KR20220096645A - Deep learning-based water management decision support information provision system and method - Google Patents

Deep learning-based water management decision support information provision system and method Download PDF

Info

Publication number
KR20220096645A
KR20220096645A KR1020200189272A KR20200189272A KR20220096645A KR 20220096645 A KR20220096645 A KR 20220096645A KR 1020200189272 A KR1020200189272 A KR 1020200189272A KR 20200189272 A KR20200189272 A KR 20200189272A KR 20220096645 A KR20220096645 A KR 20220096645A
Authority
KR
South Korea
Prior art keywords
image
deep learning
water
data
decision support
Prior art date
Application number
KR1020200189272A
Other languages
Korean (ko)
Other versions
KR102517917B1 (en
Inventor
최규훈
Original Assignee
위디비 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 위디비 주식회사 filed Critical 위디비 주식회사
Priority to KR1020200189272A priority Critical patent/KR102517917B1/en
Publication of KR20220096645A publication Critical patent/KR20220096645A/en
Application granted granted Critical
Publication of KR102517917B1 publication Critical patent/KR102517917B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use
    • Y02A20/40—Protecting water resources

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Emergency Management (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Water Supply & Treatment (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Alarm Systems (AREA)

Abstract

The present invention relates to a method for providing deep learning-based water management decision-making support information. The method of the present invention comprises the steps of: collecting, by an image collection unit, an image from a CCTV installed in a plurality of water facilities; collecting, by a measured data collection unit, measured data from measurement devices installed in the water facilities; pre-processing, by a deep-learning model generating unit, collected image data, reading pre-processed data, and learning the same on the basis of a model defined by a network to generate a deep-learning model for water management decision-making support; analyzing, by an analysis predicting unit, a water source environment for each of the water facilities, and generating an expected warning step; and generating, by an image generating unit, an intelligent water resource management image on the basis of the collected data. Therefore, decision-making for water management for each water facility can be rapidly performed.

Description

딥러닝 기반의 물관리 의사결정 지원정보 제공 방법 및 시스템{Deep learning-based water management decision support information provision system and method} Deep learning-based water management decision support information provision system and method}

본 발명은 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법 및 시스템에 관한 것으로, 특히 딥러닝 기술을 통해 영상정보와 계측정보를 융합한 지능형 수자원관리 영상을 실시간으로 제공이 가능한 물관리 의사결정 지원정보 제공 방법 및 시스템에 관한 것이다.The present invention relates to a method and system for providing information on water management decision support based on deep learning. In particular, through deep learning technology, an intelligent water resource management image that combines image information and measurement information can be provided in real time. It relates to a method and system for providing information.

정보통신기술의 발달로 댐 등의 수리시설물을 관리분야에도 IT 기술이 적용되고 있다. 이러한 기술을 물관리 시스템이라고 하나, 물관리 시스템은 여전히 영상정보와 계측정보가 각각 분리되어 제공하고 있으며, 영상정보는 단순히 현장상황을 제공하는 것에 그치는 수준이다. 이에 따라 수자원관리에서 영상정보는 일정 기간 저장기능만을 수행하고 있는 실정이다. With the development of information and communication technology, IT technology is being applied to the management of hydraulic facilities such as dams. Although this technology is called a water management system, the water management system still provides image information and measurement information separately, and the image information merely provides the on-site situation. Accordingly, in water resource management, image information is only performing a function of storage for a certain period of time.

또한, 수리시설물에 설치된 계측기기를 통해 계측정보를 얻어 위험정보, 의사결정정보를 수집할 수 있지만, 데이터 누락되어 정확한 예측을 하기 어렵고, 빈번한 오동작으로 인한 사용자 신뢰성이 저하가 발생되는 문제점이 있다. 현장에 다수의 카메라가 설치되고 있지만, 재해 발생시 능동적인 영상 표출이 불가능하여 갑작스런 현장 상황에 대응하기 어렵고, 대부분 사고 후에 확인용으로 영상정보를 활용하고 있는 문제가 있다. In addition, risk information and decision-making information can be collected by obtaining measurement information through a measuring device installed in a repair facility, but there is a problem in that it is difficult to make an accurate prediction due to missing data, and user reliability is lowered due to frequent malfunction. Although a number of cameras are installed in the field, it is difficult to respond to sudden on-site situations because it is impossible to actively display images in case of a disaster, and there is a problem in that most of the images are used for confirmation after an accident.

선행기술로는 국내등록특허 제10-1017746호(지능형 물관리 자동화시스템)가 있으나, 각종 기상 관련 정보를 수집하여 현장 여건에 맞는 홍수 예측 데이터를 생성하여 관리자에게 제공하는 기술을 개시하고 있을 뿐이나 실시간으로 지능형 영상정보를 제공하는 기술에 대해서는 개시하고 있지 않다.As a prior art, there is domestic registration patent No. 10-1017746 (intelligent water management automation system), but it is only disclosing a technology that collects various weather-related information to generate flood prediction data suitable for site conditions and provides it to managers. The technology for providing intelligent image information in real time is not disclosed.

본 발명이 해결하고자 하는 과제는 상기와 같은 종래 기술의 문제점을 해결하기 위해 안출된 것으로, 딥러닝 기술을 통해 영상정보와 계측정보를 융합하여 실시간으로 물관리에 대한 의사결정이 가능하도록 딥러닝 영상 분석 기반의 물관리 의사결정 지원정보 제공 방법 및 시스템을 제공할 수 있다.The problem to be solved by the present invention has been devised to solve the problems of the prior art as described above, and a deep learning image can be used to make decisions about water management in real time by fusion of image information and measurement information through deep learning technology. It is possible to provide a method and system for providing analysis-based water management decision support information.

본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법은, 영상수집부가 다수개의 수리시설물에 설치된 CCTV로부터 영상을 수집하는 단계와, 계측자료수집부가 다수개의 수리시설물에 설치된 계측기기로부터 계측자료를 수집하는 단계와, 딥러닝모델생성부가 수집된 영상데이터를 전처리하고, 전처리된 데이터를 읽어 네트워크로 정의된 모델을 기반으로 학습을 하여 물관리 의사결정 지원을 위한 딥러닝 모델을 생성하는 단계와, 분석예측부가 수리시설별 수자원 환경분석을 하여 예상경보단계를 생성하는 단계와, 영상생성부가 수집된 데이터들에 기초하여 지능형 수자원관리 영상을 생성하는 단계를 포함한다.The deep learning-based water management decision-making support information providing method according to an embodiment of the present invention includes the steps of: an image collection unit collecting images from CCTVs installed in a plurality of repair facilities; and a measurement data collection unit installed in a plurality of repair facilities In the step of collecting measurement data from the device, the deep learning model generator preprocesses the collected image data, reads the preprocessed data and learns based on the model defined by the network to develop a deep learning model for water management decision support. It includes the step of generating, the step of generating a predicted warning step by the analysis and prediction unit analyzing the water resource environment for each hydraulic facility, and the step of generating the intelligent water resource management image based on the data collected by the image generation unit.

본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템은, 수리시설물에 설치되어 영상을 촬영하는 CCTV와, 수리시설물에 설치되어 계측정보를 계측하는 계측기기와, 상기 CCTV로부터 수집된 영상, 상기 계측기기로부터 수집된 계측자료, 공공기관서버로부터 수신된 공공데이터자료 중 적어도 하나에 기초하여 분석 및 예측을 통해 지능형 수자원관리 영상을 생성하는 운영서버와, 상기 운영서버로부터 생성된 지능형 수자원관리 영상을 수신하여 영상을 표시하는 관리자단말을 포함하고, 상기 운영서버는, 수자원환경을 분석하여 예상경보단계를 생성하되. 홍수시와 가뭄시(평시)를 구분하여 분석예측하는 분석예측부와, 수신된 영상정보, 계측정보, 공공데이터, 생성된 예상경보단계에 기초하여 지능형 수자원관리 영상을 생성하는 영상생성부를 포함한다.The deep learning-based water management decision support information providing system according to an embodiment of the present invention includes a CCTV installed in a repair facility to take an image, a measuring device installed in a repair facility to measure measurement information, and collection from the CCTV An operation server that generates an intelligent water resource management image through analysis and prediction based on at least one of the selected image, the measurement data collected from the measurement device, and the public data data received from the public institution server, and the intelligent generated from the operation server and a manager terminal for receiving the water resource management video and displaying the video, wherein the operation server analyzes the water resource environment to generate an expected warning step. It includes an analysis prediction unit that analyzes and predicts by dividing the time of flood and drought (peace), and an image generation unit that generates an intelligent water resource management image based on the received image information, measurement information, public data, and the generated predicted warning stage. .

본 발명에 의하면 딥러닝 기반의 영상정보와 계측정보를 융합하여 관리자에게 실시간으로 제공함으로써 수리시설물별로 물관리에 대한 의사결정을 신속하게 할 수 있다. According to the present invention, by fusion of deep learning-based image information and measurement information and providing it to the manager in real time, it is possible to quickly make decisions about water management for each repair facility.

또한, 수리시설별 상황에 따라 실시간으로 가변적인 예상경보단계를 제공할 수 있다.In addition, it is possible to provide a variable predicted warning level in real time according to the situation of each repair facility.

또한, 이미 설치된 CCTV에 별도의 추가 장비 없이 엣지디바이스에 딥러닝 모델을 전달하여 적용이 가능하다.In addition, it is possible to apply the deep learning model to the edge device without additional equipment to the already installed CCTV.

도 1은 본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템의 구성도이다.
도 2는 본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법을 설명하는 흐름도이다.
도 3 내지 도 5는 본 발명의 실시예에 따른 분석예측부가 홍수시와 가뭄시에 분석예측하는 방법을 설명하는 도면이다.
도 6 내지 도 8은 본 발명의 실시예에 따라 생성된 지능형 수자원관리 영상을 도시한 예시도이다.1 is a block diagram of a deep learning-based water management decision support information providing system according to an embodiment of the present invention.
2 is a flowchart illustrating a method for providing information for providing water management decision support based on deep learning according to an embodiment of the present invention.
3 to 5 are diagrams for explaining a method of analyzing and predicting by the analysis prediction unit at the time of flood and drought according to an embodiment of the present invention.
6 to 8 are exemplary views showing intelligent water resource management images generated according to an embodiment of the present invention.

본 명세서에 개시되어 있는 본 발명의 개념에 따른 실시 예들에 대해서 특정한 구조적 또는 기능적 설명은 단지 본 발명의 개념에 따른 실시 예들을 설명하기 위한 목적으로 예시된 것으로서, 본 발명의 개념에 따른 실시 예들은 다양한 형태들로 실시될 수 있으며 본 명세서에 설명된 실시 예들에 한정되지 않는다.Specific structural or functional descriptions of the embodiments according to the concept of the present invention disclosed in this specification are only exemplified for the purpose of explaining the embodiments according to the concept of the present invention, and the embodiments according to the concept of the present invention are It may be implemented in various forms and is not limited to the embodiments described herein.

본 발명의 개념에 따른 실시 예들은 다양한 변경들을 가할 수 있고 여러 가지 형태들을 가질 수 있으므로 실시 예들을 도면에 예시하고 본 명세서에서 상세하게 설명하고자 한다. 그러나 이는 본 발명의 개념에 따른 실시 예들을 특정한 개시 형태들에 대해 한정하려는 것이 아니며, 본 발명의 사상 및 기술 범위에 포함되는 모든 변경, 균등물, 또는 대체물을 포함한다.Since the embodiments according to the concept of the present invention may have various changes and may have various forms, the embodiments will be illustrated in the drawings and described in detail herein. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes all changes, equivalents, or substitutes included in the spirit and scope of the present invention.

본 명세서에서 사용한 용어는 단지 특정한 실시 예를 설명하기 위해 사용된 것으로서, 본 발명을 한정하려는 의도가 아니다. 단수의 표현은 문맥상 명백하게 다르게 뜻하지 않는 한, 복수의 표현을 포함한다. 본 명세서에서, "포함하다" 또는 "가지다" 등의 용어는 본 명세서에 기재된 특징, 숫자, 단계, 동작, 구성 요소, 부분품 또는 이들을 조합한 것이 존재함을 지정하려는 것이지, 하나 또는 그 이상의 다른 특징들이나 숫자, 단계, 동작, 구성 요소, 부분품 또는 이들을 조합한 것들의 존재 또는 부가 가능성을 미리 배제하지 않는 것으로 이해되어야 한다.The terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that a feature, number, step, operation, component, part, or combination thereof described herein exists, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

이하, 본 명세서에 첨부된 도면들을 참조하여 본 발명의 실시 예들을 상세히 설명한다.Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

도 1은 본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템의 구성도이다.1 is a block diagram of a deep learning-based water management decision support information providing system according to an embodiment of the present invention.

도 1을 참조하면, 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템은 운영서버(100), CCTV(200), 엣지디바이스(300), 계측기기(400), 공공기관서버(500), 관리자단말(600)로 구성된다. 운영서버는 수집된 영상, 계측자료, 공공데이터자료에 기초하여 분석 및 예측을 통해 지능형 수자원관리 영상을 생성하고, 생성된 영상을 관리자단말에 제공하여 물관리에 대한 의사결정을 지원할 수 있다.1, the deep learning-based water management decision support information providing system is an operation server 100, a CCTV 200, an edge device 300, a measuring device 400, a public institution server 500, a manager It consists of a terminal (600). The operation server can generate an intelligent water resource management image through analysis and prediction based on the collected image, measurement data, and public data data, and provide the generated image to the manager terminal to support decision-making on water management.

운영서버(100)는 영상수집부(110), 계측자료수집부(120), 공공데이터자료수집부(130), 딥러닝모델생성부(140), 분석예측부(150), 영상생성부(160), 저장부(170), 통신부(180), 제어부(190)로 구성된다.The operation server 100 includes an image collection unit 110, a measurement data collection unit 120, a public data data collection unit 130, a deep learning model generation unit 140, an analysis prediction unit 150, an image generation unit ( 160 ), a storage unit 170 , a communication unit 180 , and a control unit 190 .

영상수집부(110)는 수리시설물에 설치된 다수개의 CCTV로부터 촬영된 영상을 수집한다. 영상수집부(110)는 수집한 영상을 저장부에 저장할 수 있고, 자동분류 또는 사용자분류기법을 통해 딥러닝모델 학습을 위한 데이터로 활용될 수 있다. 영상수집부(110)는 실시예에 따라 오픈소스프로그램 모듈(ffmpeg)를 활용하여 매시간 이미지 저장기능을 수행하여 영상을 수집할 수 있다.The image collection unit 110 collects images taken from a plurality of CCTVs installed in the repair facility. The image collection unit 110 may store the collected images in the storage unit, and may be used as data for deep learning model learning through automatic classification or user classification techniques. The image collection unit 110 may collect images by performing an image storage function every hour by utilizing an open source program module (ffmpeg) according to an embodiment.

계측자료수집부(120)는 계측기기(400)에서 계측된 데이터를 직접 수신하거나, 실시예에 따라 수리시설물 현장에서 계측기기가 아닌 별도의 단말에 의해 수집된 계측자료를 수신하여 현장계측정보를 생성할 수 있다. 상기 현장계측정보는 기상특보, 강수량, 시설관리조건, 수위, 유량, 가동 중 적어도 하나일 수 있다.The measurement data collection unit 120 generates field measurement information by directly receiving the data measured by the measurement device 400 or by receiving the measurement data collected by a separate terminal other than the measurement device at the repair facility site according to an embodiment. can do. The field measurement report may be at least one of a weather warning, precipitation amount, facility management condition, water level, flow rate, and operation.

공공데이터자료수집부(130)는 공공기관서버(500)로부터 기상데이터, 하천수위데이터, 주요수리시설 계측데이터를 수신할 수 있다. 공공기관서버(500)는 공공데이터포털서버와 연계하여 데이터를 수신할 수 있으며, OPEN API를 통해 연계할 수 있으며, 본 발명에 의해 생성된 데이터를 외부연계방식으로도 적용이 가능하도록 구현될 수 있다.The public data data collection unit 130 may receive meteorological data, river water level data, and main repair facility measurement data from the public institution server 500 . The public institution server 500 can receive data in connection with the public data portal server, can be connected through the OPEN API, and can be implemented so that the data generated by the present invention can be applied to an external connection method. have.

딥러닝모델 생성부(140)는 수집된 영상데이터를 측정거리에 따라 분류하여 딥러닝모델을 학습하기 위한 전처리를 수행한다. 이때, 상기 측정거리는 0.2m, 0.5m, 2.3m, 2.4m, 2.5m, 2.9m의 6가지로 분류하여 학습을 위한 데이터셋을 분류할 수 있으나 이에 대해 한정하는 것은 아니다. 딥러닝 모델생성부(140)는 전처리된 데이터를 읽고, 네트워크로 정의된 모델을 기반으로 학습을 하여 물관리 의사결정 지원을 위한 딥러닝 모델을 생성한다. 이후에, 실제 영상이미지가 입력되었을 때 평가의 정확도를 검증할 수 있다.The deep learning model generation unit 140 performs preprocessing for learning the deep learning model by classifying the collected image data according to the measurement distance. In this case, the measurement distance can be classified into six types of 0.2m, 0.5m, 2.3m, 2.4m, 2.5m, and 2.9m to classify the dataset for learning, but the present invention is not limited thereto. The deep learning model generator 140 reads the preprocessed data, and generates a deep learning model for water management decision support by learning based on the model defined as a network. Thereafter, when the actual video image is input, the accuracy of the evaluation can be verified.

분석예측부(150)는 수자원환경을 분석하여 예상경보단계를 생성한다. 분석예측부(150)는 홍수시와 가뭄시(평시)를 구분하여 분석예측할 수 있다. The analysis prediction unit 150 analyzes the water resource environment and generates a predicted warning step. The analysis prediction unit 150 may analyze and predict a flood time and a drought time (normal time).

분석예측부(150)는 홍수시 강우-유출모델을 통해 시간별 유출량을 산정할 수 있다. 이때, 적용 강우를 대상 유역에 적용하여 강우-유출모델을 통해 시간별 유출량을 산정할 수 있다. 분석예측부(150)는 유입된 홍수량을 적용하여 실시간 예측수위를 산정할 수 있다. 분석예측부(150)는 저수지 또는 배수장 등의 수리시설물 유역으로부터 유입된 홍수량을 적용하여 실시간으로 예측수위를 산정할 수 있다. 이때, 저수지의 경우 여수토게이트, 물넘이 상황을 고려하여 방류량을 산정한다. 배수장의 경우 펌프제원을 고려하여 최대 배수량을 적용한다. 분석예측부(150)는 현재 수위로부터 예상되는 수위가 홍수위로부터 최종적으로 어느 단계에 도달되는지 분석예측하여 현재 단계에 따른 예상경보단계를 생성할 수 있다. 이때, 상기 예상경보단계는 4단계로 구분되며, 관심단계, 주의단계, 경계단계, 심각단계 순으로 구분될 수 있으나 이에 대해 한정하는 것은 아니다. 기관 요청에 따라 단계를 조정할 수 있다.The analysis prediction unit 150 may calculate an hourly runoff amount through a rainfall-runoff model during flooding. In this case, the hourly runoff can be calculated through the rainfall-runoff model by applying the applied rainfall to the target watershed. The analysis prediction unit 150 may calculate a real-time predicted water level by applying the inflow amount of flood. The analysis prediction unit 150 may calculate the predicted water level in real time by applying the amount of flood flowing in from the watershed of a hydraulic facility such as a reservoir or a drainage field. At this time, in the case of a reservoir, the discharge amount is calculated considering the Yeosu togate and overflow situation. In the case of a drainage site, the maximum displacement is applied in consideration of the pump specifications. The analysis prediction unit 150 may analyze and predict at which stage the water level expected from the current water level will finally reach from the flood level to generate an expected warning stage according to the current stage. In this case, the predicted warning stage is divided into four stages, and may be divided into an interest stage, a caution stage, a warning stage, and a serious stage, but is not limited thereto. Steps can be adjusted according to institutional requests.

분석예측부(150)는 가뭄시 현재까지의 누적 강우량을 바탕으로 과거 강우현황과 비교하여 평년대비비율을 계산하여 미래강우량을 산정하고, 유역유출량을 계산할 수 있다. 분석예측부(150)는 저수지 또는 양수장의 수혜면적에 따른 수리시설별 필요수량을 산정한다. 분석예측부(150)가 산정된 수량을 바탕으로 저수지 수지 분석을 통해 관개기간 중 저수율 변화를 산정한다. 이때, 저수지 수지 분석 = 저수량 + 유역유출량 - 필요수량의 계산식에 의해 계산된다. 분석예측부(150)가 현재 저수율로부터 예측되는 요구 수량 대비 공급량 기준비율에 따라 예상경보단계를 생성한다. The analysis prediction unit 150 may calculate future rainfall by comparing with the past rainfall status based on the accumulated rainfall to date during a drought, and calculating the ratio compared to the average, and calculate the watershed runoff. The analysis and prediction unit 150 calculates the required quantity of water for each repair facility according to the beneficiary area of the reservoir or pumping station. The analysis prediction unit 150 calculates a change in the storage yield during the irrigation period through the reservoir balance analysis based on the calculated quantity. At this time, it is calculated by the equation of reservoir balance analysis = storage amount + watershed runoff - required amount. The analysis and prediction unit 150 generates a predicted warning step according to the reference ratio of the supply quantity to the required quantity predicted from the current low yield.

영상생성부(160)는 수신된 영상정보, 계측정보, 공공데이터, 생성된 예상경보단계에 기초하여 지능형 수자원관리 영상을 생성할 수 있다. 이때, 영상생성부(160)는 계측정보, 공공데이터, 생성된 예상경보단계 중 적어도 하나를 융합하여 영상을 생성할 수 있다. 실시예에 따라, 계측정보, 공공데이터, 생성된 예상경보단계 중 적어도 하나를 영상정보에 중첩하여 도시할 수 있다. 실시예에 따라 공공기관서버(500)는 기상청서버, 홍수통제소서버, 수자원공사서버, 환경부서버 중 적어도 하나일 수 있다.The image generator 160 may generate an intelligent water resource management image based on the received image information, measurement information, public data, and the generated predicted warning stage. In this case, the image generator 160 may generate an image by fusing at least one of the measurement information, public data, and the generated predicted warning step. According to an embodiment, at least one of the measurement information, public data, and the generated predicted warning step may be shown by being superimposed on the image information. According to an embodiment, the public institution server 500 may be at least one of a Meteorological Agency server, a flood control station server, a water resources corporation server, and a server of the Ministry of Environment.

저장부(170)는 생성된 딥러닝모델을 저장할 수 있다. 저장부(170)는 영상정보, 계측정보, 생성된 예상경보단계를 수리시설물별로 저장할 수 있다.The storage unit 170 may store the generated deep learning model. The storage unit 170 may store the image information, the measurement information, and the generated predicted alarm stage for each repair facility.

통신부(180)는 생성된 지능형 수자원관리 영상을 관리자단말에 전송한다. 실시예에 따라 영상정보, 현장계측정보, 공동데이터정보, 예상경보단계를 별도로 전송하여 관리자단말에서 각각을 중첩하여 표시할 수 있다. 통신부(180)는 생성된 딥러닝모델을 엣지디바이스에 전달할 수 있다. 통신부(180)는 생성된 지능형 수자원관리 영상을 관리자단말에 전송할 수 있다. 제어부(190)는 운영서버의 각 구성을 제어할 수 있다.The communication unit 180 transmits the generated intelligent water resource management image to the manager terminal. According to an embodiment, the image information, the field measurement information, the joint data information, and the predicted alarm step may be separately transmitted and displayed in a superimposed manner in the manager terminal. The communication unit 180 may transmit the generated deep learning model to the edge device. The communication unit 180 may transmit the generated intelligent water resource management image to the manager terminal. The control unit 190 may control each configuration of the operation server.

도 2는 본 발명의 실시예에 따른 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법을 설명하는 흐름도이다. 도 2를 참조하면, 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법은 영상수집부가 수리시설물에 설치된 CCTV로부터 영상을 수집한다(S201). 계측자료수집부가 계측기기로부터 계측자료를 수집한다(S203).2 is a flowchart illustrating a method for providing information for providing water management decision support based on deep learning according to an embodiment of the present invention. Referring to FIG. 2 , in the deep learning-based water management decision-making support information providing method, the image collecting unit collects images from CCTVs installed in the repair facility (S201). The measurement data collection unit collects measurement data from the measurement device (S203).

딥러닝 모델생성부가 모델을 생성한다(S205). 딥러닝 모델생성부는 수집된 영상데이터를 측정거리에 따라 분류하여 딥러닝모델을 학습하기 위한 전처리를 수행한다. 딥러닝 모델생성부는 전처리된 데이터를 읽고, 네트워크로 정의된 모델을 기반으로 학습을 하여 물관리 의사결정 지원을 위한 딥러닝 모델을 생성한다. 이후에, 실제 영상이미지가 입력되었을 때 평가의 정확도를 검증할 수 있다. 이때, 생성된 딥러닝모델은 통신부를 통해 엣지디바이스로 전달될 수 있다. The deep learning model generator generates a model (S205). The deep learning model generator performs preprocessing for learning the deep learning model by classifying the collected image data according to the measurement distance. The deep learning model generator reads the preprocessed data and creates a deep learning model for water management decision support by learning based on the model defined by the network. Thereafter, when the actual video image is input, the accuracy of the evaluation can be verified. In this case, the generated deep learning model may be transmitted to the edge device through the communication unit.

분석예측부가 수자원환경을 분석하여 예상경보단계를 생성한다(S207).The analysis prediction unit analyzes the water resource environment and generates a predicted warning step (S207).

영상생성부가 지능형 수자원관리 영상을 생성한다(S209). 영상생성부가 각 수리시설별로 현재 수위에 대해 결정된 예상경보단계, 현장계측정보, 공공데이터정보를 융합하여 지능형 수자원관리 영상을 생성할 수 있다. 영상생성부는 영상별로부여된 예상경보단계에 기초하여 경계단계 또는 심각단계인 경우 자동알람을 하도록 정보를 제공할 수 있다.The image generation unit creates an intelligent water resource management image (S209). The image generation unit may generate an intelligent water resource management image by fusion of the predicted warning stage determined for the current water level for each water facility, field measurement information, and public data information. The image generator may provide information so as to automatically generate an alarm in the case of an alert stage or a serious stage based on the predicted alert stage assigned to each image.

통신부가 생성된 지능형 수자원관리 영상을 관리자단말에 전송한다. 실시예에 따라 영상정보, 현장계측정보, 공동데이터정보, 예상경보단계를 별도로 전송하여 관리자단말에서 각각을 중첩하여 표시할 수 있다. The communication unit transmits the generated intelligent water resource management image to the manager terminal. According to an embodiment, the image information, the field measurement information, the joint data information, and the predicted alarm step may be separately transmitted and displayed in a superimposed manner in the manager terminal.

도 3 내지 도 5는 본 발명의 실시예에 따른 분석예측부가 홍수시와 가뭄시에 분석예측하는 방법을 설명하는 도면이다.3 to 5 are diagrams for explaining a method of analyzing and predicting by the analysis prediction unit at the time of flood and drought according to an embodiment of the present invention.

도 3을 참조하면, 분석예측부가 홍수시 강우-유출모델을 통해 시간별 유출량을 산정한다(S301). 분석예측부가 적용 강우를 대상 유역에 적용하여 강우-유출모델을 통해 시간별 유출량을 산정할 수 있다.Referring to FIG. 3 , the analysis and prediction unit calculates the hourly runoff through the rainfall-runoff model during flooding ( S301 ). By applying the applied rainfall to the target watershed, the analysis and forecasting unit can calculate the hourly runoff through the rainfall-runoff model.

분석예측부가 유입된 홍수량을 적용하여 실시간 예측수위를 산정한다(S303).The analysis and forecasting unit calculates the real-time predicted water level by applying the inflowing flood amount (S303).

분석예측부가 저수지 또는 배수장 등의 수리시설물 유역으로부터 유입된 홍수량을 적용하여 실시간으로 예측수위를 산정한다. 이때, 저수지의 경우 여수토게이트, 물넘이 상황을 고려하여 방류량을 산정한다. 배수장의 경우 펌프제원을 고려하여 최대 배수량을 적용한다(S305). The analysis and forecasting unit calculates the predicted water level in real time by applying the flood volume flowing in from the watershed of the hydraulic facility such as a reservoir or drainage field. At this time, in the case of reservoirs, the discharge amount is calculated considering the Yeosu togate and overflow situation. In the case of a drainage site, the maximum displacement is applied in consideration of the pump specifications (S305).

분석예측부가 현재 수위로부터 예상되는 수위가 홍수위로부터 최종적으로 어느 단계에 도달되는지 분석예측하여 현재 단계에 따른 예상경보단계를 생성한다(S307). 이때, 상기 예상경보단계는 4단계로 구분되며, 관심단계, 주의단계, 경계단계, 심각단계 순으로 구분될 수 있으나 이에 대해 한정하는 것은 아니다. 기관 요청에 따라 단계를 조정할 수 있다.The analysis prediction unit analyzes and predicts which stage the water level expected from the current water level will finally reach from the flood level, and generates an expected warning step according to the current level (S307). In this case, the predicted warning stage is divided into four stages, and may be divided into an interest stage, a caution stage, a warning stage, and a serious stage, but is not limited thereto. Steps can be adjusted according to institutional requests.

도 4를 참조하면, 분석예측부가 가뭄시 현재까지의 누적 강우량을 바탕으로 과거 강우현황과 비교하여 평년대비비율을 계산하여 미래강우량을 산정하고, 유역유출량을 계산한다(S401). 분석예측부가 저수지 또는 양수장의 수혜면적에 따른 수리시설별 필요수량을 산정한다(S403). 분석예측부가 산정된 수량을 바탕으로 저수지 수지 분석을 통해 관개기간 중 저수율 변화를 산정한다. 이때, 저수지 수지 분석 = 저수량 + 유역유출량 - 필요수량의 계산식에 의해 계산된다(S405).Referring to FIG. 4 , the analysis and forecasting unit calculates the future rainfall by comparing the accumulated rainfall to the present during a drought, comparing it with the past rainfall, and calculating the future rainfall, and calculating the watershed runoff (S401). The analysis and forecasting unit calculates the required amount of water for each repair facility according to the beneficiary area of the reservoir or pumping station (S403). Based on the amount calculated by the analysis and forecasting unit, it calculates the change in the storage yield during the irrigation period through the reservoir balance analysis. At this time, it is calculated by the equation of reservoir balance analysis = water storage amount + watershed runoff - required water amount (S405).

분석예측부가 현재 저수율로부터 예측되는 요구 수량 대비 공급량 기준비율에 따라 예상경보단계를 생성한다(S407). 이때, 상기 예상경보단계는 4단계로 구분되며, 관심단계, 주의단계, 경계단계, 심각단계 순으로 구분될 수 있으나 이에 대해 한정하는 것은 아니다. The analysis and prediction unit generates an expected warning step according to the reference ratio of the supply quantity to the required quantity predicted from the current low yield (S407). In this case, the predicted warning stage is divided into four stages, and may be divided into an interest stage, a caution stage, a warning stage, and a serious stage, but is not limited thereto.

도 5는 본 발명의 실시예에 따른 분석예측부가 홍수시 예상 수위를 예측하는 그래프이다. 도 5를 참조하면, 분석예측부는 홍수위험수위와, 현재시점의 강수량 및 저지수위에 기초하여 홍수모의데이터, 저수지수위, 하천방류수위를 예측할 수 있다. 분석예측부는 예측된 결과를 그래프로 도시하여 관리자단말에 제공할 수 있다.5 is a graph for predicting an expected water level in case of a flood by an analysis prediction unit according to an embodiment of the present invention. Referring to FIG. 5 , the analysis prediction unit may predict the flood simulation data, the reservoir water level, and the river discharge level based on the flood risk level and the current time of precipitation and low water level. The analysis prediction unit may provide the predicted result as a graph to the manager terminal.

도 6 내지 도 8은 본 발명의 실시예에 따라 생성된 지능형 수자원관리 영상을 도시한 예시도이다. 도 6은 저수지 영상 화면(700)으로 수리시설물 명칭(710), 수위(720), 공공데이터(730)를 도시한 예시도이다. 도 7은 하천 영상 화면(800)으로 심각, 경계, 주의, 관심이 표시되고, 분석예측부에서 생성한 예상경보단계를 도시할 수 있다. 도 8은 저수지 영상 화면으로 예측저수율, 예상경보단계를 다양한 형태로 도시할 수 있다.6 to 8 are exemplary views showing intelligent water resource management images generated according to an embodiment of the present invention. FIG. 6 is an exemplary diagram illustrating a name of a repair facility 710 , a water level 720 , and public data 730 as a reservoir image screen 700 . 7 is a river image screen 800 in which seriousness, alertness, caution, and interest are displayed, and may show a predicted warning step generated by the analysis and prediction unit. 8 is a reservoir image screen, and the predicted water yield and the predicted warning stage may be shown in various forms.

본 발명에 의해 딥러닝 기반의 영상정보와 계측정보를 융합하여 관리자에게 실시간으로 제공함으로써 수리시설물별로 물관리에 대한 의사결정을 신속하게 할 수 있다. According to the present invention, by fusion of deep learning-based image information and measurement information and providing it to the manager in real time, it is possible to quickly make decisions about water management for each repair facility.

본 발명은 또한 컴퓨터로 읽을 수 있는 기록매체에 컴퓨터가 읽을 수 있는 코드로서 구현하는 것이 가능하다. 컴퓨터가 읽을 수 있는 기록매체는 컴퓨터 시스템에 의하여 읽혀질 수 있는 데이터가 저장되는 모든 종류의 기록장치를 포함한다. 컴퓨터가 읽을 수 있는 기록매체의 예로는 ROM, RAM, CD-ROM, 자기 테이프, 플로피디스크, 광데이터 저장장치 등이 있다. 또한 컴퓨터가 읽을 수 있는 기록매체는 네트워크로 연결된 컴퓨터 시스템에 분산되어 분산방식으로 컴퓨터가 읽을 수 있는 코드가 저장되고 실행될 수 있다.The present invention can also be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. In addition, the computer-readable recording medium is distributed in a network-connected computer system so that the computer-readable code can be stored and executed in a distributed manner.

발명은 도면에 도시된 실시 예를 참고로 설명되었으나 이는 예시적인 것에 불과하며, 본 기술 분야의 통상의 지식을 가진 자라면 이로부터 다양한 변형 및 균등한 타 실시 예가 가능하다는 점을 이해할 것이다. 따라서, 본 발명의 진정한 기술적 보호 범위는 첨부된 등록청구범위의 기술적 사상에 의해 정해져야 할 것이다.Although the invention has been described with reference to the embodiment shown in the drawings, this is merely exemplary, and those of ordinary skill in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

100; 운영서버 200; CCTV
300; 엣지디바이스 400; 계측기기
500; 공공기관서버 600; 관리자단말100; operation server 200; CCTV
300; Edge device 400; measuring instrument
500; public institution server 600; admin terminal

Claims (5)

딥러닝 기반의 물관리 의사결정 지원정보 제공 방법에 있어서,
(a) 영상수집부가 다수개의 수리시설물에 설치된 CCTV로부터 영상을 수집하는 단계;
(b) 계측자료수집부가 다수개의 수리시설물에 설치된 계측기기로부터 계측자료를 수집하는 단계;
(c) 딥러닝모델생성부가 수집된 영상데이터를 전처리하고, 전처리된 데이터를 읽어 네트워크로 정의된 모델을 기반으로 학습을 하여 물관리 의사결정 지원을 위한 딥러닝 모델을 생성하는 단계;
(d) 분석예측부가 수리시설별 수자원 환경분석을 하여 예상경보단계를 생성하는 단계; 및
(e) 영상생성부가 수집된 데이터들에 기초하여 지능형 수자원관리 영상을 생성하는 단계를 포함하는 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법.
In the deep learning-based water management decision support information providing method,
(a) collecting images from the CCTV installed in a plurality of repair facilities by the image collecting unit;
(b) the measurement data collection unit collecting measurement data from measurement devices installed in a plurality of repair facilities;
(c) generating a deep learning model for water management decision support by preprocessing the image data collected by the deep learning model generator, reading the preprocessed data, and learning based on the model defined as a network;
(d) generating an expected warning step by the analysis and forecasting unit analyzing the water resource environment for each water facility; and
(E) Deep learning-based water management decision support information providing method comprising the step of generating an intelligent water resource management image based on the data collected by the image generator.
 제1항에 있어서,
상기 분석예측부(150)는 홍수시와 가뭄시(평시)를 구분하여 분석예측하는 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법.
According to claim 1,
The analysis prediction unit 150 is a deep learning-based water management decision support information providing method for analyzing and predicting by dividing a flood time and a drought time (normal time).
 제1항에 있어서,
상기 딥러닝모델 생성부는 수집된 영상데이터를 측정거리에 따라 분류하여 딥러닝모델을 학습하기 위한 전처리를 수행하는 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법.
According to claim 1,
The deep learning model generator classifies the collected image data according to the measurement distance to perform pre-processing for learning the deep learning model, a deep learning-based water management decision support information providing method.
 제1항에 있어서,
상기 분석예측부는 홍수시 강우-유출모델을 통해 시간별 유출량을 산정하되, 유입된 홍수량을 적용하여 실시간 예측수위를 산정하고, 저수지 또는 배수장 등의 수리시설물 유역으로부터 유입된 홍수량을 적용하여 실시간으로 예측수위를 산정하는 딥러닝 기반의 물관리 의사결정 지원정보 제공 방법.
According to claim 1,
The analysis and forecasting unit calculates the hourly runoff through the rainfall-runoff model at the time of flood, calculates the real-time predicted water level by applying the inflow flood volume, and applies the flood volume flowing in from the watershed of a hydraulic facility such as a reservoir or drainage plant to the predicted water level in real time A method of providing information to support decision-making in water management based on deep learning that calculates .
 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템에 있어서,
수리시설물에 설치되어 영상을 촬영하는 CCTV;
수리시설물에 설치되어 계측정보를 계측하는 계측기기;
상기 CCTV로부터 수집된 영상, 상기 계측기기로부터 수집된 계측자료, 공공기관서버로부터 수신된 공공데이터자료 중 적어도 하나에 기초하여 분석 및 예측을 통해 지능형 수자원관리 영상을 생성하는 운영서버;
상기 운영서버로부터 생성된 지능형 수자원관리 영상을 수신하여 영상을 표시하는 관리자단말을 포함하고,
상기 운영서버는,
수자원환경을 분석하여 예상경보단계를 생성하되. 홍수시와 가뭄시(평시)를 구분하여 분석예측하는 분석예측부;
수신된 영상정보, 계측정보, 공공데이터, 생성된 예상경보단계에 기초하여 지능형 수자원관리 영상을 생성하는 영상생성부를 포함하는 딥러닝 기반의 물관리 의사결정 지원정보 제공 시스템.


;
In the deep learning-based water management decision support information providing system,
CCTV installed in repair facilities to record images;
a measuring device installed in a repair facility to measure measurement information;
an operation server for generating an intelligent water resource management image through analysis and prediction based on at least one of the image collected from the CCTV, the measurement data collected from the measuring device, and the public data data received from a public institution server;
and a manager terminal for receiving the intelligent water resource management image generated from the operation server and displaying the image,
The operating server is
Analyze the water resource environment to generate an expected warning level. an analysis prediction unit that analyzes and predicts the flood and drought times (peace);
A deep learning-based water management decision support information providing system including an image generator that generates an intelligent water resource management image based on the received image information, measurement information, public data, and the generated predicted warning stage.


;
KR1020200189272A 2020-12-31 2020-12-31 Deep learning-based water management decision support information provision system and method KR102517917B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020200189272A KR102517917B1 (en) 2020-12-31 2020-12-31 Deep learning-based water management decision support information provision system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020200189272A KR102517917B1 (en) 2020-12-31 2020-12-31 Deep learning-based water management decision support information provision system and method

Publications (2)

Publication Number Publication Date
KR20220096645A true KR20220096645A (en) 2022-07-07
KR102517917B1 KR102517917B1 (en) 2023-04-04

Family

ID=82398801

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020200189272A KR102517917B1 (en) 2020-12-31 2020-12-31 Deep learning-based water management decision support information provision system and method

Country Status (1)

Country Link
KR (1) KR102517917B1 (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110123534A (en) * 2010-05-07 2011-11-15 이메트릭스 주식회사 Web-based drainage controlling system using a real-time water-level estimate
KR20130076158A (en) * 2011-12-28 2013-07-08 주식회사 대영 Intelligence water management automaton system using five senses information based sensor in irrigation facilities
KR20150031997A (en) * 2013-09-17 2015-03-25 제아정보통신(주) Image management system for forecasting a flood
KR20170005553A (en) * 2015-07-06 2017-01-16 주식회사 유일기연 Floods, drought assessment and forecasting techniques development for intelligent service
KR20180098181A (en) * 2017-02-24 2018-09-03 주식회사 케이티 Complexed event processing base smart monitoring platform and smart monitoring method
KR20180117025A (en) * 2017-04-18 2018-10-26 대한민국(행정안전부 국립재난안전연구원장) Method for automatic water level detection based on the intelligent CCTV
KR20190065015A (en) * 2017-12-01 2019-06-11 부산대학교 산학협력단 Support method for responding to stream disaster, and support system for responding to stream disaster
KR102043999B1 (en) * 2019-04-22 2019-11-12 (주)미래로택 Brainy remote terminal unit for flood forecast/warning and rainfall prediction method and fire/inundation related alarm transmission method using the same
KR20200048898A (en) * 2018-10-31 2020-05-08 강원대학교산학협력단 Apparatus and method for analyzing dangerous of flooding or drought using machine-learning
KR20200069211A (en) * 2018-12-06 2020-06-16 한국전자통신연구원 Intelligent river inundation alarming system and the method tehreof

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110123534A (en) * 2010-05-07 2011-11-15 이메트릭스 주식회사 Web-based drainage controlling system using a real-time water-level estimate
KR20130076158A (en) * 2011-12-28 2013-07-08 주식회사 대영 Intelligence water management automaton system using five senses information based sensor in irrigation facilities
KR20150031997A (en) * 2013-09-17 2015-03-25 제아정보통신(주) Image management system for forecasting a flood
KR20170005553A (en) * 2015-07-06 2017-01-16 주식회사 유일기연 Floods, drought assessment and forecasting techniques development for intelligent service
KR20180098181A (en) * 2017-02-24 2018-09-03 주식회사 케이티 Complexed event processing base smart monitoring platform and smart monitoring method
KR20180117025A (en) * 2017-04-18 2018-10-26 대한민국(행정안전부 국립재난안전연구원장) Method for automatic water level detection based on the intelligent CCTV
KR20190065015A (en) * 2017-12-01 2019-06-11 부산대학교 산학협력단 Support method for responding to stream disaster, and support system for responding to stream disaster
KR20200048898A (en) * 2018-10-31 2020-05-08 강원대학교산학협력단 Apparatus and method for analyzing dangerous of flooding or drought using machine-learning
KR20200069211A (en) * 2018-12-06 2020-06-16 한국전자통신연구원 Intelligent river inundation alarming system and the method tehreof
KR102043999B1 (en) * 2019-04-22 2019-11-12 (주)미래로택 Brainy remote terminal unit for flood forecast/warning and rainfall prediction method and fire/inundation related alarm transmission method using the same

Also Published As

Publication number Publication date
KR102517917B1 (en) 2023-04-04

Similar Documents

Publication Publication Date Title
KR101849730B1 (en) Local meteorological measurements based on river flood monitoring system and method
US11238356B2 (en) Method of predicting streamflow data
Dong et al. Probabilistic modeling of cascading failure risk in interdependent channel and road networks in urban flooding
KR102009574B1 (en) Support method for responding to stream disaster, and support system for responding to stream disaster
KR101134631B1 (en) Web-based drainage controlling system using a real-time water-level estimate
KR100899243B1 (en) Disaster state analysis system and method thereof using Geographic Information System
US20230259798A1 (en) Systems and methods for automatic environmental planning and decision support using artificial intelligence and data fusion techniques on distributed sensor network data
KR101290824B1 (en) Infrastructure maintenance and management businesssupport system
Yuan et al. Smart flood resilience: harnessing community-scale big data for predictive flood risk monitoring, rapid impact assessment, and situational awareness
CN109997164A (en) Measurement based on interarrival time and the measuring system and method for the imminent natural disaster sexual behavior part of prediction are provided
CN109141528A (en) A kind of urban track traffic civil engineering facility intelligent real-time monitoring system
CN106373070A (en) Four-prevention method for responding to city rainstorm waterlogging
René et al. A real‐time pluvial flood forecasting system for Castries, St. Lucia
Donratanapat et al. A national scale big data analytics pipeline to assess the potential impacts of flooding on critical infrastructures and communities
KR101954899B1 (en) Method for automatic water level detection based on the intelligent CCTV
US20220228356A1 (en) Actionable stormwater services platform
Ghaith et al. Digital twin: a city-scale flood imitation framework
Bainbridge et al. Detection and forecasting of shallow landslides: lessons from a natural laboratory
JP4799300B2 (en) Monitoring system
KR102517917B1 (en) Deep learning-based water management decision support information provision system and method
Barclay et al. Assessment of advanced LiDAR based tools for enhanced flood prediction
KR20230061012A (en) Big data-based flood warning and prevention system using CCTV and signage
Tripathy et al. Hazard at weather scale for extreme rainfall forecast reduces uncertainty
KR102377929B1 (en) System and method for measuring water level based on neural network module
CN115345348A (en) Intelligent internet of things system for urban road ponding risk management and control

Legal Events

Date Code Title Description
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant