CN114785834A - Design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment - Google Patents
Design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment Download PDFInfo
- Publication number
- CN114785834A CN114785834A CN202110011582.3A CN202110011582A CN114785834A CN 114785834 A CN114785834 A CN 114785834A CN 202110011582 A CN202110011582 A CN 202110011582A CN 114785834 A CN114785834 A CN 114785834A
- Authority
- CN
- China
- Prior art keywords
- classroom
- ipv6
- data
- people
- database
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013461 design Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000007405 data analysis Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004134 energy conservation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005923 long-lasting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/083—Network architectures or network communication protocols for network security for authentication of entities using passwords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment, which comprises the steps of collecting classroom images in real time, processing the collected images by adopting a target detection algorithm FCHD, counting the number of people in a classroom, and simultaneously installing a temperature sensor to detect the temperature of the classroom; the number of people and the temperature data are transmitted to a server through an IPv6 network, and the data are stored into a MySQL database through a pymysql packet; extracting the number of people and temperature data from the database, judging the on/off of the lighting equipment according to the detection result of the number of people, and judging the on/off of the temperature control equipment according to the temperature data under the condition that people exist in a classroom; establishing an intelligent power-saving classroom management platform, and performing initialization management on data in a MySQL database; and (3) performing data analysis on students or teaching workers accessing the website through the IPv6 campus network by adopting an IPv6 address division method based on the Merkle tree. The intelligent control system combines the image processing algorithm and the IPv6, is applied to the field of smart campuses, realizes intelligent control on classroom electric equipment, and plays a role in energy conservation and emission reduction.
Description
Technical Field
The invention belongs to the field of IPv6 innovation and application, and particularly relates to a design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment.
Background
In the existing network, almost all networks use IP protocol as the address protocol for communication, and each node in the network should be assigned a unique IP address to ensure normal communication. The IP protocol version widely used today is v4, with 32 bits, an address space of 65536 x 65536, and a result of about 42.9 hundred million. Although the total address is 42.9 hundred million, the addresses are not indicated to be available for 42.9 hundred million nodes, but the addresses are divided into network segments, that is, even in the case of one node, when the address is allocated, one network segment is allocated instead of one address, so that the space of the IP address of the version 4 becomes narrow at once, and the address capacity of the IPv4 is in a trend of being exhausted.
In the construction of a smart campus network, due to the fact that there are numerous universities in China, the number of classrooms of each university is large, and the number of sensor nodes distributed in the campus is large, the requirement for a network address space is large. Compared with IPv4, IPv6 has a larger address space, which is expressed by 128 bits, and thus the large address space can accommodate almost infinite nodes. The IPv6 also has better expandability, more efficient network transmission, better security management architecture and better mobility support, and is more suitable for the development of smart campuses.
The existing people number detection adopts two groups of correlation photoelectric sensors, and the people number detection mode has many defects. For example: when people are detained, the in-out conditions of the people are difficult to judge; if the access mode of people is not proper, the data which cannot be collected exist. With the development of artificial intelligence and deep learning, image processing technology based on convolutional neural network is rapidly developed in recent years, and the method is widely applied to many fields and has good effect. The technology is integrated into the smart campus, and the long-lasting development of the smart campus can be effectively promoted.
Disclosure of Invention
The invention aims to: the invention provides a design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment, which is convenient for the management of school resources, changes the traditional power consumption management mode of a classroom and avoids the waste of power resources.
The invention content is as follows: the invention provides a design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment, which specifically comprises the following steps:
(1) constructing an image acquisition module: selecting an intelligent machine learning visual identification camera human face image identification processing sensor module OPENMV4 Cam M7 to perform video monitoring on a classroom and acquire classroom images in real time;
(2) constructing a statistical identification module: preprocessing the acquired image by adopting an improved image super-resolution reconstruction algorithm SRCNN, then identifying the head area of the acquired image by adopting a target detection algorithm FCHD, and counting the identified head area to calculate the number of people;
(3) constructing an energy-saving module: uploading the obtained information of the number of people to a server through an IPv6 network, and storing the processed information of the number of people into a MySQL database through a data processing library pymysql of python; extracting an image processing result from the MySQL database, and feeding the result back to the lighting system and the temperature control system; the lighting system judges the on/off of the lighting equipment according to the number detection result fed back from the database; a temperature sensor is arranged in a classroom at the same time, the classroom temperature is detected, and the temperature condition is transmitted into a MySQL database of a server in real time through an IPv6 network; the temperature control system extracts classroom people number data and temperature data from the database and judges the on/off of the temperature adjusting equipment;
(4) establishing an intelligent power-saving classroom management module, and performing initialization management on data in a MySQL database;
(5) and (3) performing data analysis on students or teaching workers accessing the website through the IPv6 campus network by adopting an IPv6 address division method based on the Merkle tree.
Further, the step (2) comprises the steps of:
(21) the acquired image is preprocessed by adopting an improved image super-resolution processing algorithm SRCNN: the structure of the SRCNN comprises three layers, namely a feature extraction layer, a nonlinear mapping layer and a feature reconstruction layer, wherein the sizes of filters are respectively 3 multiplied by 9 multiplied by 64, 64 multiplied by 1 multiplied by 35 and 35 multiplied by 5 multiplied by 1; adding a channel attention mechanism into the SRCNN feature extraction layer, and carrying out secondary weighting on the convolution channel; a zero filling method is adopted in the convolution process, and the size of the image is kept unchanged;
(22) performing human head region identification on the acquired image by adopting an object detection algorithm FCHD, performing feature migration on a model trained by VGG16 by using the FCHD model without including the last layer after conv5 layers as a feature extraction layer, taking the residual weight as the starting point of new model training, outputting the dimension of 40 × 30 × 512, then inputting the model to a convolution layer (3 × 3 × 512, 512), coding the acquired feature information, dividing the result obtained by the convolution layer into two paths, respectively inputting the two paths to a full convolution layer with convolution kernels of (1 × 1 × 512, N × 4) and (1 × 1 × 512, N × 2), respectively inputting the two paths to the full convolution layer with convolution kernels of (1 × 1 × 512, N × 4) for predicting head coordinates to position, regressing a head, and (1 × 1 × 512, N × 2) for predicting the probability that the position is a head, classifying the head and non-head regions, wherein N represents the number of marked human heads, the value of N depends on the number of anchor points per pixel location; the two outputs are represented as 40 × 30 × (N × 4) and 40 × 30 × (N × 2), respectively, where × 2 and × 4 represent the anchor point scaling;
an anchor is a set of predefined bounding boxes used to predict scale and displacement, and the anchor size calculation formula is expressed as:
Anchor size＝S×R×C (3)
wherein S represents a step size, R represents an aspect ratio, and C represents an anchor point scaling ratio; the model defines an anchor aspect ratio of 1:1 with a step size of 16, with anchor scaling ratios of (× 2) and (× 4) corresponding to anchor sizes of 32 × 32 and 64 × 64, respectively;
(23) and taking the preprocessed image data set as the input of the model, outputting the image data set as a marked image, and counting the marked head region coordinates to obtain the number of the heads.
Further, the step (3) includes the steps of:
(31) creating a database named class, creating a data table named stu _ db, wherein fields contained in the data table comprise self-increment id, classroom number class _ id, classroom number peo _ num, classroom temperature class _ temp and data update time update _ time; wherein the field types of id, class _ id and peo _ num are int, the field type of class _ temp is double, and the field type of update _ time is timestamp; the counted number of people sets the IP address of the server, the user name and the password of the database, the name clasbroom of the database and the coding mode through the python library pymysql, and the collected data is stored in a data table stu _ db through an SQL statement INSERT INTO;
(32) extracting the value of the field peo _ num from the stu _ db data table, and feeding the result back to the lighting system and the temperature control system;
(33) an illumination system: if the value of peo _ num is greater than 1, indicating that the classroom has a person, turning on the lighting system, and if the value of peo _ num is 0, indicating that the classroom has no person, keeping the lighting system in an off state;
(34) the classroom is simultaneously provided with a temperature sensor, the classroom temperature is detected, and the temperature condition is transmitted into a field class _ temp in a stu _ db data table in real time;
(35) a temperature control system: the temperature control system extracts the values of field peo _ num and class _ temp from the database, if the value of peo _ num is greater than 1 and the value of class _ temp is higher than a set threshold, the fan is turned on, and if the value is lower than the threshold, the fan is kept off; if the temperature control system detects that the value of peo _ num is less than 1, the fan is turned off, and the lighting device is also turned off.
Further, the step (4) comprises the steps of:
(41) the intelligent power-saving classroom management module comprises a login page and an intelligent power-saving classroom management platform page;
(42) the intelligent power-saving classroom management module comprises a back-end functional design and a front-end page rendering design, wherein the back-end design is compiled by adopting a Django framework of python, and the front-end is compiled by adopting html and css languages;
(43) designing a landing page: the 'user name' input box, the 'password' input box and the 'login' button are aligned in the middle of the page, and the 'user name' input box and the 'password' input box are arranged to have the same length and width; aiming at unregistered users, designing a registration button on the right side of a login box;
(44) designing a smart power-saving classroom management platform page: the left column comprises three modules, namely a homepage, user information, data statistics and information search; the home page module displays the number of visitors on the current date, the user information module displays the basic information of a user by adopting a table, and the data statistics module displays the change condition of the number of classroom persons in a week by adopting a line chart; in the search bar of the information search module, the specific time is input, and the number of the classroom people can be fed back.
Further, the step (5) includes the steps of:
(51) performing information authentication when equipment of a student or a teaching worker is accessed to an IPv6 campus network for the first time;
(52) dynamically allocating a temporary IPv6 address through the DHCPv6 server;
(53) portal Server provides an authentication page for user, and the user needs to fill in specified related attributes for authentication;
(54) the authentication center obtains the user attribute through the step (53) to construct a Merkle tree, and the Merkle tree is matched with the Hash value of the user attribute in the database;
(55) the SDN switch allocates an IPv6 address for the terminal equipment according to the result of the step (54), if the matching is successful, an IPv6 address is allocated for the user according to the tree root of the Merkle tree and is bound with the MAC address of the equipment, and if the matching is unsuccessful, the SDN switch is quickly positioned to which attribute is wrongly filled and informs the user of the failure of IPv6 address allocation;
(56) a unique IPv6 address is allocated to each network terminal of the school, and the campus network center carries out data analysis on the access conditions of the teacher and student websites of the school according to the method.
Has the advantages that: compared with the prior art, the invention has the beneficial effects that: 1. the image processing technology is integrated with the management of the resources of the school, so that the intelligent degree of the classroom is improved, the management of the resources of the school is facilitated, the traditional power utilization management mode of the classroom is changed, the waste of power resources is avoided, and meanwhile, the construction of the intelligent campus of colleges and universities is promoted; 2. an IPv6 address partitioning method based on a Merkle tree is adopted, and the characteristic of abundant IPv6 addresses is utilized to distribute a unique IP address for each network terminal of a school, so that the tracing of data is realized, the management is convenient, and the safety of data transmission in a network is ensured.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of people counting in the present invention;
FIG. 3 is a diagram of an improved image super-resolution reconstruction algorithm SRCNN model in the present invention;
FIG. 4 is a specific implementation principle of the target detection algorithm FCHD in the present invention;
FIG. 5 is a flow chart of the energy saving system design of the present invention;
FIG. 6 is a diagram of a landing page of the intelligent power-saving classroom management platform of the present invention;
FIG. 7 is a main page view of the intelligent power-saving classroom management platform of the present invention;
fig. 8 is a diagram of an IPv6 address structure in the present invention.
Detailed Description
The technical scheme of the invention is clearly and completely described below with reference to the accompanying drawings of the invention.
As shown in fig. 1, the invention provides a design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment, which specifically comprises the following steps:
step 1: constructing an image acquisition module: selecting an intelligent machine learning visual identification camera human face image identification processing sensor module OPENMV4 Cam M7 to perform video monitoring on a classroom and acquire classroom images in real time;
installing a camera, and collecting classroom pictures: the OPENMV4 Cam M7 is arranged obliquely above a classroom to ensure that a video can shoot a global picture of the classroom; the characteristic that the outline of the human head is relatively fixed is utilized to detect and analyze the number of people in the video monitoring under the classroom scene, and classroom pictures collected by the camera in real time are represented by a data set A.
And 2, step: constructing a statistical identification module: the collected images are preprocessed by adopting an improved image super-resolution reconstruction algorithm SRCNN, then the collected images are identified by adopting a target detection algorithm FCHD, and the number of people in the identified head area is calculated by statistics.
As shown in fig. 2, the overall flow chart of people counting of the present invention adopts improved SRCNN to perform picture preprocessing, and a target detection algorithm FCHD identifies the head of a person; counting the number of the marked head region coordinates to obtain the number of the heads; and storing the obtained data into a MySQL database.
Image preprocessing: in practical application, it is found that in an acquired classroom picture, a part of head information is located at the edge of an image and the boundary is fuzzy, and a target detection algorithm cannot accurately identify the head information at the edge of the image, so that people counting is inaccurate. Therefore, before the number of people is identified in the classroom image, the acquired image is preprocessed by adopting the improved image super-resolution processing algorithm SRCNN, so that the shadow with fuzzy image edges becomes clearer, the head boundary is more obvious, and the accuracy of the number of people identification is improved. The pre-processed image is represented by data set a-1.
Recognizing the human head: and (3) adopting a target detection algorithm FCHD to identify the head area of the collected image, and then counting the identified head area to calculate the number of people. FCHD is called A fast and a secure head detector, and the algorithm can realize rapid and accurate human head detection. The model structure is based on a Faster-RCNN algorithm, but different from the Faster-RCNN algorithm, the model structure has a two-stage assembly line, and the FCHD algorithm can realize a single-stage assembly line for head detection.
Counting the number of people: and taking the picture of the data set A-1 as the input of the model, outputting the picture as a marked picture, and counting the marked coordinates of the head area to obtain the number of the heads.
In order to avoid wasting computing resources, the counted number information is stored in real time and uploaded to a database of a server, managers can judge the flow condition of students by checking the number information of each classroom in the database, classrooms with large flow of people are selectively opened, classrooms with small flow of people are closed, and the waste of teaching resources is avoided. Meanwhile, the storage of the statistical data is convenient for various researches and uses.
As shown in fig. 3, in the present invention, the improved SRCNN model structure is:
SRCNN is the action of applying a convolutional neural network to the mountaineering in the super-resolution field, has few convolutional layers and smaller model, and is easy to migrate to the actual field for application. The structure of the SRCNN comprises three layers, namely a feature extraction layer, a nonlinear mapping layer and a feature reconstruction layer, wherein the sizes of filters are respectively 3 multiplied by 9 multiplied by 64, 64 multiplied by 1 multiplied by 35 and 35 multiplied by 5 multiplied by 1. In order to enable the model training to be more concentrated on the human head features, a channel attention mechanism is added in an SRCNN feature extraction layer, and key information in a learning image can be concentrated on by a method of carrying out secondary weighting on a convolution channel, so that a human head region in the image is clearer. And a zero filling method is adopted in the convolution process, so that the size of the image is kept unchanged.
As shown in fig. 4, the target detection algorithm FCHD principle:
FCHD model structure: the model performs feature migration on a model trained by VGG16, the last layer after a conv5 layer is not included as a feature extraction layer, the rest weight is used as a starting point of new model training, the output dimension is 40 × 30 × 512, then the weight is input into a convolution layer of (3 × 3 × 512, 512), the obtained feature information is encoded, the obtained result of the convolution layer is divided into two paths, the two paths are respectively input into a full convolution layer with convolution kernels of (1 × 1 × 512, N × 4) and (1 × 1 × 512, N × 2), the (1 × 1 × 512, N × 4) full convolution layer is used for predicting head coordinates to position, and the head is regressed, and the (1 × 1 × 512, N × 2) full convolution layer is used for predicting the probability that the position is the head, and head and non-head regions are classified. Where N represents the number of heads of the tag, which value depends on the number of anchor points per pixel location. The two outputs are represented as 40 × 30 × (N × 4) and 40 × 30 × (N × 2), respectively, and × 2 and × 4 represent the anchor point scaling.
An anchor is a set of predefined bounding boxes used to predict scale and displacement. The Anchor size equation is expressed as:
Anchor size＝S×R×C (3)
where S represents the step size, R represents the aspect ratio, and C represents the anchor scaling ratio. The model defines an anchor aspect ratio of 1:1 with a step size of 16, so anchor scaling ratios of x 2 and x 4 correspond to anchor sizes of 32 x 32 and 64 x 64, respectively. And the small anchor point proportion is beneficial to positioning the human head area.
And step 3: constructing an energy-saving module: uploading the obtained information of the number of people to a server through an IPv6 network, and storing the processed information of the number of people into a MySQL database through a data processing library pymysql of python; extracting an image processing result from the MySQL database, and feeding the result back to the lighting system and the temperature control system; the lighting system judges the on/off of the lighting equipment according to the number of people detection result fed back from the database; a temperature sensor is arranged in a classroom at the same time, the classroom temperature is detected, and the temperature condition is transmitted into a MySQL database of a server in real time through an IPv6 network; the temperature control system extracts the classroom number data and the temperature data from the database and judges the on/off of the temperature adjusting equipment.
As shown in table 1, the database design is as follows: creating a database named class, creating a data table named stu _ db, wherein fields contained in the data table comprise self-increment id, classroom number class _ id, classroom number peo _ num, classroom temperature class _ temp and data update time update _ time. Wherein the field types of id, class _ id and peo _ num are int, the field type of class _ temp is double, and the field type of update _ time is time. And B, setting the IP address of the server, the user name and the password of the database, the name clasbroom of the database and the coding mode of the server by the counted number of people through the python library pymysql, and storing the acquired data INTO a data table stu _ db through an SQL statement INSERT INTO.
Table 1 database design table
As shown in fig. 5, the energy saving system is designed as follows:
(1) the value of field peo _ num is extracted from the stu _ db data table and the result is fed back to the lighting system and the temperature control system.
(2) An illumination system: if the value of peo _ num is greater than 1, indicating that there is a person in the classroom, the lighting system is turned on, and if the value of peo _ num is 0, indicating that there is no person in the classroom, the lighting system remains off.
(3) The classroom is simultaneously provided with a temperature sensor, the classroom temperature is detected, and the temperature condition is transmitted into a field class _ temp in an stu _ db data table in real time.
(4) A temperature control system: the temperature control system extracts the values of field peo _ num and class _ temp from the database, if the value of peo _ num is greater than 1 and the value of class _ temp is higher than a set threshold, the fan is turned on, and if the value is lower than the threshold, the fan is kept off; if the temperature control system detects a value of peo _ num that is less than 1, the fan is turned off and the lighting device is also turned off.
And 4, step 4: and a website named as an intelligent power-saving classroom management platform is created, and the data in the MySQL database can be managed in an initialization mode.
As shown in fig. 6 and 7, the "smart power-saving classroom management platform" website is designed as follows:
(1) the platform comprises a landing page and an intelligent power-saving classroom management platform page.
(2) The website comprises a back-end functional design and a front-end page rendering design, wherein the back-end design is written by adopting a Django framework of python, and the front-end is written by adopting html and css languages.
(3) Designing a landing page: the 'user name' input box, the 'password' input box and the 'login' button are aligned in the middle of the page, and the 'user name' input box and the 'password' input box are arranged in the same length and width. For unregistered users, a registration button is designed on the right side of the login box.
(4) Intelligent power-saving classroom management platform' page design: the left column includes three modules, which are respectively homepage, user information, data statistics, and information search. The home page module displays the visitor number of the current date, the user information module displays the basic information of the user by adopting a table, and the data statistics module displays the change condition of the number of the classroom in one week by adopting a line graph. The classroom number can be fed back by inputting specific time in a search bar of the information search module, and teachers can save the roll call time through the function.
And 5: and (3) performing data analysis on students or teaching workers accessing the website through the IPv6 campus network by adopting an IPv6 address division method based on the Merkle tree. As shown in fig. 8, the specific design is as follows:
(1) information authentication is carried out when equipment of a student or a teaching worker is accessed to an IPv6 campus network for the first time;
(2) dynamically allocating a temporary IPv6 address through the DHCPv6 server;
(3) portal Server provides an authentication page for user, and the user needs to fill in specified related attributes for authentication;
(4) the authentication center obtains the user attribute through the steps e-c to construct a Merkle tree, and the Merkle tree is matched with the Hash value of the user attribute in the database;
(5) the SDN switch distributes an IPv6 address for the terminal equipment according to the result of the step e-d, if the matching is successful, an IPv6 address is distributed for the user according to the tree root of the Merkle tree and is bound with the MAC address of the equipment, if the matching is unsuccessful, the SDN switch is quickly positioned to which attribute is wrongly filled and informs the user that the IPv6 address distribution is failed;
(6) a unique IPv6 address is allocated to each network terminal of the school, and the campus network center performs data analysis on the access conditions of teachers and students in the school according to the method.
The design method provided by the invention has a certain practical value, integrates the IPv6 with the image processing technology, ensures the safety and reliability of the implementation of the image processing technology, has a large address space, is convenient for wide popularization of the technology, is not limited by the shortage of address resources, allocates a unique IP address for each network terminal, binds the IP address with the MAC address of the physical equipment, can realize traceability and is convenient for management. The invention promotes the long-term continuous development of the smart campus, and also widely popularizes and applies the IPv6, thereby promoting the development of the IPv 6. The trained image processing model can be repeated and used for many times, and computing resources are saved.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A design method of an intelligent video monitoring energy-saving system of a teaching building under an IPv6 environment is characterized by comprising the following steps:
(1) constructing an image acquisition module: selecting an intelligent machine learning visual identification camera human face image identification processing sensor module OPENMV4 Cam M7 to perform video monitoring on a classroom and acquire classroom images in real time;
(2) constructing a statistical identification module: preprocessing the acquired image by adopting an improved image super-resolution reconstruction algorithm SRCNN, then identifying the head area of the acquired image by adopting a target detection algorithm FCHD, and counting the identified head area to calculate the number of people;
(3) constructing an energy-saving module: uploading the obtained information of the number of people to a server through an IPv6 network, and storing the processed information of the number of people into a MySQL database through a data processing library pymysql of python; extracting an image processing result from the MySQL database, and feeding the result back to the lighting system and the temperature control system; the lighting system judges the on/off of the lighting equipment according to the number of people detection result fed back from the database; a temperature sensor is arranged in a classroom at the same time, the classroom temperature is detected, and the temperature condition is transmitted into a MySQL database of a server in real time through an IPv6 network; the temperature control system extracts classroom people number data and temperature data from the database and judges the on/off of the temperature adjusting equipment;
(4) establishing an intelligent power-saving classroom management module, and performing initialization management on data in a MySQL database;
(5) and (3) performing data analysis on students or teaching workers accessing the website through the IPv6 campus network by adopting an IPv6 address division method based on the Merkle tree.
2. The design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment according to claim 1, wherein said step (2) includes the steps of:
(21) the acquired image is preprocessed by adopting an improved image super-resolution processing algorithm SRCNN: the SRCNN structure comprises three layers, namely a characteristic extraction layer, a nonlinear mapping layer and a characteristic reconstruction layer, wherein the sizes of filters are respectively 3 multiplied by 9 multiplied by 64, 64 multiplied by 1 multiplied by 35 and 35 multiplied by 5 multiplied by 1; adding a channel attention mechanism into the SRCNN feature extraction layer, and carrying out secondary weighting on the convolution channel; a zero filling method is adopted in the convolution process, and the size of the image is kept unchanged;
(22) adopting an object detection algorithm FCHD to identify a human head region of the acquired image, carrying out feature migration on a VGG16 trained model by the FCHD model, not including the last layer after a conv5 layer, serving as a feature extraction layer, taking the residual weight as the starting point of new model training, outputting the dimension of 40 × 30 × 512, then inputting the result into a (3 × 3 × 512, 512) convolution layer, coding the acquired feature information, dividing the result obtained by the convolution layer into two paths, respectively inputting the two paths into full convolution layers with convolution kernels of (1 × 1 × 512, N × 4) and (1 × 1 × 512, N × 2), respectively, positioning the (1 × 1 × 512, N × 4) full convolution layers for predicting head coordinates, regressing a head, (1 × 1 × 512, N × 2) full convolution layers for predicting the position as a head, classifying the head and a non-head region, wherein N represents the number of marked human heads, the value of N depends on the number of anchor points per pixel location; the two outputs are represented as 40 × 30 × (N × 4) and 40 × 30 × (N × 2), respectively, where × 2 and × 4 represent the anchor point scaling;
an anchor is a set of predefined bounding boxes used for predicting scale and displacement, and the anchor size calculation formula is expressed as:
Anchor size＝S×R×C (3)
wherein S represents a step size, R represents an aspect ratio, and C represents an anchor point scaling ratio; the model defines an anchor aspect ratio of 1:1 with a step size of 16, with anchor scaling ratios of (× 2) and (× 4) corresponding to anchor sizes of 32 × 32 and 64 × 64, respectively;
(23) and taking the preprocessed image data set as the input of the model, outputting the model as a marked picture, and counting the marked head region coordinates to obtain the number of the heads.
3. The design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment according to claim 1, wherein said step (3) includes the steps of:
(31) creating a database named class, creating a data table named stu _ db, wherein fields contained in the data table comprise self-increment id, classroom number class _ id, classroom number peo _ num, classroom temperature class _ temp and data update time update _ time; wherein the field types of id, class _ id and peo _ num are int, the field type of class _ temp is double, and the field type of update _ time is time; the counted number of people sets the IP address of the server, the user name and the password of the database, the name clasbroom of the database and the coding mode through the python library pymysql, and the collected data is stored in a data table stu _ db through an SQL statement INSERT INTO;
(32) extracting the value of the field peo _ num from the stu _ db data table, and feeding the result back to the lighting system and the temperature control system;
(33) an illumination system: if the value of peo _ num is greater than 1, indicating that there is a person in the classroom and turning on the lighting system, and if the value of peo _ num is 0, indicating that there is no person in the classroom and the lighting system remains off;
(34) the classroom is simultaneously provided with a temperature sensor, the classroom temperature is detected, and the temperature condition is transmitted into a field class _ temp in a stu _ db data table in real time;
(35) a temperature control system: the temperature control system extracts the values of the field peo _ num and class _ temp from the database, if the value of peo _ num is greater than 1 and the value of class _ temp is higher than a set threshold, the fan is turned on, and if the value of class _ temp is lower than the threshold, the fan is kept off; if the temperature control system detects a value of peo _ num that is less than 1, the fan is turned off and the lighting device is also turned off.
4. The design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment according to claim 1, wherein said step (4) includes the steps of:
(41) the intelligent power-saving classroom management module comprises a login page and an intelligent power-saving classroom management platform page;
(42) the intelligent power-saving classroom management module comprises a back-end functional design and a front-end page rendering design, wherein the back-end design is compiled by adopting a Django framework of python, and the front-end is compiled by adopting html and css languages;
(43) designing a landing page: the 'user name' input box, the 'password' input box and the 'login' button are aligned in the middle of the page, and the 'user name' input box and the 'password' input box are arranged to have the same length and width; aiming at unregistered users, designing a registration button on the right side of a login box;
(44) designing a smart power-saving classroom management platform page: the left column comprises three modules, namely a homepage, user information, data statistics and information search; the home page module displays the number of visitors on the current date, the user information module displays the basic information of a user by adopting a table, and the data statistics module displays the change condition of the number of classroom persons in a week by adopting a line chart; in the search column of the information search module, the specific time is input, and the number of the classroom people can be fed back.
5. The design method of intelligent video monitoring energy-saving system of teaching building under IPv6 environment of claim 1, wherein step (5) includes the following steps:
(51) information authentication is carried out when equipment of a student or a teaching worker is accessed to an IPv6 campus network for the first time;
(52) dynamically allocating a temporary IPv6 address through the DHCPv6 server;
(53) portal Server provides an authentication page for user, and the user needs to fill in specified related attributes for authentication;
(54) the authentication center obtains the user attribute through the step (53) to construct a Merkle tree, and the Merkle tree is matched with the Hash value of the user attribute in the database;
(55) the SDN switch allocates an IPv6 address for the terminal equipment according to the result of the step (54), if the matching is successful, an IPv6 address is allocated for the user according to the tree root of the Merkle tree and is bound with the MAC address of the equipment, and if the matching is unsuccessful, the SDN switch is quickly positioned to which attribute is wrongly filled and informs the user of the failure of IPv6 address allocation;
(56) a unique IPv6 address is allocated to each network terminal of the school, and the campus network center performs data analysis on the access conditions of teachers and students in the school according to the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011582.3A CN114785834B (en) | 2021-01-06 | 2021-01-06 | Teaching building intelligent video monitoring energy-saving system design method under IPv6 environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011582.3A CN114785834B (en) | 2021-01-06 | 2021-01-06 | Teaching building intelligent video monitoring energy-saving system design method under IPv6 environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114785834A true CN114785834A (en) | 2022-07-22 |
| CN114785834B CN114785834B (en) | 2024-04-09 |
Family
ID=82407665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110011582.3A Active CN114785834B (en) | 2021-01-06 | 2021-01-06 | Teaching building intelligent video monitoring energy-saving system design method under IPv6 environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114785834B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116938986A (en) * | 2023-09-19 | 2023-10-24 | 深圳市爱为物联科技有限公司 | Intelligent campus management method and system based on Internet of things |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013159544A1 (en) * | 2012-04-28 | 2013-10-31 | 华南理工大学 | Schedule-based method and system for managing central air-conditioning end devices in teaching building |
| CN103679592A (en) * | 2013-11-12 | 2014-03-26 | 南京邮电大学 | College classroom perception management system |
| CN203552305U (en) * | 2013-11-12 | 2014-04-16 | 南京邮电大学 | College classroom perception management apparatus |
| CN107479388A (en) * | 2017-09-26 | 2017-12-15 | 西南科技大学 | A kind of classroom central air-conditioning and the energy-saving control system and control method of illumination |
| CN108540586A (en) * | 2018-03-06 | 2018-09-14 | 南京邮电大学 | A kind of addresses campus network IPv6 division methods based on Merkle trees |
| CN109979251A (en) * | 2019-03-02 | 2019-07-05 | 广东新源信息技术有限公司 | A kind of wisdom classroom system based on IPv6 technology |
| CN110390613A (en) * | 2019-04-24 | 2019-10-29 | 南京邮电大学 | A kind of wisdom Teaching Service management system based on IPV6 network |
| CN110503017A (en) * | 2019-08-12 | 2019-11-26 | 北京交通大学 | Wisdom energy conservation occupancy detection system and method based on image procossing |
| CN110889923A (en) * | 2019-11-29 | 2020-03-17 | 南京邮电大学 | Campus intelligent bathroom queuing system based on IPv6 |
| CN111189201A (en) * | 2020-01-15 | 2020-05-22 | 西安建筑科技大学 | Air conditioner prediction control method based on machine vision |
| CN111192200A (en) * | 2020-01-02 | 2020-05-22 | 南京邮电大学 | Image super-resolution reconstruction method based on fusion attention mechanism residual error network |
| CN111191610A (en) * | 2019-12-31 | 2020-05-22 | 河海大学常州校区 | People flow detection and processing method in video monitoring |
-
2021
- 2021-01-06 CN CN202110011582.3A patent/CN114785834B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013159544A1 (en) * | 2012-04-28 | 2013-10-31 | 华南理工大学 | Schedule-based method and system for managing central air-conditioning end devices in teaching building |
| CN103679592A (en) * | 2013-11-12 | 2014-03-26 | 南京邮电大学 | College classroom perception management system |
| CN203552305U (en) * | 2013-11-12 | 2014-04-16 | 南京邮电大学 | College classroom perception management apparatus |
| CN107479388A (en) * | 2017-09-26 | 2017-12-15 | 西南科技大学 | A kind of classroom central air-conditioning and the energy-saving control system and control method of illumination |
| CN108540586A (en) * | 2018-03-06 | 2018-09-14 | 南京邮电大学 | A kind of addresses campus network IPv6 division methods based on Merkle trees |
| CN109979251A (en) * | 2019-03-02 | 2019-07-05 | 广东新源信息技术有限公司 | A kind of wisdom classroom system based on IPv6 technology |
| CN110390613A (en) * | 2019-04-24 | 2019-10-29 | 南京邮电大学 | A kind of wisdom Teaching Service management system based on IPV6 network |
| CN110503017A (en) * | 2019-08-12 | 2019-11-26 | 北京交通大学 | Wisdom energy conservation occupancy detection system and method based on image procossing |
| CN110889923A (en) * | 2019-11-29 | 2020-03-17 | 南京邮电大学 | Campus intelligent bathroom queuing system based on IPv6 |
| CN111191610A (en) * | 2019-12-31 | 2020-05-22 | 河海大学常州校区 | People flow detection and processing method in video monitoring |
| CN111192200A (en) * | 2020-01-02 | 2020-05-22 | 南京邮电大学 | Image super-resolution reconstruction method based on fusion attention mechanism residual error network |
| CN111189201A (en) * | 2020-01-15 | 2020-05-22 | 西安建筑科技大学 | Air conditioner prediction control method based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| CHAO DONG等: "Image Super-Resolution Using Deep Convolutional Networks", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 38, no. 2, pages 295 - 307, XP055559563, DOI: 10.1109/TPAMI.2015.2439281 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116938986A (en) * | 2023-09-19 | 2023-10-24 | 深圳市爱为物联科技有限公司 | Intelligent campus management method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114785834B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697435B (en) | People flow monitoring method and device, storage medium and equipment | |
| CN112562161A (en) | Based on 5G thing networking and AI intelligent entrance guard integrated management system | |
| CN103824053A (en) | Face image gender marking method and face gender detection method | |
| CN109376637A (en) | Passenger number statistical system based on video monitoring image processing | |
| CN106772685A (en) | Similar typhoon matching algorithm and software support system based on Web GIS | |
| CN112132197A (en) | Model training method, image processing method, device, computer equipment and storage medium | |
| CN110019617B (en) | Method and device for determining address identifier, storage medium and electronic device | |
| CN105678476A (en) | Video-based intelligent guidance system and guidance method for self-study room | |
| CN115775085B (en) | Digital twinning-based smart city management method and system | |
| CN107392238A (en) | Outdoor knowledge of plants based on moving-vision search expands learning system | |
| CN110740298A (en) | Distributed classroom discipline behavior detection system, method and medium | |
| CN113255915A (en) | Knowledge distillation method, device, equipment and medium based on structured instance graph | |
| CN109800756A (en) | A kind of text detection recognition methods for the intensive text of Chinese historical document | |
| CN109871812A (en) | A kind of multi-temporal remote sensing image urban vegetation extracting method neural network based | |
| CN114785834B (en) | Teaching building intelligent video monitoring energy-saving system design method under IPv6 environment | |
| CN110866564A (en) | Season classification method, system, electronic device and medium for multiple semi-supervised images | |
| CN115422452A (en) | Smart home control method, device, equipment and storage medium based on big data | |
| CN116684477A (en) | Personalized information accurate pushing method and system based on user portrait | |
| Rodriguez et al. | Appraising daylight changes in window views: systematic procedures for classifying and capturing dynamic outdoor scenes | |
| CN114898460A (en) | Teacher non-verbal behavior detection method based on graph convolution neural network | |
| CN109308584A (en) | A kind of noninductive attendance system and method | |
| CN110135274A (en) | A kind of people flow rate statistical method based on recognition of face | |
| CN109064578A (en) | A kind of attendance system and method based on cloud service | |
| CN115146126A (en) | Artwork display recommendation system based on intelligent cloud platform | |
| CN107895385A (en) | The Forecasting Methodology to individual outdoor images position of sun based on convolutional neural networks |
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 |