KR20220112590A - Artificial Intelligence-based Water Quality Contaminant Monitoring System and Method - Google Patents

Abstract

Disclosed are an artificial intelligence-based water quality pollution source monitoring system and method. According to one embodiment of the present invention, the artificial intelligence-based water quality pollution source monitoring method implemented through a computer device may comprise: a step of generating input data by using at least any one of RGB, multiple spectroscopy, and thermal infrared images of an area to be monitored; a step of analyzing information on a type or state of a pollution source by inputting the input data to a trained image deep learning neural network; and a step of displaying information on the type or state of the pollution source by using location information of an image to monitor the pollution source.

Description

Artificial Intelligence-based Water Quality Contaminant Monitoring System and Method}

The following embodiments relate to an artificial intelligence-based water pollution source monitoring system and method, and more particularly, to an artificial intelligence-based water pollution source monitoring system and method for determining the type and information of a pollution source based on image deep learning.

Non-point pollution sources refer to sources that discharge water pollutants in unspecified places such as cities, roads, farmland, mountain areas, and construction sites. Point sources (點汚染源) are easy to collect because the discharge route of pollutants is clear, and the amount of pollutants generated throughout the year can be predicted because the seasonal influence is relatively small, making it easy to design and maintain/manage treatment facilities such as conduits and treatment plants. On the other hand, non-point source pollutants are difficult to collect because the outflow and discharge routes of pollutants are not clearly separated, and since the amount/discharge is greatly dependent on weather conditions such as precipitation, design and maintenance of treatment facilities is difficult. In addition, non-point pollution sources that generate a load due to rainwater runoff have various sources and transport processes, so management methods are diverse, and it is very difficult to treat them simply like point sources. Therefore, it is impossible to treat the initial rainwater to the level of sewage treatment, and it is difficult to control the treatment using any one treatment method.

Currently, the government is promoting step-by-step measures against nonpoint pollution sources as a long-term plan. Specifically, laws and regulations for the management of non-point pollution sources are prepared, the management duties of non-point pollution sources are imposed on major business sites, and development and maintenance projects that reflect management measures are being implemented, and a project to monitor non-point pollution sources is being promoted. Therefore, it is urgent to develop a technology that can manage and monitor various types of nonpoint pollution sources distributed locally in a vast area.

Korean Patent No. 10-1659433 relates to such a river pollution management system and its operation method, and it analyzes the concentration behind the point and nonpoint pollution sources flowing into urban rivers and evaluates the pollution degree, and investigates and analyzes pollution source attribute data and geospatial information. technology that utilizes the convergence monitoring technique of

Korean Patent No. 10-1659433

The embodiments describe an artificial intelligence-based water pollution source monitoring system and method, and more specifically, provide a technology for determining the type and information of a pollution source based on image deep learning.

Embodiments are to provide an artificial intelligence-based water pollution source monitoring system and method for automatically determining a pollution source through an image deep learning neural network that is learned by matching RGB, multispectral, and thermal infrared images individually or by matching.

In addition, embodiments provide an artificial intelligence-based water pollution source monitoring system and method that can minimize monitoring manpower consumption through an algorithm that autonomously flies over a wide area by designing autonomous flight of a drone based on the location of a pollution source.

An artificial intelligence-based water pollution source monitoring method implemented through a computer device according to an embodiment includes generating input data using at least one image of RGB, multi-spectral and thermal infrared of a monitoring target area; inputting the input data into a learned image deep learning neural network to analyze information on a type or state of a pollutant; and displaying information on the type or state of the pollution source by using the location information of the image to monitor the pollution source.

The method may further include acquiring an image of at least one of RGB, multispectral, and thermal infrared for a pollution source through setting of an autonomous flight path of the drone, and the input data may be generated using the image.

In the acquiring of the image, the image of the monitoring target area is captured by RGB, multi-spectral and thermal infrared according to the setting of the autonomous flight path of the drone, and then converted into an orthographic image through image processing, and the input data is generated In the orthogonal image, input data may be formed using RGB, multi-spectral and thermal infrared images of regions suspected of contamination.

The acquiring of the image may include: acquiring an RGB image by moving the drone while scanning the monitoring area at an altitude of a predetermined height; confirming the presence or absence of a contamination source through object detection in the RGB image; when a pollution source is detected through the object detection, setting a flight route so that the drone intensively captures an area in which the pollution source is detected; and the drone moves according to the set flight path and intensively captures at least one image of RGB, multi-spectral and thermal infrared rays.

In the intensive photographing, the drone may acquire images from different viewpoints by intensively photographing by changing at least one setting of a position, an angle, and a focusing.

In the displaying of the information on the type or state of the pollutant, the information on the type or state of the pollutant may be matched to the ortho image and displayed to monitor the non-point pollution source.

generating learning data by combining at least one image of RGB, multi-spectral, and thermal infrared of a pollutant source and a label for each type of pollutant; and training the image deep learning neural network using the generated training data.

The training of the image deep learning neural network may include: inputting the generated training data into the image deep learning neural network to classify a type of pollutant into an image; and identifying the state of each of the classified pollutants through image segmentation.

The image deep learning neural network can be configured by learning RGB, multispectral and thermal infrared images as one matched image, or by learning RGB, multispectral and thermal infrared images individually and finally combining them. .

An artificial intelligence-based water pollution source monitoring system according to another embodiment includes: an input data generator for generating input data using at least one image of RGB, multi-spectral, and thermal infrared of a monitoring target area; an analysis and analysis unit for inputting the input data into a learned image deep learning neural network and analyzing information on a type or state of a pollutant; and an information display unit for displaying information on the type or state of the pollution source by using the location information of the image to monitor the pollution source.

The drone may further include an image collector configured to acquire at least one image of RGB, multispectral, and thermal infrared for a pollution source through setting of an autonomous flight path of the drone, and may generate the input data using the image.

The image collection unit, after taking an image of the monitoring target area in RGB, multi-spectral and thermal infrared according to the setting of the autonomous flight path of the drone, converts it into an orthographic image through image processing, and the input data generating unit, Input data can be formed using RGB, multispectral, and thermal infrared images of regions suspected of contamination in the image.

The image collection unit, the drone moves while scanning the monitoring area at a predetermined height, acquires an RGB image, checks the RGB image for the presence of a contamination source through object detection, and then through the object detection When a pollution source is detected, a flight path is set so that the drone intensively captures the area where the pollution source is detected, and the drone moves according to the set flight path, and at least one image of RGB, multi-spectral and thermal infrared is displayed. You can focus on shooting.

The image collecting unit may acquire images from different viewpoints by intensively photographing the drone by changing at least one setting of a position, an angle, and a focusing.

A model for generating training data by combining at least any one or more images of RGB, multispectral, and thermal infrared image of a pollutant and a label for each type of pollutant, and using the generated training data to train the image deep learning neural network It may further include a learning unit.

According to embodiments, it is possible to provide an artificial intelligence-based water pollution source monitoring system and method for automatically determining a pollution source through an image deep learning neural network that is learned by individually or matching RGB, multispectral, and thermal infrared images.

In addition, according to embodiments, it is possible to provide an artificial intelligence-based water pollution source monitoring system and method that can minimize monitoring manpower consumption through an algorithm that autonomously flies over a wide area by designing autonomous flight of a drone based on the location of a pollution source. have.

1 is a block diagram for explaining an example of an internal configuration of a computer device (system) according to an embodiment.
2 is a diagram for explaining a learning method of an image deep learning neural network according to an embodiment.
3 is a block diagram illustrating a water pollution source monitoring system according to an embodiment.
4 is a flowchart illustrating a method for monitoring a water pollution source according to an embodiment.
5 is a diagram illustrating an example of performing basic learning and reinforcement learning of an image deep learning neural network according to an embodiment.
6 is a diagram illustrating an example of detecting a pollutant in an image deep learning neural network according to an embodiment.
7 is a diagram illustrating an example of a heat map and cluster distribution according to an embodiment.
8 is a diagram illustrating an example of a module structure for detecting yard compost according to an embodiment.
9 shows an example of a result of detecting open compost according to an embodiment. As shown in FIG. 9 , it is possible to monitor the result of the detection of yard compost by displaying it on the image.
10 is a diagram for explaining a method of constructing learning data using a drone according to an embodiment.
11 is a diagram for explaining a method for improving the accuracy of pollution source classification according to an embodiment.
12 is a view for explaining a method of using an artificial intelligence-based water pollution source monitoring system according to an embodiment.

Hereinafter, embodiments will be described with reference to the accompanying drawings. However, the described embodiments may be modified in various other forms, and the scope of the present invention is not limited by the embodiments described below. In addition, various embodiments are provided in order to more completely explain the present invention to those of ordinary skill in the art. The shapes and sizes of elements in the drawings may be exaggerated for clearer description.

The following examples use not only RGB images but also thermal infrared images and multispectral images as input data to identify the characteristics of individual pollutants and use the learned image deep learning neural network to identify the types of pollutants and determine the status of pollutants. It is possible to provide an artificial intelligence pollution source monitoring system that identifies and monitors.

According to the embodiments, it is possible to provide a pollution source monitoring system that distinguishes and monitors various types of point source and nonpoint source in a wide area. In addition, according to embodiments, it is possible to provide a monitoring system capable of determining the type and information of a pollutant source based on image deep learning, identifying the need for management for each pollutant state, and giving a warning. In addition, according to embodiments, autonomous flight of a drone may be designed based on the location of a pollutant, and monitoring manpower consumption may be minimized through an algorithm that autonomously flies over a wide area.

1 is a block diagram for explaining an example of an internal configuration of a computer device (system) according to an embodiment. For example, the water pollution source monitoring system according to embodiments of the present invention may be implemented through the computer system 100 of FIG. 1 . As shown in FIG. 1, the computer system 100 is a component for executing the method for monitoring a water pollution source, and includes a processor 110, a memory 120, a permanent storage device 130, a bus 140, an input/output interface ( 150 ) and a network interface 160 .

Processor 110 may include or be part of any apparatus capable of processing any sequence of instructions. Processor 110 may include, for example, a computer processor, a processor in a mobile device, or other electronic device and/or a digital processor. The processor 110 may be included in, for example, a server computing device, a server computer, a set of server computers, a server farm, a cloud computer, a content platform, a mobile computing device, a smartphone, a tablet, a set-top box, a media player, and the like. The processor 110 may be connected to the memory 120 through the bus 140 .

Memory 120 may include volatile memory, persistent, virtual, or other memory for storing information used by or output by computer system 100 . The memory 120 may include, for example, random access memory (RAM) and/or dynamic RAM (DRAM). Memory 120 may be used to store any information, such as state information of computer system 100 . Memory 120 may also be used to store instructions of computer system 100 including instructions for monitoring water sources, for example. Computer system 100 may include one or more processors 110 as needed or appropriate.

Bus 140 may include a communications infrastructure that enables interaction between various components of computer system 100 . Bus 140 may carry data between, for example, components of computer system 100 , such as between processor 110 and memory 120 . Bus 140 may include wireless and/or wired communication media between components of computer system 100 and may include parallel, serial, or other topological arrangements.

Persistent storage 130 is a component, such as memory or other persistent storage, as used by computer system 100 to store data for an extended period of time (eg, compared to memory 120 ). may include Persistent storage 130 may include non-volatile main memory as used by processor 110 in computer system 100 . Persistent storage 130 may include, for example, flash memory, a hard disk, an optical disk, or other computer readable medium.

The input/output interface 150 may include interfaces to a keyboard, mouse, voice command input, display, or other input or output device. Configuration commands and/or information for monitoring the water pollution source may be received through the input/output interface 150 .

Network interface 160 may include one or more interfaces to networks such as a local area network or the Internet. Network interface 160 may include interfaces for wired or wireless connections. Configuration commands and/or information for monitoring water sources may be received via the network interface 160 .

Also, in other embodiments, computer system 100 may include more components than those of FIG. 1 . However, there is no need to clearly show most of the prior art components. For example, the computer system 100 is implemented to include at least some of the input/output devices connected to the above-described input/output interface 150, or a transceiver, a global positioning system (GPS) module, a camera, various sensors, It may further include other components such as a database and the like.

2 is a diagram for explaining a learning method of an image deep learning neural network according to an embodiment.

Referring to FIG. 2 , pollutants may be automatically detected and classified using an image deep learning neural network according to an embodiment. After collecting 210 data for learning of the image deep learning neural network, input data of the image deep learning neural network may be generated 220 . Through the image deep learning neural network, input data may be analyzed and interpreted (230), the image may be classified (240), and accuracy may be verified (250) through the result. For example, during data collection 210 , an image may be captured 211 using a drone (unmanned aerial vehicle), and the captured image may be pre-processed 212 to generate an orthodox image 213, and When generating 220 , NDVI, NDRE, NDBI, thermal infrared information 211 and height, position, inclination, plane information 212 and the like may be utilized. In addition, during analysis and analysis (230), it is possible to analyze (231) using the regional statistical method, the quartile method, the Norm.dist function, etc. , the analysis result can be interpreted (233). After the analysis, a classification item may be set 241 , and an image through the learning data 242 may be classified 243 . Thereafter, the accuracy can be verified and the efficiency compared 250 .

More specifically, for learning of an image deep learning neural network, learning data can be generated by combining images captured by RGB, multi-spectral, and thermal infrared cameras of various pollutants and labels for each type of pollutant. At this time, by unmanned flying the drone to the location where the nonpoint source is registered, it is possible to automatically acquire RGB, multispectral, and thermal infrared image data for the nonpoint source. In addition, an unmanned flight path may be set to intensively capture an image of an area determined as a contamination source through object detection. The area detected through object detection may be photographed from different viewpoints at least once or more, and may be photographed from different viewpoints by, for example, changing a photographing angle, position, focusing, and the like.

The image deep learning neural network can be trained through the generated training data. At this time, it is possible to construct an image deep learning neural network that learns RGB, multispectral, and thermal infrared images as a single matched image. .

When the training of the image deep learning neural network is completed, an image of the area to be monitored can be acquired and converted into an orthographic image through image processing. Then, by inputting RGB, multispectral, and thermal infrared images of regions suspected of contamination in the orthoimage to the image deep learning neural network, the type and state of the contamination source can be identified and matched to the orthographic image and displayed. The nonpoint pollution source may be monitored according to the type and/or state of the pollution source matched to the orthographic image.

Hereinafter, a method of acquiring a pollution source analysis image through setting the autonomous flight path of a drone will be described as an example.

The drone can move while scanning the monitoring area at a high altitude. In this case, the drone can only shoot RGB images. Thereafter, only the presence or absence of a contamination source can be identified through object detection, which is a light program, in the images scanned by the drone. When a pollution source is detected by object detection, the drone can autonomously fly toward the pollution source area. After identifying through the contamination source area (bounding box), at least two or more positions, angles, and focusing are taken differently, and at this time, not only RGB images but also multi-spectral and thermal infrared images can be acquired.

By inputting each image into each trained image deep learning neural network, the type of pollutant may be classified into image classification. In addition, through image segmentation of each classified pollutant, the state of the pollutant can be precisely grasped. Thereafter, by matching the identified pollutant source information to the orthographic image, it is possible to provide monitoring of the pollutant source distribution and information in the entire area.

3 is a block diagram illustrating a water pollution source monitoring system according to an embodiment.

3 is a diagram illustrating an example of components that the processor 110 of the computer system according to the embodiment of FIG. 1 may include. Here, the processor 110 of the computer system 100 may include the water pollution source monitoring system 300 according to an embodiment. The water pollution source monitoring system 300 according to an embodiment may include an input data generation unit 330 , an analysis and analysis unit 340 , and an information display unit 350 . In addition, according to an embodiment, the image collection unit 310 and the model learning unit 320 may be further included.

The processor 110 and the components of the processor 110 may perform steps 410 to 460 included in the method for monitoring a water pollution source of FIG. 4 . For example, the processor 110 and the components of the processor 110 may be implemented to execute an operating system code included in the memory 120 and an instruction according to at least one program code described above. Here, at least one program code may correspond to a code of a program implemented to process the water pollution source monitoring method.

The water pollution source monitoring method may not occur in the order shown, and some of the steps may be omitted or additional processes may be further included.

4 is a flowchart illustrating a method for monitoring a water pollution source according to an embodiment.

Referring to FIG. 4 , the artificial intelligence-based water pollution source monitoring method implemented through a computer device according to an embodiment generates input data using at least one image of RGB, multi-spectral, and thermal infrared of a monitoring target area. step 440, inputting the input data into the learned image deep learning neural network to analyze information on the type or state of the pollutant source 450, and the type of the pollutant source by using the location information of the image to monitor the pollutant source Alternatively, the step 460 of displaying information about the state may be included.

In addition, the method may further include a step 410 of acquiring at least one image of RGB, multi-spectral, and thermal infrared for a pollution source through setting of an autonomous flight path of the drone, and generating input data using the image. .

In addition, generating training data by combining at least any one or more images of RGB, multispectral, and thermal infrared image of a pollutant and a label for each pollutant type ( 420 ), and using the generated training data to perform an image deep learning neural The method may further include training the network (430).

Hereinafter, a method for monitoring a water pollution source according to an embodiment will be described with an example of a water pollution source monitoring system according to an embodiment.

First, in step 410 , the image collection unit 310 may acquire an image of at least any one of RGB, multispectral, and thermal infrared for a pollution source through setting of an autonomous flight path of the drone. In this case, the image collection unit 310 may generate input data by acquiring all RGB, multi-spectral, and thermal infrared images of the pollutant source.

The image collection unit 310 forms input data using RGB, multispectral and thermal infrared images of the pollutant source, or converts the acquired RGB, multispectral and thermal infrared images of the pollutant source into orthographic images through a post-processing program. to form input data. For example, the image collection unit 310 may take an image of a monitoring target area in RGB, multi-spectral and thermal infrared according to the setting of the autonomous flight path of the drone, and then convert it into an orthographic image through image processing. In addition, the input data generator 330 may form input data using RGB, multispectral, and thermal infrared images of regions suspected of being a contamination source in the orthogonal image.

The image collection unit 310 moves the drone while scanning the monitoring area at an altitude of a predetermined height to obtain an RGB image, and after confirming the presence or absence of a contamination source through object detection in the RGB image, through object detection When a pollution source is detected, a flight path is set so that the drone intensively captures the area where the pollution source is detected, the drone moves according to the set flight path, and at least one image of RGB, multi-spectral and thermal infrared can be captured. . In this case, the image collection unit 310 may acquire images from different viewpoints by intensively capturing the drone by changing at least one setting among position, angle, and focusing.

Meanwhile, the image deep learning neural network may be trained through the model learning unit 320 .

In step 420 , the model learning unit 320 may generate training data by combining at least one image of RGB, multi-spectral, and thermal infrared image of a pollutant and a label for each type of pollutant.

In step 430 , the model learning unit 320 may train the image deep learning neural network using the generated training data. The model learning unit 320 inputs the generated training data to the image deep learning neural network to image classification of the types of pollutants, and then analyzes the state of the pollutants through image segmentation of each classified pollutant. can figure out Here, the image deep learning neural network can be configured by learning RGB, multispectral and thermal infrared images as one matched image, or by learning RGB, multispectral and thermal infrared images individually and finally combining them. .

Accordingly, by inputting the image of the monitoring target area to the learned image deep learning neural network, it is possible to analyze the information of the pollutant source.

In operation 440 , the input data generator 330 may generate input data using at least one image of RGB, multi-spectral, and thermal infrared of the monitoring target area.

In step 450 , the analysis and interpretation unit 340 may analyze information on the type or state of a pollutant by inputting the input data into the learned image deep learning neural network.

In operation 460, the information display unit 350 may display information on the type or state of the pollution source by using the location information of the image to monitor the pollution source. For example, the information display unit 350 may monitor the non-point pollution source by matching and displaying information on the type or state of the pollution source to the orthographic image.

As such, the artificial intelligence-based water pollution source monitoring system and method according to an embodiment acquires RGB, multi-spectral and thermal infrared images through shooting using a drone, and learns an image deep learning neural network to detect pollution sources. and the detection result can be displayed and monitored.

5 is a diagram illustrating an example of performing basic learning and reinforcement learning of an image deep learning neural network according to an embodiment.

As shown in (a) to (c) of FIG. 5 , an acquired image may be input to an image deep learning neural network to detect a contamination source using artificial intelligence. An image deep learning neural network can be trained by repeatedly performing basic learning and reinforcement learning through an optimal algorithm-based learning model.

6 is a diagram illustrating an example of detecting a contamination source of an image deep learning neural network according to an embodiment.

As shown in FIG. 6 , an image taken by a drone may be registered (a) to detect a contamination source (b). For example, in the detection of a pollutant source, an image corresponding to a critical point may be classified, and a weight may be applied as it is similar to a pollutant source using information such as vegetation index and surrounding environment. This can be re-trained by applying it to the training model (image deep learning neural network).

7 is a diagram illustrating an example of a heat map and cluster distribution according to an embodiment.

As shown in (a) to (c) of FIG. 7 , the detection result of the contaminant may be expressed as a heat map or cluster distribution. That is, by using the detection result of the pollutant, a location information-based database (eg GIS DB) for the detection result is built, or a web-based GIS DB search system, a distribution map in the form of a heat map, a distribution map in the form of a cluster, etc. can be expressed as

Below, as an example of an experiment using an artificial intelligence-based water pollution source monitoring system, a method and results for detecting yard compost will be described.

8 is a diagram illustrating an example of a module structure for detecting yard compost according to an embodiment.

Referring to FIG. 8 , in step 810 , the image size was resized from [5472x3648] size to [416x416] size in pre-processing to make it into a data format suitable for the YOLO model, and the image pixel value (pixel value) was analyzed by scaling from [0,255] to [0,1]. In step 820 , it is possible to construct yard compost detection training data through image labeling. As an example, in step 830 , score_threshold among hyperparameters may be set to 0.5, and IOU_threshold may be set to 0.3. If the output value is greater than the set threshold, it passes to the YOLO model in step 840 , displays the output in step 850 , and stores the result in step 860 . On the other hand, if the output value is less than or equal to the set threshold, the input data is discarded in step 870 .

9 shows an example of a result of detecting yard compost according to an embodiment. As shown in FIG. 9 , it is possible to monitor the result of the detection of yard compost by displaying it on the image.

10 is a diagram for explaining a method of constructing learning data using a drone according to an embodiment.

Referring to FIG. 10 , a shooting plan may be established ( 1010 ) for drone shooting, and permission ( 1020 ) for shooting and flight approval may be obtained. Thereafter, drone image-based learning data can be built through drone shooting, or drone orthographic image-based learning data can be built.

As an example, RGB, multispectral, and thermal infrared images may be acquired ( 1040 ) through drone photography ( 1030 ), and image-based learning data of the drone may be constructed ( 1050 ). When learning is performed using drone image-based learning data, the location information of the pollutant can be indicated by using the location information of the image.

As another example, by correcting (1060, 1070) image distortion and positioning accuracy through a drone image post-processing program, and obtaining (1080) a drone orthographic image (two-dimensional image map) through image registration, the drone orthographic image based Build 1090 training data. In the case of learning using drone orthographic image-based learning data, the location information of the contamination source can be expressed by converting the object detection area into a shape file format that can express spatial location and shape.

11 is a diagram for explaining a method for improving the accuracy of pollution source classification according to an embodiment.

Referring to FIG. 11 , in operation 1110 , characteristics of image information may be analyzed and images may be classified. For example, a primary database (DB) can be built by classifying pollutants using GPS, date information, etc. of the training image and the classification probability can be calculated.

In step 1120, pollution sources can be classified, and weights can be set by using related learning information such as vegetation index and coverage, and the secondary classification probability can be calculated by applying the weight assigned to the primary classification probability. have.

In operation 1130, data may be learned. For example, if the secondary classification probability does not include the primary threshold, the classified training image can be used as training data. can

In step 1140 , data may be stored. For example, the secondary database can be built by adding related learning information of images that have been trained and classified to the primary database.

In this way, the accuracy can be improved by repeatedly performing the basic learning and reinforcement learning processes from the basic model learning. In addition, it is possible to improve the accuracy of the learning model by analyzing factors to improve the accuracy of the learning model and assigning weights using additional learning data such as national spatial information data and vegetation index data.

As described above, according to embodiments, it is possible to automatically determine a contamination source through an image deep learning neural network trained by matching RGB, multi-spectral, and thermal infrared images, respectively. In addition, image data of a pollution source area can be acquired through autonomous drone flight through object detection. In addition, the monitoring area can be monitored by matching the identified pollutant source to the orthographic map and displaying the pollutant source information at the exact location of the pollutant source.

12 is a diagram for explaining a method of using an artificial intelligence-based water pollution source monitoring system according to an embodiment.

Referring to FIG. 12 , image information such as a photographed image, an aerial photograph, and a satellite image using a drone may be acquired ( 1210 ), and a pollutant source may be extracted ( 1220 ) based on artificial intelligence, in which case distribution information of the pollutant is extracted. can do. Accordingly, the central government may provide information on the pollutant source, such as an environmental spatial information service, to monitor and manage the pollutant source (1230). In addition, local governments, etc. can build pollutant source information in the cadastral map to monitor and manage (1240) the emission of pollutants. In addition, it is possible to guide pollution source management in preparation for rainfall, and for example, a notification message requiring pollution source management may be sent to a user terminal using weather information.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be embodied in The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (15)

In the artificial intelligence-based water pollution source monitoring method implemented through a computer device,
generating input data using at least one image of RGB, multi-spectral, and thermal infrared of a monitoring target area;
inputting the input data into a learned image deep learning neural network to analyze information on a type or state of a pollutant; and
Displaying information on the type or state of the pollution source by using the location information of the image to monitor the pollution source
Containing, a water-based pollutant monitoring method. According to claim 1,
Acquiring at least one image of RGB, multi-spectral, and thermal infrared for the pollution source through setting the autonomous flight path of the drone
further comprising,
A method of monitoring a water-based pollutant source for generating the input data by using the image. 3. The method of claim 2,
Acquiring the image includes:
According to the setting of the autonomous flight path of the drone, the image of the monitoring target area is captured in RGB, multi-spectral and thermal infrared, and then converted into orthographic images through image processing,
The step of generating the input data includes:
Forming input data using RGB, multispectral and thermal infrared images of regions suspected of being a contamination source in the orthogonal image
A method for monitoring water pollution sources, characterized in that. 3. The method of claim 2,
Acquiring the image includes:
acquiring an RGB image by moving the drone while scanning the monitoring area at a predetermined height;
confirming the presence or absence of a contamination source through object detection in the RGB image;
when a pollution source is detected through the object detection, setting a flight route so that the drone intensively captures an area in which the pollution source is detected; and
The drone moves according to the set flight path and intensively photographing at least one image of RGB, multi-spectral and thermal infrared rays
Containing, a water-based pollutant monitoring method. 5. The method of claim 4,
The intensive shooting step is,
The drone acquires images from different viewpoints by changing at least one setting of position, angle, and focusing
A method for monitoring water pollution sources, characterized in that. According to claim 1,
The step of displaying information on the type or state of the pollutant source includes:
Monitoring non-point pollution sources by matching and displaying information on the type or state of the pollution source to the ortho image
A method for monitoring water pollution sources, characterized in that. According to claim 1,
generating learning data by combining at least one image of RGB, multi-spectral, and thermal infrared of a pollutant source and a label for each type of pollutant; and
Learning the image deep learning neural network using the generated training data
Further comprising, a water-based pollution source monitoring method. 8. The method of claim 7,
The step of training the image deep learning neural network is,
inputting the generated training data into the image deep learning neural network to classify a type of pollutant into an image; and
Recognizing the state of each of the classified pollutants through image segmentation
Containing, a water-based pollutant monitoring method. 8. The method of claim 7,
The image deep learning neural network,
Learning and composing RGB, multispectral and thermal infrared images as one matched image, or learning RGB, multispectral and thermal infrared images individually and finally combining them
A method for monitoring water pollution sources, characterized in that. In the artificial intelligence-based water pollution source monitoring system,
an input data generator for generating input data using at least one image of RGB, multi-spectral, and thermal infrared of a monitoring target area;
an analysis and analysis unit for inputting the input data into a learned image deep learning neural network and analyzing information on a type or state of a pollutant; and
An information display unit for displaying information on the type or state of the pollution source by using the location information of the image to monitor the pollution source
Containing, water pollution source monitoring system. 11. The method of claim 10,
An image collection unit that acquires at least one image of RGB, multi-spectral, and thermal infrared for a pollutant source through setting of an autonomous flight path of the drone
further comprising,
A water-based pollution source monitoring system that generates the input data using the image. 12. The method of claim 11,
The image collection unit,
According to the setting of the autonomous flight path of the drone, the image of the monitoring target area is captured in RGB, multi-spectral and thermal infrared, and then converted into orthographic images through image processing,
The input data generation unit,
Forming input data using RGB, multispectral and thermal infrared images of regions suspected of being a contamination source in the orthogonal image
Characterized in, the water pollution source monitoring system. 13. The method of claim 12,
The image collection unit,
When the drone scans and moves the monitoring area at a predetermined height, acquires an RGB image, checks the RGB image for the presence or absence of a contamination source through object detection, and the contamination source is detected through the object detection , Setting a flight path so that the drone intensively captures the area in which the pollution source is detected, the drone moves according to the set flight path, and intensively photographing at least one image of RGB, multi-spectral and thermal infrared rays
Characterized in, the water pollution source monitoring system. 14. The method of claim 13,
The image collection unit,
The drone acquires images from different viewpoints by changing at least one setting of position, angle, and focusing
Characterized in, the water pollution source monitoring system. 11. The method of claim 10,
A model for generating training data by combining at least any one or more images of RGB, multispectral, and thermal infrared image of a pollutant and a label for each type of pollutant, and using the generated training data to train the image deep learning neural network study department
Further comprising a, water-based pollution source monitoring system.

Images