CN110191317A - A kind of electronic monitoring and control system based on image recognition - Google Patents
A kind of electronic monitoring and control system based on image recognition Download PDFInfo
- Publication number
- CN110191317A CN110191317A CN201910423166.7A CN201910423166A CN110191317A CN 110191317 A CN110191317 A CN 110191317A CN 201910423166 A CN201910423166 A CN 201910423166A CN 110191317 A CN110191317 A CN 110191317A
- Authority
- CN
- China
- Prior art keywords
- point
- module
- image
- information
- face
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of electronic monitoring and control systems based on image recognition, including image information to obtain module, counting module, image information processing unit, image information analysis module, prompting message transmission, image contrast module, data storage module, top control module, clearance module and alarm modules;Wherein, the image information obtains module for acquiring face information and human body information, the image information obtains module and is made of No.1 high-definition camera, No. two high-definition cameras and No. three high-definition cameras, No.1 high-definition camera is mounted on face inlet and obtains face image, and No. two high-definition cameras and No. three high-definition cameras are mounted on the two sides of inlet;The present invention, which can effectively reduce influence of the outside environmental elements to monitor video image definition, can also allow the system with can preferably be applied in combination with external other systems, so that the system be allowed more to be worth of widely use.
Description
Technical field
The invention belongs to monitoring fields, are related to image recognition utilization technology, specifically a kind of electronics based on image recognition
Monitoring system.
Background technique
Electronic monitoring and control system is mainly made of headend equipment and rear end equipment this two large divisions, and wherein rear end equipment can be into one
Step is divided into central control equipment and sub-control control equipment.There are many constituted mode, the connection between them can pass through front and back ends equipment
The various ways such as cable, optical fiber or microwave realize, video monitoring system be conducive to improve public security organ site tissue, commander,
Coordination and control ability especially improve police in the activity such as large-scale activity security, Mass disturbance disposition and guard duty
Business efficiency.
Existing screen monitoring system, in use, monitoring process are easy to be caused to monitor by extraneous factor image
Image is unintelligible, and mostly simple screen monitoring cannot analyze collected image and not combine with other systems
It uses, so that the monitoring effect of monitoring system, safety is not good enough, in order to solve these defects, it is proposed that a solution.
Summary of the invention
The purpose of the present invention is to provide a kind of electronic monitoring and control systems based on image recognition.
The technical problems to be solved by the invention are as follows:
(1) influence of the external environment to monitoring image definition how is reduced;
(2) how preferably to allow the system to connect with external other systems to be applied in combination;
The purpose of the present invention can be achieved through the following technical solutions:
A kind of electronic monitoring and control system based on image recognition, including image information obtain module, counting module, image information
Processing unit, prompting message transmission, image contrast module, data storage module, top control module, is put at image information analysis module
Row module and alarm modules;
Wherein, the image information obtains module and obtains for acquiring face information and human body information, the image information
Module is made of No.1 high-definition camera, No. two high-definition cameras and No. three high-definition cameras, and No.1 high-definition camera is mounted on
Face inlet obtains face image, and No. two high-definition cameras and No. three high-definition cameras are mounted on the two sides of inlet, and No. two
High-definition camera shoots body image from the top down and obtains human body information, and No. three high-definition cameras shoot body image from bottom to top
Human body information is obtained, the image information obtains module and sends data processing mould for collected human body information and face information
Block;
The counting module from face information for obtaining out number information;
Wherein, the specific acquisition process of number information is as follows:
SS1: number information is the face quantity appeared in face information in the unit time;
SS2: preset time is labeled as TM, TM≤2h;
SS3: the number appeared in image information acquisition module in the TM period is labeled as Rsi, i=1 ... n;
SS3: in the TM period, when TM is greater than preset value, image data processing module handles out No.1 prompting message
It issues;
The image processing module therefrom gets human face characteristic point and people for handling face information and human body information
Body characteristics point, the image information analysis module get real time contrast for analyzing human face characteristic point and characteristics of human body's image
Coefficient SCircle ratio、STriangleAnd LtThan;
Its clarity can also be handled when the data processing module processing face information and human body information, when continuous
When can not identify more than preset times, image data processing module can handle out No. two prompting messages and issue;
The prompting message sending module has prestored system peace for sending prompting message in the data storage module
Fill original Contrast's COEFFICIENT K S of permanent personnelCircle ratio、KLtThanAnd KSTriangle, the image contrast module is for real time contrast's coefficient
It is compared with original Contrast's coefficient, the result compared is sent to top control module;
The specific comparison process of image contrast module is as follows:
(1): passing through formula SCircle ratio- KSCircle ratio=KSDifference, it can obtain real time contrast's coefficient SCircle ratioWith former coefficient of correlation
KSCircle ratioDifference KSDifference;
(2): working as KSDifferenceWhen=0 or | KSDifference| comparison passes through when less than preset value, and top control module is located when comparison passes through
Clearance instruction is managed out to clearance module;
(3): when | KSDifference| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than default in preset time
When, top control module handles out alarm command to alarm modules;
(4): passing through formula STriangle- KSTriangle=KSDifference, available real time contrast's coefficient STriangleWith former coefficient of correlation KSTriangle;
(5): working as KSTriangleWhen=0 or | KSTriangle| comparison passes through when less than preset value, and top control module is i.e. when passing through for comparison
Clearance instruction is handled out to clearance module;
(6): when | KSTriangle| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than pre- in preset time
If when, top control module handles out alarm command to alarm modules;
(7): passing through formula LtThan- KLtThan=KLtDifference, it can make real time contrast's coefficient LtThan remoteAnd KLtThanDifference
KLtDifference;
(8): working as KLtDifferenceWhen=0 or | KLtDifference| comparison passes through when less than preset value, and top control module is i.e. when passing through for comparison
Clearance instruction is handled out to clearance module;
(9): when | KLtDifference| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than pre- in preset time
If when, top control module handles out alarm command to alarm modules;
The top control module is used to convert comparison result to control signal and is sent to clearance module and alarm modules;
The clearance module and alarm modules are installed in gate inhibition's gate.
Further, the concrete processing procedure of the face information is as follows:
Step 1: after image information obtains module acquisition face information, one can be first extracted from face information clearly
Spend highest photo;
Step 2: pre-set dimension is scaled it, and extracts human face characteristic point, face characteristic from the photo scaled
The specific extraction process of point is as follows:
I: two tail of the eyes of face are set as human face characteristic point in face image, are marked as K1 point and K2 point;
II: two inner eye corners of the face in face image are set as human face characteristic point, are marked as K3 point and K4 point,
K3 point and the same side of K1 point, K4 and the same side K2;
III: the prenasale in face image is set as human face characteristic point, is marked as P point;
IV: the chin two sides minimum point in face image is set as human face characteristic point, is labeled as X1 point and X2 point;
Step 3: obtaining straight line L1 for K1 point and K3 point line, K2 and K4 point line is obtained straight line L2;
Step 4: being also configured as human face characteristic point for the midpoint of straight line L1, is marked as Z1 point;
Step 5: being also configured as human face characteristic point for the midpoint of straight line L2, is marked as Z2 point;
Step 6: obtaining straight line L3 for P point and Z1 point line, and P point and Z2 point line are obtained straight line L4;
Step 7: obtaining straight line L5 for P point and X1 point line, and P point and X2 point line are obtained straight line L6;
Step 8: obtaining straight line L7 for X1 point and X2 point line, is to be a vertical line L8 with the midpoint of L7, and the one of vertical line L8
End is connect with the midpoint of L7, and the other end is connect with P point;
The concrete processing procedure of the human body information is as follows:
S1: the highest photo of clarity is extracted from the body image that No. two cameras are shot and is marked as
PS1, then the highest photo PS2 of a clarity is extracted from the body image that No. three cameras are shot;
S2: human body feature point is set by the point of human body in PS1 and ground face contact, is marked as Q1;
S3: human body feature point is set by the highest point of human body shoulder in PS1, is marked as Q2;
S4: by PS2, the point of human body and ground face contact is set as human body feature point, is marked as Q3;
S5: human body feature point is set by the highest point of human body shoulder in PS2, is marked as Q4;
S6: obtaining straight line Lt1 for Q1 and Q2 line, Q3 and Q4 line is obtained straight line Lt2.
Further, detailed process is as follows for the image data analysis module analysis face information:
Step (1): using L4 as radius, circle is drawn centered on P point and obtains round R1;
Step (2): using L5 as radius, circle is talked about centered on P point and obtains round R2;
Step (3): pass through formula SCircle 1=π * L32The area S of available R1Circle 1;
Step (4): pass through formula SCircle 2=π * L42The area S of available R2Circle 2;
Step (5): pass through formula SCircle 1/SCircle 2=SCircle ratio, the area S of available R1Circle 1With the area S of R2Circle 2Ratio, i.e.,
Real time contrast's coefficient SCircle ratio;
Step (6): straight line L5, straight line L6 and straight line L7 have encircled a city triangle SJ;
Step (7): measuring the length of vertical line L8 and L7, passes through formula (L7*L8)/2=STriangle, it can obtain triangle
The area S of shape SJTriangle, i.e. real time contrast's coefficient STriangle
Detailed process is as follows for the image data analysis module analysis human body information:
Step a: measuring the length of straight line Lt1, then measures the length of straight line Lt2;
Step b: pass through formula Lt1/Lt2=LtThan, the ratio Lt of available straight line Lt1 and straight line Lt2Than.Real time contrast
Coefficient LtThan
Further, detailed process is as follows for the image data analysis module analysis face information: the No.1 is reminded
The content of information is " current flow of the people is excessive, and staff is asked to dredge ", and the content of No. two prompting messages is " shooting
Image is unintelligible, and staff is asked to clear up high-definition camera " content of the No.1 prompting message is " current flow of the people
It is excessive, ask staff to dredge ", the content of No. two prompting messages is that " filmed image is unintelligible, asks staff couple
High-definition camera is cleared up ".
Beneficial effects of the present invention:
(1) counting module that is arranged of the present invention and image information processing module, can to the number appeared in image into
Row analysis of accounts analyzes the number in preset time period, obtains module when appearing in image information in preset time period
When middle, system can send prompt information to administrative staff by prompting message sending module to prompt administrative staff to carry out the stream of people and dredge
It leads, avoids and be in the presence of that queuing is too long using the region of the system, while image information processing module can be to received people
Body information and face information carry out the analysis of clarity, when the body image letter of discovery shooting is low with face information clarity,
Prompt information can be sent to administrative staff to prompt staff to take the photograph the high definition of acquisition image by prompting message sending module
As head progress cleaning and maintenance, so that the situation hair of video identification can not be fed by effectively reducing the system caused by external factor
It is raw;
(2) present invention, can be by the more of acquisition by the image information analysis module and image contrast module of setting
Kind face information and human body information are analyzed, and the safety of Lai Tigao electronic monitoring and control system, image information analysis module can
Pass through formula SCircle 1/SCircle 2=SCircle ratioWith formula (L7*L8)/2=STriangle, available real time contrast's coefficient SCircle ratioWith real time contrast's coefficient
LtThan, while passing through formula STriangle- KSTriangle=KSDifference, available real time contrast's coefficient STriangleWith former coefficient of correlation KSTriangle, will be real-time
Coefficient of correlation SCircle ratio, real time contrast's coefficient STriangleWith real time contrast's coefficient LtThanWith former coefficient of correlation KSCircle ratio、KLtThanAnd KSTriangleCompared
Compared with when the comparison of three's one of which passes through, i.e. expression comparison is by that can let pass, by a variety of way of contrast of setting, no
The accuracy that only ensure that video monitoring verifying also avoids the impassable situation of validation failure and occurs, the monitoring system is allowed to make
The flexibility ratio used is higher, allow the system to it is more preferable be applied in combination with external other systems, allow the system to be more suitable
It promotes the use of.
Detailed description of the invention
In order to facilitate the understanding of those skilled in the art, the present invention will be further described below with reference to the drawings.
Fig. 1 is system block diagram of the invention.
Specific embodiment
As shown in Figure 1, a kind of electronic monitoring and control system based on image recognition, including image information obtain module, count module
Block, image information processing unit, image information analysis module, prompting message transmission, image contrast module, data storage module,
Top control module, clearance module and alarm modules;
Wherein, the image information obtains module and obtains for acquiring face information and human body information, the image information
Module is made of No.1 high-definition camera, No. two high-definition cameras and No. three high-definition cameras, and No.1 high-definition camera is mounted on
Face inlet obtains face image, and No. two high-definition cameras and No. three high-definition cameras are mounted on the two sides of inlet, and No. two
High-definition camera shoots body image from the top down and obtains human body information, and No. three high-definition cameras shoot body image from bottom to top
Human body information is obtained, the image information obtains module and sends data processing mould for collected human body information and face information
Block;
The counting module from face information for obtaining out number information;
Wherein, the specific acquisition process of number information is as follows:
SS1: number information is the face quantity appeared in face information in the unit time;
SS2: preset time is labeled as TM, TM≤2h;
SS3: the number appeared in image information acquisition module in the TM period is labeled as Rsi, i=1 ... n;
SS3: in the TM period, when TM is greater than preset value, image data processing module handles out No.1 prompting message
It issues;
The image processing module therefrom gets human face characteristic point and people for handling face information and human body information
Body characteristics point, the image information analysis module get real time contrast for analyzing human face characteristic point and characteristics of human body's image
Coefficient SCircle ratio、STriangleAnd LtThan;
Its clarity can also be handled when the data processing module processing face information and human body information, when continuous
When can not identify more than preset times, image data processing module can handle out No. two prompting messages and issue;
The prompting message sending module has prestored system peace for sending prompting message in the data storage module
Fill original Contrast's COEFFICIENT K S of permanent personnelCircle ratio、KLtThanAnd KSTriangle, the image contrast module is for real time contrast's coefficient
It is compared with original Contrast's coefficient, the result compared is sent to top control module;
The specific comparison process of image contrast module is as follows:
(1): passing through formula SCircle ratio- KSCircle ratio=KSDifference, it can obtain real time contrast's coefficient SCircle ratioWith former coefficient of correlation
KSCircle ratioDifference KSDifference;
(2): working as KSDifferenceWhen=0 or | KSDifference| comparison passes through when less than preset value, and top control module is located when comparison passes through
Clearance instruction is managed out to clearance module;
(3): when | KSDifference| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than default in preset time
When, top control module handles out alarm command to alarm modules;
(4): passing through formula STriangle- KSTriangle=KSDifference, available real time contrast's coefficient STriangleWith former coefficient of correlation KSTriangle;
(5): working as KSTriangleWhen=0 or | KSTriangle| comparison passes through when less than preset value, and top control module is i.e. when passing through for comparison
Clearance instruction is handled out to clearance module;
(6): when | KSTriangle| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than pre- in preset time
If when, top control module handles out alarm command to alarm modules;
(7): passing through formula LtThan- KLtThan=KLtDifference, it can make real time contrast's coefficient LtThan remoteAnd KLtThanDifference
KLtDifference;
(8): working as KLtDifferenceWhen=0 or | KLtDifference| comparison passes through when less than preset value, and top control module is i.e. when passing through for comparison
Clearance instruction is handled out to clearance module;
(9): when | KLtDifference| it when being greater than preset value, that is, compares and does not pass through, continuous not number of pass times is more than pre- in preset time
If when, top control module handles out alarm command to alarm modules;
The top control module is used to convert comparison result to control signal and is sent to clearance module and alarm modules;
The clearance module and alarm modules are installed in gate inhibition's gate.
The concrete processing procedure of the face information is as follows:
Step 1: after image information obtains module acquisition face information, one can be first extracted from face information clearly
Spend highest photo;
Step 2: pre-set dimension is scaled it, and extracts human face characteristic point, face characteristic from the photo scaled
The specific extraction process of point is as follows:
I: two tail of the eyes of face are set as human face characteristic point in face image, are marked as K1 point and K2 point;
II: two inner eye corners of the face in face image are set as human face characteristic point, are marked as K3 point and K4 point,
K3 point and the same side of K1 point, K4 and the same side K2;
III: the prenasale in face image is set as human face characteristic point, is marked as P point;
IV: the chin two sides minimum point in face image is set as human face characteristic point, is labeled as X1 point and X2 point;
Step 3: obtaining straight line L1 for K1 point and K3 point line, K2 and K4 point line is obtained straight line L2;
Step 4: being also configured as human face characteristic point for the midpoint of straight line L1, is marked as Z1 point;
Step 5: being also configured as human face characteristic point for the midpoint of straight line L2, is marked as Z2 point;
Step 6: obtaining straight line L3 for P point and Z1 point line, and P point and Z2 point line are obtained straight line L4;
Step 7: obtaining straight line L5 for P point and X1 point line, and P point and X2 point line are obtained straight line L6;
Step 8: obtaining straight line L7 for X1 point and X2 point line, is to be a vertical line L8 with the midpoint of L7, and the one of vertical line L8
End is connect with the midpoint of L7, and the other end is connect with P point;
The concrete processing procedure of the human body information is as follows:
S1: the highest photo of clarity is extracted from the body image that No. two cameras are shot and is marked as
PS1, then the highest photo PS2 of a clarity is extracted from the body image that No. three cameras are shot;
S2: human body feature point is set by the point of human body in PS1 and ground face contact, is marked as Q1;
S3: human body feature point is set by the highest point of human body shoulder in PS1, is marked as Q2;
S4: by PS2, the point of human body and ground face contact is set as human body feature point, is marked as Q3;
S5: human body feature point is set by the highest point of human body shoulder in PS2, is marked as Q4;
S6: obtaining straight line Lt1 for Q1 and Q2 line, Q3 and Q4 line is obtained straight line Lt2.
Detailed process is as follows for the image data analysis module analysis face information:
Step (1): using L4 as radius, circle is drawn centered on P point and obtains round R1;
Step (2): using L5 as radius, circle is talked about centered on P point and obtains round R2;
Step (3): pass through formula SCircle 1=π * L32The area S of available R1Circle 1;
Step (4): pass through formula SCircle 2=π * L42The area S of available R2Circle 2;
Step (5): pass through formula SCircle 1/SCircle 2=SCircle ratio, the area S of available R1Circle 1With the area S of R2Circle 2Ratio, i.e.,
Real time contrast's coefficient SCircle ratio;
Step (6): straight line L5, straight line L6 and straight line L7 have encircled a city triangle SJ;
Step (7): measuring the length of vertical line L8 and L7, passes through formula (L7*L8)/2=STriangle, it can obtain triangle
The area S of shape SJTriangle, i.e. real time contrast's coefficient STriangle
Detailed process is as follows for the image data analysis module analysis human body information:
Step a: measuring the length of straight line Lt1, then measures the length of straight line Lt2;
Step b: pass through formula Lt1/Lt2=LtThan, the ratio Lt of available straight line Lt1 and straight line Lt2Than.Real time contrast
Coefficient LtThan
Detailed process is as follows: the content of the No.1 prompting message for the image data analysis module analysis face information
For " current flow of the people is excessive, and staff is asked to dredge ", the content of No. two prompting messages is that " filmed image is unclear
Clear, staff is asked to clear up high-definition camera " content of the No.1 prompting message is that " current flow of the people is excessive, asks
Staff dredges ", the content of No. two prompting messages is that " filmed image is unintelligible, and staff is asked to take the photograph high definition
As head is cleared up ".
A kind of electronic monitoring and control system based on image recognition, at work, image information, which obtains module, first can acquire people
Face information and human body information, image information storage module are made of three groups of high-definition cameras, wherein one group of high-definition camera installation
In face inlet, face image can be shot, another two groups of high-definition cameras are mounted on the two sides of inlet, wherein one group of high definition is taken the photograph
Human body information is obtained as head shoots body image from the top down, another set high-definition camera shoots body image from bottom to top and obtains
Human body information is taken, image information obtains module and sends data processing module for collected human body information and face information, counts
Digital-to-analogue block will record the number information for appearing in and occurring in image information acquisition module, and send data processing for number information
Module, image processing module can handle face information, human body information and number information, and will treated face information, human body
Information and number information are sent to image data analysis module and carry out data analysis, and treated for the analysis of image information analysis module
Face information, human body information and number information, and image contrast module is sent by the face information analyzed, human body information
In, comparing is carried out, sends prompting letter sending module for the number information analyzed, prompting message sending module can be sent
Prompting message, the content of prompting message be " asking staff to carry out personnel to dredge ", this prestored in data storage module is
System installs the face information and human body information of permanent personnel, and image contrast module can believe the face information and human body received
Breath carries out modelling and processing and is compared, and in different time to can generate different comparison results, the result of comparison includes
Clearance instruction and alarm command, top control module, which can will let pass to instruct to be converted into alarm command, controls signal from clearance module and police
It is issued in report module.
The counting module that is arranged of the present invention and image information processing module first, can to the number appeared in image into
Row analysis of accounts analyzes the number in preset time period, obtains module when appearing in image information in preset time period
When middle, system can send prompt information to administrative staff by prompting message sending module to prompt administrative staff to carry out the stream of people and dredge
It leads, avoids and be in the presence of that queuing is too long using the region of the system, while image information processing module can be to received people
Body information and face information carry out the analysis of clarity, when the body image letter of discovery shooting is low with face information clarity,
Prompt information can be sent to administrative staff to prompt staff to take the photograph the high definition of acquisition image by prompting message sending module
As head progress cleaning and maintenance, so that the situation hair of video identification can not be fed by effectively reducing the system caused by external factor
It is raw;
Secondly the present invention, can be by the more of acquisition by the image information analysis module and image contrast module of setting
Kind face information and human body information are analyzed, and the safety of Lai Tigao electronic monitoring and control system, image information analysis module can
Pass through formula SCircle 1/SCircle 2=SCircle ratioWith formula (L7*L8)/2=STriangle, available real time contrast's coefficient SCircle ratioWith real time contrast's coefficient
LtThan, while passing through formula STriangle- KSTriangle=KSDifference, available real time contrast's coefficient STriangleWith former coefficient of correlation KSTriangle, will be real-time
Coefficient of correlation SCircle ratio, real time contrast's coefficient STriangleWith real time contrast's coefficient LtThanWith former coefficient of correlation KSCircle ratio、KLtThanAnd KSTriangleCompared
Compared with when the comparison of three's one of which passes through, i.e. expression comparison is by that can let pass, by a variety of way of contrast of setting, no
The accuracy that only ensure that video monitoring verifying also avoids the impassable situation of validation failure and occurs, the monitoring system is allowed to make
The flexibility ratio used is higher, allow the system to it is more preferable be applied in combination with external other systems, allow the system to be more suitable
It promotes the use of.
Above content is only to structure of the invention example and explanation, affiliated those skilled in the art couple
Described specific embodiment does various modifications or additions or is substituted in a similar manner, without departing from invention
Structure or beyond the scope defined by this claim, is within the scope of protection of the invention.
Claims (4)
1. a kind of electronic monitoring and control system based on image recognition, which is characterized in that obtain module, count module including image information
Block, image information processing unit, image information analysis module, prompting message transmission, image contrast module, data storage module,
Top control module, clearance module and alarm modules;
Wherein, the image information obtains module and obtains module for acquiring face information and human body information, the image information
It is made of No.1 high-definition camera, No. two high-definition cameras and No. three high-definition cameras, No.1 high-definition camera is mounted on face
Inlet obtains face image, and No. two high-definition cameras and No. three high-definition cameras are mounted on the two sides of inlet, No. two high definitions
Camera shoots body image from the top down and obtains human body information, and No. three high-definition cameras shoot body image acquisition from bottom to top
Human body information, the image information obtain module and send data processing module for collected human body information and face information;
The counting module from face information for obtaining out number information;
Wherein, the specific acquisition process of number information is as follows:
SS1: number information is the face quantity appeared in face information in the unit time;
SS2: preset time is labeled as TM, TM≤2h;
SS3: the number appeared in image information acquisition module in the TM period is labeled as Rsi, i=1 ... n;
SS3: in the TM period, when TM is greater than preset value, image data processing module handles out the sending of No.1 prompting message;
The image processing module therefrom gets human face characteristic point and human body spy for handling face information and human body information
Point is levied, the image information analysis module gets real time contrast's coefficient for analyzing human face characteristic point and characteristics of human body's image
SCircle ratio、STriangleAnd LtThan;
Its clarity can also be handled when data processing module processing face information and human body information, when continuing to exceed
When preset times can not identify, image data processing module can handle out No. two prompting messages and issue;
The prompting message sending module has prestored system installation ground for sending prompting message in the data storage module
Original Contrast's COEFFICIENT K S of permanent personnelCircle ratio、KLtThanAnd KSTriangle, the image contrast module is for real time contrast's coefficient and original
Beginning coefficient of correlation is compared, and the result compared is sent to top control module;
The specific comparison process of image contrast module is as follows:
(1): passing through formula SCircle ratio- KSCircle ratio=KSDifference, it can obtain real time contrast's coefficient SCircle ratioWith the KS of former coefficient of correlationCircle ratio's
Difference KSDifference;
(2): working as KSDifferenceWhen=0 or | KSDifference| comparison passes through when less than preset value, and top control module is handled out when comparison passes through
Clearance module is arrived in instruction of letting pass;
(3): when | KSDifference| when being greater than preset value, that is, compares and do not pass through, when continuous not number of pass times is more than default in preset time,
Top control module handles out alarm command to alarm modules;
(4): passing through formula STriangle- KSTriangle=KSDifference, available real time contrast's coefficient STriangleWith former coefficient of correlation KSTriangle;
(5): working as KSTriangleWhen=0 or | KSTriangle| comparison passes through when less than preset value, and top control module is handled when comparison passes through
Clearance module is arrived in instruction of letting pass out;
(6): when | KSTriangle| when being greater than preset value, that is, compares and do not pass through, when continuous not number of pass times is more than default in preset time,
Top control module handles out alarm command to alarm modules;
(7): passing through formula LtThan- KLtThan=KLtDifference, it can make real time contrast's coefficient LtThan remoteAnd KLtThanDifference KLtDifference;
(8): working as KLtDifferenceWhen=0 or | KLtDifference| comparison passes through when less than preset value, and top control module is handled when comparison passes through
Clearance module is arrived in instruction of letting pass out;
(9): when | KLtDifference| when being greater than preset value, that is, compares and do not pass through, when continuous not number of pass times is more than default in preset time,
Top control module handles out alarm command to alarm modules;
The top control module is used to convert comparison result to control signal and is sent to clearance module and alarm modules;
The clearance module and alarm modules are installed in gate inhibition's gate.
2. a kind of electronic monitoring and control system based on image recognition according to claim 1, which is characterized in that the face letter
The concrete processing procedure of breath is as follows:
Step 1: after image information obtains module acquisition face information, a clarity can be first extracted from face information most
High photo;
Step 2: scaling it pre-set dimension, and extract human face characteristic point from the photo scaled, human face characteristic point
Specific extraction process is as follows:
I: two tail of the eyes of face are set as human face characteristic point in face image, are marked as K1 point and K2 point;
II: two inner eye corners of the face in face image are set as human face characteristic point, are marked as K3 point and K4 point, K3 point
With the same side of K1 point, K4 and the same side K2;
III: the prenasale in face image is set as human face characteristic point, is marked as P point;
IV: the chin two sides minimum point in face image is set as human face characteristic point, is labeled as X1 point and X2 point;
Step 3: obtaining straight line L1 for K1 point and K3 point line, K2 and K4 point line is obtained straight line L2;
Step 4: being also configured as human face characteristic point for the midpoint of straight line L1, is marked as Z1 point;
Step 5: being also configured as human face characteristic point for the midpoint of straight line L2, is marked as Z2 point;
Step 6: obtaining straight line L3 for P point and Z1 point line, and P point and Z2 point line are obtained straight line L4;
Step 7: obtaining straight line L5 for P point and X1 point line, and P point and X2 point line are obtained straight line L6;
Step 8: obtaining straight line L7 for X1 point and X2 point line, is to be a vertical line L8 with the midpoint of L7, one end of vertical line L8 with
The midpoint of L7 connects, and the other end is connect with P point;
The concrete processing procedure of the human body information is as follows:
S1: extracting the highest photo of clarity from the body image that No. two cameras are shot and be marked as PS1, then
The highest photo PS2 of a clarity is extracted from the body image that No. three cameras are shot;
S2: human body feature point is set by the point of human body in PS1 and ground face contact, is marked as Q1;
S3: human body feature point is set by the highest point of human body shoulder in PS1, is marked as Q2;
S4: by PS2, the point of human body and ground face contact is set as human body feature point, is marked as Q3;
S5: human body feature point is set by the highest point of human body shoulder in PS2, is marked as Q4;
S6: obtaining straight line Lt1 for Q1 and Q2 line, Q3 and Q4 line is obtained straight line Lt2;.
3. a kind of electronic monitoring and control system based on image recognition according to claim 1, which is characterized in that the image number
According to analysis module analysis face information, detailed process is as follows:
Step (1): using L4 as radius, circle is drawn centered on P point and obtains round R1;
Step (2): using L5 as radius, circle is talked about centered on P point and obtains round R2;
Step (3): pass through formula SCircle 1=π * L32The area S of available R1Circle 1;
Step (4): pass through formula SCircle 2=π * L42The area S of available R2Circle 2;
Step (5): pass through formula SCircle 1/SCircle 2=SCircle ratio, the area S of available R1Circle 1With the area S of R2Circle 2Ratio, i.e., in real time
Coefficient of correlation SCircle ratio;
Step (6): straight line L5, straight line L6 and straight line L7 have encircled a city triangle SJ;
Step (7): measuring the length of vertical line L8 and L7, passes through formula (L7*L8)/2=STriangle, it can obtain triangle SJ
Area STriangle, i.e. real time contrast's coefficient STriangle
Detailed process is as follows for the image data analysis module analysis human body information:
Step a: measuring the length of straight line Lt1, then measures the length of straight line Lt2;
Step b: pass through formula Lt1/Lt2=LtThan, the ratio Lt of available straight line Lt1 and straight line Lt2Than.Real time contrast's coefficient
LtThan。
4. a kind of electronic monitoring and control system based on image recognition according to claim 1, which is characterized in that
The content of the No.1 prompting message is " current flow of the people is excessive, and staff is asked to dredge ", No. two promptings
The content of information is " filmed image is unintelligible, and staff is asked to clear up high-definition camera ".
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910423166.7A CN110191317B (en) | 2019-05-21 | 2019-05-21 | Electronic monitoring system based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910423166.7A CN110191317B (en) | 2019-05-21 | 2019-05-21 | Electronic monitoring system based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110191317A true CN110191317A (en) | 2019-08-30 |
CN110191317B CN110191317B (en) | 2020-02-11 |
Family
ID=67717161
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910423166.7A Active CN110191317B (en) | 2019-05-21 | 2019-05-21 | Electronic monitoring system based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110191317B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110492577A (en) * | 2019-09-06 | 2019-11-22 | 马鞍山问鼎网络科技有限公司 | A kind of intelligent charging security protection system based on cloud computing |
CN111091640A (en) * | 2019-12-19 | 2020-05-01 | 深圳市图美电子技术有限公司 | Network storage device capable of authorizing time management control |
CN111508126A (en) * | 2020-03-31 | 2020-08-07 | 苏州科腾软件开发有限公司 | Intelligent security system based on 5G communication |
CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
CN112231670A (en) * | 2020-10-10 | 2021-01-15 | 安徽讯呼信息科技有限公司 | Identity recognition system based on data processing |
CN112562352A (en) * | 2020-12-07 | 2021-03-26 | 合肥诺必达信息技术有限责任公司 | Intelligent monitoring system for parking in residential area |
CN112699752A (en) * | 2020-12-22 | 2021-04-23 | 安徽配隆天环保科技有限公司 | Automatic tracking evidence obtaining system for unmanned aerial vehicle feature marker |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090033622A1 (en) * | 2007-05-30 | 2009-02-05 | 24/8 Llc | Smartscope/smartshelf |
CN101833829A (en) * | 2010-03-12 | 2010-09-15 | 秦小枢 | Teller machine or cash recycling system with image monitoring recognizing analysis system |
CN102955933A (en) * | 2011-08-24 | 2013-03-06 | 苏州飞锐智能科技有限公司 | Household access control method based on face recognition |
US20130071033A1 (en) * | 2011-09-21 | 2013-03-21 | Tandent Vision Science, Inc. | Classifier for use in generating a diffuse image |
CN103325209A (en) * | 2013-07-09 | 2013-09-25 | 綦涛 | Intelligent security alarm system based on wireless |
US20130304683A1 (en) * | 2010-01-19 | 2013-11-14 | James Ting-Ho Lo | Artificial Neural Networks based on a Low-Order Model of Biological Neural Networks |
CN103440475A (en) * | 2013-08-14 | 2013-12-11 | 北京博思廷科技有限公司 | Automatic teller machine user face visibility judging system and method |
US20140247347A1 (en) * | 2013-03-04 | 2014-09-04 | Matthew C. McNeill | Methods and Apparatus for Video Based Process Monitoring and Control |
CN104224204A (en) * | 2013-12-24 | 2014-12-24 | 烟台通用照明有限公司 | Driver fatigue detection system on basis of infrared detection technology |
CN105760832A (en) * | 2016-02-14 | 2016-07-13 | 武汉理工大学 | Escaped prisoner recognition method based on Kinect sensor |
CN106951876A (en) * | 2017-03-27 | 2017-07-14 | 北京品恩科技股份有限公司 | A kind of three-dimensional portrait synthesis recognition system |
-
2019
- 2019-05-21 CN CN201910423166.7A patent/CN110191317B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090033622A1 (en) * | 2007-05-30 | 2009-02-05 | 24/8 Llc | Smartscope/smartshelf |
US20130304683A1 (en) * | 2010-01-19 | 2013-11-14 | James Ting-Ho Lo | Artificial Neural Networks based on a Low-Order Model of Biological Neural Networks |
CN101833829A (en) * | 2010-03-12 | 2010-09-15 | 秦小枢 | Teller machine or cash recycling system with image monitoring recognizing analysis system |
CN102955933A (en) * | 2011-08-24 | 2013-03-06 | 苏州飞锐智能科技有限公司 | Household access control method based on face recognition |
US20130071033A1 (en) * | 2011-09-21 | 2013-03-21 | Tandent Vision Science, Inc. | Classifier for use in generating a diffuse image |
US20140247347A1 (en) * | 2013-03-04 | 2014-09-04 | Matthew C. McNeill | Methods and Apparatus for Video Based Process Monitoring and Control |
CN103325209A (en) * | 2013-07-09 | 2013-09-25 | 綦涛 | Intelligent security alarm system based on wireless |
CN103440475A (en) * | 2013-08-14 | 2013-12-11 | 北京博思廷科技有限公司 | Automatic teller machine user face visibility judging system and method |
CN104224204A (en) * | 2013-12-24 | 2014-12-24 | 烟台通用照明有限公司 | Driver fatigue detection system on basis of infrared detection technology |
CN105760832A (en) * | 2016-02-14 | 2016-07-13 | 武汉理工大学 | Escaped prisoner recognition method based on Kinect sensor |
CN106951876A (en) * | 2017-03-27 | 2017-07-14 | 北京品恩科技股份有限公司 | A kind of three-dimensional portrait synthesis recognition system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110492577A (en) * | 2019-09-06 | 2019-11-22 | 马鞍山问鼎网络科技有限公司 | A kind of intelligent charging security protection system based on cloud computing |
CN111091640A (en) * | 2019-12-19 | 2020-05-01 | 深圳市图美电子技术有限公司 | Network storage device capable of authorizing time management control |
CN111508126A (en) * | 2020-03-31 | 2020-08-07 | 苏州科腾软件开发有限公司 | Intelligent security system based on 5G communication |
CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
CN112231670A (en) * | 2020-10-10 | 2021-01-15 | 安徽讯呼信息科技有限公司 | Identity recognition system based on data processing |
CN112562352A (en) * | 2020-12-07 | 2021-03-26 | 合肥诺必达信息技术有限责任公司 | Intelligent monitoring system for parking in residential area |
CN112699752A (en) * | 2020-12-22 | 2021-04-23 | 安徽配隆天环保科技有限公司 | Automatic tracking evidence obtaining system for unmanned aerial vehicle feature marker |
Also Published As
Publication number | Publication date |
---|---|
CN110191317B (en) | 2020-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110191317A (en) | A kind of electronic monitoring and control system based on image recognition | |
CN110084196B (en) | Monitoring video identification system for cloud computing | |
CN107665419A (en) | The labor service real-name management system of national grid wisdom building site control platform | |
CN107271011A (en) | A kind of truck scale intelligent measuring system | |
CN211509189U (en) | Electric power operation field supervision equipment and system | |
CN109903411A (en) | A kind of meeting signature device and application method based on recognition of face | |
CN109815899A (en) | Safety defense monitoring system based on recognition of face | |
CN106355724A (en) | Intelligent entrance guard lock system based on remote control | |
CN110390784A (en) | A kind of transmission line of electricity external force damage prevention monitoring system based on deep learning | |
CN109035537A (en) | A kind of intelligent visitor system based on testimony of a witness unification | |
CN209149389U (en) | The quick checking device of recognition of face pass gates | |
CN107024903A (en) | The method and system that a kind of ship lockage video detection is checked | |
CN102724394A (en) | Surveillance camera for examination halls | |
CN112528952B (en) | Working state intelligent recognition system for electric power business hall personnel | |
CN208126452U (en) | A kind of building site Work attendance device | |
CN207946826U (en) | A kind of system of registering based on dynamic human face identification | |
CN110177254A (en) | A kind of wisdom building site system for managing video and its control method | |
CN206584433U (en) | A kind of intelligent management gate control system | |
CN110445763A (en) | A kind of light current intelligent monitor system with safety | |
CN211604188U (en) | A KVM device for scenic spot visitor flow control and management | |
CN109376635B (en) | A kind of nursing quality checking system and security incident report method | |
CN208805847U (en) | A kind of staff attendance grasp shoot device based on recognition of face | |
CN208335271U (en) | A kind of monitoring system of the class efficacy information based on students ' behavior data | |
CN109587449B (en) | Remote court trial method | |
CN214410117U (en) | Monitoring device for gate main body |
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 |