KR102426943B1 - Air pollutants ouput and fine dust monitoring Smart CCTV system of road vehicle - Google Patents

Abstract

The present invention relates to a CCTV system for monitoring air pollutant emission and fine dust of a moving vehicle on a road. The present invention relates to the system for monitoring air pollutant emission and fine dust of the moving vehicle, comprising: one or more cameras connected through a network, installed in a certain area, photographing an image and transmitting the photographed image; a lidar sensor part formed in the camera to measure the speed of the vehicle; an image sensor for detecting the image photographed by a lens part of the camera; an image processing means including an image processing unit for receiving a digital signal converted from the image sensor and processing the image, an image collection unit for receiving the processed image signal, compressing the image and storing the compressed image, and an image output port for outputting the image information to an external image display device; a remote control center connected to the plurality of cameras through a wired/wireless network and including an engine server controlling the cameras, a database (DB) server storing the image, a display part displaying the image, and an operation server managing the engine server, the DB server, and the display part; an NVR connected to the image processing means through the network to receive and store the image photographed from the camera, and monitoring and searching the image; a Korea Road Traffic Authority server part connected to the cameraes and the remote control center and having a software device for calculating air pollutant emission of the vehicle; and a monitor for displaying the emission calculated through the software for calculating air pollutant emission. The smart CCTV system records a driving vehicle through CCTV and recognizes vehicle information to calculate an hourly or real-time vehicle operation status and air pollutant emission so as to monitor a fine dust concentration.

Description

Air pollutants ouput and fine dust monitoring Smart CCTV system of road vehicle}

The present invention relates to an emission calculation and fine dust monitoring system of air pollutants (CO, VOC, NOx, PM ₁₀ , PM _2.5 , SOx, NH ₃ , BC) emitted from vehicles moving on the road.

In general, structures such as street lights, traffic lights, and road sign boards have only one purpose and are built on roads and sidewalks, so there is a problem that their utilization is low.

Recently, as a countermeasure against the problem of high concentrations of fine dust and global warming, research and policies are focused on creating a more pleasant global atmospheric environment by reducing air pollutants and greenhouse gases from road vehicles. Air pollutants and carbon dioxide (CO ₂ ) generated from road vehicles are not only health problems such as human respiratory diseases, but also serious problems of global warming.

Therefore, accurate monitoring of exhaust gas from road moving vehicles, which is a major emission source of air pollutants, is very important.

In particular, vehicle exhaust gas is the main culprit of air pollution, and 'emergency reduction measures' are implemented on days when high concentrations of fine dust occur, and some vehicles are restricted from operating with a two-part system. However, the conditions for restrictions such as the vehicle 2 system are determined by the type of vehicle and fuel, the degree of aging, etc. These conditions are only indirect indicators rather than direct information on emissions. It may be different from the exhaust gas emissions from driving.

In addition, policies such as the two-way vehicle system are being promoted only as regional restrictions regardless of road conditions and conditions in the relevant area.

Therefore, it is urgently required to establish a system that accurately monitors air pollutants and concentrations emitted from vehicles running on roads in real time in the field.

Korean Patent Publication No. 2010-0103911 Korean Patent Publication No. 2020-0076115 Korean Patent Publication No. 2021-0082664

Therefore, the present invention records a vehicle traveling through CCTV, stores image data such as vehicle number and speed, and recognizes vehicle information (vehicle type, fuel, year, etc.) Alternatively, it aims to provide a smart CCTV system that monitors air pollutant emissions and fine dust of road moving vehicles that can calculate real-time vehicle operation status and emission of air pollutants and monitor fine dust concentration.

In addition, it is possible to monitor changes in fine dust concentration based on the number of real-time moving vehicles, vehicle model, year, fuel, speed, and fine dust concentration, predict emergency reduction measures according to the situation in advance, and evaluate the effect before and after the implementation of the 2 vehicle system. It aims to provide a smart CCTV system that monitors air pollutant emissions and fine dust of road moving vehicles using artificial intelligence algorithms.

In order to solve this problem, the smart CCTV system for monitoring air pollutant emission and fine dust of a road moving vehicle according to the present invention is formed with a camera that captures and collects an image in the surveillance area and the camera is spaced apart by a certain distance to measure fine dust A fine dust measuring sensor that is formed in the camera and a lidar sensor unit that measures the speed of a vehicle, a DSP unit that digitally processes the surveillance image collected by the camera, and a vehicle in the traffic monitoring image processed by the DSP unit Vehicle number recognition unit for recognizing a number; and a PLC that integrally inputs and outputs the traffic monitoring image by the DSP unit and the vehicle number by the vehicle number recognition unit, provides it to the situation room server, and controls the operation of the control target and applies a control signal. and a situation room server that monitors the real-time image transmitted from the video monitoring device and monitors the amount of change through the fine dust concentration through the fine dust measurement sensor and the video monitoring device, and is connected to the network to display the captured image and vehicle number. The NVR that can receive and store the image, monitor and search the image, and the vehicle number extracted by the vehicle number recognition unit are inquired about the vehicle through the internal vehicle record inquiry DB, and data is transmitted from the fine dust measurement sensor The air pollution emission and concentration calculated from the traffic management corporation server unit and the traffic management corporation server unit, which is connected to the receiving control center and the control center, and has a software device for calculating or measuring the concentration of air pollutants of the vehicle It is characterized in that it includes a monitor to display.

In addition, the lidar sensor unit measures the speed of the vehicle photographed through the camera, and transmits it to the situation room server or the Traffic Management Corporation server unit.

In addition, the traffic management corporation server unit analyzes and outputs the fine dust emission of the vehicle, it is characterized in that it is transmitted to the electric sign board for display.

In addition, it is characterized in that the emission is calculated through the emission calculation software, and the vehicle owner is notified of the emission amount above a certain reference value.

In addition, the situation room server is characterized in that it monitors the change in the concentration of fine dust based on the number of moving vehicles in real time, vehicle model, year, fuel, etc. in conjunction with the traffic management corporation server unit.

The effects of the air pollutant emission and fine dust monitoring smart CCTV system in the road moving vehicle according to the present invention are as follows.

Utilizing advanced image collection management technology, measuring equipment and networks, It is possible to three-dimensionally monitor air pollution from mobile pollution sources by identifying the flow of vehicles and vehicle types.

In addition, it more accurately grasps the trend of fine dust emission and concentration changes before and after the implementation of the fine dust seasonal management system, improves the execution power of the fine dust seasonal management system, and operates the entire region through video data monitored in subdivided regions. It is possible to prevent economic loss and congestion of vehicles caused by enforcing restrictions.

In addition, it can be used as a response data to form a national consensus according to the fine dust reduction policy and the implementation of the seasonal management system, and to draw civic consent to the implementation of active management measures during the period of emergency reduction measures. Therefore, smart CCTV according to the present invention Using the system data, it is possible to more accurately estimate the amount of emissions for mobile pollutants.

In addition, on national expressways and national roads, Through three-dimensional monitoring of mobile pollution sources, the reliability of the national air pollution monitoring network can be improved.

In addition, it can be used to calculate carbon dioxide emissions, a greenhouse gas emitted from roads nationwide in the future, and can contribute to the establishment of carbon-neutral policies.

1 is a block diagram of an image monitoring apparatus;
2 is a conceptual diagram of a smart CCTV system for monitoring air pollutant emissions and fine dust of a road moving vehicle according to the present invention.
Figure 3 is a connection structure diagram of the air pollutant emission software device.
4 is an exemplary view of a screen on which the fine dust management monitoring system is displayed together with an image.
5 is a graph of air pollutant emissions displayed on the monitor.
6 is a view for explaining the operation relationship of the air pollutant emission of the vehicle and the fine dust monitoring system according to the present invention.
7 is a flowchart of a monitoring method using a smart CCTV system for monitoring air pollutant emissions and fine dust of a road moving vehicle.
8 is a flowchart illustrating a method of recognizing a license plate.
9 is a block diagram of a real-time fine dust monitoring system.
10 is a block diagram of an artificial intelligence module.
11 is a flowchart of a method for monitoring fine dust in real time.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. First, in adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are marked on different drawings.

In addition, in the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

In addition, since the terms used in the present application are only used to describe specific embodiments, it is not intended to limit the present invention, and the singular expression means a plural expression unless the context clearly indicates otherwise. we want to leave

1 is a conceptual diagram of a smart CCTV system for monitoring air pollutant emission and fine dust of a road moving vehicle according to the present invention, FIG. 2 is a connection structure diagram of an air pollutant emission software device, and FIG. 3 is data in a graph format on a video screen It is an exemplary view of a screen on which a trend is displayed together with an image, FIG. 4 is an exemplary view of a screen on which the fine dust management monitoring system is displayed with an image, and FIG. 5 is a graph of air pollutant emission displayed on the monitor, , FIG. 6 is a view for explaining the operation relationship of the air pollutant emission and fine dust monitoring system of a vehicle according to the present invention, and FIG. 7 is a monitoring using a smart CCTV system for monitoring air pollutant emission and fine dust of a road moving vehicle It is a flowchart of the method, FIG. 8 is a flowchart explaining a method of recognizing a license plate, FIG. 9 is a configuration diagram of a real-time fine dust monitoring system, FIG. 10 is a configuration diagram of an artificial intelligence module, and FIG. 11 is a diagram of real-time fine dust It is a flow chart of the method of monitoring.

Hereinafter, with reference to the drawings, the configuration and operation of the smart CCTV system for monitoring air pollutant emissions and fine dust of a road moving vehicle according to the present invention will be described. First, the image monitoring apparatus 100 will be described.

As shown in FIG. 1 , the configuration of the image monitoring device 100 includes a camera 10 that captures and collects images of a monitoring area such as a road. The camera 10 is connected through a network, is installed in a certain area, is formed of one or more that shoots an image and transmits the captured image. In addition, the camera 10 is installed in a plurality of may also be installed in several locations in the monitoring area.

The camera 10 acquires the monitoring target information of the area desired by the manager by shooting a traffic monitoring image of the traffic monitoring area designated in advance through the manager. Then, the camera 10 transmits the captured image of the traffic monitoring area to the DSP unit 40 to be described later so that it can be processed as a monitoring image to be provided to the situation room server 110 .

The fine dust measuring sensor 20 is formed to be spaced apart from the camera 10 by a predetermined distance to measure fine dust and extract the data. In addition, it is possible to measure the concentration of fine dust in real time. For reference, the fine dust sensor 20 is formed and is used to measure fine dust. The simple measuring device, which is the fine dust sensor 20, is an excellent product that has received the first grade performance certification by the Ministry of Environment, and minimizes the concentration of fine dust. Real-time measurement within 1 minute.

The lidar sensor unit 30 is formed in the camera 10 , and the lidar sensor unit 30 measures the speed of the vehicle photographed through the camera 10 , and the situation room server 110 or traffic It serves to transmit to the management corporation server unit (140).

The lidar sensor unit 30 is literally composed of a lidar sensor, and the lidar is a radar system that emits a laser pulse and measures the time it takes to reflect and return to measure the position coordinates of the reflector. , aerial or satellite-mounted, used for terrain surveying, and also used in speed guns, autonomous mobile robots, and autonomous vehicles. That is, the vehicle speed is calculated through the time measured during the moving distance.

Therefore, it is possible to detect the speed of the vehicle using the lidar sensor unit 30, and exhaust gas emission by utilizing the emission calculation algorithm device (S) of the traffic management corporation server unit 140, which will be described later, for the detected speed. It is possible to display the speed on the graph described.

The DSP unit 40 digitally processes the image of the traffic monitoring area captured by the camera 10 to generate the above-described monitoring image, thereby providing vehicle image information for traffic information control.

Therefore, as a result of the comparison, the DSP unit 40 processes the image information of a vehicle traveling on a road on which the current camera 10 is installed in high quality through a preset viewport, and performs processing with the background image except for the viewport. By processing the object in low quality, it is provided to the license plate recognition unit 50 . For reference, the viewport is a port for transmitting information, and when an event to collect image information occurs, it means a display area for transmitting information through the port.

Accordingly, through this, the DSP unit 40 flexibly determines the image quality so that the vehicle image information can be transmitted with an optimized traffic amount. And, when vehicle image information is generated in this way, it is integrally input to the PLC controller 60 like other various types of sensing information.

The vehicle number recognition unit 50 recognizes the vehicle number of a vehicle traveling on a corresponding road.

Briefly describing a method of recognizing a vehicle number through the vehicle number recognition unit 50, by extracting a feature (feature) of a moving vehicle through a surveillance image of a road, the vehicle is recognized through the vehicle feature And, by applying a deep learning algorithm learned as a sample character of the license plate in the recognized vehicle, the license plate number is recognized as a character.

That is, by extracting the features of the vehicle through the surveillance image of the road, recognizing the vehicle through the features (features) of the vehicle, and applying a deep learning algorithm learned from the recognized vehicle as a sample character of the license plate to the vehicle number is a method of character recognition. Furthermore, it has a function of extracting the data of the license plate from the photographed image of the license plate.

The vehicle number recognition unit 50 recognizes the vehicle number to be controlled from the traffic monitoring image processed by the DSP unit 40 . The vehicle feature metadata is extracted by comparing the current vehicle image information of the image quality processed for each view port with the vehicle feature metadata set in advance (data information that collects only the features to use the data efficiently), and such vehicle feature metadata is extracted. Extracting the overall vehicle features from the data.

The vehicle number recognition unit 50 recognizes a vehicle by applying a preset AI format to the extracted vehicle features to estimate the size and location of the entire vehicle from the vehicle features. That is, by using the AI format, it is possible to estimate the overall size and location of each vehicle for a plurality of different vehicle features and combine them to estimate the overall size and location of the vehicle.

Next, the license plate recognition unit 50 classifies the license plate by using the license plate shape feature set in advance in the vehicle thus recognized. So, the license plate is recognized as a character by applying a deep learning algorithm learned as a sample character of the license plate to these classified license plates.

Therefore, it does not require RAW data from the camera, so it is possible to monitor the driving image of the vehicle for which the license plate is recognized at any time, for example, to recognize all the license plates of a vehicle passing through multiple lanes.

When such vehicle number information is recognized, it is integrally input to the PLC 60 like other various types of detection information.

The PLC 60 integrates input/output processing of the traffic monitoring image by the DSP unit 40 and the vehicle number by the vehicle number recognition unit 50, and provides it to the situation room server 110, and controls the operation of the control target. It controls and applies a control signal.

Hereinafter, components related to the image monitoring apparatus 100 will be described with reference to FIG. 2 .

The situation room server 110 receives real-time image information and the extracted vehicle number and measurement data of the fine dust measurement sensor 20 from the camera 10 of the image monitoring device 100, and monitors the transmitted real-time image, The extracted vehicle number is converted into information by inquiring the vehicle model, year, fuel, etc. of the vehicle through the vehicle registration inquiry server (not shown).

In addition, the situation room server 110 monitors the change in the concentration of fine dust based on the real-time fine dust concentration from the fine dust measurement sensor 20, and the number of moving vehicles, vehicle types, and It is to monitor and evaluate the current status of emissions by fuel. Therefore, the emergency reduction measures according to the situation are predicted in advance.

Furthermore, the situation room server 110 also monitors the calculation of air pollutant emissions and changes in fine dust concentration based on the number of moving vehicles in real time, vehicle model, year, fuel, etc. in conjunction with the Traffic Management Corporation server 140 to be described later. and exchange of relevant information.

In addition, the NVR 120 is connected to the network by wire or wireless, and the NVR 120 is an abbreviation of Network Video Recorder. is transmitted and stored, and there is an effect of monitoring and searching for the video that the party wants to find.

As shown, the NVR 120 is connected to the camera 10 and the control center 130 through a network to receive and store the images captured by the camera 10, and to monitor and search the captured images from time to time. can At least one image display device (not shown) is installed in the NVR 120 .

Hereinafter, a relationship between the camera 10 and the control center 130 interconnected by a network will be described. Additionally, it is preferable that the remote control center 130 and the camera 10 be formed to be connected to the communication unit 90 through a network to enable mutual signal transmission.

The control center 130 serves as a wired/wireless network-based operation server, which converts images into a database and issues an image storage command to a DB server (not shown).

The DB server serves to store images captured by the camera 10 . Therefore, it is possible to retrieve the recorded video later and replay it again. In addition, the control center 130 inquires the vehicle number extracted by the vehicle number recognition unit 50 through an internal vehicle record inquiry DB (not shown) to make it information, and data h from the fine dust measurement sensor 20 get sent

In addition, the control center 130 monitors and digitizes the state of the minimum minute by linking with real-time measured values based on vehicle information such as the vehicle model and year, etc. Operate software that can be visualized.

In addition, the system according to an embodiment of the present invention is characterized in that it interworks with the Traffic Management Corporation server unit 140 , and the Traffic Management Corporation server unit 140 is also connected with the camera 50 and the control center 130 . It is characterized in that the software (S) that calculates the emission through the vehicle type, vehicle fuel, vehicle year, and vehicle speed is formed from the vehicle of the image captured by the camera 10 and can measure the concentration and emission. .

That is, the traffic management corporation server unit 140 receives the vehicle speed information from the lidar sensor unit 30, analyzes and outputs the fine dust and air pollutant emissions of the vehicle, and outputs the It is transmitted to the display board 160 for display.

It is to calculate and analyze the emission data and/or concentration of the corresponding vehicle photographed by the camera 10 through the emission calculation software device S stored in the traffic management corporation server 140 .

And, by acquiring vehicle information (car model, fuel, year, etc.) through communication between the camera 10 and the Traffic Management Corporation server unit 140 , the real-time or hourly vehicle operation status is also identified.

The monitor 150 displays the amount and/or concentration calculated through the air pollutant emission calculation software device S of the traffic management corporation server 140 as a graph or the like on a screen.

Hereinafter, the configuration and operation of the traffic management corporation server unit 140 and the air pollutant emission calculation software device (S) of the vehicle will be described with accompanying drawings.

As shown in FIG. 3 , the emission calculation software device (S) includes a communication unit 11 that is connected to the traffic management corporation server unit 140 by communication, a storage unit 13 that stores information on the emission amount, and the emission amount. It includes a calculation unit 15 for calculating and calculating.

Then, the calculation unit 15 calculates and calculates the amount of emission using vehicle information and the like.

Hereinafter, a description will be given of a method of calculating the amount of air pollutant emission in the calculator 15 .

First, the emission factor that calculates air pollutants is made through the type of vehicle (for example, large, medium, and small in the case of a passenger car), the fuel of the vehicle (diesel, gasoline, LPG, hybrid, etc.), the year of the vehicle, and the vehicle speed. .

When the speed and vehicle number are transmitted through the image of the vehicle photographed by the camera 10, the calculation unit 15 calculates an emission factor based on the above-mentioned vehicle model, vehicle fuel type, vehicle year, and vehicle speed of the vehicle. do. That is, the emission of air pollutants is calculated using the emission coefficient.

In other words, the camera 10 detects the vehicle number and speed, communicates with the traffic management corporation server 140 and the communication unit 11 through the communication unit 11 to recognize what type of vehicle the corresponding vehicle is, To calculate the emission factor through the type, year, and speed, and to calculate the emission of pollutants with the emission factor.

The discharge amount of the air pollutant is E _i,j . The formula for calculating the discharge amount (E _i,j ) is as follows.

E _{i, j} = VKT × EF _It's /1,000 × DF × (1-R/100)

E _{i,j :} Contaminants generated by vehicle j driving on the road _It's of emissions (kg/yr)

VKT : Mileage (km/yr)

EF _i: Emission factor by vehicle type, fuel, year, and vehicle speed (g/km)

DF : deterioration coefficient

R : Reduction device attachment efficiency (%)

As described above, when the emission of vehicle air pollutants is calculated and sensed, the NVR 120, which is a device for clearly storing an image of a vehicle emitting vehicle air pollutants, is required.

Referring to FIG. 4 , it is an exemplary view of a screen on which the fine dust management monitoring system is displayed on the monitor 150 together with an image.

In addition, the monitor 150 capable of displaying the exhaust gas emission amount of the monitored vehicle is formed, and as shown in FIG. 5 , the exhaust gas emission amount through the monitor 150 is shown in a graph.

Hereinafter, with reference to FIG. 6 , the operating relationship of the exhaust gas emission of the vehicle and the fine dust monitoring system will be described.

6 shows that the vehicle speed of the lidar sensor unit 30 of the camera 10 is detected to detect a vehicle with excessive vehicle emissions, and the number and image of the vehicle are extracted through the camera 10 . This is to notify the number of the corresponding vehicle of the number to the traffic management corporation server unit 140. The emission calculation of the vehicle number of the corresponding vehicle is obtained by using the software device (S).

Then, the amount of emissions is calculated and extracted through the traffic management corporation server unit 140, and with respect to a vehicle over a certain reference value, the vehicle owner is notified of this through a transmission means such as a text message, e-mail, Kakao Talk, and the like.

The above notification is, for example, "Your vehicle is a vehicle that emits excessive amounts of emissions, and our Korea Transportation Management Corporation has confirmed it, so please drive your vehicle with caution." It is possible to request and recommend the self-weight of the vehicle to the owner (or driver) of the vehicle.

In addition, the image of the vehicle taken through the camera 10 and the image through the NVR 120 are stored through the fine dust sensor 20 that detects fine dust of the vehicle, and the image is displayed in the NVR 120 . express

Then, the traffic management corporation server unit 140 analyzes and outputs the fine dust emission of the vehicle, and the result is displayed through the monitor 150 .

In this way, the content displayed on the monitor 150 is transmitted to the electric sign 160 connected to the monitor 150 to express it.

Hereinafter, with reference to the drawings, a method of extracting and recognizing a vehicle number through the fine dust monitoring system according to the present invention to calculate the amount of moving pollution and the amount of emission will be described.

Referring to FIG. 7 , an image of a vehicle traveling in a corresponding area is photographed through the camera 10 , and the related image and measurement data through the fine dust measurement sensor 20 are transmitted to the situation room server 110 (first step).

By setting an arbitrary lane as a shooting area, fine dust emission data of a vehicle traveling on multiple lanes is monitored. Accordingly, the camera 10 and the fine dust measuring sensor 20 are interlocked with each other.

Furthermore, the camera 10 digitally processes the monitoring image captured in this way through the DSP unit 40 to generate a monitoring image for controlling traffic information in the control center 130, so that for the control of traffic information It is also provided as vehicle image information.

Then, the image transmitted from the situation room server 110 is monitored in real time, and a vehicle number having a high measurement data such as fine dust is extracted (step 2).

Hereinafter, a method of extracting a vehicle number in the second step will be described with reference to the drawings.

Referring to FIG. 8 , the DSP unit 40 monitors the amount of fine dust, etc. of the vehicle in the image monitored by the camera 10 ( S1 ).

So, as a result of the monitoring, if the current vehicle image information is higher than the preset fine dust emission risk (S2), the DSP unit 40 processes it in high quality through the preset prediction viewport (S3), and the prediction By processing the remaining background images and objects except for the viewport in low quality (S4), the traffic monitoring image is provided to the control center 130.

Accordingly, through this, the DSP unit 40 flexibly determines the image quality so that the vehicle image information can be transmitted with an optimized amount of traffic.

Next, the vehicle number recognition unit 130 compares vehicle image information in the thus-processed traffic monitoring image with preset vehicle feature metadata to extract vehicle feature metadata while driving (S5).

In this case, the vehicle feature metadata means, for example, metadata representing attributes or characteristics of a vehicle.

Then, the entire vehicle features are extracted from the thus extracted vehicle feature metadata (S6). When extracting these vehicle features, for example, a deep learning cluster is applied. The deep learning cluster extracts characteristic information for vehicle recognition for recognition from a vehicle. The extracted feature information for vehicle recognition is stored in the learned model big data storage unit. The characteristic information for vehicle recognition extracted by such a deep learning cluster includes, for example, an image name (eg, image frame information and time), an image including a vehicle number, the type of vehicle, the color of the vehicle, etc. may have been

Next, a vehicle is recognized by applying a preset AI format for estimating the size and location of the entire vehicle from the vehicle features to the extracted vehicle features (S7). In this case, the AI format is, for example, a YOLO format. More specifically, the YOLO format is made by estimating the overall size and location of the vehicle by estimating and combining the overall size and location of each vehicle for a plurality of different vehicle features.

Next, the license plate is classified using the preset shape feature of the license plate in the recognized vehicle (S8). For the license plate classified in this way, the license plate is recognized as a character by applying a deep learning algorithm learned as a sample character of the license plate (S9).

That is, by first recognizing the character information included in the license plate through a deep learning algorithm learned from the sample characters of the license plate, the license plate number is determined. In this case, the deep learning algorithm may recognize the character of the character and analyze the character to recognize character information. The deep learning algorithm module modulates one or more deep learning algorithms, such as a deep neural network, a convolutional neural network, and a recurrent neural network, and applies them. This is to apply the optimized algorithm among the deep learning algorithms as described above according to the characteristics of the character.

The deep learning algorithm module applies a deep neural network, a convolutional neural network, and a recurrent neural network alone or in combination according to preset criteria. For example, the deep learning algorithm module applies any one of the preceding neural networks alone when text is the main object, and complexly applies the neural network when not only text but also additional information such as color and shading are the main object. .

Next, referring to FIG. 7 again, the vehicle license plate is recognized and extracted through the processes of S1 to S9, and the vehicle model, model year, fuel, etc. are inquired through the vehicle identification server DB (not shown) to be informatized. and save it (step 3).

The vehicle tracking server DB can check the enforcement time, site name, lane, and vehicle number through the stored image, and stores the data generated by the image and number recognition enforcement information of the enforcement vehicle, the location name, and system environment setting data.

In addition, the situation room server 110 monitors the amount of change in the concentration of fine dust based on the real-time number of moving vehicles, year, fine dust concentration, etc., and predicts emergency reduction measures according to the situation in advance.

Next, the emission is calculated and extracted through the exhaust gas emission calculation software (S) of the Traffic Management Corporation server unit 140, and for vehicles above a certain standard value, a text message, e-mail, This is notified by means of transmission such as Kakao Talk (Step 4).

Hereinafter, a system and method for monitoring fine dust in real time using artificial intelligence will be described with reference to the drawings.

Referring to FIG. 9 , the real-time fine dust monitoring system includes a measuring device 200 , a management server 300 , a mapping module 400 , and an artificial intelligence module 500 .

The measuring device 200 is attached to a mobile means of transportation such as a taxi, a bus, a postal/delivery vehicle, and a passenger car, and a measuring unit 210 that measures the concentration of fine dust every 5 to 10 seconds, and a GPS 220 that collects location information ), a communication unit 230 for transmitting fine dust measurement information including the fine dust concentration and location information to the management server 300 at intervals of 10 to 15 minutes, a power supply unit 240 and a control unit 250 for supplying power ) is included.

The measurement unit 210 measures fine dust at a specific location, the GPS 220 collects location information for classifying and storing the fine dust measurement information by location, and the communication unit 230 collects the fine dust The measurement information is transmitted to the management server 300 , the power supply unit 240 supplies operating power used by the measurement device 200 , and the control unit 250 measures and collects the measurement information by the measurement device 200 . It controls the digital data of the fine dust measurement value, and controls the transmission of the digital dataized fine dust measurement information to the management server 300 .

In addition, it is preferable that the measuring device 200 for measuring fine dust measures air quality while moving in an outdoor environment and is designed to minimize air resistance.

The management server 300 receives fine dust measurement information from the measuring device 200 every 10 to 15 minutes, and stores the fine dust concentration by location based on the fine dust measurement information to build a DB (database) do.

The mapping module 400 forms a two-dimensional or three-dimensional fine dust map by combining and interworking with geographic information system data including latitude and longitude based on the DB of the management server 300 . do.

The mapping module 400 receives the DB from the management server 300, and combines and interworks with geographic information system (GIS) data including latitude and longitude based on the DB to create a two-dimensional or three-dimensional fine dust map ( not shown) is formed. In this case, the geographic information system is preferably a complex geographic information system in which topographic information such as a general map and related information such as underground facilities can be collected with artificial satellites, written on a computer, and searched and analyzed.

Accordingly, the mapping module 400 displays the distribution status of the actual fine dust concentration measured by the measuring device 200 on the map of the geographic information system by location on the map of the geographic information system and expresses it as an image. .

The artificial intelligence module 500 analyzes the image of the fine dust app processed by the mapping module 400, which will be described below with reference to the drawings.

Referring to FIG. 10 , the artificial intelligence module 500 may include a data learning unit 510 and a data analysis unit 520 . The data learning unit 510 may include a deep-learning framework, and accordingly, a neural network algorithm such as a convolutional neural network (CNN) and a vision algorithm such as a scale invariant feature transform (SIFT) may be performed.

The data learning unit 510 may learn various image analysis criteria, such as object/pattern recognition and similarity check of objects. The data learning unit 510 may learn and inferencing criteria regarding which data to use for image analysis.

The data learning unit 510 may acquire data to be used for learning, and apply the acquired data to a data analysis model to learn a criterion for image analysis.

The data analyzer 520 may analyze an input image in response to a request from a control module (not shown). The data analyzer 520 may perform image analysis using the learned data recognition model.

In addition, the data analysis unit 520 acquires data according to criteria set by learning, performs image analysis by using a data analysis model using the acquired data as an input value, and outputs result information according to the analysis can do. In addition, the result information of the image analysis may be used to update the data analysis model.

Therefore, it is possible to analyze the image of the fine dust app processed by the mapping module 400 using artificial intelligence through the artificial intelligence module 500 .

Hereinafter, a method of real-time monitoring of fine dust will be described with reference to FIG. 11 . A description that overlaps with the description of the system described above will be omitted. As shown, S10 measures the fine dust concentration at intervals of 5 to 10 seconds through a measuring device 200 attached to a mobile means of transportation including a taxi, a bus, and a postal/delivery vehicle, and the measuring device 200 By collecting location information with the built-in GPS 220, fine dust measurement information including the fine dust concentration and location information is collected.

S20 builds a DB by classifying the fine dust concentration by location based on the location information and storing it in the management server 300 at intervals of 10 to 15 minutes.

S30 forms a fine dust map indicating the distribution status of fine dust by location through the mapping module 400 based on the DB of the management server 300 .

S40 is an image analysis of the fine dust map through the artificial intelligence module 500 based on the DB.

At this time, the S40 reflects environmental information including temperature, climate, humidity, wind speed, air volume, altitude, etc. in the DB accumulated in the management server 300, and the fine dust analyzed through the S40 in units of 4 to 6 hours The map is provided to a user terminal (not shown) in a mobile or web-included form.

Those skilled in the art to which the present invention pertains as described above will understand that the present invention may be implemented in other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it should be understood that the above-described embodiments are illustrative and not restrictive.

The scope of the present invention is indicated by the appended claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

10: camera 11: communication unit 13: storage unit 15: calculation unit 20: fine dust measuring sensor 30: lidar sensor unit
40: DSP unit 50: vehicle number recognition unit
60: PLC 100: video monitoring device
110: control room server 120: NVR
130: Control Center 140: Traffic Management Corporation Server Department
150: monitor 160: electric sign
200: measuring device S: exhaust gas emission calculation software device
210: measurement unit 220: GPS
230: communication unit 240: power unit
250: control unit 300: management unit 400: mapping module 500: artificial intelligence module 510: data learning unit 520: data analysis unit

Claims (5)

In the smart CCTV system for monitoring air pollutant emissions and fine dust of road moving vehicles,
a camera that captures and collects images of a certain monitoring area;
a fine dust measuring sensor that is formed and spaced apart from the camera by a certain distance to measure fine dust;
a lidar sensor unit formed in the camera to measure the speed of the vehicle;
DSP unit for digital signal processing the surveillance image collected by the camera;
a vehicle number recognition unit for recognizing a vehicle number to be controlled from the traffic monitoring image processed by the DSP unit; and
A video monitoring device comprising a; a PLC for integrating the input/output processing of the traffic monitoring image by the DSP unit and the vehicle number by the vehicle number recognition unit, providing it to the situation room server, and controlling the operation of the control target and applying the control signal; ;
a situation room server that monitors the real-time image transmitted from the image monitoring device and monitors the amount of change through the fine dust concentration through the fine dust measurement sensor;
an NVR connected to the camera and a network to receive and store the captured image and vehicle number, and to monitor and search for the image;
a control center that inquires and informationizes the vehicle number extracted by the vehicle number recognition unit through an internal vehicle registration DB, and receives data from the fine dust measurement sensor;
a traffic management corporation server unit connected to the control center and provided with a software device for calculating the emission amount or measuring the concentration of air pollutants of the vehicle;
Including a monitor for displaying the air pollution emission and concentration calculated from the traffic management corporation server unit,

The emission calculation software device includes a communication unit connected by communication with the traffic management corporation server unit, a storage unit for storing information on the emission amount, and a calculation unit for calculating and calculating the emission amount,
The calculation unit calculates the emission amount by using the information of the vehicle,
The method of calculating the emission of the calculator is
When the speed and vehicle number are transmitted to the calculation unit through the image of the vehicle captured by the camera, the calculation unit calculates an emission factor using the vehicle model, vehicle fuel type, vehicle year, and vehicle speed of the vehicle to calculate air pollutants Air pollutant emission and fine dust monitoring smart CCTV system of road moving vehicles, characterized in that the emission (E _i,j ) is calculated as follows.
(ceremony)
E _i,j = VKT × EF _i /1,000 × DF × (1-R/100)
E _{i,j :} Emissions of pollutant _i generated during road driving of car j (kg/yr)
VKT : Mileage (km/yr)
EF _{i :} Emission factor by vehicle type, fuel, year, and vehicle speed (g/km)
DF : deterioration coefficient
R : Reduction device attachment efficiency (%)
According to claim 1,
The lidar sensor unit
A smart CCTV system for monitoring air pollutant emissions and fine dust of road moving vehicles, characterized in that the speed of the vehicle photographed through the camera is measured and transmitted to the situation room server or the Traffic Management Corporation server unit.
3. The method of claim 1 or 2,
The Traffic Management Corporation server unit analyzes and outputs the fine dust emission of the vehicle, and transmits it to an electric signboard for display. Air pollutant emission and fine dust monitoring smart CCTV system of a road moving vehicle.
According to claim 1,
Air pollutant emission and fine dust monitoring smart CCTV system of road moving vehicles, characterized in that the emission is calculated through the emission calculation software device, and the emission amount is above a certain standard value and notifies the vehicle owner.
According to claim 1,
The situation room server interworks with the traffic management corporation server unit to monitor air pollutant emission and fine dust monitoring of road moving vehicles, characterized in that it monitors the amount of change in the concentration of fine dust based on the number of moving vehicles, vehicle model, year, fuel, etc. in real time Smart CCTV system.

Images