CN115565214A - Regional alarm supervisory systems based on block chain - Google Patents
Regional alarm supervisory systems based on block chain Download PDFInfo
- Publication number
- CN115565214A CN115565214A CN202210658435.XA CN202210658435A CN115565214A CN 115565214 A CN115565214 A CN 115565214A CN 202210658435 A CN202210658435 A CN 202210658435A CN 115565214 A CN115565214 A CN 115565214A
- Authority
- CN
- China
- Prior art keywords
- image
- radio frequency
- frequency signal
- module
- alarm
- 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.)
- Pending
Links
- 239000013598 vector Substances 0.000 claims description 70
- 238000012545 processing Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 14
- 210000000697 sensory organ Anatomy 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 8
- 230000001815 facial effect Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 210000003128 head Anatomy 0.000 description 60
- 239000003086 colorant Substances 0.000 description 10
- 208000007256 Nevus Diseases 0.000 description 8
- 206010027145 Melanocytic naevus Diseases 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 4
- NOQGZXFMHARMLW-UHFFFAOYSA-N Daminozide Chemical compound CN(C)NC(=O)CCC(O)=O NOQGZXFMHARMLW-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a block chain-based regional alarm supervision system, which comprises: the system comprises a radio frequency signal receiving module, an image acquisition module, a face recognition module and an alarm module, wherein the radio frequency signal receiving module receives signals transmitted by a radio frequency transmitter in a personnel identity card in a designated area through a radio frequency signal receiver and recognizes the information of personnel bound by the radio frequency signals; the image acquisition module acquires image information of personnel in the designated area through the high-definition camera; and the alarm module is used for carrying out graded alarm on each area according to the specified rule according to whether the violation condition occurs in the area. According to the invention, the identity of the person is confirmed by two modes of receiving the radio frequency signal and identifying the face of the person, the identification effect is better, the identity of the person can be accurately locked, a grading alarm mode is adopted according to different violation conditions, the alarm source can be quickly locked, and the reasonable distribution of security personnel is realized.
Description
Technical Field
The invention relates to the technical field of safe region alarm, in particular to a regional alarm monitoring system based on a block chain.
Background
The radio frequency identification technology is a non-contact automatic identification technology, automatically identifies a target object and obtains related data through radio frequency signals, does not need manual intervention in identification work, and can work in various severe environments.
Meanwhile, with the development of society, the requirements of factory owners on safety are higher and higher, in order to prevent foreign people from entering a factory area to steal secret and to monitor whether their employees are illegal and careless, generally, the factory owners can hire the personnel to monitor pictures of various areas of the factory area through a camera, but the attention focusing time of the personnel is limited, and the monitoring effect is not good.
In view of the above situation, a need exists for a block chain-based regional alarm supervision system and method, which confirm the identity of a person by receiving a radio frequency signal and performing face recognition on the person, wherein the face recognition is recognized from multi-factor comprehensive consideration, the recognition effect is better, the precision is higher, meanwhile, the identity of the person can be quickly and accurately locked by adding dual check of the radio frequency signal, a graded alarm mode is adopted according to different violation conditions, the alarm source can be quickly locked, and reasonable distribution of security personnel is realized according to different grades.
Disclosure of Invention
The present invention provides a block chain-based area alarm monitoring system and method, so as to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: a zone alarm surveillance system based on blockchains, comprising: a radio frequency signal receiving module, an image acquisition module, a face recognition module and an alarm module,
the radio frequency signal receiving module receives a signal transmitted by a radio frequency transmitter in the personnel identity card in the designated area through a radio frequency signal receiver and identifies the employee information bound by the radio frequency signal;
the image acquisition module acquires image information of personnel in a designated area through a high-definition camera;
the face recognition module is used for carrying out gray level processing on the image transmitted by the image acquisition module, screening out the head outline of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of a mole and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the face information of the person transmitted by the radio frequency signal receiving module or the face information of all the staff in the factory;
the alarm module is used for carrying out graded alarm on each area according to the specified rule according to whether the violation condition occurs in the area or not;
in the same area, the employee information identified by the radio frequency signal receiving module and the image information acquired by the image acquisition module are jointly transmitted to the face identification module.
The invention realizes the function of area alarm through the cooperation of all modules, the radio frequency signal receiving module identifies the employee information bound by the radio frequency signal through the acquired radio frequency signal, the image acquisition module mainly acquires the pictures shot in the area through the camera, the face recognition module mainly processes the pictures acquired by the camera so as to judge the identity of the personnel appearing in the pictures, and the alarm module judges whether to alarm or how to alarm according to the results of the radio frequency signal receiving module and the face recognition module.
A regional alarm supervision method based on a block chain comprises the following specific steps:
s1, in a radio frequency signal receiving module, receiving a signal transmitted by a radio frequency transmitter in a personnel identity card in a designated area through a radio frequency signal receiver, and identifying staff information bound by the radio frequency signal;
s2, in the image acquisition module, acquiring image information of personnel in the designated area through a high-definition camera;
s3, in the same area, the employee information identified by the radio frequency signal receiving module and the image information collected by the image collecting module are jointly transmitted to the face identification module;
s4, in the face recognition module, carrying out gray level processing on the image transmitted by the image acquisition module, screening out the outline of the head of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of moles and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the position with the face information of the staff transmitted by the radio frequency signal receiving module or the face information of all staff in the factory,
the face information of the staff transmitted by the radio frequency signal receiving module and the face information of all staff in the factory are comparison images;
and S5, in the alarm module, carrying out graded alarm on each area according to the specified rule according to whether the violation condition occurs in the area.
Further, the radio frequency signal includes a name, a number, and a factory area of the corresponding identification card, and the radio frequency signal receiving module retrieves a face image of a person belonging to the corresponding number in a factory area person database according to the number of the corresponding identification card in the radio frequency signal.
According to the invention, each radio frequency signal is bound with the personal information of one employee, and the personal information of the corresponding employee can be obtained by identifying the radio frequency signal.
Further, after the face recognition module extracts a head image of the original image, feature points of five sense organs in the head image are extracted, a straight line where a nose tip and a chin are located serves as a y-axis, a straight line which passes through the nose tip and is perpendicular to the y-axis serves as an x-axis, the nose tip serves as an origin to establish a plane rectangular coordinate system, the nose tip in the comparison image is overlapped with the origin in the same coordinate system, and the comparison file is scaled in an equal proportion mode until the point where the chin is located in the comparison image is overlapped with the chin of the head image in the original image.
The face recognition module of the invention establishes the same plane rectangular coordinate system by scaling the head image and the comparison image in equal proportion, and then uses the same standard to carry out datamation on the head image and the comparison image, thereby facilitating the subsequent data processing.
Further, in the rectangular plane coordinate system, every two feature points in the head image are connected to form a vector, and the vectors are numbered according to a specified sequence; connecting every two feature points in the comparison image to form vectors, numbering the vectors according to the specified sequence to make every vector in the head image correspond to every vector in the comparison image one by one,
respectively calculating the module length of two corresponding vectors in the head image and the comparison image, then subtracting the module length of the vector in the comparison image from the module length of the vector in the head image, and then multiplying the sine value of the included angle of the two vectors by the obtained module length difference value to obtain the error value of a group of vectors, namely:
when the modulo length of the vector in the head image is | a |, the modulo length of the corresponding vector in the comparison image is | b |, and the included angle between the two vectors is β, then the error value c = (| a | - | b |) × sin β of the set of vectors,
and respectively solving errors of all vectors in the head image and corresponding vectors in the comparison image, and finally summing all the errors to obtain the error d of the five sense organs.
In the invention, the characteristic points are connected in pairs according to a specified rule to form vectors, and the error between the two corresponding vectors is further confirmed by the difference of the modular lengths of the two corresponding vectors and the included angle between the two vectors, so that the error d of the five sense organs can be further solved by using the method.
Further, the head image and the comparison image are respectively processed in the plane rectangular coordinate system, the distance e between the vertex and the chin is calculated to be (0, f) at a certain position on the y axis, the distance between the position and the chin is three fifths of the distance e,
the y-axis coordinate of the lip peak in the coordinate system is g, the x-axis coordinate of the left alar is h1, the x-axis coordinate of the right alar is h2,
the intersection area of the straight line y = f, y = g, x = h1 and the four lines of the head contour is the left face range,
the intersection area of the straight line y = f, y = g, x = h2 and the four lines of the head contour is the right face range.
The invention firstly calculates the straight line for limiting the face area, divides the specific face area through the intersection area of the four straight lines, selects a certain position coordinate as (0, f), and makes the distance between the position and the chin three fifths of e, because the straight line y = f where the point with the distance from the chin three fifths of e is just under the eyes and belongs to the edge of the face area.
Furthermore, the left face range and the right face range are divided into n regions respectively, all the regions in the left face and the right face are numbered, extreme values of three primary colors R, G and B in pixel points of each numbered region are respectively obtained, namely, the maximum value and the minimum value of R, the maximum value and the minimum value of G and the maximum value and the minimum value of B in all the pixel points of each numbered region are obtained, the sum of the maximum values of the numbered regions R, G and B is subtracted by the sum of the minimum values of the numbered regions R, G and B, the obtained difference value k is compared with a first threshold value,
if the difference k is smaller than the first threshold, the numbering area is not continuously processed;
if the difference k is more than or equal to the first threshold, the numbering area is further processed, the average values of three primary colors R, G and B in each pixel point of the numbering area are respectively obtained, then the difference values of the average value corresponding to each pixel point and the average values corresponding to the surrounding pixel points are respectively calculated, then the difference values are compared with a second threshold,
when the difference value is not larger than or equal to the second threshold value, the pixel point is not processed continuously,
and when the difference value is larger than or equal to the second threshold value, marking the pixel point, and acquiring the coordinate of the pixel point in the plane rectangular coordinate system.
According to the invention, the extreme values of the three primary colors R, G and B in the pixel points of each numbering region are obtained, and the maximum value minus the minimum value of the extreme value of each numbering region is compared with the first threshold value, so that the rapid screening of the numbering regions to be processed is realized, the mode can reduce the burden of data processing, and the workload of the data processing to be performed is reduced; the average value of the three primary colors of each pixel point in the area is obtained, the difference value between adjacent pixel points can be accurately compared, and the difference value is compared with the second threshold value, so that the special pixel points can be screened out.
Further, respectively obtaining the coordinates of the marked pixel points in each numbered region in the head image and the comparison image, then carrying out nonlinear fitting on the coordinates of the marked pixel points in each numbered region, then comparing the obtained nonlinear relation with a prefabricated nevus nonlinear model,
if the obtained nonlinear relation is the same as the type of the nonlinear model of the prefabricated mole, judging that the midpoint coordinate of the obtained nonlinear relation is the coordinate of the mole;
if the obtained nonlinear relation is different from the type of the nonlinear model of the prefabricated nevus, the data processing is not continuously carried out on the numbered area;
the coordinates of each mole in the head image and the coordinates of a mole closest to the mole in the contrast image are respectively selected, the distance between the two moles is calculated to be the error of the two moles, and finally the errors of all moles are summed.
The method carries out nonlinear fitting on special pixel points in a coordinate system, compares the special pixel points with a nonlinear model of a prefabricated mole, determines the coordinates of the mole if the types of the mole are the same, further calculates the error of the corresponding mole, and further screens and identifies the detail characteristic points of the face.
Further, the error d of five sense organs is added with the sum of the errors of all nevi to obtain the total error of the head image and the contrast image, the total error is compared with a third threshold value,
if the total error is larger than or equal to a third threshold value, judging that the head image does not accord with the contrast image;
and if the total error is smaller than the third threshold value, judging that the head image is consistent with the comparison image.
In the face recognition module, the errors of the five sense organs and the errors of all nevus are accumulated to obtain the total error of the head image and the whole contrast image, and further judge whether the two images are consistent.
Further, in the classification alarm, the alarm is set to alarm,
if the radio frequency signal receiving module receives the radio frequency signal and the face recognition module confirms that the person is a person in the factory, the situation is normal and no alarm is given;
if the radio-frequency signal is not received by the radio-frequency signal receiving module but the face identification module confirms that the personnel in the factory are identified, the situation is special, and an alarm needs to be given to an in-field area corresponding to the personnel to remind the personnel of the default;
if the face recognition module determines that the personnel is not the personnel in the plant, the situation is special, all areas in the plant need to be alarmed, the plant area where the personnel corresponding to the radio frequency signal are located is taken as the center, the alarm level is highest, and the alarm level is lower in the areas far away from the center.
In the hierarchical alarm, the judgment is carried out according to the receiving condition of the radio frequency signal and the identification result of the face identification module, and when the abnormal condition occurs, different alarm schemes are provided according to different abnormal conditions.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the identity of the personnel is confirmed by two modes of receiving the radio frequency signal and identifying the face of the personnel, the face identification is identified by comprehensive consideration of multiple factors, the identification effect is better, the precision is higher, meanwhile, the identity of the personnel can be quickly and accurately locked by double check of the radio frequency signal, a graded alarm mode is adopted according to different violation conditions, the alarm source can be quickly locked, and the reasonable distribution of security personnel is realized according to different grades.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a block chain-based regional alarm monitoring system according to the present invention;
FIG. 2 is a schematic flow chart of a radio frequency signal receiving module of a block chain-based area alarm monitoring system according to the present invention;
FIG. 3 is a schematic flow chart of a face recognition module of the regional alarm monitoring system based on the block chain according to the present invention;
FIG. 4 is a schematic flow chart of a hierarchical alarm of the regional alarm monitoring system based on the blockchain according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1-4, the present invention provides the following technical solutions: a blockchain-based area alarm surveillance system, comprising: a radio frequency signal receiving module, an image acquisition module, a face recognition module and an alarm module,
the radio frequency signal receiving module receives a signal transmitted by a radio frequency transmitter in the personnel identity card in the designated area through a radio frequency signal receiver and identifies the employee information bound by the radio frequency signal;
the image acquisition module acquires image information of personnel in the designated area through the high-definition camera;
the face recognition module is used for carrying out gray level processing on the image transmitted by the image acquisition module, screening out the head outline of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of a mole and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the face information of the person transmitted by the radio frequency signal receiving module or the face information of all the staff in the factory;
the alarm module is used for carrying out graded alarm on each area according to an appointed rule according to whether the violation condition occurs in the area;
in the same area, the employee information identified by the radio frequency signal receiving module and the image information acquired by the image acquisition module are jointly transmitted to the face identification module.
The invention realizes the function of area alarm through the cooperation of all modules, the radio frequency signal receiving module identifies the employee information bound by the radio frequency signal through the acquired radio frequency signal, the image acquisition module mainly acquires the pictures shot in the area through the camera, the face recognition module mainly processes the pictures acquired by the camera so as to judge the identity of the personnel appearing in the pictures, and the alarm module judges whether to alarm or how to alarm according to the results of the radio frequency signal receiving module and the face recognition module.
A block chain-based area alarm supervision system and method specifically comprises the following steps:
s1, in a radio frequency signal receiving module, receiving a signal transmitted by a radio frequency transmitter in a personnel identity card in a designated area through a radio frequency signal receiver, and identifying staff information bound by the radio frequency signal;
s2, in the image acquisition module, acquiring image information of personnel in a designated area through a high-definition camera;
s3, in the same area, the employee information identified by the radio frequency signal receiving module and the image information collected by the image collecting module are jointly transmitted to the face identification module;
s4, in the face recognition module, carrying out gray level processing on the image transmitted by the image acquisition module, screening out the outline of the head of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of moles and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the position with the face information of the staff transmitted by the radio frequency signal receiving module or the face information of all staff in the factory,
the face information of the staff transmitted by the radio frequency signal receiving module and the face information of all staff in the factory are comparison images;
and S5, in the alarm module, carrying out graded alarm on each area according to the specified rule according to whether the violation condition occurs in the area.
The radio frequency signal comprises the name, the number and the belonging factory of the corresponding identity card, and the radio frequency signal receiving module calls the face image of the person belonging to the corresponding number in the factory personnel database according to the number of the corresponding identity card in the radio frequency signal.
According to the invention, each radio frequency signal is bound with the personal information of one employee, and the personal information of the corresponding employee can be obtained by identifying the radio frequency signal.
In this embodiment, if the name of the identity card bound to a certain radio frequency signal is liu san, the serial number is 000001, and the factory area to which the identity card belongs is the sixth factory area, the radio frequency signal receiving module may call the face image of the person to which the serial number 000001 belongs in the sixth factory area person database, that is, the face image of liu san.
After the face recognition module extracts a head image of the original image, feature points of five sense organs in the head image are extracted, a straight line where a nose tip and a chin are located serves as a y axis, a straight line which passes through the nose tip and is perpendicular to the y axis serves as an x axis, a plane rectangular coordinate system is established by taking the nose tip as an original point, the nose tip in a comparison image is overlapped with the original point in the same coordinate system, and a comparison file is scaled in an equal proportion mode until the point where the chin is located in the comparison image is overlapped with the chin of the head image in the original image.
The face recognition module of the invention establishes the same plane rectangular coordinate system by scaling the head image and the comparison image in equal proportion, and then uses the same standard to carry out datamation on the head image and the comparison image, thereby facilitating the subsequent data processing.
In the plane rectangular coordinate system, every two feature points in the head image are connected to form a vector, and the vectors are numbered according to a specified sequence; connecting every two feature points in the comparison image to form vectors, numbering the vectors according to the specified sequence to make every vector in the head image correspond to every vector in the comparison image one by one,
respectively calculating the module length of two corresponding vectors in the head image and the comparison image, then subtracting the module length of the vector in the comparison image from the module length of the vector in the head image, and then multiplying the sine value of the included angle of the two vectors by the obtained module length difference value to obtain the error value of a group of vectors, namely:
when the modulo length of the vector in the head image is | a |, the modulo length of the corresponding vector in the comparison image is | b |, and the included angle between the two vectors is β, then the error value c = (| a | - | b |) × sin β of the set of vectors,
and respectively solving errors of all vectors in the head image and corresponding vectors in the comparison image, and finally summing all the errors to obtain the error d of the five sense organs.
In the invention, two characteristic points are connected in pairs according to a specified rule to form a vector, and through the difference of the module lengths of two corresponding vectors and the included angle between the two vectors, in the prior art, when the two vectors are compared, the module length of one vector is multiplied by the cosine value of the included angle of the two vectors to be compared with the module length of the other vector.
If the vector a1 exists in the head image of this embodiment, the modulo length of the vector a1 is 10, the vector b1 corresponding to the vector a1 exists in the comparison image, the modulo length of the vector b1 is 8, and the included angle between the vector a1 and the vector b1 is 30 degrees, then:
the error value c1= (10-8) × sin30 ° =1 for the set of vectors.
The head image and the comparison image are respectively processed in the plane rectangular coordinate system, the distance e between the vertex of the head and the chin is calculated, the coordinate of a certain position on the y axis is (0, f), the distance between the position and the chin is three fifths of the distance e,
the y-axis coordinate of the lip peak in the coordinate system is g, the x-axis coordinate of the left nasal ala is h1, the x-axis coordinate of the right nasal ala is h2,
the intersection area of the straight line y = f, y = g, x = h1 and the four lines of the head contour is the left face range,
the intersection area of the straight line y = f, y = g, x = h2 and the four lines of the head contour is the right face range.
The invention firstly calculates the straight line for limiting the face area, divides the specific face area through the intersection area of the four straight lines, selects a certain position coordinate as (0, f), and makes the distance between the position and the chin three fifths of e, because the straight line y = f where the point with the distance from the chin three fifths of e is just under the eyes and belongs to the edge of the face area.
In this embodiment, if f =4,g = -2, h1= -1, and h2=1, then:
the intersection area of the straight line y =4,y = -2,x = -1 and the four lines of the head contour is the left face range,
the intersection area of the straight line y =4,y = -2,x = -1 and the four lines of the head contour is the right face range.
The left face range and the right face range are respectively divided into n areas, all the areas in the left face and the right face are numbered, the extreme values of three primary colors R, G and B in pixel points of each numbered area are respectively obtained, namely the maximum value and the minimum value of R, the maximum value and the minimum value of G and the maximum value and the minimum value of B in all the pixel points of each numbered area are obtained, the sum of the maximum values of R, G and B of the numbered areas is subtracted by the sum of the minimum values of R, G and B of the numbered areas, and the obtained difference value k is compared with a first threshold value,
if the difference k is smaller than the first threshold, the numbering area is not continuously processed;
if the difference k is more than or equal to the first threshold, the numbering area is further processed, the average values of three primary colors R, G and B in each pixel point of the numbering area are respectively obtained, then the difference values of the average value corresponding to each pixel point and the average values corresponding to the surrounding pixel points are respectively calculated, then the difference values are compared with a second threshold,
when the difference value is not larger than or equal to the second threshold value, the pixel point is not processed continuously,
and when the difference value is larger than or equal to the second threshold value, marking the pixel point and acquiring the coordinate of the pixel point in the plane rectangular coordinate system.
According to the invention, the extreme values of three primary colors R, G and B in the pixel points of each numbering region are obtained, and the maximum value minus the minimum value of the extreme value of each numbering region is compared with the first threshold value, so that the rapid screening of the numbering regions to be processed is realized, the mode can reduce the burden of data processing, and the workload of data processing to be performed is reduced; the average value of the three primary colors of each pixel point in the area is obtained, the difference value between adjacent pixel points can be accurately compared, the difference value is compared with the second threshold value, and the special pixel points can be screened out.
In this embodiment, if the maximum value and the minimum value of the three primary colors R in the first region pixel point are 252 and 80 respectively, the maximum value and the minimum value of G are 230 and 87 respectively, and the maximum value and the minimum value of B are 245 and 82 respectively; the maximum and minimum values of the three primary colors R in the pixels of the second region are 255 and 240, respectively, the maximum and minimum values of G are 230 and 225, respectively, the maximum and minimum values of B are 235 and 230, respectively, the first threshold is 200,
subtracting the sum of the minimum values of the numbered regions R, G, B from the sum of the maximum values of the first regions R, G, B to obtain:
252+230+245-80-87-82＝478，
subtracting the sum of the minimum values of the numbered regions R, G, B from the sum of the maximum values of the second regions R, G, B to obtain:
255+230+235-240-225-230＝25；
if 478>200, 200>25, then the second region is not continued to be processed and further processing of the first region needs to be continued.
Respectively obtaining the coordinates of the marked pixel points in each numbered region in the head image and the comparison image, then carrying out nonlinear fitting on the coordinates of the marked pixel points in each numbered region, then comparing the obtained nonlinear relation with a prefabricated nevus nonlinear model,
if the obtained nonlinear relation is the same as the type of the nonlinear model of the prefabricated mole, determining that the midpoint coordinate of the obtained nonlinear relation is the coordinate of the mole;
if the obtained nonlinear relation is different from the type of the nonlinear model of the prefabricated nevus, the data processing is not continuously carried out on the numbered area;
the coordinates of each mole in the head image and the coordinates of a mole closest to the mole in the contrast image are respectively selected, the distance between the two moles is calculated to be the error of the two moles, and finally the errors of all moles are summed.
The method carries out nonlinear fitting on special pixel points in a coordinate system, compares the special pixel points with a nonlinear model of a prefabricated mole, determines the coordinates of the mole if the types of the mole are the same, further calculates the error of the corresponding mole, and further screens and identifies the detail characteristic points of the face.
In this example, the result of the nonlinear fitting is (x-2.1) 2 +(y-1) 2 =0.01, non-linear model of mole prefabricated (x-k 1) 2 +(y-k2) 2 K1, k2 and k3 are all constants, so that the obtained nonlinear relation (x-2.1) can be judged 2 +(y-1) 2 The midpoint coordinate of =0.01 is the coordinate of a mole (2.1,1).
Adding the error d of five sense organs and the sum of the errors of all nevus to obtain the total error of the head image and the contrast image, comparing the total error with a third threshold value,
if the total error is larger than or equal to a third threshold value, judging that the head image does not accord with the contrast image;
and if the total error is smaller than the third threshold value, judging that the head image is consistent with the comparison image.
In the face recognition module, the errors of the five sense organs and the errors of all nevus are accumulated to obtain the total error of the head image and the whole contrast image, and further judge whether the two images are consistent.
In the case of the classification alarm, the alarm is set,
if the radio frequency signal receiving module receives the radio frequency signal and the face recognition module confirms that the person is a person in the factory, the condition is normal and no alarm is given;
if the radio-frequency signal is not received by the radio-frequency signal receiving module but the face identification module confirms that the personnel in the factory are identified, the situation is special, and an alarm needs to be given to an in-field area corresponding to the personnel to remind the personnel of the default;
if the face recognition module determines that the personnel is not the personnel in the factory, the situation is special, all areas in the factory need to be alarmed, the factory area where the personnel corresponding to the radio frequency signal is located is taken as the center, the alarm level is highest, and the alarm level is lower in the areas which are farther away from the center.
In the hierarchical alarm, the judgment is carried out according to the receiving condition of the radio frequency signal and the identification result of the face identification module, and when the abnormal condition occurs, different alarm schemes are provided for different abnormal conditions.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A regional alarm supervisory system based on block chains, comprising: a radio frequency signal receiving module, an image acquisition module, a face recognition module and an alarm module,
the radio frequency signal receiving module receives a signal transmitted by a radio frequency transmitter in the personnel identity card in the designated area through a radio frequency signal receiver and identifies the employee information bound by the radio frequency signal;
the image acquisition module acquires image information of personnel in a designated area through a high-definition camera;
the face recognition module is used for carrying out gray level processing on the image transmitted by the image acquisition module, screening out the head outline of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of a mole and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the face information of the person transmitted by the radio frequency signal receiving module or the face information of all the staff in the factory;
the alarm module is used for carrying out graded alarm on each area according to an appointed rule according to whether the violation condition occurs in the area;
in the same area, the employee information identified by the radio frequency signal receiving module and the image information acquired by the image acquisition module are jointly transmitted to the face identification module;
the method comprises the following specific steps:
s1, in a radio frequency signal receiving module, receiving a signal transmitted by a radio frequency transmitter in a personnel identity card in a designated area through a radio frequency signal receiver, and identifying staff information bound by the radio frequency signal;
s2, in the image acquisition module, acquiring image information of personnel in the designated area through a high-definition camera;
s3, in the same area, the employee information identified by the radio frequency signal receiving module and the image information collected by the image collecting module are jointly transmitted to the face identification module;
s4, in the face recognition module, carrying out gray level processing on the image transmitted by the image acquisition module, screening out the outline of the head of a person through the gray level difference between the head and the background, further extracting the head image of the original image, then extracting the position of moles and each facial feature point in the head image through face recognition, and further confirming the identity of the person through comparing the position with the face information of the staff transmitted by the radio frequency signal receiving module or the face information of all staff in the factory,
the face information of the staff transmitted by the radio frequency signal receiving module and the face information of all staff in the factory are comparison images;
s5, in the alarm module, according to whether violation conditions occur in the areas, the areas are subjected to graded alarm according to specified rules;
the radio frequency signal comprises a name, a number and a factory area of the corresponding identity card, and the radio frequency signal receiving module calls a face image of a person belonging to the corresponding number in a factory area person database according to the number of the corresponding identity card in the radio frequency signal;
after the face recognition module extracts a head image of the original image, extracting feature points of five sense organs in the head image, taking a straight line where a nose tip and a chin are located as a y axis, taking a straight line which passes through the nose tip and is vertical to the y axis as an x axis, taking the nose tip as an original point to establish a plane rectangular coordinate system, overlapping the nose tip in a comparison image with the original point in the same coordinate system, and scaling a comparison file in equal proportion until the point where the chin is located in the comparison image is overlapped with the chin of the head image in the original image;
in the plane rectangular coordinate system, every two feature points in the head image are connected to form a vector, and the vectors are numbered according to a specified sequence; connecting every two feature points in the comparison image to form vectors, numbering the vectors according to the specified sequence to make every vector in the head image correspond to every vector in the comparison image one by one,
respectively calculating the module length of two corresponding vectors in the head image and the comparison image, then subtracting the module length of the vector in the comparison image from the module length of the vector in the head image, and then multiplying the sine value of the included angle of the two vectors by the obtained module length difference value to obtain the error value of a group of vectors, namely:
when the modulo length of the vector in the head image is | a |, the modulo length of the corresponding vector in the comparison image is | b |, and the included angle between the two vectors is β, then the error value c = (| a | - | b |) × sin β of the set of vectors,
respectively solving errors of all vectors in the head image and corresponding vectors in the comparison image, and finally summing all the errors to obtain the error d of the five sense organs;
in the case of the classification alarm, the alarm is set,
if the radio frequency signal receiving module receives the radio frequency signal and the face recognition module confirms that the person is a person in the factory, the situation is normal and no alarm is given;
if the radio-frequency signal is not received by the radio-frequency signal receiving module but the face identification module confirms that the personnel in the factory are identified, the situation is special, and an alarm needs to be given to an in-field area corresponding to the personnel to remind the personnel of the default;
if the face recognition module determines that the personnel is not the personnel in the factory, the situation is special, all areas in the factory need to be alarmed, the factory area where the personnel corresponding to the radio frequency signal is located is taken as the center, the alarm level is highest, and the alarm level is lower in the areas which are farther away from the center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210658435.XA CN115565214A (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervisory systems based on block chain |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210658435.XA CN115565214A (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervisory systems based on block chain |
| CN202110393963.2A CN113111780B (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervision system and method based on block chain |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110393963.2A Division CN113111780B (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervision system and method based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115565214A true CN115565214A (en) | 2023-01-03 |
Family
ID=76716334
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210658435.XA Pending CN115565214A (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervisory systems based on block chain |
| CN202110393963.2A Active CN113111780B (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervision system and method based on block chain |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110393963.2A Active CN113111780B (en) | 2021-04-13 | 2021-04-13 | Regional alarm supervision system and method based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN115565214A (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639191A (en) * | 2022-04-22 | 2022-06-17 | 三峡新能源海上风电运维江苏有限公司 | Control method of intelligent lock applied to offshore wind farm |
| CN115223100A (en) * | 2022-08-02 | 2022-10-21 | 上海三力信息科技有限公司 | Intelligent park abnormal person identification method, system, equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542299B (en) * | 2011-12-07 | 2015-03-25 | 惠州Tcl移动通信有限公司 | Face recognition method, device and mobile terminal capable of recognizing face |
| CN103268484A (en) * | 2013-06-06 | 2013-08-28 | 温州大学 | Design method of classifier for high-precision face recognitio |
| CN104850838B (en) * | 2015-05-19 | 2017-12-08 | 电子科技大学 | Three-dimensional face identification method based on expression invariant region |
| CN106303438A (en) * | 2016-08-26 | 2017-01-04 | 无锡卓信信息科技股份有限公司 | A kind of indoor video monitoring system for Prison staff |
| CN109186584B (en) * | 2018-07-18 | 2020-09-29 | 浙江臻万科技有限公司 | Indoor positioning method and positioning system based on face recognition |
| CN111091641A (en) * | 2018-10-24 | 2020-05-01 | 大连永航科技有限公司 | Ship security system based on face recognition |
| CN110189447B (en) * | 2019-05-31 | 2022-03-22 | 安徽无界万禾传媒科技有限公司 | Intelligent community gate control system based on face identity recognition |
| CN110262428A (en) * | 2019-06-29 | 2019-09-20 | 南京奥灵克物联网科技有限公司 | A kind of remote supervisory device of the industrial plant based on RFID |
| CN111724029A (en) * | 2020-05-08 | 2020-09-29 | 上海市公安局出入境管理局 | Workshop staff violation confirmation method and device and computer equipment |
| CN111598766B (en) * | 2020-05-09 | 2023-05-02 | 绍兴聚量数据技术有限公司 | Encryption domain three-dimensional model reversible information hiding method based on prediction error expansion |
-
2021
- 2021-04-13 CN CN202210658435.XA patent/CN115565214A/en active Pending
- 2021-04-13 CN CN202110393963.2A patent/CN113111780B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111780A (en) | 2021-07-13 |
| CN113111780B (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113111780B (en) | Regional alarm supervision system and method based on block chain | |
| US7149325B2 (en) | Cooperative camera network | |
| CN106548147B (en) | A kind of quick noise robustness image foreign matter detection method and TEDS system | |
| WO2020057159A1 (en) | Video analysis system and method for food processing violation behavior in university restaurant | |
| CN110650316A (en) | Intelligent patrol and early warning processing method and device, electronic equipment and storage medium | |
| CN110008831A (en) | A kind of Intellectualized monitoring emerging system based on computer vision analysis | |
| CN111898486B (en) | Monitoring picture abnormality detection method, device and storage medium | |
| CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
| CN109460719A (en) | A kind of electric operating safety recognizing method | |
| CN116416579B (en) | Intelligent analysis management system for park security monitoring storage information | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN113343854A (en) | Fire operation flow compliance detection method based on video monitoring | |
| CN115171361B (en) | Dangerous behavior intelligent detection and early warning method based on computer vision | |
| CN118196068A (en) | Textile printing and dyeing quality monitoring system based on artificial intelligence | |
| CN112101260A (en) | Method, device, equipment and storage medium for identifying safety belt of operator | |
| CN110969202A (en) | Portrait collection environment verification method and system based on color component and perceptual hash algorithm | |
| CN113808087A (en) | Defect management and control method and device for surface of steel plate and computer readable storage medium | |
| CN115861940A (en) | Working scene behavior evaluation method and system based on human body tracking and recognition technology | |
| CN115147939A (en) | Data distribution management system and method in large-scale scene | |
| CN113111771A (en) | Method for identifying unsafe behaviors of power plant workers | |
| CN106650735B (en) | A kind of LED character automatic positioning recognition methods | |
| CN110446025B (en) | Camera module detection system and method applied to electronic equipment | |
| CN114387542A (en) | Video acquisition unit abnormity identification system based on portable ball arrangement and control | |
| CN113408338A (en) | Method, device and system for monitoring abnormal behavior of miner |
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 |