CN117315591A - Intelligent campus safety monitoring prediction management system - Google Patents
Intelligent campus safety monitoring prediction management system Download PDFInfo
- Publication number
- CN117315591A CN117315591A CN202311499242.5A CN202311499242A CN117315591A CN 117315591 A CN117315591 A CN 117315591A CN 202311499242 A CN202311499242 A CN 202311499242A CN 117315591 A CN117315591 A CN 117315591A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- image
- image information
- leaving
- conditions
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 230000002159 abnormal effect Effects 0.000 claims abstract description 105
- 230000005856 abnormality Effects 0.000 claims abstract description 68
- 238000012937 correction Methods 0.000 claims abstract description 46
- 230000009471 action Effects 0.000 claims abstract description 35
- 210000003414 extremity Anatomy 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 14
- 210000001503 joint Anatomy 0.000 claims description 9
- 230000036544 posture Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 210000004394 hip joint Anatomy 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/776—Validation; Performance evaluation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Psychiatry (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an intelligent campus safety monitoring prediction management system, which relates to the technical field of intelligent campus monitoring and comprises a camera marking unit, a monitoring mode switching unit, an off-calibration prediction unit, a remaining calibration prediction unit and an abnormality notification unit; according to the invention, the abnormal leaving correction and abnormal detention conditions of students are judged in a learning period and a non-learning period through the leaving correction prediction unit and the leaving correction prediction unit in time periods, the image information of the extracted portrait features is marked as an abnormal image, the action features of the portrait features are further analyzed, the actions of abnormal personnel in the learning period or the non-learning period are judged, and the regional monitoring is realized through time periods, so that the monitoring dead angle is avoided, and the privacy of teachers and students is protected to the greatest extent; the student parents and the teacher side are preferentially informed under the condition that the student is judged to have abnormal leaving school through the leaving school prediction unit, and the teacher side and the school guard are preferentially informed under the condition that the student is judged to have abnormal detention through the leaving school prediction unit.
Description
Technical Field
The invention relates to the technical field of intelligent campus monitoring, in particular to a system for predicting and managing intelligent campus safety monitoring.
Background
The intelligent campus is an intelligent campus working, learning, safety, management and living integrated environment based on the Internet of things, and the integrated environment fully fuses teaching, scientific research, management and campus living by taking various application service systems as carriers.
The campus security has close relations with each teacher, each student, each parent and each society, good campus security has very important security guarantee effect on each student and each family, and as the degree of freedom of campus personnel management is higher and higher, the limit of the students to go in and go out of the school gate is lower and lower, the potential safety hazard is increased, and the system for controlling by taking the students as an entrance in the campus receives more and more importance. The campus is a region with more concentrated population, although a plurality of schools are provided with a plurality of video monitoring devices in the campus at present, the video monitoring devices are monitored only by security personnel, the situation of omission is caused when personnel shift is still unfavorable for the prevention of safety accidents, the schools and parents are inconvenient to timely know the situation of students, the students are inconvenient to manage and control in some emergency, and excessive monitoring equipment easily causes the students and educational staff to lose privacy, and the monitoring equipment has dead angles and is easy to cause the monitoring to be out of place;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims at: the abnormal leaving correction and abnormal detention conditions of students are judged in the learning period and the non-learning period through the leaving correction prediction unit and the leaving correction prediction unit, the image information of the extracted portrait features is marked as an abnormal image, the action features of the portrait features are further analyzed, the actions of abnormal personnel in the learning period or the non-learning period are judged, and the regional monitoring is realized through the time division, so that monitoring dead angles are avoided, and the privacy of teachers and students is protected to the greatest extent.
In order to achieve the above purpose, the present invention adopts the following technical scheme: an intelligent campus safety monitoring prediction management system comprises a camera marking unit, a monitoring mode switching unit, an off-correction prediction unit, a remaining-correction prediction unit and an abnormality notification unit;
the camera marking unit marks cameras distributed in the campus as N, and the cameras are divided into an outdoor camera and an indoor camera according to the distribution positions of the cameras, the outdoor camera is marked as N1, and the indoor camera is marked as N2;
the monitoring mode switching unit inputs a learning period of a school to generate a leaving-correction monitoring mode and a leaving-correction monitoring mode, wherein outdoor personnel flow belongs to an abnormal condition in the leaving-correction monitoring mode, indoor personnel stay belongs to an abnormal condition in the leaving-correction monitoring mode, and the leaving-correction monitoring mode are switched according to the learning period to pertinently analyze image information acquired by an outdoor camera and an indoor camera;
the off-school prediction unit acquires image information through an outdoor camera in a learning period of a student, pre-judges the image information, marks the image information with the extracted portrait characteristic as an abnormal image, further analyzes action characteristics of the portrait characteristic, and judges abnormal personnel actions in the learning period;
the leave-check prediction unit acquires image information through an indoor camera in a non-learning period of the school, pre-judges the image information, marks the image information of the extracted portrait features as an abnormal image, further analyzes the action features of the portrait features, and judges the actions of abnormal personnel in the non-learning period;
the abnormality notification unit obtains the abnormality judgment notification of the departure prediction unit and generates abnormality information to parents of students and teacher sides; and acquiring an abnormality judgment notification of the leave-check prediction unit, and generating abnormality information to the teacher end and the campus guard.
Further, outdoor cameras are distributed in areas outside buildings in the campus, including playgrounds, school gates and campus roads, and indoor cameras are distributed in the buildings in the campus, including classrooms, equipment rooms, teacher offices and libraries.
Further, the image information of the outdoor camera is preferentially sent to the leaving correction prediction unit in the leaving correction monitoring mode, the image information is processed through the leaving correction prediction unit, meanwhile, the indoor camera is in a dormant state, privacy of students and educational administration staff is guaranteed, the image information of the indoor camera is preferentially sent to the leaving correction prediction unit in the leaving correction monitoring mode, the image information is processed through the leaving correction prediction unit, meanwhile, the outdoor camera is in a working state, and abnormal retention of staff in a non-learning time period is convenient to judge.
Further, the specific method for judging the abnormal personnel action in the learning period is as follows:
s1, screening out image information with portrait features based on a convolutional neural network, and marking the image information as an abnormal image;
s2, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represent abnormal school leaving conditions of students in a learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class of conditions, and the second class of conditions represent that the abnormal correction situation of the student accompanies occurs in the learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent abnormal school leaving conditions of the student clusters in a learning period;
s3, aiming at one type of situation and three types of situations, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for situation confirmation;
s4, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing abnormal condition pre-judgment.
Further, the specific method for judging the abnormal personnel action in the non-learning period is as follows:
sa, screening out image information with portrait features based on a convolutional neural network as well, and marking the image information as an abnormal image;
sb, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represents that the abnormal student leaving and correcting conditions occur in a non-learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class condition, and the second class condition indicates that the abnormal correction situation of the student accompanies in a non-learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent that the abnormal school keeping condition of the student clusters occurs in a non-learning period;
sc, aiming at one class of conditions and three classes of conditions, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for condition confirmation;
sd, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing the prejudgment of the abnormal conditions.
Further, the specific method for screening the image information with the portrait features based on the convolutional neural network is as follows:
s I, constructing a convolutional neural network model: acquiring image data from an outdoor camera N1 or an indoor camera N2, intensively reading the data and storing the data in a memory or a hard disk, wherein the data set comprises training data for training and test data for testing;
s II, converting training data and test data in the data set into a three-dimensional tensor form to represent a multichannel image;
and S III, data normalization: carrying out normalization operation on the image number by adopting mean value to remove standard deviation so that the numerical value is between 0 and 1 or between-1 and 1;
IV, performing contrast adjustment processing on the normalized image data, then enhancing the brightness of the image to obtain a large amount of training data, enabling the training data to have diversity and improving the generalization capability of the model, and dividing the image data into three parts of a training set, a verification set and a test set according to the proportion of 8:1:1, wherein the training set is used for training a building type, the verification set is used for adjusting super parameters and preventing overfitting, and the test set is used for evaluating the performance and the generalization capability of the model;
s V, modifying the last full-connection layer of the convolutional neural network, keeping the input unchanged, setting the output as characteristic data with portrait characteristics, initializing the weight of the last layer, learning by using a gradient descent algorithm, and retraining the whole network to obtain an action characteristic recognition model;
s VI, acquiring real-time image information of the outdoor camera N1 or the indoor camera N2 as a test set, evaluating the model effect, and outputting image information with portrait characteristics.
Further, the specific method for further identifying the action features in the abnormal image according to the second class condition is as follows:
s (1) carrying out human body feature separation processing on image information with human body features, extracting independent feature value sets of each person in an image through a convolution layer and a pooling layer, and establishing a reference coordinate system;
s (2) marking key node coordinates M (xa, xb) of a person on a reference coordinate system, wherein the key nodes comprise neck joint points, double-elbow joint points, double-shoulder joint points, hip joint points, double-knee joint points and double-ankle joint points, and the key nodes are connected with human joint points to form a human body posture simplified model;
s (3), calculating the area S of the gesture comparison area by taking joint node coordinates M (xa, ya) as a circle center and taking a radius as r, and obtaining four boundary point coordinates of the gesture comparison area, namely A (xa-r, ya), B (xa, ya+r), C (xa+r, ya) and D (xa, ya-r);
s (4) calculating the length d of a common chord between two adjacent gesture comparison areas,
when d is less than d0, representing that the postures of two adjacent people are not overlapped, the two adjacent people are free from limb release, and the people in the image information are in a safe state;
when d is more than d0, representing that the postures of two adjacent people are mutually overlapped, wherein the two adjacent people are in limb contact, and the people in the image information are in an active state;
s (5) based on the image judgment of the acquisition state, taking t0 as a time period, acquiring image information, calculating a public chord length number value set in the image information, and calculating the length change rate of the public chord by adopting SPSS to obtain
When omega < omega 0 represents t0 time, low-frequency limb contact exists among all people, the possibility of limb conflict among all people is predicted to be low, and normal limb communication is realized;
when ωm is less than ω and less than or equal to ω0, indicating that low-frequency limb contact exists between people, predicting that the possibility of limb collision between people is high, and sending an abnormality judgment notification to an abnormality notification unit;
when ω is equal to or greater than ωm, and t0 is time, there is high-frequency limb contact between each character, and it is predicted that there is a possibility that there is a limb conflict between each character, and an abnormality judgment notification is sent to the abnormality notification unit.
Further, when the abnormality notification unit obtains the abnormality judgment notification of the departure prediction unit, the abnormality notification unit preferentially generates abnormality information to the parents of the students and the teacher end, and after obtaining feedback of the parents of the students and the teacher end, the abnormality notification unit sends the abnormality information to the campus guard to notify the campus guard to take precaution measures; when the abnormality judgment notification of the stay school prediction unit is obtained, the abnormality information is preferentially generated to the teacher end and the campus guard, and after the processing feedback of the teacher end and the campus guard is obtained, the processing result is sent to parents of students.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. according to the intelligent campus safety monitoring prediction management system, the conditions of abnormal departure and abnormal detention of students are judged through the departure prediction unit and the reservation prediction unit in a learning period and a non-learning period, the image information of the extracted portrait features is marked as an abnormal image, the action features of the portrait features are further analyzed, the actions of abnormal personnel in the learning period or the non-learning period are judged, and the regional monitoring is realized through time division, so that monitoring dead angles are avoided, and the privacy of teachers and students is protected to the greatest extent.
2. This wisdom campus safety monitoring predicts management system judges through leaving school prediction unit that the student has under the circumstances of unusual school, and the priority tells student's head of a family and teacher end, under the prerequisite of confirming unusual through student's head of a family or teacher end, sends the unusual information to school guard department, prevents the student from leaving the school through the guard of school guard department taking appropriate measure, under the prerequisite of guaranteeing student privacy, avoids appearing unexpected condition.
3. This wisdom campus safety monitoring predicts management system judges through reserving school prediction unit that the student has the circumstances that is detained abnormally, and the teacher holds and school guard department of notifying in priority, adopts the urgent principle of nearby, makes quick response to the circumstances that is detained abnormally, carries out the processing properly at classroom end and campus guard department simultaneously after, sends the result of processing to student's parents, under the prerequisite of guaranteeing processing efficiency, ensures that student's parents obtain the right of knowing, avoids student's parents too tension simultaneously.
Drawings
Fig. 1 shows a schematic flow diagram of the system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples:
as shown in FIG. 1, the intelligent campus security monitoring prediction management system comprises a camera marking unit, a monitoring mode switching unit, an off-correction prediction unit, a remaining-correction prediction unit and an abnormality notification unit;
the working principle is as follows:
the method comprises the steps that firstly, cameras distributed in a campus are marked as N by a camera marking unit, the cameras are divided into an outdoor camera and an indoor camera according to the distribution positions of the cameras, the outdoor camera is marked as N1, and the indoor camera is marked as N2;
outdoor cameras are distributed in areas outside buildings in the campus, including playgrounds, school gates and campus roads, and indoor cameras are distributed in the buildings in the campus, including classrooms, equipment rooms, teacher offices and libraries.
Step two, a monitoring mode switching unit inputs a learning period of a school to generate a leaving-correction monitoring mode and a leaving-correction monitoring mode, wherein the outdoor personnel flow belongs to an abnormal condition in the leaving-correction monitoring mode, the indoor personnel retention belongs to an abnormal condition in the leaving-correction monitoring mode, and the leaving-correction monitoring mode are switched according to the learning period to analyze image information acquired by an outdoor camera and an indoor camera in a targeted manner;
image information of the outdoor camera is preferentially sent to the leaving-correction prediction unit in the leaving-correction monitoring mode, the image information is processed through the leaving-correction prediction unit, meanwhile, the indoor camera is in a dormant state, privacy of students and educational staff is guaranteed, the image information of the indoor camera is preferentially sent to the leaving-correction prediction unit in the leaving-correction monitoring mode, the image information is processed through the leaving-correction prediction unit, meanwhile, the outdoor camera is in a working state, and abnormal detention of staff in a non-learning time period is convenient to judge.
Step three, the leaving-school prediction unit acquires image information through an outdoor camera in a learning period of students, pre-judges the image information, marks the image information of the extracted portrait features as an abnormal image, further analyzes action features of the portrait features, and judges actions of abnormal personnel in the learning period;
the specific method for judging the abnormal personnel action in the learning period is as follows:
s1, screening out image information with portrait features based on a convolutional neural network, and marking the image information as an abnormal image;
s2, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represent abnormal school leaving conditions of students in a learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class of conditions, and the second class of conditions represent that the abnormal correction situation of the student accompanies occurs in the learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent abnormal school leaving conditions of the student clusters in a learning period;
s3, aiming at one type of situation and three types of situations, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for situation confirmation;
s4, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing abnormal condition pre-judgment.
Step four, the leave-check prediction unit acquires image information through an indoor camera in a non-learning period of the school, pre-judges the image information, marks the image information of the extracted portrait features as an abnormal image, further analyzes action features of the portrait features, and judges abnormal personnel actions in the non-learning period;
the specific method for judging the abnormal personnel action in the non-learning period is as follows:
sa, screening out image information with portrait features based on a convolutional neural network as well, and marking the image information as an abnormal image;
sb, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represents that the abnormal student leaving and correcting conditions occur in a non-learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class condition, and the second class condition indicates that the abnormal correction situation of the student accompanies in a non-learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent that the abnormal school keeping condition of the student clusters occurs in a non-learning period;
sc, aiming at one class of conditions and three classes of conditions, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for condition confirmation;
sd, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing the prejudgment of the abnormal conditions.
The specific method for screening the image information with the portrait features based on the convolutional neural network comprises the following steps:
s I, constructing a convolutional neural network model: acquiring image data from an outdoor camera N1 or an indoor camera N2, intensively reading the data and storing the data in a memory or a hard disk, wherein the data set comprises training data for training and test data for testing;
s II, converting training data and test data in the data set into a three-dimensional tensor form to represent a multichannel image;
and S III, data normalization: carrying out normalization operation on the image number by adopting mean value to remove standard deviation so that the numerical value is between 0 and 1 or between-1 and 1;
IV, performing contrast adjustment processing on the normalized image data, then enhancing the brightness of the image to obtain a large amount of training data, enabling the training data to have diversity and improving the generalization capability of the model, and dividing the image data into three parts of a training set, a verification set and a test set according to the proportion of 8:1:1, wherein the training set is used for training a building type, the verification set is used for adjusting super parameters and preventing overfitting, and the test set is used for evaluating the performance and the generalization capability of the model;
s V, modifying the last full-connection layer of the convolutional neural network, keeping the input unchanged, setting the output as characteristic data with portrait characteristics, initializing the weight of the last layer, learning by using a gradient descent algorithm, and retraining the whole network to obtain an action characteristic recognition model;
s VI, acquiring real-time image information of the outdoor camera N1 or the indoor camera N2 as a test set, evaluating the model effect, and outputting image information with portrait characteristics.
The specific method for further identifying the action features in the abnormal image aiming at the second class of conditions is as follows:
s (1) carrying out human body feature separation processing on image information with human body features, extracting independent feature value sets of each person in an image through a convolution layer and a pooling layer, and establishing a reference coordinate system;
s (2) marking key node coordinates M (xa, xb) of a person on a reference coordinate system, wherein the key nodes comprise neck joint points, double-elbow joint points, double-shoulder joint points, hip joint points, double-knee joint points and double-ankle joint points, and the key nodes are connected with human joint points to form a human body posture simplified model;
s (3), calculating the area S of the gesture comparison area by taking joint node coordinates M (xa, ya) as a circle center and taking a radius as r, and obtaining four boundary point coordinates of the gesture comparison area, namely A (xa-r, ya), B (xa, ya+r), C (xa+r, ya) and D (xa, ya-r);
s (4) calculating the length d of a common chord between two adjacent gesture comparison areas,
when d is less than d0, representing that the postures of two adjacent people are not overlapped, the two adjacent people are free from limb release, and the people in the image information are in a safe state;
when d is more than d0, representing that the postures of two adjacent people are mutually overlapped, wherein the two adjacent people are in limb contact, and the people in the image information are in an active state;
s (5) based on the image judgment of the acquisition state, taking t0 as a time period, acquiring image information, calculating a public chord length number value set in the image information, and calculating the length change rate of the public chord by adopting SPSS to obtain
When omega < omega 0 represents t0 time, low-frequency limb contact exists among all people, the possibility of limb conflict among all people is predicted to be low, and normal limb communication is realized;
when ωm is less than ω and less than or equal to ω0, indicating that low-frequency limb contact exists between people, predicting that the possibility of limb collision between people is high, and sending an abnormality judgment notification to an abnormality notification unit;
when ω is equal to or greater than ωm, and t0 is time, there is high-frequency limb contact between each character, and it is predicted that there is a possibility that there is a limb conflict between each character, and an abnormality judgment notification is sent to the abnormality notification unit.
Step five, an abnormality notification unit obtains an abnormality judgment notification of the departure prediction unit and generates abnormality information to parents of students and teacher sides; and acquiring an abnormality judgment notification of the leave-check prediction unit, and generating abnormality information to the teacher end and the campus guard.
When the abnormality notification unit obtains abnormality judgment notification of the departure prediction unit, the abnormality notification unit preferentially sends abnormality information to a student parent and a teacher side, after obtaining feedback of the student parent and the teacher side, the abnormality information is sent to a campus guard, the campus guard is notified to take early warning measures, the departure prediction unit preferentially informs the student parent and the teacher side when judging that the student has abnormality, the abnormality information is sent to the school guard on the premise of confirming the abnormality through the student parent or the teacher side, and the student is prevented from leaving the school by taking appropriate measures through security personnel at the school guard, so that accidents are avoided on the premise of guaranteeing the privacy of the student;
when the abnormality judgment notification of the stay school prediction unit is obtained, the abnormality information is preferentially generated to the teacher end and the campus guard, and after the processing feedback of the teacher end and the campus guard is obtained, the processing result is sent to parents of students; the reservation and correction prediction unit judges that the students are in abnormal retention, the teacher end and the school guard are informed preferentially, the nearby urgent principle is adopted, quick response is made to the abnormal retention condition, meanwhile, after the classroom end and the school guard are properly processed, processing results are sent to parents of the students, and under the premise of guaranteeing processing efficiency, the parents of the students are guaranteed to obtain the awareness, and meanwhile the parents of the students are prevented from being overstressed.
The interval and the threshold are set for the convenience of comparison, and the size of the threshold depends on the number of sample data and the number of cardinalities set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
The formulas are all formulas with dimensions removed and numerical calculation, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by a person skilled in the art according to the actual situation;
those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware; whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution; skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application;
in the several embodiments provided in this application, it should be understood that the disclosed apparatus and system may be implemented in other ways; for example, the apparatus embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed; alternatively, the coupling or direct coupling or communication connection shown or discussed with respect to each other may be through some interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form;
in addition, each functional module in each embodiment of the present application may be integrated in one processing module, or each module may exist alone physically, or two or more modules may be integrated in one module;
the functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium; based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application; and the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk or an optical disk;
the foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (8)
1. The intelligent campus safety monitoring prediction management system is characterized by comprising a camera marking unit, a monitoring mode switching unit, an off-correction prediction unit, a remaining-correction prediction unit and an abnormality notification unit;
the camera marking unit marks cameras distributed in the campus as N, and the cameras are divided into an outdoor camera and an indoor camera according to the distribution positions of the cameras, the outdoor camera is marked as N1, and the indoor camera is marked as N2;
the monitoring mode switching unit inputs a learning period of a school to generate a leaving-correction monitoring mode and a leaving-correction monitoring mode, wherein outdoor personnel flow belongs to an abnormal condition in the leaving-correction monitoring mode, indoor personnel stay belongs to an abnormal condition in the leaving-correction monitoring mode, and the leaving-correction monitoring mode are switched according to the learning period to pertinently analyze image information acquired by an outdoor camera and an indoor camera;
the off-school prediction unit acquires image information through an outdoor camera in a learning period of a student, pre-judges the image information, marks the image information with the extracted portrait characteristic as an abnormal image, further analyzes action characteristics of the portrait characteristic, and judges abnormal personnel actions in the learning period;
the leave-check prediction unit acquires image information through an indoor camera in a non-learning period of the school, pre-judges the image information, marks the image information of the extracted portrait features as an abnormal image, further analyzes the action features of the portrait features, and judges the actions of abnormal personnel in the non-learning period;
the abnormality notification unit obtains the abnormality judgment notification of the departure prediction unit and generates abnormality information to parents of students and teacher sides; and acquiring an abnormality judgment notification of the leave-check prediction unit, and generating abnormality information to the teacher end and the campus guard.
2. The intelligent campus security monitoring predictive management system of claim 1, wherein the outdoor cameras are distributed in areas outside buildings in the campus, including playgrounds, school gates and campus roads, and the indoor cameras are distributed in buildings in the campus, including classrooms, equipment rooms, teacher offices and libraries.
3. The intelligent campus safety monitoring prediction management system according to claim 1, wherein the image information of the outdoor camera is preferentially sent to the leaving prediction unit in the leaving monitoring mode, the image information is processed through the leaving prediction unit, meanwhile, the indoor camera is in a dormant state, privacy of students and educational staff is guaranteed, the image information of the indoor camera is preferentially sent to the leaving prediction unit in the leaving monitoring mode, the image information is processed through the leaving prediction unit, meanwhile, the outdoor camera is in a working state, and abnormal detention of staff in a non-learning period is convenient to judge.
4. The intelligent campus security monitoring predictive management system according to claim 1, wherein the specific method for judging abnormal personnel actions in the learning period is as follows:
s1, screening out image information with portrait features based on a convolutional neural network, and marking the image information as an abnormal image;
s2, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represent abnormal school leaving conditions of students in a learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class of conditions, and the second class of conditions represent that the abnormal correction situation of the student accompanies occurs in the learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent abnormal school leaving conditions of the student clusters in a learning period;
s3, aiming at one type of situation and three types of situations, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for situation confirmation;
s4, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing abnormal condition pre-judgment.
5. The intelligent campus security monitoring predictive management system of claim 1, wherein the specific method for determining abnormal personnel actions during the non-learning period is as follows:
sa, screening out image information with portrait features based on a convolutional neural network as well, and marking the image information as an abnormal image;
sb, carrying out face recognition on the portrait features in the abnormal image, obtaining the number R of the independent portrait features, and classifying and judging the number of the independent portrait features as follows:
when R is more than H1, wherein H1 is a natural number greater than 0, the abnormal image is marked as a class of conditions, and the class of conditions represents that the abnormal student leaving and correcting conditions occur in a non-learning period;
when H2 is more than R and is more than or equal to H1, wherein H2 is a natural number which is more than 0, the abnormal image is marked as a second class condition, and the second class condition indicates that the abnormal correction situation of the student accompanies in a non-learning period;
when H3 is more than R and is more than or equal to H2, wherein H3 is a natural number more than 0, the abnormal image is marked into three types of conditions, and the three types of conditions represent that the abnormal school keeping condition of the student clusters occurs in a non-learning period;
sc, aiming at one class of conditions and three classes of conditions, judging results are sent to an abnormality notification unit, and abnormality information is sent to parents of students and teacher sides for condition confirmation;
sd, further identifying action features in the abnormal images aiming at the second class of conditions, and realizing the prejudgment of the abnormal conditions.
6. The intelligent campus security monitoring prediction management system according to claim 1, wherein the specific method for screening the image information with portrait features based on the convolutional neural network is as follows:
s I, constructing a convolutional neural network model: acquiring image data from an outdoor camera N1 or an indoor camera N2, intensively reading the data and storing the data in a memory or a hard disk, wherein the data set comprises training data for training and test data for testing;
s II, converting training data and test data in the data set into a three-dimensional tensor form to represent a multichannel image;
and S III, data normalization: carrying out normalization operation on the image number by adopting mean value to remove standard deviation so that the numerical value is between 0 and 1 or between-1 and 1;
IV, performing contrast adjustment processing on the normalized image data, then enhancing the brightness of the image to obtain a large amount of training data, dividing the image data into three parts of a training set, a verification set and a test set according to the proportion of 8:1:1, wherein the training set is used for training a building type, the verification set is used for adjusting super parameters and preventing overfitting, and the test set is used for evaluating the performance and generalization capability of a model;
s V, modifying the last full-connection layer of the convolutional neural network, keeping the input unchanged, setting the output as characteristic data with portrait characteristics, initializing the weight of the last layer, learning by using a gradient descent algorithm, and retraining the whole network to obtain an action characteristic recognition model;
s VI, acquiring real-time image information of the outdoor camera N1 or the indoor camera N2 as a test set, evaluating the model effect, and outputting image information with portrait characteristics.
7. The intelligent campus security monitoring predictive management system of claim 1, wherein the specific method for further identifying motion features in the anomaly image for the class two case is as follows:
s (1) carrying out human body feature separation processing on image information with human body features, extracting independent feature value sets of each person in an image through a convolution layer and a pooling layer, and establishing a reference coordinate system;
s (2) marking key node coordinates M (xa, xb) of a person on a reference coordinate system, wherein the key nodes comprise neck joint points, double-elbow joint points, double-shoulder joint points, hip joint points, double-knee joint points and double-ankle joint points, and the key nodes are connected with human joint points to form a human body posture simplified model;
s (3), calculating the area S of the gesture comparison area by taking joint node coordinates M (xa, ya) as a circle center and taking a radius as r, and obtaining four boundary point coordinates of the gesture comparison area, namely A (xa-r, ya), B (xa, ya+r), C (xa+r, ya) and D (xa, ya-r);
s (4) calculating the length d of a common chord between two adjacent gesture comparison areas,
when d is less than d0, representing that the postures of two adjacent people are not overlapped, the two adjacent people are free from limb release, and the people in the image information are in a safe state;
when d is more than d0, representing that the postures of two adjacent people are mutually overlapped, wherein the two adjacent people are in limb contact, and the people in the image information are in an active state;
s (5) based on the image judgment of the acquisition state, taking t0 as a time period, acquiring image information, calculating a public chord length number value set in the image information, and calculating the length change rate of the public chord by adopting SPSS to obtain
When omega < omega 0 represents t0 time, low-frequency limb contact exists among all people, the possibility of limb conflict among all people is predicted to be low, and normal limb communication is realized;
when ωm is less than ω and less than or equal to ω0, indicating that low-frequency limb contact exists between people, predicting that the possibility of limb collision between people is high, and sending an abnormality judgment notification to an abnormality notification unit;
when ω is equal to or greater than ωm, and t0 is time, there is high-frequency limb contact between each character, and it is predicted that there is a possibility that there is a limb conflict between each character, and an abnormality judgment notification is sent to the abnormality notification unit.
8. The intelligent campus safety monitoring prediction management system according to claim 1, wherein when the abnormality notification unit obtains the abnormality judgment notification of the departure prediction unit, the abnormality notification unit preferentially sends abnormality information to a student parent and a teacher end, and after obtaining feedback of the student parent and the teacher end, the abnormality information is sent to a campus guard to notify the campus guard to take early warning measures; when the abnormality judgment notification of the stay school prediction unit is obtained, the abnormality information is preferentially generated to the teacher end and the campus guard, and after the processing feedback of the teacher end and the campus guard is obtained, the processing result is sent to parents of students.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311499242.5A CN117315591B (en) | 2023-11-13 | 2023-11-13 | Intelligent campus safety monitoring prediction management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311499242.5A CN117315591B (en) | 2023-11-13 | 2023-11-13 | Intelligent campus safety monitoring prediction management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117315591A true CN117315591A (en) | 2023-12-29 |
| CN117315591B CN117315591B (en) | 2024-03-22 |
Family
ID=89286665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311499242.5A Active CN117315591B (en) | 2023-11-13 | 2023-11-13 | Intelligent campus safety monitoring prediction management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117315591B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117690331A (en) * | 2024-02-04 | 2024-03-12 | 西南医科大学附属医院 | Prostate puncture operation training system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101674461A (en) * | 2008-09-11 | 2010-03-17 | 上海市长宁区少年科技指导站 | Intelligent network monitoring system for safety of primary and secondary school campuses |
| CN107464196A (en) * | 2017-08-04 | 2017-12-12 | 卓智网络科技有限公司 | Student group is left school Forecasting Methodology and device |
| CN108446836A (en) * | 2018-03-05 | 2018-08-24 | 兴义市点石文化传播有限责任公司 | A kind of university student's campus life management system |
| US10202204B1 (en) * | 2016-03-25 | 2019-02-12 | AAR Aerospace Consulting, LLC | Aircraft-runway total energy measurement, monitoring, managing, safety, and control system and method |
| CN109344688A (en) * | 2018-08-07 | 2019-02-15 | 江苏大学 | The automatic identifying method of people in a kind of monitor video based on convolutional neural networks |
| CN113128383A (en) * | 2021-04-07 | 2021-07-16 | 杭州海宴科技有限公司 | Recognition method for campus student cheating behavior |
| CN114386774A (en) * | 2021-12-21 | 2022-04-22 | 中国中煤能源集团有限公司 | CPIM-based three-dimensional visual full-life-cycle management platform for coal preparation plant |
| CN116563797A (en) * | 2023-07-10 | 2023-08-08 | 安徽网谷智能技术有限公司 | Monitoring management system for intelligent campus |
-
2023
- 2023-11-13 CN CN202311499242.5A patent/CN117315591B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101674461A (en) * | 2008-09-11 | 2010-03-17 | 上海市长宁区少年科技指导站 | Intelligent network monitoring system for safety of primary and secondary school campuses |
| US10202204B1 (en) * | 2016-03-25 | 2019-02-12 | AAR Aerospace Consulting, LLC | Aircraft-runway total energy measurement, monitoring, managing, safety, and control system and method |
| CN107464196A (en) * | 2017-08-04 | 2017-12-12 | 卓智网络科技有限公司 | Student group is left school Forecasting Methodology and device |
| CN108446836A (en) * | 2018-03-05 | 2018-08-24 | 兴义市点石文化传播有限责任公司 | A kind of university student's campus life management system |
| CN109344688A (en) * | 2018-08-07 | 2019-02-15 | 江苏大学 | The automatic identifying method of people in a kind of monitor video based on convolutional neural networks |
| CN113128383A (en) * | 2021-04-07 | 2021-07-16 | 杭州海宴科技有限公司 | Recognition method for campus student cheating behavior |
| CN114386774A (en) * | 2021-12-21 | 2022-04-22 | 中国中煤能源集团有限公司 | CPIM-based three-dimensional visual full-life-cycle management platform for coal preparation plant |
| CN116563797A (en) * | 2023-07-10 | 2023-08-08 | 安徽网谷智能技术有限公司 | Monitoring management system for intelligent campus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117690331A (en) * | 2024-02-04 | 2024-03-12 | 西南医科大学附属医院 | Prostate puncture operation training system and method |
| CN117690331B (en) * | 2024-02-04 | 2024-05-14 | 西南医科大学附属医院 | Prostate puncture operation training system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117315591B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117315591B (en) | Intelligent campus safety monitoring prediction management system | |
| US20190156496A1 (en) | Methods, systems, apparatuses and devices for facilitating motion analysis in an environment | |
| Vanderhaar et al. | Reconsidering the alternatives: The relationship between suspension, disciplinary alternative school placement, subsequent juvenile detention, and the salience of race | |
| Williams et al. | Traffic management center use of incident detection algorithms: Findings of a nationwide survey | |
| Ronchi et al. | New approaches to evacuation modelling for fire safety engineering applications | |
| EP3655916B1 (en) | Systems and methods for location fencing within a controlled environment | |
| CN110781771A (en) | Abnormal behavior real-time monitoring method based on deep learning | |
| CN111260314A (en) | Wisdom campus security situation perception system | |
| CN109087478A (en) | A kind of early warning of the anti-swarm and jostlement of intelligence and method of river diversion and system | |
| CN105208325B (en) | The land resources monitoring and early warning method captured and compare analysis is pinpointed based on image | |
| CN107403158A (en) | A kind of personnel video frequency identifying method on duty and intelligent subscriber information carrying means | |
| CN101751553A (en) | Method for analyzing and predicting large-scale crowd density | |
| CN110428678A (en) | A kind of computer online teaching management system | |
| CN108256447A (en) | A kind of unmanned plane video analysis method based on deep neural network | |
| CN113935643A (en) | Campus security risk prevention and control method, system, equipment and storage medium | |
| CN117151528A (en) | Vocational education training management system | |
| US11030884B1 (en) | Real-time prevention and emergency management system and respective method of operation | |
| CN109886850A (en) | A kind of data comprehensive management system and management method for smart classroom | |
| CN111860308A (en) | Intelligent student sleep safety management method based on video behavior recognition | |
| CN111553264A (en) | Campus non-safety behavior detection and early warning method suitable for primary and secondary school students | |
| Fu et al. | Application of naive bayes classifier in stampede risk early-warning of large-scale activities | |
| CN112104837A (en) | Intelligent behavior analysis system applied to school places | |
| Liao et al. | A novel stochastic agent-based model of building occupancy | |
| Hao et al. | A detection method of abnormal event in crowds based on image entropy | |
| Bolia | Risk management strategies to avoid stampede at Mass gatherings |
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 |