000001351 cycling effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000007123 defense Effects 0.000 claims 1
- 238000012795 verification Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a data encryption-based intelligent community police service patrol method and system, which relate to the technical field of community intelligent management, and the data encryption-based intelligent community police service patrol method comprises the following steps: respectively registering information by residents and administrators; preprocessing the monitoring video data; dividing communities into a dense residential area, a sparse residential area and a non-residential area; judging whether the normal condition of the information login registration is met or not through comparison with the information login registration, and timely notifying a community police service to process; and carrying out data encryption on the monitoring video data. The invention is convenient for follow-up activity verification and abnormality identification, improves police service pertinence, can help optimize police service patrol route, thereby improving working efficiency, and simultaneously can transmit encrypted monitoring video data to a management center in real time, thereby realizing accurate management and protecting privacy information.
Description
Technical Field
The invention relates to the technical field of community intelligent management, in particular to a method and a system for intelligent community police service patrol based on data encryption.
Background
The intelligent urban area (community) is fully utilized by the Internet and the Internet of things, and relates to the fields of intelligent building, intelligent home, road network monitoring, intelligent hospitals, urban life line management, food and drug management, ticket management, home care, personal health, digital life and the like, the important opportunities of new technological innovation revolution and information industry surge are mastered, the advantages of advanced Information Communication (ICT) industry, advanced RFID related technology, excellent telecom service and informationized infrastructure and the like are fully exerted, the key technology attack of the industry is accelerated by constructing ICT infrastructure, authentication, safety and other platforms and demonstration engineering, the intelligent environment developed by the urban area (community) is constructed, and the novel life, industry development, social management and other modes based on massive information and intelligent filtering treatment are formed, so that the novel urban area (community) form is constructed in the future. The intelligent community construction introduces the concept of intelligent city into communities, takes happiness of community masses as a starting point, and brings convenience to community people by creating intelligent communities, so that harmonious community construction is quickened, and regional social progress is promoted. The intelligent community based on the high and new technologies such as the Internet of things and cloud computing is a cell of the intelligent city, and is an artificial intelligent management system, so that people can work and live more conveniently, comfortably and efficiently.
In community management, security personnel can check identities of personnel entering and exiting the community and implement patrol in the entrance and the interior space of the community, suspicious people can be found in time, old and young people are helped, irregular behaviors such as disordered parking, occupied private parking spaces, blocked roads, fire channels and the like are corrected, and accordingly safety environment and civilized order in the community are maintained.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a data encryption-based intelligent community police service patrol method and system, which solve the problems that the prior art has large community distribution, more residents, limited security manpower, incapability of covering all corners, personal errors and illegal molecule camouflage risks of security personnel, inconvenience in judging the abnormal risk of communities according to monitoring videos, incapability of carrying out good encryption on transmitted video data, and incapability of guaranteeing the safety of data transmission and storage.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
according to one aspect of the invention, there is provided a data encryption-based intelligent community police service patrol method, comprising the steps of:
s1, a community service program and a resident management program are formulated, and residents and administrators respectively register information login;
s2, collecting monitoring video data generated by each monitoring terminal device in the community, and preprocessing the monitoring video data;
s3, dividing communities into a dense residential area, a sparse residential area and a non-residential area by utilizing an image recognition technology;
s4, continuously monitoring the activities of residents in each area based on an abnormal behavior detection algorithm of the similarity graph, judging whether the activities are in accordance with the normal conditions of the information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
and S5, carrying out data encryption on the monitoring video data, transmitting the data to a management center in real time, and adjusting a management strategy according to the monitoring video data.
Further, collecting monitoring video data generated by each monitoring terminal device in the community, and preprocessing the monitoring video data comprises the following steps:
s21, converting an RGB color space of a color image in the monitoring video into a gray image by a linear weighting method;
s22, clustering is carried out according to the gray levels of the pixels by adopting a threshold segmentation method, and the pixels with the same gray levels are regarded as the same region;
s23, forming an area sequence of areas of each area according to a certain sequence, and using the areas as characteristic vectors to represent images;
s24, representing the image through ordered feature vectors of the Euclidean distance calculation area;
s25, carrying out thinning and binarization processing on the gradient image, and taking pixel points with gradient values larger than a threshold value as edge points;
and S27, connecting adjacent edge points into a connected domain to obtain a final edge image.
Further, the method for dividing the community into a dense area, a sparse area and a no-resident area by using the image recognition technology comprises the following steps:
s31, denoising, filtering and smoothing the obtained repeated data, missing value and abnormal value of the edge image to obtain a restored edge image;
s32, performing foreground extraction on the restored edge image by using an improved Gaussian mixture model to obtain a foreground image only containing resident targets;
s33, removing noise pixels adhered to the edge in the foreground image through morphological processing to obtain a processed new image;
s34, carrying out wavelet packet decomposition on the restored edge image to obtain a primary component and a secondary component;
s35, calculating fractal box dimensions of the new image, the primary component and the secondary component to obtain a first characteristic value, a second characteristic value and a third characteristic value;
s36, training an SVM model by taking the first characteristic value, the second characteristic value and the third characteristic value as characteristic vectors, and dividing the density of residents into resident dense areas, resident rare areas and non-resident area categories;
s37, carrying out parameter optimization on the SVM by using an optimization algorithm based on a support vector machine, so as to realize optimization of model parameters;
s38, repeating the steps S31 to S34 for the new edge image, and extracting a new feature value I, a new feature value II and a new feature value III;
s39, classifying the new first characteristic value, the new second characteristic value and the new third characteristic value by using the trained SVM model, and counting the density level of residents in real time;
s310, cycling the step S39 and the step S310 until the monitoring video processing is finished, and obtaining the density distribution of residents in the community.
Further, the foreground extraction of the restored edge image by using the improved Gaussian mixture model, and the acquisition of the foreground image only containing the resident target comprises the following steps:
s321, carrying out Gaussian mixture modeling on a community monitoring video, and enabling a static target pixel point and a background pixel point in a short time to be not matched in an updating mode of optimized parameters;
s322, for the pixels matched with the background, the parameters are updated, and for the pixels not matched with the background, the parameters are reserved;
s323, setting a minimum time interval from a static state to a motion state of the foreground target pixel point;
s324, defining accumulated rest time of the pixel points at a preset moment;
s325, when the time that the object moves or is occluded is less than the time threshold and the value of the accumulated stationary time is greater than the minimum time interval, then the pixel is considered to be a foreground object.
Further, the optimization algorithm based on the support vector machine is used for carrying out parameter optimization on the SVM, and the optimization of model parameters is realized, which comprises the following steps:
s371, establishing a region scanner, and determining a parameter optimizing range of the SVM model;
s372, randomly generating an initial seed group randomly, and calculating individual fitness of each parameter pair;
s373, selecting, crossing and mutation operations are carried out in the maximum evolution algebra, and parameter pairs are optimized;
s374, calculating individual fitness of the new group, and extracting a parameter set of the current optimal fitness;
s375, training the SVM model by using the optimized parameter set to realize optimization of model parameters.
Further, based on the abnormal behavior detection algorithm of the similarity graph, the method continuously monitors the activities of residents in each area, judges whether the activities accord with the normal conditions of information login registration or not by comparing the activities with the information login registration, and timely notifies community police to process the activities, and comprises the following steps:
s41, continuously monitoring each region by a system, and extracting a crowd movement mode by using a video frame-based active-less characteristic;
s42, learning a motion change rule of normal behaviors in a training stage by the system through a motion conversion space of the video frame pairs;
s43, in a test stage, the system compares a historical frame with a current frame, and learns and recognizes a motion change rule;
s44, the system builds a similar graph through a motion change rule, and if the difference of the similar graphs exceeds a preset threshold value, the area is marked as a position where abnormal behaviors occur;
s45, comparing the position marked as abnormal behavior with the information login registration, judging whether the normal condition of the information login registration is met, if so, not needing to be processed, and if not, timely notifying the community police service to be processed.
Further, the calculation formula of the abnormal behavior detection algorithm based on the similarity graph is as follows:
；
wherein,Srepresented as a similarity graph;
Simexpressed as a similarity function;
t x representing a transfer matrix;
xrepresented as test video frames;
jrepresenting the first of the group motion lawsjAn element;
r i denoted as the firstiAnd the motion rule of each group.
Further, the method for encrypting the data of the monitoring video data and transmitting the data to the management center in real time, and adjusting the management strategy according to the monitoring video data comprises the following steps:
s51, generating two large prime numbers by using a prime number generation algorithm, generating a public key and a private key by using an RSA algorithm, wherein the public key is used for encryption, and the private key is used for decryption;
s52, generating a plurality of bit random keys by using a 3DES algorithm, and encrypting the monitoring video data by using the keys;
s53, encrypting the secret key generated by the 3DES algorithm by using the public key of the RSA algorithm, and transmitting the secret key to a management center;
s54, the management center decrypts the key of the 3DES algorithm by using the private key of the RSA algorithm, decrypts the received monitoring video data by using the decrypted 3DES key, and restores the original data;
s55, according to the decrypted original monitoring video data, the management center analyzes and adjusts the management strategy of the community in real time;
s56, circulating the steps S52 to S55, continuously carrying out encryption transmission and decryption analysis on the monitoring video data, and adjusting community management in real time.
Further, a calculation formula for encrypting the key generated by the 3DES algorithm by using the public key of the RSA algorithm is as follows:
；
wherein,Cexpressed as encrypted surveillance video data;
Mmonitoring video data which is indicated as requiring encryption;
erepresented as a key at the time of encryption;
nexpressed as modulus.
According to another aspect of the present invention, there is also provided a data encryption-based intelligent community police service patrol system, including:
the user management module is used for making a community service program and a resident management program, and residents and administrators respectively register information login;
the acquisition data and processing module is used for collecting monitoring video data generated by each monitoring terminal device in the community and preprocessing the monitoring video data;
the regional division module is used for dividing communities into resident dense regions, resident rare regions and non-resident regions by utilizing an image recognition technology;
the abnormal detection module is used for continuously monitoring the activity condition of residents in each area based on an abnormal behavior detection algorithm of the similarity graph, judging whether the activity condition accords with the normal condition of the information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
the data encryption module is used for carrying out data encryption on the monitoring video data, transmitting the data to the management center in real time, and adjusting the management strategy according to the monitoring video data;
the user management module is connected with the processing module and the area dividing module through acquired data, and the area dividing module is connected with the data encryption module through the abnormality detection module.
The beneficial effects of the invention are as follows:
1. the resident identity database can be established through resident information registration, so that follow-up activity verification and anomaly identification are facilitated, police work pertinence is improved, police patrol route optimization can be facilitated, work efficiency is improved, encrypted monitoring video data can be transmitted to a management center in real time, the management center can timely adjust and optimize management strategies according to the monitoring data, community security and management efficiency is improved, and accurate management and privacy information protection are realized.
2. According to the invention, through continuously monitoring activities of residents in each area in the community, whether the activities meet normal conditions or not is judged by using the abnormal behavior detection algorithm, so that abnormal conditions can be found in time and the community police service can be notified, and the community security is improved.
3. According to the invention, the community is divided into different areas through the image recognition technology, different management strategies can be adopted for different areas, so that accurate management is realized, intensive management can be carried out on the areas with dense residents, the areas with rare residents can be properly relaxed, and the labor force of security personnel is further reduced.
4. The invention can well protect resident privacy information by encrypting the monitoring video data, avoid information leakage, and transmit the encrypted monitoring video data to the management center in real time, and the management center can adjust and optimize the management strategy in time according to the monitoring data, thereby realizing management uniformity and optimization.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for intelligent community police service patrol based on data encryption according to an embodiment of the invention;
fig. 2 is a schematic block diagram of a smart community police service patrol system based on data encryption according to an embodiment of the invention.
In the figure:
1. a user management module; 2. acquiring data and a processing module; 3. a region dividing module; 4. an anomaly detection module; 5. and a data encryption module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
According to the embodiment of the invention, an intelligent community police service patrol method and system based on data encryption are provided.
The invention will be further described with reference to the accompanying drawings and the specific embodiments, as shown in fig. 1, according to an embodiment of the invention, the smart community police service patrol method based on data encryption includes the following steps:
s1, a community service program and a resident management program are formulated, and residents and administrators respectively register information login;
s2, collecting monitoring video data generated by each monitoring terminal device in the community, and preprocessing the monitoring video data;
s3, dividing communities into a dense residential area, a sparse residential area and a non-residential area by utilizing an image recognition technology;
s4, continuously monitoring the activities of residents in each area based on an abnormal behavior detection algorithm of the similarity graph, judging whether the activities are in accordance with the normal conditions of the information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
and S5, carrying out data encryption on the monitoring video data, transmitting the data to a management center in real time, and adjusting a management strategy according to the monitoring video data.
In one embodiment, collecting monitoring video data generated by each monitoring terminal device in a community, and preprocessing the monitoring video data includes the following steps:
s21, converting an RGB color space of a color image in the monitoring video into a gray image by a linear weighting method;
specifically, the linear weighting method is an image processing method for converting a color image into a gray-scale image. It converts the color information of a color image into gray levels by weighted averaging of the RGB color channels.
Specifically, the calculation formula of the linear weighting method is as follows:
gray value=0.29×r+0.587×g+0.114×b;
wherein R, G, B represents the brightness values of the red, green and blue color channels in the color image, and 0.299, 0.587 and 0.114 are the corresponding weight coefficients.
S22, clustering is carried out according to the gray levels of the pixels by adopting a threshold segmentation method, and the pixels with the same gray levels are regarded as the same region;
specifically, the threshold segmentation method is an image segmentation method for dividing an image into different regions, wherein each region has similar characteristics. The threshold segmentation method classifies pixels in an image according to their gray value versus threshold value based on setting one or more thresholds.
S23, forming an area sequence of areas of each area according to a certain sequence, and using the areas as characteristic vectors to represent images;
s24, representing the image through ordered feature vectors of the Euclidean distance calculation area;
in particular, euclidean distance is a commonly used method of calculating the distance between two vectors. In extracting motion features, the euclidean distance may be used to compare the similarity between two motion sequences, and in practical applications, the motion sequences are generally divided into multiple time windows, and feature vectors in each time window are calculated respectively. The euclidean distance from the feature vector in the corresponding time window in the other sequence of actions can then be calculated for the feature vector in each time window.
S25, carrying out thinning and binarization processing on the gradient image, and taking pixel points with gradient values larger than a threshold value as edge points;
and S27, connecting adjacent edge points into a connected domain to obtain a final edge image.
In one embodiment, dividing communities into densely populated areas, sparsely populated areas, and non-populated areas using image recognition techniques includes the steps of:
s31, denoising, filtering and smoothing the obtained repeated data, missing value and abnormal value of the edge image to obtain a restored edge image;
s32, performing foreground extraction on the restored edge image by using an improved Gaussian mixture model to obtain a foreground image only containing resident targets;
s33, removing noise pixels adhered to the edge in the foreground image through morphological processing to obtain a processed new image;
specifically, morphological processing is an image processing technique for extracting shape information of an image, and mainly includes two basic operations of expansion and corrosion, wherein the expansion can expand objects in the image, and the corrosion can reduce the objects in the image.
S34, carrying out wavelet packet decomposition on the restored edge image to obtain a primary component and a secondary component;
specifically, wavelet packet decomposition (Wavelet Packet Decomposition) is a signal processing method that is an extension of the standard wavelet transform. It analyzes the signal by using a set of wavelet functions (called wavelet packets) that can more finely divide the frequency band. This allows the wavelet packet decomposition to better represent the frequency structure of the signal than the standard wavelet transform.
S35, calculating fractal box dimensions of the new image, the primary component and the secondary component to obtain a first characteristic value, a second characteristic value and a third characteristic value;
specifically, the characteristic value one: fractal box dimension of new image.
And the characteristic value II: fractal box dimension of primary component.
And the characteristic value is three: fractal box dimension of secondary component.
S36, training an SVM model by taking the first characteristic value, the second characteristic value and the third characteristic value as characteristic vectors, and dividing the density of residents into resident dense areas, resident rare areas and non-resident area categories;
s37, carrying out parameter optimization on the SVM by using an optimization algorithm based on a support vector machine, so as to realize optimization of model parameters;
specifically, genetic algorithm is a search optimization method that mimics the process of natural selection and inheritance. The main parameters include: population Size (probability), evolution algebra (generation), crossover probability (Crossover Probability), mutation probability (mutation probability), and the like.
Specifically, population Size (Population Size): the population size determines the breadth of the search space, and a larger population size can increase the global search capacity of the algorithm.
Specifically, evolution algebra (Generations): the algebra refers to the number of iterative optimizations of the algorithm. Increasing the algebra of evolution may increase the global search capability of the algorithm.
Specifically, cross probability (Crossover Probability): it is determined whether or not certain two individuals are performing a crossover operation to generate a new solution.
Specifically, mutation probability (Mutation Probability): it is determined whether a newly generated solution is mutated.
S38, repeating the steps S31 to S34 for the new edge image, and extracting a new feature value I, a new feature value II and a new feature value III;
s39, classifying the new first characteristic value, the new second characteristic value and the new third characteristic value by using the trained SVM model, and counting the density level of residents in real time;
s310, cycling the step S39 and the step S310 until the monitoring video processing is finished, and obtaining the density distribution of residents in the community.
In one embodiment, the foreground extraction of the restored edge image using the modified mixture gaussian model, the acquisition of the foreground image containing only the resident target comprises the steps of:
s321, carrying out Gaussian mixture modeling on a community monitoring video, and enabling a static target pixel point and a background pixel point in a short time to be not matched in an updating mode of optimized parameters;
s322, for the pixels matched with the background, the parameters are updated, and for the pixels not matched with the background, the parameters are reserved;
s323, setting a minimum time interval from a static state to a motion state of the foreground target pixel point;
s324, defining accumulated rest time of the pixel points at a preset moment;
s325, when the time that the object moves or is occluded is less than the time threshold and the value of the accumulated stationary time is greater than the minimum time interval, then the pixel is considered to be a foreground object.
In one embodiment, the optimization algorithm based on the support vector machine is used for carrying out parameter optimization on the SVM, and the optimization of model parameters is realized by the following steps:
s371, establishing a region scanner, and determining a parameter optimizing range of the SVM model;
s372, randomly generating an initial seed group randomly, and calculating individual fitness of each parameter pair;
s373, selecting, crossing and mutation operations are carried out in the maximum evolution algebra, and parameter pairs are optimized;
s374, calculating individual fitness of the new group, and extracting a parameter set of the current optimal fitness;
s375, training the SVM model by using the optimized parameter set to realize optimization of model parameters.
In one embodiment, based on the abnormal behavior detection algorithm of the similarity graph, the activity condition of residents in each area is continuously monitored, whether the activity condition accords with the normal condition of the information login registration is judged by comparing the activity condition with the information login registration, and community police service is timely notified to process, and the method comprises the following steps:
s41, continuously monitoring each region by a system, and extracting a crowd movement mode by using a video frame-based active-less characteristic;
specifically, the active-ness feature is used to identify and extract the dominant motion pattern of the crowd in the video frame. Then in the training stage, the system learns the motion change rule of normal behavior in the motion conversion space of the video frame pair. In the test stage, the system can compare the historical frame with the current frame, learn and obtain the corresponding motion change rule. And finally, constructing a similarity graph through a motion change rule, wherein the region with the difference exceeding a threshold value in the similarity graph is regarded as the position where the abnormal behavior occurs.
S42, learning a motion change rule of normal behaviors in a training stage by the system through a motion conversion space of the video frame pairs;
s43, in a test stage, the system compares a historical frame with a current frame, and learns and recognizes a motion change rule;
s44, the system builds a similar graph through a motion change rule, and if the difference of the similar graphs exceeds a preset threshold value, the area is marked as a position where abnormal behaviors occur;
s45, comparing the position marked as abnormal behavior with the information login registration, judging whether the normal condition of the information login registration is met, if so, not needing to be processed, and if not, timely notifying the community police service to be processed.
In one embodiment, the computation formula of the similarity graph-based abnormal behavior detection algorithm is:
；
wherein,Srepresented as a similarity graph;
Simexpressed as a similarity function;
t x representing a transfer matrix, aniAndjis an element in the transfer matrix;
xrepresented as test video frames;
jrepresenting the first of the group motion lawsjAn element;
r i denoted as the firstiAnd the motion rule of each group.
In one embodiment, the data encryption is performed on the monitoring video data, and the data is transmitted to the management center in real time, and the adjustment of the management policy according to the monitoring video data comprises the following steps:
s51, generating two large prime numbers by using a prime number generation algorithm, generating a public key and a private key by using an RSA algorithm, wherein the public key is used for encryption, and the private key is used for decryption;
s52, generating a plurality of bit random keys by using a 3DES algorithm, and encrypting the monitoring video data by using the keys;
specifically, the 3DES algorithm generates 128-bit random numbers, i.e., keys.
S53, encrypting the secret key generated by the 3DES algorithm by using the public key of the RSA algorithm, and transmitting the secret key to a management center;
s54, the management center decrypts the key of the 3DES algorithm by using the private key of the RSA algorithm, decrypts the received monitoring video data by using the decrypted 3DES key, and restores the original data;
specifically, the calculation formula for decrypting the received monitoring video data by using the decrypted 3DES key is as follows:
；
wherein,Mmonitoring video data which is indicated as requiring encryption;
Cexpressed as encrypted surveillance video data;
da key representing the time of decryption;
nexpressed as modulus.
S55, according to the decrypted original monitoring video data, the management center analyzes and adjusts the management strategy of the community in real time;
s56, circulating the steps S52 to S55, continuously carrying out encryption transmission and decryption analysis on the monitoring video data, and adjusting community management in real time.
In one embodiment, the calculation formula for encrypting the key generated by the 3DES algorithm using the public key of the RSA algorithm is:
；
wherein,Cexpressed as encrypted surveillance video data;
Mmonitoring indicated as requiring encryptionVideo data;
erepresented as a key at the time of encryption;
nexpressed as modulus.
According to another embodiment of the present invention, as shown in fig. 2, there is also provided a data encryption-based intelligent community police service patrol system, including:
the user management module 1 is used for making a community service program and a resident management program, and residents and administrators respectively register information login;
the acquisition data and processing module 2 is used for collecting monitoring video data generated by each monitoring terminal device in the community and preprocessing the monitoring video data;
the area dividing module 3 is used for dividing communities into a dense residential area, a sparse residential area and a non-residential area by utilizing an image recognition technology;
the anomaly detection module 4 is used for continuously monitoring the activity condition of residents in each area based on an anomaly behavior detection algorithm of the similarity graph, judging whether the activity condition accords with the normal condition of information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
the data encryption module 5 is used for carrying out data encryption on the monitoring video data, transmitting the data to the management center in real time, and adjusting the management strategy according to the monitoring video data;
the user management module 1 is connected with the processing module 2 and the area dividing module 3 through acquired data, and the area dividing module 3 is connected with the data encryption module 5 through the anomaly detection module 4.
In summary, by means of the technical scheme, the community security is improved by continuously monitoring activities of residents in each area in the community and judging whether the activities meet normal conditions or not by using an abnormal behavior detection algorithm, so that abnormal conditions can be found in time and community police can be notified. According to the invention, the community is divided into different areas through the image recognition technology, different management strategies can be adopted for different areas, so that accurate management is realized, intensive management can be carried out on the areas with dense residents, the areas with rare residents can be properly relaxed, and the labor force of security personnel is further reduced. The invention can well protect resident privacy information by encrypting the monitoring video data, avoid information leakage, and transmit the encrypted monitoring video data to the management center in real time, and the management center can adjust and optimize the management strategy in time according to the monitoring data, thereby realizing management uniformity and optimization.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The intelligent community police service patrol method based on data encryption is characterized by comprising the following steps of:
s1, a community service program and a resident management program are formulated, and residents and administrators respectively register information login;
s2, collecting monitoring video data generated by each monitoring terminal device in the community, and preprocessing the monitoring video data;
s3, dividing communities into a dense residential area, a sparse residential area and a non-residential area by utilizing an image recognition technology;
s4, continuously monitoring the activities of residents in each area based on an abnormal behavior detection algorithm of the similarity graph, judging whether the activities are in accordance with the normal conditions of the information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
s5, carrying out data encryption on the monitoring video data, transmitting the data to a management center in real time, and adjusting a management strategy according to the monitoring video data;
the method for collecting the monitoring video data generated by each monitoring terminal device in the community and preprocessing the monitoring video data comprises the following steps:
s21, converting an RGB color space of a color image in the monitoring video into a gray image by a linear weighting method;
s22, clustering is carried out according to the gray levels of the pixels by adopting a threshold segmentation method, and the pixels with the same gray levels are regarded as the same region;
s23, forming an area sequence of areas of each area according to a certain sequence, and using the areas as characteristic vectors to represent images;
s24, representing the image through ordered feature vectors of the Euclidean distance calculation area;
s25, carrying out thinning and binarization processing on the gradient image, and taking pixel points with gradient values larger than a threshold value as edge points;
s27, connecting adjacent edge points into a connected domain to obtain a final edge image;
the method for dividing communities into densely populated areas, sparsely populated areas and non-populated areas by using the image recognition technology comprises the following steps of:
s31, denoising, filtering and smoothing the obtained repeated data, missing value and abnormal value of the edge image to obtain a restored edge image;
s32, performing foreground extraction on the restored edge image by using an improved Gaussian mixture model to obtain a foreground image only containing resident targets;
s33, removing noise pixels adhered to the edge in the foreground image through morphological processing to obtain a processed new image;
s34, carrying out wavelet packet decomposition on the restored edge image to obtain a primary component and a secondary component;
s35, calculating fractal box dimensions of the new image, the primary component and the secondary component to obtain a first characteristic value, a second characteristic value and a third characteristic value;
s36, training an SVM model by taking the first characteristic value, the second characteristic value and the third characteristic value as characteristic vectors, and dividing the density of residents into resident dense areas, resident rare areas and non-resident area categories;
s37, carrying out parameter optimization on the SVM by using an optimization algorithm based on a support vector machine, so as to realize optimization of model parameters;
s38, repeating the steps S31 to S34 for the new edge image, and extracting a new feature value I, a new feature value II and a new feature value III;
s39, classifying the new first characteristic value, the new second characteristic value and the new third characteristic value by using the trained SVM model, and counting the density level of residents in real time;
s310, cycling the step S39 and the step S310 until the monitoring video processing is finished, and obtaining the density distribution of residents in the community;
the data encryption is carried out on the monitoring video data, the data are transmitted to the management center in real time, and the management strategy is adjusted according to the monitoring video data, and the method comprises the following steps:
s51, generating two large prime numbers by using a prime number generation algorithm, generating a public key and a private key by using an RSA algorithm, wherein the public key is used for encryption, and the private key is used for decryption;
s52, generating a plurality of bit random keys by using a 3DES algorithm, and encrypting the monitoring video data by using the keys;
s53, encrypting the secret key generated by the 3DES algorithm by using the public key of the RSA algorithm, and transmitting the secret key to a management center;
s54, the management center decrypts the key of the 3DES algorithm by using the private key of the RSA algorithm, decrypts the received monitoring video data by using the decrypted 3DES key, and restores the original data;
s55, according to the decrypted original monitoring video data, the management center analyzes and adjusts the management strategy of the community in real time;
s56, circulating the steps S52 to S55, continuously carrying out encryption transmission and decryption analysis on the monitoring video data, and adjusting community management in real time.
2. The intelligent community policing and defense method based on data encryption according to claim 1, wherein the foreground extraction of the restored edge image by using the improved mixed gaussian model, and the acquisition of the foreground image only including the resident target comprises the following steps:
s321, carrying out Gaussian mixture modeling on a community monitoring video, and enabling a static target pixel point and a background pixel point in a short time to be not matched in an updating mode of optimized parameters;
s322, for the pixels matched with the background, the parameters are updated, and for the pixels not matched with the background, the parameters are reserved;
s323, setting a minimum time interval from a static state to a motion state of the foreground target pixel point;
s324, defining accumulated rest time of the pixel points at a preset moment;
s325, when the time that the object moves or is occluded is less than the time threshold and the value of the accumulated stationary time is greater than the minimum time interval, then the pixel is considered to be a foreground object.
3. The intelligent community police service patrol method based on data encryption according to claim 2, wherein the optimization algorithm based on the support vector machine is used for optimizing parameters of the SVM, and the optimization of model parameters is achieved comprises the following steps:
s371, establishing a region scanner, and determining a parameter optimizing range of the SVM model;
s372, randomly generating an initial seed group randomly, and calculating individual fitness of each parameter pair;
s373, selecting, crossing and mutation operations are carried out in the maximum evolution algebra, and parameter pairs are optimized;
s374, calculating individual fitness of the new group, and extracting a parameter set of the current optimal fitness;
s375, training the SVM model by using the optimized parameter set to realize optimization of model parameters.
4. The intelligent community police service patrol method based on data encryption according to claim 1, wherein the abnormal behavior detection algorithm based on the similarity graph continuously monitors activities of residents in each area, judges whether the activities are in accordance with normal conditions of information login registration by comparing the activities with the information login registration, and timely notifies community police service to process, and the method comprises the following steps:
s41, continuously monitoring each region by a system, and extracting a crowd movement mode by using a video frame-based active-less characteristic;
s42, learning a motion change rule of normal behaviors in a training stage by the system through a motion conversion space of the video frame pairs;
s43, in a test stage, the system compares a historical frame with a current frame, and learns and recognizes a motion change rule;
s44, the system builds a similar graph through a motion change rule, and if the difference of the similar graphs exceeds a preset threshold value, the area is marked as a position where abnormal behaviors occur;
s45, comparing the position marked as abnormal behavior with the information login registration, judging whether the normal condition of the information login registration is met, if so, not needing to be processed, and if not, timely notifying the community police service to be processed.
5. The intelligent community police service patrol method based on data encryption according to claim 4, wherein the calculation formula of the abnormal behavior detection algorithm based on the similarity graph is as follows:
；
wherein,Srepresented as a similarity graph;
Simexpressed as a similarity function;
t x representing a transfer matrix;
xrepresented as test video frames;
jrepresenting the first of the group motion lawsjAn element;
r i denoted as the firstiAnd the motion rule of each group.
6. The intelligent community police service patrol method based on data encryption according to claim 1, wherein the calculation formula for encrypting the key generated by the 3DES algorithm by using the public key of the RSA algorithm is:
；
wherein,Cexpressed as encrypted surveillance video data;
Mmonitoring video data which is indicated as requiring encryption;
erepresented as a key at the time of encryption;
nexpressed as modulus.
7. A data encryption-based intelligent community police service patrol system for implementing the data encryption-based intelligent community police service patrol method as claimed in any one of claims 1 to 6, characterized in that the data encryption-based intelligent community police service patrol system comprises:
the user management module is used for making a community service program and a resident management program, and residents and administrators respectively register information login;
the acquisition data and processing module is used for collecting monitoring video data generated by each monitoring terminal device in the community and preprocessing the monitoring video data;
the regional division module is used for dividing communities into resident dense regions, resident rare regions and non-resident regions by utilizing an image recognition technology;
the abnormal detection module is used for continuously monitoring the activity condition of residents in each area based on an abnormal behavior detection algorithm of the similarity graph, judging whether the activity condition accords with the normal condition of the information login registration or not through comparison with the information login registration, and timely notifying a community police service to process;
the data encryption module is used for carrying out data encryption on the monitoring video data, transmitting the data to the management center in real time, and adjusting the management strategy according to the monitoring video data;
the user management module is connected with the processing module and the area dividing module through acquired data, and the area dividing module is connected with the data encryption module through the abnormality detection module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311456344.9A CN117176923B (en) | 2023-11-03 | 2023-11-03 | Intelligent community police service patrol method and system based on data encryption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311456344.9A CN117176923B (en) | 2023-11-03 | 2023-11-03 | Intelligent community police service patrol method and system based on data encryption |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117176923A CN117176923A (en) | 2023-12-05 |
| CN117176923B true CN117176923B (en) | 2023-12-29 |
Family
ID=88930330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311456344.9A Active CN117176923B (en) | 2023-11-03 | 2023-11-03 | Intelligent community police service patrol method and system based on data encryption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117176923B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
| CN104658011A (en) * | 2015-01-31 | 2015-05-27 | 北京理工大学 | Intelligent transportation moving object detection tracking method |
| CN109587142A (en) * | 2018-12-10 | 2019-04-05 | 北京华虹集成电路设计有限责任公司 | A kind of the data safety AM access module and equipment of service-oriented stream |
| CN112084529A (en) * | 2020-09-09 | 2020-12-15 | 清华大学 | Privacy data encryption access method and system based on block chain technology for community |
| CN112116502A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community security management system |
| CN115271635A (en) * | 2022-06-29 | 2022-11-01 | 深圳市双银科技有限公司 | Intelligent community service platform system |
-
2023
- 2023-11-03 CN CN202311456344.9A patent/CN117176923B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
| CN104658011A (en) * | 2015-01-31 | 2015-05-27 | 北京理工大学 | Intelligent transportation moving object detection tracking method |
| CN109587142A (en) * | 2018-12-10 | 2019-04-05 | 北京华虹集成电路设计有限责任公司 | A kind of the data safety AM access module and equipment of service-oriented stream |
| CN112084529A (en) * | 2020-09-09 | 2020-12-15 | 清华大学 | Privacy data encryption access method and system based on block chain technology for community |
| CN112116502A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community security management system |
| CN115271635A (en) * | 2022-06-29 | 2022-11-01 | 深圳市双银科技有限公司 | Intelligent community service platform system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117176923A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110113353B (en) | Intrusion detection method based on CVAE-GAN | |
| CN112906903A (en) | Network security risk prediction method and device, storage medium and computer equipment | |
| CN104601596B (en) | Data-privacy guard method in a kind of Classification Data Mining system | |
| CN101547445B (en) | System and method for detecting abnormal incursion based on mobility in mobile communication network | |
| Dammavalam et al. | Quality assessment of pixel-level imagefusion using fuzzy logic | |
| AU2019100349A4 (en) | Face - Password Certification Based on Convolutional Neural Network | |
| CN112688928A (en) | Network attack flow data enhancement method and system combining self-encoder and WGAN | |
| CN112689281B (en) | Sensor network malicious node judgment method based on two-type fuzzy system | |
| CN114301850B (en) | Military communication encryption flow identification method based on generation of countermeasure network and model compression | |
| CN117176923B (en) | Intelligent community police service patrol method and system based on data encryption | |
| Wu et al. | Vehicle-based secure location clustering for IoT-equipped building and facility management in smart city | |
| US20240119714A1 (en) | Image recognition model training method and apparatus | |
| CN112560059B (en) | Vertical federal model stealing defense method based on neural pathway feature extraction | |
| Kashir et al. | Machine learning techniques for sim box fraud detection | |
| El-emam | Embedding a large amount of information using high secure neural based steganography algorithm | |
| Malani et al. | Implementation of the naive bayes classifier method for potential network port selection | |
| CN115861034B (en) | Wireless routing data intelligent management system | |
| CN116155592A (en) | AMI network intrusion detection method based on DCGAN federal semi-supervised learning | |
| CN115189966A (en) | Block chain private data encryption and decryption service system | |
| Xu et al. | Fraud detection in telecommunication: a rough fuzzy set based approach | |
| Sun et al. | Visual analytics for anomaly classification in LAN based on deep convolutional neural network | |
| Wu et al. | Detecting Adversarial Examples Using Rich Residual Models to Improve Data Security in CNN Models | |
| CN114363464B (en) | Method and system for preventing fraud information from spreading | |
| CN116933818B (en) | Scenic spot two-dimension code management method, system and storage medium | |
| CN117093903B (en) | Label reasoning attack method in longitudinal federal learning scene |
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 |