CN110245568B - area security method and system based on face recognition - Google Patents
area security method and system based on face recognition Download PDFInfo
- Publication number
- CN110245568B CN110245568B CN201910407992.2A CN201910407992A CN110245568B CN 110245568 B CN110245568 B CN 110245568B CN 201910407992 A CN201910407992 A CN 201910407992A CN 110245568 B CN110245568 B CN 110245568B
- Authority
- CN
- China
- Prior art keywords
- wanted
- criminal suspect
- suspect
- criminal
- fan
- 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
Images
Classifications
-
- 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—Systems or methods specially adapted for 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the application provides area security methods and systems based on face recognition, the method comprises the steps of extracting a criminal suspect feature set through a multiple-overlapping face recognition algorithm, calculating a fan-shaped angle according to the escaping direction of the criminal suspect, sending the criminal suspect feature set to recognition equipment in a fan-shaped area by taking the position of the criminal suspect recognized by the recognition equipment as the center of a circle, starting a criminal suspect wanted program, returning wanted results when the criminal suspect is hit, sending criminal suspect prompts to traffic control equipment in a traffic hub when the fan-shaped area touches the traffic hub, monitoring and intercepting the criminal suspect in real time, and returning the intercepted results to a security management part , sending criminal suspect prompts to an forbidden system of the residential area, forbidding the criminal entering, and returning the security management part .
Description
Technical Field
The application relates to the field of security management, in particular to area security methods and systems based on face recognition.
Background
Criminal suspects 'wanted men are important components of security and protection safety management, and the criminal suspects' wanted men aim at improving security and protection management and social safety level and provide better support for protecting the safety of people. The wanted criminal suspects adopt the identification of the criminal suspects as the core, analyze the characteristics of the criminal suspects and monitor the latent escape area of the criminal suspects in a key way. Traditional criminal suspects wanted to arrest still is in the mode of artifical wanted to arrest, or waits for the relevant personnel passively and reports to the police, does not realize daily detection and wisdom control, does not realize the utilization to face identification technology, when extravagant a large amount of manpower, material resources, financial resources, has still delayed sometimes and has arrested the opportunity of arresting, has seriously influenced the automatic paces that criminal suspects wanted to arrest.
Therefore, the face recognition technology and the wanted practice of the criminal suspect need to be combined urgently, the wanted efficiency of the criminal suspect is improved, the wanted accuracy of the criminal suspect is improved, and unnecessary manpower, material resources and financial resources are saved.
Disclosure of Invention
In view of the above, the present application aims to provide area security methods and systems based on face recognition, to improve the wanted level of the criminal suspect, and to solve the technical problems of low risk recognition efficiency, large artificial cost and low accuracy in the current wanted process of the criminal suspect.
Based on the above purpose, the present application provides area security methods based on face recognition, including:
carrying out face recognition on at least crime suspect photos, and extracting a crime suspect feature set by a multiple-overlapping face recognition algorithm;
calculating a fan-shaped angle according to the running direction of the criminal suspect, sending the characteristic set of the criminal suspect to recognition equipment in a fan-shaped area by taking the position of the criminal suspect recognized by the recognition equipment as the center of a circle in a fan-shaped gradient diffusion mode, starting a wanted program of the criminal suspect, and returning a wanted result when the criminal suspect is found out;
when the sector area touches the transportation junction, sending a criminal suspect prompt to the traffic control equipment in the transportation junction, monitoring and intercepting the criminal suspect in real time, and returning an interception result to the security management part ;
when the sector area touches the residential area, a criminal suspect prompt is sent to an forbidden system of the residential area, the criminal suspect is forbidden to enter, and an interception result is returned to the security management part .
In , the multiple overlapping face recognition algorithm extracts a feature set of a suspect, including:
dividing the photo of the criminal suspect into an upper part and a lower part;
extracting the facial features of the upper half of criminal suspects one by one, and overlapping to form th facial features;
and extracting the facial features of the criminal suspect at the lower half part one by one, and comparing and correcting the facial features with th facial features to form a criminal suspect feature set.
In , the fan-shaped gradient diffusion method includes:
gradually reducing the wanted important grade along the outward direction of the radius by taking the radius direction as the gradient descending direction according to a preset fan-shaped angle;
corresponding to the wanted importance level of the identification device on the radius of .
In , the radial gradient gradually decreases the wanted importance level radially outward, including:
the wanted importance level calculation formula is as follows:
wherein I is wanted importance level at time t, I0The method is an initial wanted important grade, R is the wanted radius at the time t, and mu is a conversion coefficient of the radius-wanted important grade.
In , the wanted result includes a geographic location, a time of discovery, a physical status of the criminal suspect;
and pushing the wanted result to all wanted devices in real time through a transmission device, and judging whether the wanted program is finished or not.
In , the method when starting the criminal suspect wanted program to touch the transportation junction comprises:
the method comprises the steps that the place of a criminal suspect identified by identification equipment is taken as the center of a circle, and the wanted radius is expanded by a preset length along with the time lapse to form a wanted fan-shaped area;
and when the geographical position of the transportation hub enters the wanted sector area, judging that the wanted program touches the transportation hub.
In embodiments, the fan-shaped angle is calculated according to the run-away direction of the criminal suspect, the criminal suspect feature set is sent to the sector-shaped area identification device by taking the identification device to identify the criminal suspect location as the center of a circle in a fan-shaped gradient diffusion mode, and the criminal suspect wanted-to-be-wanted program is started, including:
after the criminal suspect is successfully identified by the identification device in the th sector area, defining the position of the identification device for identifying the criminal suspect as a th identification point;
sending an identification result to a security management part by taking the th identification point as the circle center, calculating a fan-shaped angle according to the escaping direction of the criminal suspect, and sending the characteristic set of the criminal suspect to identification equipment in a fan-shaped area in a fan-shaped gradient diffusion mode to form a second fan-shaped area;
when the identification equipment in the second fan-shaped area successfully identifies the criminal suspect, defining the position of the identification equipment for identifying the criminal suspect at the moment as a second identification point;
this is repeated until the criminal suspect is controlled by the security management unit .
Based on the above-mentioned purpose, this application has still provided kinds of regional security protection systems based on face identification, include:
the system comprises an initial identification module, a face recognition module and a face recognition module, wherein the initial identification module is used for carrying out face recognition on at least crime suspect pictures and extracting a crime suspect feature set through a multiple-overlapping face recognition algorithm;
the diffusion wanted-wanted module is used for calculating a fan-shaped angle according to the running direction of a criminal suspect, sending the characteristic set of the criminal suspect to recognition equipment in a fan-shaped area by taking the place of the criminal suspect recognized by the recognition equipment as the center of a circle in a fan-shaped gradient diffusion mode, starting a criminal suspect wanted-wanted program, and returning wanted-wanted results when the criminal suspect is found out;
the traffic interception module is used for sending a criminal suspect prompt to the traffic control equipment in the traffic junction when the sector area touches the traffic junction, monitoring and intercepting the criminal suspect in real time, and returning an interception result to the security management part ;
and the community prevention module is used for sending a criminal suspect prompt to an forbidden system of the residential area when the sector area touches the residential area, forbidding the criminal suspect to enter, and returning an interception result to the security management part .
In , the initial identification module includes:
the dividing unit is used for dividing the photo of the criminal suspect into an upper part and a lower part;
the extracting unit is used for extracting the facial features of the criminal suspects in the upper half one by one and overlapping to form th facial features;
and the correcting unit is used for extracting the facial features of the criminal suspect in the lower half part one by one, and comparing and correcting the facial features with the th facial features to form a criminal suspect feature set.
In embodiments, the diffusion wanted module comprises:
an th identification unit, configured to define an identification device position for identifying the criminal suspect as a th identification point after the criminal suspect is successfully identified by the identification device in the th sector area;
an th diffusion unit, configured to send an identification result to the security management unit with the th identification point as a center of circle, calculate a sector angle according to the escape direction of the criminal suspect, and send the characteristic set of the criminal suspect to an identification device in a sector area in a sector gradient diffusion manner to form a second sector area;
the second identification unit is used for defining the position of the identification equipment for identifying the criminal suspect as a second identification point after the identification equipment in the second fan-shaped area successfully identifies the criminal suspect;
and a circulation unit configured to circulate until the criminal suspect is controlled by the security management unit .
Drawings
In the drawings, like numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified, and in which not are drawn to scale, it should be understood that these drawings depict only embodiments of in accordance with the present disclosure and are not to be considered limiting of the scope of the disclosure.
Fig. 1 shows a flowchart of a region security method based on face recognition according to an embodiment of the present invention.
Fig. 2 is a block diagram illustrating a region security system based on face recognition according to an embodiment of the present invention.
Fig. 3 illustrates a constitutional view of an initial recognition module according to an embodiment of the present invention.
Fig. 4 shows a composition diagram of a diffusion wanted module according to an embodiment of the present invention.
Fig. 5 is a schematic diagram illustrating a region security method based on face recognition according to an embodiment of the present invention.
Detailed Description
The present application is described in further detail in with reference to the drawings and the examples, it being understood that the specific examples are set forth herein for the purpose of illustration and not as a definition of the limits of the invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flowchart of a region security method based on face recognition according to an embodiment of the present invention. As shown in fig. 1, the area security method based on face recognition includes:
and S11, performing face recognition on at least crime suspect pictures, and extracting a crime suspect feature set through a multiple-overlapping face recognition algorithm.
In embodiments, the extracting the feature set of the suspect by the multiple overlapping face recognition algorithm includes:
dividing the photo of the criminal suspect into an upper part and a lower part;
extracting the facial features of the upper half of criminal suspects one by one, and overlapping to form th facial features;
and extracting the facial features of the criminal suspect at the lower half part one by one, and comparing and correcting the facial features with th facial features to form a criminal suspect feature set.
Because the photo of the criminal suspect is a static image, the face features of the criminal suspect can only extract local features due to historical corrosion, light, angles, makeup, shooting methods and the like, or the face features of the criminal suspect even if extracted, have the problem of inaccuracy. Therefore, it is necessary to collect a plurality of photos of the criminal suspect, extract the face features a plurality of times, and superimpose and accumulate the face features of the criminal suspect more comprehensively.
In addition, , the photo of the criminal suspect is divided into two parts, wherein the part is used for overlapped recognition of the face characteristics of the criminal suspect, and the part is used for correcting the accuracy of face extraction, so that the accuracy of the face characteristics of the criminal suspect can be further improved , and a solid foundation is laid for the wanted work of the criminal suspect.
In embodiments, the photos of the criminal suspect are divided into upper and lower parts, which can be grouped by random selection or sorted by sequence.
In embodiments, when the face features of the criminal suspect are extracted in an overlapping manner and enter a steady state and more face features cannot be extracted, the remaining photos of the criminal suspect can be used for checking the face features.
And S12, calculating a fan-shaped angle according to the escape direction of the criminal suspect, sending the characteristic set of the criminal suspect to a recognition device in a fan-shaped area by taking the position of the criminal suspect recognized by the recognition device as the center of a circle in a fan-shaped gradient diffusion mode, starting a wanted program of the criminal suspect, and returning a wanted result when the criminal suspect is found out to be hit.
In , the fan-shaped gradient diffusion mode comprises:
gradually reducing the wanted important grade along the outward direction of the radius by taking the radius direction as the gradient descending direction according to a preset fan-shaped angle;
corresponding to the wanted importance level of the identification device on the radius of .
In , the radial direction is taken as a gradient descending direction, and the wanted importance level is gradually reduced along the radial direction, which comprises the following steps:
the wanted importance level calculation formula is as follows:
wherein I is wanted importance level at time t, I0The method is an initial wanted important grade, R is the wanted radius at the time t, and mu is a conversion coefficient of the radius-wanted important grade.
According to the formula, the wanted importance level is continuously reduced along with the time, which shows that the criminal suspect may escape from the nearby area along with the time, and in addition, the wanted importance level is lower in the area far away from the escape origin at the same time point of , because the criminal suspect cannot escape to the far area at the time, the occurrence probability is lower, and the wanted resource is not wasted for wanted seizing.
In embodiments, the wanted result includes a geographic location, a time of discovery, a physical status of the criminal suspect;
and pushing the wanted result to all wanted devices in real time through a transmission device, and judging whether the wanted program is finished or not.
Specifically, wanted devices within the area may include portable devices (e.g., handheld identity recognizers used by police), cameras, disabled, ticket gates, etc., sensing devices that may capture criminal suspect information.
In embodiments, after the criminal suspect is successfully identified by the identification device in the th sector area, the position of the identification device for identifying the criminal suspect is defined as a th identification point;
sending an identification result to a security management part by taking the th identification point as the circle center, calculating a fan-shaped angle according to the escaping direction of the criminal suspect, and sending the characteristic set of the criminal suspect to identification equipment in a fan-shaped area in a fan-shaped gradient diffusion mode to form a second fan-shaped area;
when the identification equipment in the second fan-shaped area successfully identifies the criminal suspect, defining the position of the identification equipment for identifying the criminal suspect at the moment as a second identification point;
this is repeated until the criminal suspect is controlled by the security management unit .
And step S13, when the sector area touches the traffic junction, sending a criminal suspect prompt to the traffic control equipment in the traffic junction, monitoring and intercepting the criminal suspect in real time, and returning an interception result to the security management part .
In , the method for detecting the criminal suspects wanted program touching the transportation junction comprises:
the method comprises the steps that the place of a criminal suspect identified by identification equipment is taken as the center of a circle, and the wanted radius is expanded by a preset length along with the time lapse to form a wanted fan-shaped area;
and when the geographical position of the transportation hub enters the wanted sector area, judging that the wanted program touches the transportation hub.
And S14, when the sector area touches the residential area, sending a criminal suspect prompt to a forbidden system of the residential area, forbidding the criminal suspect to enter, and returning an interception result to the security management part .
Particularly, security experience shows that is favored to avoid in residential areas after criminal suspects are escaped, is more complicated in human mouth environment in residential areas, people flow greatly and are not easy to find, is also favored to tie up common people after some criminal suspects are found, so that criminal suspects can be found in time by sending criminal suspects prompts to forbidden systems in residential areas which can enter, controlling the security systems in the residential areas to forbid the criminal suspects from entering and timely returning interception results to the security management part , and the security management part is facilitated to find the criminal suspects in time and carry out capture and general arrest.
Fig. 2 is a block diagram illustrating a region security system based on face recognition according to an embodiment of the present invention. As shown in fig. 2, the whole area security system based on face recognition can be divided into:
the initial identification module 21 is used for carrying out face identification on at least crime suspect photos and extracting a crime suspect feature set by a multiple-overlapping face identification algorithm;
the diffusion wanted-wanted module 22 is used for calculating a fan-shaped angle according to the running direction of a criminal suspect, sending the characteristic set of the criminal suspect to recognition equipment in a fan-shaped area by taking the place of the criminal suspect recognized by the recognition equipment as the center of a circle in a fan-shaped gradient diffusion mode, starting a criminal suspect wanted-wanted program, and returning a wanted result when the criminal suspect is found out;
the traffic intercepting module 23 is configured to send a criminal suspect prompt to a traffic control device in the traffic junction when the sector area touches the traffic junction, monitor and intercept the criminal suspect in real time, and return an intercepting result to the security management unit ;
and the community prevention module 24 is configured to send a criminal suspect prompt to an forbidden system of a residential area when the sector area touches the residential area, forbid the criminal suspect from entering the residential area, and return an interception result to the security management unit .
Fig. 3 illustrates a constitutional view of an initial recognition module according to an embodiment of the present invention. As can be seen from fig. 3, the initial identification module includes:
a dividing unit 211 for dividing the photo of the criminal suspect into an upper part and a lower part;
an extracting unit 212, configured to extract facial features of the criminal suspect in the upper half one by one, and overlap to form th facial features;
and a correcting unit 213, configured to extract the facial features of the lower half of the criminal suspect one by one, and compare and correct the extracted facial features with the th facial features to form a criminal suspect feature set.
Fig. 4 shows a composition diagram of a diffusion wanted module according to an embodiment of the present invention. As can be seen from fig. 4, the diffusion wanted module comprises:
an th identification unit 221, configured to define an identification device position for identifying the criminal suspect as a th identification point after the criminal suspect is successfully identified by the identification device in the th sector area;
an th diffusion unit 222, configured to send an identification result to the security management unit with the th identification point as a center of circle, calculate a sector angle according to the escape direction of the criminal suspect, and send the characteristic set of the criminal suspect to an identification device in a sector area in a sector gradient diffusion manner, so as to form a second sector area;
a second identification unit 223, configured to define, as a second identification point, a position of an identification device that identifies the criminal suspect at the time when the identification device in the second sector area successfully identifies the criminal suspect;
a circulation unit 224 for circulating so until the criminal suspect is controlled by the security management section .
Fig. 5 is a schematic diagram illustrating a region security method based on face recognition according to an embodiment of the present invention.
As can be seen from fig. 5, in embodiments, the criminal suspect escapes from the origin O, the wanted range of the criminal suspect continuously diffuses from the point O to the periphery in a fan-shaped gradient diffusion manner, the wanted range of the criminal suspect continuously expands as time goes on, the wanted importance level is also transmitted to the edge of the fan-shaped region, the fan-shaped region which is diffused first is the fan-shaped region OPT, and when an escape trace is found at the point P, the fan-shaped region OAB starts to be diffused with the point P as the center of the circle.
Each node on the same circumference of has the same wanted importance level because of the equal distance with the point O, namely the wanted importance level of the P point and the T point is equal in the diffusion process, and the wanted importance level of the A point and the B point is also equal.
In embodiments, when a sector area that is spreading continuously touches a transportation junction T, such as an airport, various traffic control devices (e.g., forbidden machines, gate machines, ticket checker machines, etc.) in the airport are notified to intercept a criminal suspect and immediately send out wanted alarms to the control center and local staff of the transportation junction, so that the criminal suspect cannot run away through transportation tools, the escape range of the criminal suspect is limited, and valuable time is won for the criminal suspect.
In real-time cases, the criminal suspect data from each server can be stored in a plurality of storage modes such as distributed storage, local centralized storage, cloud storage and edge storage according to the wanted scale and data volume of the criminal suspect, so that the data storage efficiency is improved, and the data transmission delay is reduced.
In the description herein, reference to the terms " embodiments," " embodiments," "examples," "specific examples," or " examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least embodiments or examples of the invention.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include or more executable instructions for implementing specific logical functions or steps in the process, and the scope of the preferred embodiments of the present invention includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
For the purposes of this description, a "computer-readable medium" can be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device (e.g., a computer-based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions).
For example, if implemented in hardware, and in another embodiment , it may be implemented using any item or combination thereof known in the art, a discrete logic circuit having logic circuits for implementing logic functions on data signals, an application specific integrated circuit having appropriate combinational logic circuits, a programmable array (PGA), a field programmable array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware associated with instructions of a program, which may be stored in computer readable storage media, and when executed, the program includes or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present invention may be integrated into processing modules, or each unit may exist alone physically, or two or more units are integrated into modules.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (4)
1, area security protection method based on face recognition, which comprises:
carrying out face recognition on at least crime suspect pictures, and extracting a crime suspect feature set through a multiple overlapping face recognition algorithm, wherein the multiple overlapping face recognition algorithm extracts the crime suspect feature set and comprises the steps of dividing the crime suspect pictures into an upper part and a lower part, extracting the facial features of the upper half crime suspect one by one, overlapping to form a th facial feature, extracting the facial features of the lower half crime suspect one by one, and carrying out comparison and correction on the extracted facial features and the th facial feature to form a crime suspect feature set;
calculating a fan-shaped angle according to the escaping direction of a criminal suspect, sending the characteristic set of the criminal suspect to a recognition device in a fan-shaped area by taking the place of the criminal suspect recognized by the recognition device as the center of a circle through a fan-shaped gradient diffusion mode, starting a wanted program of the criminal suspect, and returning a wanted result when the criminal suspect is found out, wherein the fan-shaped gradient diffusion mode comprises the steps of gradually reducing wanted important grades along the radial outward direction by taking the radial direction as the gradient descending direction according to a preset fan-shaped angle, and is equal to the wanted important grade of the recognition device on the radius of ;
when the sector area touches the transportation junction, sending a criminal suspect prompt to the traffic control equipment in the transportation junction, monitoring and intercepting the criminal suspect in real time, and returning an interception result to the security management part ;
when the sector area touches a residential area, sending a criminal suspect prompt to an forbidden system of the residential area, forbidding the criminal suspect to enter, and returning an interception result to a security management part ;
use the radius direction as gradient decline direction, along the outside direction of radius gradually reduce wanted important grade, include:
the wanted importance level calculation formula is as follows:
wherein I is the wanted importance level at the time t,
is an initial wanted level, R is a wanted radius at the moment t,the conversion coefficient is radius-wanted important grade.
2. The method of claim 1,
the wanted result comprises the geographical position, the discovery time and the physical state of the criminal suspect;
and pushing the wanted result to all wanted devices in real time through a transmission device, and judging whether the wanted program is finished or not.
3. The method of claim 1, wherein when the sector area touches a transportation junction, comprising:
the method comprises the steps that the place of a criminal suspect identified by identification equipment is taken as the center of a circle, and the wanted radius is expanded by a preset length along with the time lapse to form a wanted fan-shaped area;
and when the geographical position of the transportation hub enters the wanted sector area, judging that the wanted program touches the transportation hub.
4. The method of claim 1, wherein the calculating of the fan-shaped angle according to the escape direction of the criminal suspect, the sending of the criminal suspect feature set to the identification device in the fan-shaped area by using the identification device to identify the location of the criminal suspect as the center of the circle in a fan-shaped gradient diffusion manner, and the starting of the criminal suspect wanted program comprise:
after the criminal suspect is successfully identified by the identification device in the th sector area, defining the position of the identification device for identifying the criminal suspect as a th identification point;
sending an identification result to a security management part by taking the th identification point as the circle center, calculating a fan-shaped angle according to the escaping direction of the criminal suspect, and sending the characteristic set of the criminal suspect to identification equipment in a fan-shaped area in a fan-shaped gradient diffusion mode to form a second fan-shaped area;
when the identification equipment in the second fan-shaped area successfully identifies the criminal suspect, defining the position of the identification equipment for identifying the criminal suspect at the moment as a second identification point;
this is repeated until the criminal suspect is controlled by the security management unit .
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910407992.2A CN110245568B (en) | 2019-05-15 | 2019-05-15 | area security method and system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910407992.2A CN110245568B (en) | 2019-05-15 | 2019-05-15 | area security method and system based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110245568A CN110245568A (en) | 2019-09-17 |
| CN110245568B true CN110245568B (en) | 2020-01-31 |
Family
ID=67884148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910407992.2A Active CN110245568B (en) | 2019-05-15 | 2019-05-15 | area security method and system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245568B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111372191B (en) * | 2020-02-03 | 2023-01-10 | 重庆特斯联智慧科技股份有限公司 | Target tracking method and system for special population |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451555A (en) * | 2017-07-27 | 2017-12-08 | 安徽慧视金瞳科技有限公司 | A kind of hair based on gradient direction divides to determination methods |
| CN108073577A (en) * | 2016-11-08 | 2018-05-25 | 中国电信股份有限公司 | A kind of alarm method and system based on recognition of face |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104902004B (en) * | 2015-04-13 | 2016-04-27 | 深圳位置网科技有限公司 | The emergency rescue system of a kind of Missing Persons and method |
| CN106709468A (en) * | 2016-12-31 | 2017-05-24 | 北京中科天云科技有限公司 | City region surveillance system and device |
| KR20180137155A (en) * | 2017-06-16 | 2018-12-27 | 남서울대학교 산학협력단 | System for smart cpted based reinforcing approach control and method by using the same |
| US10699148B2 (en) * | 2017-08-21 | 2020-06-30 | Lifesize, Inc. | Dynamic calibration of detection system for active areas of interest within video data |
| CN109743541B (en) * | 2018-12-15 | 2023-04-18 | 深圳壹账通智能科技有限公司 | Intelligent monitoring method and device, computer equipment and storage medium |
-
2019
- 2019-05-15 CN CN201910407992.2A patent/CN110245568B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073577A (en) * | 2016-11-08 | 2018-05-25 | 中国电信股份有限公司 | A kind of alarm method and system based on recognition of face |
| CN107451555A (en) * | 2017-07-27 | 2017-12-08 | 安徽慧视金瞳科技有限公司 | A kind of hair based on gradient direction divides to determination methods |
Non-Patent Citations (1)
| Title |
|---|
| "复杂环境下的人脸识别技术研究";李静天;《中国优秀硕士学位论文全文数据库（电子库）信息科技辑》;20130615;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245568A (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN110334238B (en) | missing population tracing method and system based on face recognition | |
| CN107341443B (en) | Method for processing video frequency, device and storage medium | |
| CA2791590A1 (en) | Biometric matching engine | |
| CN109978215B (en) | Patrol management method and device | |
| US20240095862A1 (en) | Method for determining dangerousness of person, apparatus, system and storage medium | |
| CN110177255B (en) | Case scheduling-based video information publishing method and system | |
| KR20170112904A (en) | Risk early warning method and device | |
| CN105357216A (en) | Secure access method and system | |
| CN104660987A (en) | Target motion trail analysis method and monitoring system | |
| CN105608464A (en) | Face recognition mobile terminal solving system and solving method | |
| CN110245568B (en) | area security method and system based on face recognition | |
| CN105447385B (en) | A kind of applied database honey jar detected at many levels realizes system and method | |
| CN112380892B (en) | Image recognition method, device, equipment and medium | |
| CN111368615A (en) | Violation building early warning method and device and electronic equipment | |
| CN114202839A (en) | Gate passage control method, device, equipment and storage medium | |
| CN110865415A (en) | Security inspection method and device | |
| CN105574498A (en) | Face recognition system and recognition method based on customs security check | |
| KR20160109516A (en) | Rescue object grasp system and method | |
| CN115410224A (en) | Electric power operation site violation identification system and method based on image data | |
| Ige et al. | Enhancing Border Security and Countering Terrorism Through Computer Vision: A Field of Artificial Intelligence | |
| CN105447408A (en) | Data protection method and apparatus | |
| Ar et al. | A computer vision-based object detection and counting for COVID-19 protocol compliance: a case study of Jakarta | |
| JP2016062207A (en) | Emergency detector, emergency detection system, emergency detection program, and emergency detecting method | |
| CN108335050A (en) | A kind of event worksheet processing intelligent control method and control device |
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 |