WO2023128014A1 - Air conditioner control apparatus for controlling air conditioner by recognizing occupant in room - Google Patents

Air conditioner control apparatus for controlling air conditioner by recognizing occupant in room Download PDF

Info

Publication number
WO2023128014A1
WO2023128014A1 PCT/KR2021/020265 KR2021020265W WO2023128014A1 WO 2023128014 A1 WO2023128014 A1 WO 2023128014A1 KR 2021020265 W KR2021020265 W KR 2021020265W WO 2023128014 A1 WO2023128014 A1 WO 2023128014A1
Authority
WO
WIPO (PCT)
Prior art keywords
occupant
air conditioner
unit
recognizing
recognition unit
Prior art date
Application number
PCT/KR2021/020265
Other languages
French (fr)
Korean (ko)
Inventor
강정훈
채철승
김형구
Original Assignee
한국전자기술연구원
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 한국전자기술연구원 filed Critical 한국전자기술연구원
Publication of WO2023128014A1 publication Critical patent/WO2023128014A1/en

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/46—Improving electric energy efficiency or saving
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
    • F24F11/79—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling the direction of the supplied air
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • 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
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00—Control inputs relating to users or occupants
    • F24F2120/10—Occupancy
    • F24F2120/12—Position of occupants
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00—Control inputs relating to users or occupants
    • F24F2120/10—Occupancy
    • F24F2120/14—Activity of occupants

Definitions

  • the present invention relates to a control device for controlling an air conditioner, and relates to an air conditioner control device based on occupant presence or absence located in an indoor space.
  • An air conditioner is a device that adjusts air conditions such as indoor temperature or humidity appropriately for health, and is installed to provide a comfortable environment to occupants by adjusting the indoor environment according to circumstances.
  • Conventional air conditioners are not automatically controlled by detecting conditions in the indoor space, and the user has to control the air conditioners one by one, which is cumbersome and user-friendly.
  • the indoor air environment has a different level of comfort that the user feels according to the indoor place.
  • a hallway is a space where most users move without staying
  • a conference room or lecture room is a space where a user stays for a long time without significant movement. Therefore, it is necessary to set the temperature or humidity of the indoor space differently between the hallway and the conference room.
  • the air conditioner continues to operate in the empty indoor space unless the user stops the air conditioner.
  • recently used air conditioners are operated with low noise, so users sometimes forget to turn off the power of the air conditioners.
  • the applicant of the present invention has conducted research and development on an air conditioner control device that can be automatically controlled by detecting such indoor environmental conditions and changes.
  • An object of the present invention is to provide an air conditioner control device capable of controlling an indoor environment according to the type or situation of an indoor space.
  • the present invention includes a photographing unit for photographing an image including a plurality of objects located in an indoor space; a place recognition unit for recognizing the place of the image taken by the photographing unit using the indoor place-by-place characteristics pre-learned by artificial intelligence; an occupant recognizing unit recognizing occupants in the image of the photographing unit; a movement recognition unit recognizing a movement of an occupant in consideration of a change in the occupant's position over time based on a recognition result of the occupant recognizing unit; and a control unit that controls the operation of the air conditioner by integrating the recognition result of the location recognition unit, the occupant recognition unit, or the movement recognition unit.
  • the place recognition unit divides the indoor space into a plurality of areas in the image captured by the photographing unit, detects the characteristics of each indoor place pre-learned by artificial intelligence, and recognizes each area as a plurality of areas. It can be recognized as a separate place.
  • the photographing unit includes a plurality of cameras, a distance sensor, or a direction sensor, wherein the distance sensor senses a scale of an indoor space, and the distance sensor or the direction sensor measures a distance of an occupant based on the camera. and direction can be sensed.
  • the occupant recognizing unit recognizes a plurality of objects included in the image of the photographing unit and recognizes the existence of occupants based on human image data learned through artificial intelligence.
  • the occupant recognizing unit recognizes a change in motion captured in an image of the photographing unit using a result of learning a change in motion of a person, thereby recognizing the existence of an occupant.
  • the movement recognition unit sets a recognition area individually for each occupant and tracks the movement of each occupant, thereby recognizing the occupant's moving direction or moving speed.
  • control unit includes a database for storing air conditioner setting standards according to the type of indoor place, the number of occupants, or the movement status of occupants, and the location recognizing unit, the occupant recognizing unit, or the movement recognizing unit.
  • the air conditioner may be controlled by comparing the recognition result with the setting criterion.
  • control unit may individually control the air conditioner according to the location when the location recognizing unit classifies and recognizes the indoor space as a separate location.
  • the controller may control the direction or intensity of the air conditioner in consideration of the size of the indoor space, the position of occupants in the indoor space, or the number of occupants.
  • control unit may further include a receiving unit for bringing outdoor temperature data from a server storing outdoor temperature information, so that when controlling the air conditioner, the outdoor temperature condition and the indoor space condition may be considered.
  • control unit controls the air conditioner to be turned off when the occupant recognition unit recognizes that there is no occupant, and controls the air conditioner to be turned off when the occupant recognition unit recognizes the occupant but the movement recognition unit does not recognize the movement of the occupant.
  • the movement detection time of the movement recognition unit 70 may be controlled while maintaining the state on.
  • the air conditioner control device of the present invention a comfortable indoor environment can be created and energy can be saved by controlling the air conditioner according to the type of indoor space or the situation of the indoor space.
  • the present invention detects the presence or movement of an occupant and controls the air conditioner according to the situation, it has an advantage of higher user convenience.
  • the present invention it is possible to control according to the type of indoor space by automatically identifying the function of the indoor space where the air conditioner is operated through artificial intelligence learning.
  • FIG. 1 shows a configuration diagram of an air conditioner control device according to an embodiment of the present invention.
  • the air conditioner control device 1 can control the air conditioner 3 installed in the indoor space, and includes a photographing unit 10, a location recognition unit 30, an occupant recognition unit 30, a movement recognition unit 70, and a control unit ( 90) may be included.
  • the photographing unit 10 may capture an image including a plurality of objects located in an indoor space.
  • the photographing unit 10 may include a plurality of cameras 101 , a distance sensor 103 , and a direction sensor 105 .
  • a plurality of cameras 101 may be provided to capture an entire indoor space and generate an image including all objects existing in the indoor space.
  • the distance sensor 103 may sense the size of the indoor space in which the camera 101 is installed and the distance to the occupant based on the camera 101 .
  • the direction sensor 105 may sense a direction in which an occupant is located based on the camera 101 .
  • the distance sensor 103 and the direction sensor 105 are operated when the presence of an occupant is confirmed by the occupant recognizing unit 50, and the occupant's position in the indoor space can be detected by distance and direction.
  • the place recognition unit 30 may recognize the place of the image captured by the photographing unit 10 using the characteristics of each indoor place pre-learned by artificial intelligence.
  • the database 910 of the controller 90 may include place learning data for characteristics of each indoor place learned based on artificial intelligence.
  • the place learning data is a feature of each indoor place, and may be a criterion for distinguishing which place a corresponding indoor space is according to an object extracted from a specific image. For example, when images of a large monitor and a number of desks and chairs are recognized, the corresponding space may be classified as a lecture room. Based on such place learning data, the type of indoor space may be recognized by comparing and analyzing object images recognized from images captured by the photographing unit 10 .
  • the place recognition unit 30 classifies the indoor space into a plurality of areas in the image captured by the photographing unit 10 and detects the characteristics of each indoor place pre-learned by artificial intelligence, and when recognized as a plurality of areas, each Areas can be recognized as separate places. Images of the photographing unit 10 may be images of a plurality of indoor spaces. In this case, the place recognition unit 30 may classify the area of the indoor space and recognize it as a separate place. When the place recognizing unit 30 recognizes a plurality of places and divides the areas, the controller 90 may control the air conditioner 3 differently for each place when controlling the air conditioner 3 thereafter.
  • the place recognition unit 30 recognizes the classroom and the hallway as separate places based on the place learning data for classifying the indoor space
  • the controller 90 may separately control the indoor environment of the lecture room and the hallway.
  • the occupant recognition unit 30 may recognize the occupant from the image of the photographing unit 10 .
  • the occupant recognition unit 30 recognizes a plurality of objects included in the image of the photographing unit 10 and recognizes the presence or absence of occupants based on human image data learned through artificial intelligence.
  • the occupant recognition unit 30 may recognize the occupant dependent part by recognizing the motion change captured in the image of the photographing unit 10 using the result of learning the motion change of the person.
  • the database 910 of the controller 90 may include object learning data for object recognition learned based on artificial intelligence.
  • the object learning data may be an image structured by learning an object by type such as a person, an object, or an animal.
  • the database 910 may include action (motion) images of people frequently seen in a specific space among object learning data for people. For example, depending on whether the place where the air conditioner 3 is to be controlled is a lecture room or an indoor golf course, data for recognizing a person may be different. Since the indoor space may be related to the place, the recognition result of the place recognizing unit 30 may be considered. That is, the occupant recognizing unit 30 is basically based on an object image of a person, and when a person's action image varies depending on a specific place, it can recognize whether an occupant exists in the indoor space in consideration of this.
  • the movement recognition unit 70 may recognize the movement of the occupant in consideration of the occupant's location change over time based on the recognition result of the occupant recognition unit 50 recognizing whether or not there is a occupant in the indoor space. Since the photographing unit 10 may photograph the indoor space multiple times or continuously according to time changes, the photographing unit 10 may generate a plurality of images according to time. Based on this, the movement recognition unit 70 may individually set a recognition area for each occupant and track the movement of each occupant to recognize the occupant's moving direction or moving speed.
  • the control unit 90 may control the operation of the air conditioner by integrating the recognition results of the place recognition unit 30, the occupant recognition unit 50, or the movement recognition unit 70.
  • the controller 90 may include a database 910 and a receiver 930 .
  • the database 910 may store air conditioner setting standards according to the type of indoor place, the number of occupants, or the moving situation of occupants.
  • the control unit 90 may control the air conditioner by comparing a recognition result of the place recognition unit 30, the occupant recognition unit 50, or the movement recognition unit 70 with a setting criterion stored in the database 910.
  • the control unit 90 may individually control the air conditioner 3 according to the location when the location recognition unit 30 classifies and recognizes the indoor space as a separate location.
  • the controller 90 may control the direction or intensity of the air conditioner 3 in consideration of the size of the indoor space, the position of occupants in the indoor space, or the number of occupants.
  • the database 910 may include place learning data serving as a criterion for distinguishing which place an indoor space is with respect to the characteristics of each indoor place learned based on artificial intelligence.
  • the database 910 may include object learning data for object recognition learned based on artificial intelligence.
  • the receiving unit 930 may retrieve outdoor temperature data from a server storing outdoor temperature information, and may control an air conditioner in consideration of outdoor temperature conditions and indoor space conditions.
  • the server updates the outdoor temperature information in real time, and it is sufficient if the weather data can be transmitted to the outside.
  • the receiving unit 930 may be, for example, the Korea Meteorological Administration server, but is not limited thereto.
  • the controller 90 may reflect outdoor temperature data obtained from the receiver 930. For example, when the outdoor temperature is low, the air conditioner 3 may be controlled to maintain a temperature higher than a preset standard for the temperature.
  • the controller 90 may control the operation of the air conditioner according to indoor conditions.
  • the control unit 90 can control the air conditioner to be turned off to reduce unnecessary energy consumption.
  • the movement recognition unit 70 may detect the movement of the occupant by setting the movement detection time of the occupant longer than the standard while maintaining the state of the air conditioner 3 in the on state.
  • the present invention relates to a control device for controlling an air conditioner, and relates to an air conditioner control device based on occupant presence located in an indoor space, and creates a comfortable indoor environment by controlling the air conditioner according to the type of indoor space or the situation of the indoor space. It can be done, and it has the effect of saving energy.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Fuzzy Systems (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Databases & Information Systems (AREA)
  • Air Conditioning Control Device (AREA)
  • Image Analysis (AREA)

Abstract

The present invention comprises: a photographing unit which captures an image including a plurality of objects located in an indoor space; a place recognition unit which recognizes a place of the image captured by the photographing unit by using characteristics of each indoor place pre-learned by artificial intelligence; an occupant recognition unit which recognizes an occupant in the image of the photographing unit; a movement recognition unit which recognizes, on the basis of a result of recognition by the occupant recognition unit, a movement of the occupant in consideration of a change in location of the occupant over time; and a control unit which controls operation of an air conditioner by integrating results of recognition by the place recognition unit, the occupant recognition unit, or the movement recognition unit. Therefore, by controlling the air conditioner according to a type of indoor space or a situation in the indoor space, a pleasant indoor environment may be created and energy may be saved.

Description

실내 재실자를 인식하여 공조기를 제어하는 공조기 제어장치Air conditioner control device that recognizes indoor occupants and controls the air conditioner
본 발명은 공조기를 제어하는 제어장치에 관한 것으로, 실내 공간 내에 위치한 재실자 존부를 기반으로 하는 공조기 제어장치에 관한 것이다.The present invention relates to a control device for controlling an air conditioner, and relates to an air conditioner control device based on occupant presence or absence located in an indoor space.
공조기는 실내의 온도나 습도 따위의 공기 상태를 보건에 알맞게 조절하는 기구로서, 실내 환경을 상황에 따라 조절하여 재실자에게 쾌적한 환경을 제공하기 위해 설치된다. 종래의 공조기는 실내 공간의 상황을 감지하여 자동으로 제어되지 못하고, 사용자가 공조기를 일일이 제어해야 했기 때문에 번거롭고 사용자 이용 편의성의 떨어지는 문제가 있었다.An air conditioner is a device that adjusts air conditions such as indoor temperature or humidity appropriately for health, and is installed to provide a comfortable environment to occupants by adjusting the indoor environment according to circumstances. Conventional air conditioners are not automatically controlled by detecting conditions in the indoor space, and the user has to control the air conditioners one by one, which is cumbersome and user-friendly.
실내 공기 환경은 실내 장소에 따라 사용자가 쾌적하다고 느끼는 수준이 상이하다. 예를 들어, 복도는 사용자가 대부분 머무르지 않고 이동하는 공간인 반면, 회의실 또는 강의실 등은 사용자가 큰 움직임 없이 장시간 머무르는 공간이다. 따라서, 복도와 회의실은 실내 공간의 온도나 습도가 달리 설정될 필요가 있다. The indoor air environment has a different level of comfort that the user feels according to the indoor place. For example, a hallway is a space where most users move without staying, whereas a conference room or lecture room is a space where a user stays for a long time without significant movement. Therefore, it is necessary to set the temperature or humidity of the indoor space differently between the hallway and the conference room.
또한, 사용자가 실내 공간에 들어가서 공조기를 가동시킨 후에 사용자가 외부로 나가는 경우, 사용자가 공조기를 정지시키지 않으면 빈 공간의 실내 공간에 계속해서 공조기가 가동된다. 특히 최근 사용되는 공조기는 저소음으로 가동되므로, 사용자는 공조기의 전원을 끄는 것을 잊는 경우가 있다.In addition, when the user goes outside after entering the indoor space and operating the air conditioner, the air conditioner continues to operate in the empty indoor space unless the user stops the air conditioner. In particular, recently used air conditioners are operated with low noise, so users sometimes forget to turn off the power of the air conditioners.
그러므로, 실내 공간이 종류 또는 기능에 따라 상이한 공조기 제어가 요구되고, 실내에 사용자가 존재하는지 등 상황에 따른 제어가 요구된다. 이에 본 출원인은 이러한 실내 환경 상태 및 변화를 감지하여 자동으로 제어될 수 있는 공조기 제어장치에 관한 연구 개발을 진행하였다. Therefore, different control of the air conditioner is required according to the type or function of the indoor space, and control according to circumstances, such as whether a user is present in the room, is required. Accordingly, the applicant of the present invention has conducted research and development on an air conditioner control device that can be automatically controlled by detecting such indoor environmental conditions and changes.
본 발명은 공조기 제어장치로서, 실내 공간의 종류 또는 상황에 따라 실내 환경을 제어할 수 있는 제어장치를 제공하고자 한다.An object of the present invention is to provide an air conditioner control device capable of controlling an indoor environment according to the type or situation of an indoor space.
본 발명이 해결하려는 과제들은 앞에서 언급한 과제들로 제한되지 않는다. 본 발명의 다른 과제 및 장점들은 아래 설명에 의해 더욱 분명하게 이해될 것이다.The problems to be solved by the present invention are not limited to the problems mentioned above. Other problems and advantages of the present invention will be more clearly understood from the description below.
상기 목적을 달성하기 위하여 본 발명은, 실내 공간에 위치한 복수의 객체들이 포함된 이미지를 촬영하는 촬영부; 인공지능으로 기학습된 실내 장소별 특징을 이용하여 상기 촬영부에서 촬영된 이미지의 장소를 인식하는 장소 인식부; 상기 촬영부의 이미지에서 재실자를 인식하는 재실자 인식부; 상기 재실자 인식부의 인식 결과를 기반으로 시간에 따른 재실자의 위치 변화를 고려하여 재실자의 이동을 인식하는 이동 인식부; 및 상기 장소 인식부, 상기 재실자 인식부 또는 상기 이동 인식부의 인식 결과를 통합하여 공조기의 운전을 제어하는 제어부를 포함하는 특징으로 한다.In order to achieve the above object, the present invention includes a photographing unit for photographing an image including a plurality of objects located in an indoor space; a place recognition unit for recognizing the place of the image taken by the photographing unit using the indoor place-by-place characteristics pre-learned by artificial intelligence; an occupant recognizing unit recognizing occupants in the image of the photographing unit; a movement recognition unit recognizing a movement of an occupant in consideration of a change in the occupant's position over time based on a recognition result of the occupant recognizing unit; and a control unit that controls the operation of the air conditioner by integrating the recognition result of the location recognition unit, the occupant recognition unit, or the movement recognition unit.
바람직하게, 상기 장소 인식부는, 상기 촬영부를 통해 촬영된 이미지에서, 실내 공간을 복수의 영역으로 구분하여 인공지능으로 기학습된 실내 장소별 특징을 감지하며, 복수의 영역으로 인식되는 경우 각 영역을 별개의 장소로 인식할 수 있다.Preferably, the place recognition unit divides the indoor space into a plurality of areas in the image captured by the photographing unit, detects the characteristics of each indoor place pre-learned by artificial intelligence, and recognizes each area as a plurality of areas. It can be recognized as a separate place.
바람직하게, 상기 촬영부는, 복수의 카메라, 거리 센서 또는 방향 센서를 포함하며, 상기 거리 센서는, 실내 공간의 규모를 센싱하고, 상기 거리 센서 또는 상기 방향 센서는, 상기 카메라를 기준으로 재실자의 거리와 방향을 센싱할 수 있다.Preferably, the photographing unit includes a plurality of cameras, a distance sensor, or a direction sensor, wherein the distance sensor senses a scale of an indoor space, and the distance sensor or the direction sensor measures a distance of an occupant based on the camera. and direction can be sensed.
바람직하게, 상기 재실자 인식부는, 상기 촬영부의 이미지 내에 포함된 복수의 객체를 인식하고, 인공지능으로 학습된 사람 이미지 데이터를 기반으로 재실자의 존부를 인식할 수 있다.Preferably, the occupant recognizing unit recognizes a plurality of objects included in the image of the photographing unit and recognizes the existence of occupants based on human image data learned through artificial intelligence.
바람직하게, 상기 재실자 인식부는, 사람의 모션 변화를 학습한 결과를 이용하여, 상기 촬영부의 이미지에서 포착되는 모션 변화를 인식하여 재실자의 존부를 인식할 수 있다.Preferably, the occupant recognizing unit recognizes a change in motion captured in an image of the photographing unit using a result of learning a change in motion of a person, thereby recognizing the existence of an occupant.
바람직하게, 상기 이동 인식부는, 각 재실자에 대해 개별적으로 인식영역을 설정하고 개별 재실자의 이동을 추적하여, 재실자의 이동 방향 또는 이동 속도를 인식할 수 있다.Preferably, the movement recognition unit sets a recognition area individually for each occupant and tracks the movement of each occupant, thereby recognizing the occupant's moving direction or moving speed.
바람직하게, 상기 제어부는, 실내 장소의 종류, 재실자의 수 또는 재실자의 이동상황에 따른 공조기의 설정 기준을 저장하는 데이터베이스를 포함하여, 상기 장소 인식부, 상기 재실자 인식부 또는 상기 이동 인식부에서의 인식 결과와 상기 설정 기준을 비교하여 공조기를 제어할 수 있다.Preferably, the control unit includes a database for storing air conditioner setting standards according to the type of indoor place, the number of occupants, or the movement status of occupants, and the location recognizing unit, the occupant recognizing unit, or the movement recognizing unit. The air conditioner may be controlled by comparing the recognition result with the setting criterion.
바람직하게, 상기 제어부는, 상기 장소 인식부에서 실내 공간을 별개의 장소로 구분하여 인식한 경우 장소에 따라 공조기를 개별적으로 제어할 수 있다.Preferably, the control unit may individually control the air conditioner according to the location when the location recognizing unit classifies and recognizes the indoor space as a separate location.
바람직하게, 상기 제어부는, 실내 공간의 규모, 실내 공간 내에서의 재실자의 위치 또는 재실자의 수를 고려하여 공조기의 방향 또는 세기를 제어할 수 있다.Preferably, the controller may control the direction or intensity of the air conditioner in consideration of the size of the indoor space, the position of occupants in the indoor space, or the number of occupants.
바람직하게, 상기 제어부는, 실외의 기온 정보가 저장된 서버에서 실외 기온 데이터를 가져오는 수신부를 더 포함하여, 공조기 제어 시, 실외 기온 상태 및 실내 공간 상황을 고려할 수 있다.Preferably, the control unit may further include a receiving unit for bringing outdoor temperature data from a server storing outdoor temperature information, so that when controlling the air conditioner, the outdoor temperature condition and the indoor space condition may be considered.
바람직하게, 상기 제어부는, 상기 재실자 인식부에서 재실자가 없는 것으로 인식되는 경우 공조기가 off 되도록 제어하고, 상기 재실자 인식부에서 재실자는 인식되지만 상기 이동 인식부에서 재실자의 움직임이 인식되지 않는 경우 공조기의 상태를 on으로 유지하면서 이동 인식부(70)의 이동 감지 시간을 제어할 수 있다.Preferably, the control unit controls the air conditioner to be turned off when the occupant recognition unit recognizes that there is no occupant, and controls the air conditioner to be turned off when the occupant recognition unit recognizes the occupant but the movement recognition unit does not recognize the movement of the occupant. The movement detection time of the movement recognition unit 70 may be controlled while maintaining the state on.
본 발명의 공조기 제어장치에 따르면, 실내 공간의 종류 또는 실내 공간의 상황에 따라 공조기가 제어됨으로써 쾌적한 실내 환경을 조성할 수 있으며, 에너지를 절감할 수 있는 효과가 있다. 특히 본 발명은 재실자의 존부 또는 이동을 감지하여 상황에 따라 공조기를 제어하므로, 더욱 사용자 편의성이 높은 장점을 가진다.According to the air conditioner control device of the present invention, a comfortable indoor environment can be created and energy can be saved by controlling the air conditioner according to the type of indoor space or the situation of the indoor space. In particular, since the present invention detects the presence or movement of an occupant and controls the air conditioner according to the situation, it has an advantage of higher user convenience.
본 발명은 공조기가 가동되는 실내 공간이 어떤 기능을 하는지 그 종류를 인공지능 학습을 통해 자동으로 파악하여 실내 공간의 종류에 따른 제어가 가능하다. 또한, 본 발명은 실내 공간에 재실자가 있는지 그 존부와 재실자의 수 또는 위치를 파악하여 재실 상태에 따른 공조기 제어가 가능하다. 재실자가 실내 공간에서 이동하는 경우, 재실자의 이동 방향 또는 이동 속도를 감지하여 공조기 제어에 반영한다. 이를 통해 재실자가 실내 공간에서 외부로 나가는지, 다른 실내 공간으로 이동하는지 등을 파악할 수 있다.According to the present invention, it is possible to control according to the type of indoor space by automatically identifying the function of the indoor space where the air conditioner is operated through artificial intelligence learning. In addition, according to the present invention, it is possible to control an air conditioner according to an occupant state by determining whether or not there are occupants in an indoor space and the number or location of occupants. When an occupant moves in the indoor space, the moving direction or speed of the occupant is detected and reflected in the air conditioner control. Through this, it is possible to determine whether an occupant goes out from an indoor space or moves to another indoor space.
도 1은 본 발명의 실시 예에 따른 공조기 제어장치의 구성도를 나타낸다.1 shows a configuration diagram of an air conditioner control device according to an embodiment of the present invention.
이하, 첨부된 도면들에 기재된 내용들을 참조하여 본 발명을 상세히 설명한다. 다만, 본 발명이 예시적 실시 예들에 의해 제한되거나 한정되는 것은 아니다. 각 도면에 제시된 동일 참조부호는 실질적으로 동일한 기능을 수행하는 부재를 나타낸다.Hereinafter, the present invention will be described in detail with reference to the contents described in the accompanying drawings. However, the present invention is not limited or limited by exemplary embodiments. The same reference numerals in each figure indicate members performing substantially the same function.
본 발명의 목적 및 효과는 하기의 설명에 의해서 자연스럽게 이해되거나 보다 분명해질 수 있으며, 하기의 기재만으로 본 발명의 목적 및 효과가 제한되는 것은 아니다. 또한, 본 발명을 설명함에 있어서 본 발명과 관련된 공지 기술에 대한 구체적인 설명이, 본 발명의 요지를 불필요하게 흐릴 수 있다고 판단되는 경우에는 그 상세한 설명을 생략하기로 한다.The objects and effects of the present invention can be naturally understood or more clearly understood by the following description, and the objects and effects of the present invention are not limited only by the following description. In addition, in describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted.
도 1은 본 발명의 실시 예에 따른 공조기 제어장치(1)의 구성도를 나타낸다. 공조기 제어장치(1)는 실내 공간에 설치된 공조기(3)를 제어할 수 있으며, 촬영부(10), 장소 인식부(30), 재실자 인식부(30), 이동 인식부(70) 및 제어부(90)를 포함할 수 있다.1 shows a configuration diagram of an air conditioner control device 1 according to an embodiment of the present invention. The air conditioner control device 1 can control the air conditioner 3 installed in the indoor space, and includes a photographing unit 10, a location recognition unit 30, an occupant recognition unit 30, a movement recognition unit 70, and a control unit ( 90) may be included.
촬영부(10)는 실내 공간에 위치한 복수의 객체들이 포함된 이미지를 촬영할 수 있다. 촬영부(10)는 복수의 카메라(101), 거리 센서(103), 방향 센서(105)를 포함할 수 있다. 카메라(101)는 복수 개 마련되어 실내 공간을 전체적으로 촬영하여 실내 공간 내에 존재하는 모든 객체가 포함된 이미지를 생성할 수 있다. 거리 센서(103)는 카메라(101)가 설치된 실내 공간의 규모와 카메라(101)를 기준으로 재실자와의 거리를 센싱할 수 있다. 방향 센서(105)는 카메라(101)를 기준으로 재실자가 위치한 방향을 센싱할 수 있다. 거리 센서(103)와 방향 센서(105)는 재실자 인식부(50)에서 재실자의 존재가 확인된 경우에 동작하여 실내 공간에서의 재실자의 위치를 거리와 방향으로 파악할 수 있다.The photographing unit 10 may capture an image including a plurality of objects located in an indoor space. The photographing unit 10 may include a plurality of cameras 101 , a distance sensor 103 , and a direction sensor 105 . A plurality of cameras 101 may be provided to capture an entire indoor space and generate an image including all objects existing in the indoor space. The distance sensor 103 may sense the size of the indoor space in which the camera 101 is installed and the distance to the occupant based on the camera 101 . The direction sensor 105 may sense a direction in which an occupant is located based on the camera 101 . The distance sensor 103 and the direction sensor 105 are operated when the presence of an occupant is confirmed by the occupant recognizing unit 50, and the occupant's position in the indoor space can be detected by distance and direction.
장소 인식부(30)는 인공지능으로 기학습된 실내 장소별 특징을 이용하여 촬영부(10)에서 촬영된 이미지의 장소를 인식할 수 있다. 제어부(90)의 데이터베이스(910)는 인공지능 기반으로 학습된 실내 장소별 특징에 대한 장소 학습 데이터를 포함할 수 있다. 장소 학습 데이터는 실내 장소별 특징으로서, 특정 이미지에서 추출되는 객체에 따라 해당 실내 공간이 어느 장소인지 구분하는 기준이 될 수 있다. 예를 들어, 큰 모니터, 다수의 책상과 의자 이미지가 인식되는 경우 해당 공간은 강의실인 것으로 분류될 수 있다. 이러한 장소학습 데이터를 기반으로 하여, 촬영부(10)에서 촬영된 이미지에서 인식된 객체 이미지를 비교분석하여 실내 공간의 종류를 인식할 수 있다.The place recognition unit 30 may recognize the place of the image captured by the photographing unit 10 using the characteristics of each indoor place pre-learned by artificial intelligence. The database 910 of the controller 90 may include place learning data for characteristics of each indoor place learned based on artificial intelligence. The place learning data is a feature of each indoor place, and may be a criterion for distinguishing which place a corresponding indoor space is according to an object extracted from a specific image. For example, when images of a large monitor and a number of desks and chairs are recognized, the corresponding space may be classified as a lecture room. Based on such place learning data, the type of indoor space may be recognized by comparing and analyzing object images recognized from images captured by the photographing unit 10 .
장소 인식부(30)는 촬영부(10)를 통해 촬영된 이미지에서, 실내 공간을 복수의 영역으로 구분하여 인공지능으로 기학습된 실내 장소별 특징을 감지하며, 복수의 영역으로 인식되는 경우 각 영역을 별개의 장소로 인식할 수 있다. 촬영부(10)의 이미지가 복수의 실내 공간이 촬영된 것일 수 있다. 이 경우 장소 인식부(30)는 실내 공간의 영역을 구분하여 별개의 장소로 인식할 수 있다. 장소 인식부(30)에서 복수의 장소로 인식하여 영역을 구분하는 경우에는, 이후 제어부(90)가 공조기(3)를 제어함에 있어서 각 장소별로 공조기(3)를 상이하게 제어할 수 있다. 예를 들어, 촬영부(10)의 이미지에 강의실과 복도가 함께 포함된 경우, 장소 인식부(30)는 실내 공간 분류를 위한 장소 학습 데이터를 기반으로 강의실과 복도를 별개의 장소로 인식하고, 제어부(90)는 강의실과 복도의 실내 환경을 구분하여 제어할 수 있다.The place recognition unit 30 classifies the indoor space into a plurality of areas in the image captured by the photographing unit 10 and detects the characteristics of each indoor place pre-learned by artificial intelligence, and when recognized as a plurality of areas, each Areas can be recognized as separate places. Images of the photographing unit 10 may be images of a plurality of indoor spaces. In this case, the place recognition unit 30 may classify the area of the indoor space and recognize it as a separate place. When the place recognizing unit 30 recognizes a plurality of places and divides the areas, the controller 90 may control the air conditioner 3 differently for each place when controlling the air conditioner 3 thereafter. For example, when a classroom and a hallway are included in the image of the photographing unit 10, the place recognition unit 30 recognizes the classroom and the hallway as separate places based on the place learning data for classifying the indoor space, The controller 90 may separately control the indoor environment of the lecture room and the hallway.
재실자 인식부(30)는 촬영부(10)의 이미지에서 재실자를 인식할 수 있다. 재실자 인식부(30)는 촬영부(10)의 이미지 내에 포함된 복수의 객체를 인식하고, 인공지능으로 학습된 사람 이미지 데이터를 기반으로 재실자의 존부를 인식할 수 있다. 재실자 인식부(30)는 사람의 모션 변화를 학습한 결과를 이용하여, 촬영부(10)의 이미지에서 포착되는 모션 변화를 인식하여 재실자의존부를 인식할 수 있다.The occupant recognition unit 30 may recognize the occupant from the image of the photographing unit 10 . The occupant recognition unit 30 recognizes a plurality of objects included in the image of the photographing unit 10 and recognizes the presence or absence of occupants based on human image data learned through artificial intelligence. The occupant recognition unit 30 may recognize the occupant dependent part by recognizing the motion change captured in the image of the photographing unit 10 using the result of learning the motion change of the person.
제어부(90)의 데이터베이스(910)는 인공지능 기반으로 학습된 객체 인식에 대한 객체 학습 데이터를 포함할 수 있다. 객체 학습 데이터는 객체를 사람, 물건, 동물 등 종류별로 학습하여 구조화된 이미지일 수 있다. 특히, 데이터베이스(910)는 사람에 대한 객체 학습 데이터 중 특정 공간에서 자주 보여지는 사람의 행동(모션) 이미지를 포함할 수 있다. 예를 들어, 공조기(3)를 제어하려는 장소가 강의실인지 또는 실내 골프장인지에 따라 주로 사람임을 인식하는 데이터가 상이할 수 있다. 이는 실내 공간이 장소와 연관될 수 있으므로, 장소 인식부(30)의 인식 결과가 고려될 수 있다. 즉, 재실자 인식부(30)는 기본적으로 사람이라는 객체의 이미지를 기반으로 하며, 특정 장소에 따라 사람의 행동 이미지가 달라지는 경우 이를 고려하여 실내 공간에 재실자가 존재하는지를 인식할 수 있다.The database 910 of the controller 90 may include object learning data for object recognition learned based on artificial intelligence. The object learning data may be an image structured by learning an object by type such as a person, an object, or an animal. In particular, the database 910 may include action (motion) images of people frequently seen in a specific space among object learning data for people. For example, depending on whether the place where the air conditioner 3 is to be controlled is a lecture room or an indoor golf course, data for recognizing a person may be different. Since the indoor space may be related to the place, the recognition result of the place recognizing unit 30 may be considered. That is, the occupant recognizing unit 30 is basically based on an object image of a person, and when a person's action image varies depending on a specific place, it can recognize whether an occupant exists in the indoor space in consideration of this.
이동 인식부(70)는 재실자 인식부(50)에서 실내 공간에 재실자가 존재하는지를 인식한 인식 결과를 기반으로 시간에 따른 재실자의 위치 변화를 고려하여 재실자의 이동을 인식할 수 있다. 촬영부(10)는 시간 변화에 따라 복수회 또는 연속적으로 실내 공간을 촬영할 수 있으므로, 촬영부(10)는 시간에 따라 복수의 이미지를 생성할 수 있다. 이를 기반으로 이동 인식부(70)는 각 재실자에 대해 개별적으로 인식영역을 설정하고 개별 재실자의 이동을 추적하여, 재실자의 이동 방향 또는 이동 속도를 인식할 수 있다. The movement recognition unit 70 may recognize the movement of the occupant in consideration of the occupant's location change over time based on the recognition result of the occupant recognition unit 50 recognizing whether or not there is a occupant in the indoor space. Since the photographing unit 10 may photograph the indoor space multiple times or continuously according to time changes, the photographing unit 10 may generate a plurality of images according to time. Based on this, the movement recognition unit 70 may individually set a recognition area for each occupant and track the movement of each occupant to recognize the occupant's moving direction or moving speed.
제어부(90)는 장소 인식부(30), 재실자 인식부(50) 또는 이동 인식부(70)의 인식 결과를 통합하여 공조기의 운전을 제어할 수 있다.The control unit 90 may control the operation of the air conditioner by integrating the recognition results of the place recognition unit 30, the occupant recognition unit 50, or the movement recognition unit 70.
제어부(90)는 데이터베이스(910), 수신부(930)를 포함할 수 있다. The controller 90 may include a database 910 and a receiver 930 .
데이터베이스(910)는 실내 장소의 종류, 재실자의 수 또는 재실자의 이동상황에 따른 공조기의 설정 기준을 저장할 수 있다. 제어부(90)는 장소 인식부(30), 재실자 인식부(50) 또는 이동 인식부(70)에서의 인식 결과와 데이터베이스(910)에 저장된 설정 기준을 비교하여 공조기를 제어할 수 있다.The database 910 may store air conditioner setting standards according to the type of indoor place, the number of occupants, or the moving situation of occupants. The control unit 90 may control the air conditioner by comparing a recognition result of the place recognition unit 30, the occupant recognition unit 50, or the movement recognition unit 70 with a setting criterion stored in the database 910.
제어부(90)는 장소 인식부(30)에서 실내 공간을 별개의 장소로 구분하여 인식한 경우 장소에 따라 공조기(3)를 개별적으로 제어할 수 있다. 제어부(90)는 실내 공간의 규모, 실내 공간 내에서의 재실자의 위치 또는 재실자의 수를 고려하여 공조기(3)의 방향 또는 세기를 제어할 수 있다.The control unit 90 may individually control the air conditioner 3 according to the location when the location recognition unit 30 classifies and recognizes the indoor space as a separate location. The controller 90 may control the direction or intensity of the air conditioner 3 in consideration of the size of the indoor space, the position of occupants in the indoor space, or the number of occupants.
또한, 데이터베이스(910)는 인공지능 기반으로 학습된 실내 장소별 특징에 대해 실내 공간이 어느 장소인지 구분하는 기준이 되는 장소 학습 데이터를 포함할 수 있다. 데이터베이스(910)는 인공지능 기반으로 학습된 객체 인식에 대한 객체 학습 데이터를 포함할 수 있다. In addition, the database 910 may include place learning data serving as a criterion for distinguishing which place an indoor space is with respect to the characteristics of each indoor place learned based on artificial intelligence. The database 910 may include object learning data for object recognition learned based on artificial intelligence.
수신부(930)는 실외의 기온 정보가 저장된 서버에서 실외 기온 데이터를 가져올 수 있으며, 실외 기온 상태 및 실내 공간 상황을 고려하여 공조기를 제어할 수 있다. 서버는 실외의 기온 정보를 실시간으로 업데이트하며 외부로 기상 데이터를 전송할 수 있으면 충분하다. 수신부(930)는 예를 들어 기상청 서버일 수 있으나, 이에 제한되는 것은 아니다. 제어부(90)는 공조기(3) 제어 시, 수신부(930)에서 가져온 실외 기온 데이터를 반영할 수 있다. 예를 들어 실외 기온이 낮은 경우, 온도에 대해 공조기(3)에 기설정된 설정 기준보다 높은 온도를 유지하도록 제어할 수 있다.The receiving unit 930 may retrieve outdoor temperature data from a server storing outdoor temperature information, and may control an air conditioner in consideration of outdoor temperature conditions and indoor space conditions. The server updates the outdoor temperature information in real time, and it is sufficient if the weather data can be transmitted to the outside. The receiving unit 930 may be, for example, the Korea Meteorological Administration server, but is not limited thereto. When controlling the air conditioner 3, the controller 90 may reflect outdoor temperature data obtained from the receiver 930. For example, when the outdoor temperature is low, the air conditioner 3 may be controlled to maintain a temperature higher than a preset standard for the temperature.
제어부(90)는 실내 상황에 따라 공조기의 동작을 제어할 수 있다. 재실자 인식부(30)에서 재실자가 없는 것으로 인식되는 경우, 제어부(90)는 공조기가 off 되도록 제어하여 불필요한 에너지 소비를 감축시킬 수 있다. 한편, 재실자 인식부(30)에서 재실자가 인식되지만, 이동 인식부(70)에서는 재실자의 움직임이 감지되지 않는 경우가 있을 수 있다. 이 경우 재실자의 존재는 인식되므로 공조기(3)의 상태를 on으로 유지하면서, 이동 인식부(70)는 재실자의 움직임 감지 시간을 기준보다 더 길게 설정하여 움직임을 감지할 수 있다.The controller 90 may control the operation of the air conditioner according to indoor conditions. When the occupant recognition unit 30 recognizes that there is no occupant, the control unit 90 can control the air conditioner to be turned off to reduce unnecessary energy consumption. Meanwhile, although the occupant is recognized by the occupant recognition unit 30 , there may be a case in which the motion of the occupant is not detected by the movement recognition unit 70 . In this case, since the presence of the occupant is recognized, the movement recognition unit 70 may detect the movement of the occupant by setting the movement detection time of the occupant longer than the standard while maintaining the state of the air conditioner 3 in the on state.
이상에서 대표적인 실시예를 통하여 본 발명을 상세하게 설명하였으나, 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자는 상술한 실시예에 대하여 본 발명의 범주에서 벗어나지 않는 한도 내에서 다양한 변형이 가능함을 이해할 것이다. 그러므로 본 발명의 권리 범위는 설명한 실시예에 국한되어 정해져서는 안 되며, 후술하는 특허청구범위뿐만 아니라 특허청구범위와 균등 개념으로부터 도출되는 모든 변경 또는 변형된 형태에 의하여 정해져야 한다. Although the present invention has been described in detail through representative embodiments, those skilled in the art will understand that various modifications are possible to the above-described embodiments without departing from the scope of the present invention. will be. Therefore, the scope of the present invention should not be limited to the described embodiments and should not be defined, and should be defined by all changes or modifications derived from the claims and equivalent concepts as well as the claims to be described later.
(부호의 설명)(Description of code)
1 : 공조기 제어장치1: Air conditioner control device
10 : 촬영부10: shooting department
101 : 카메라101: camera
103 : 거리 센서103: distance sensor
105 : 방향 센서105: direction sensor
30 : 장소 인식부30: place recognition unit
50 : 재실자 인식부50: occupant recognition unit
70 : 이동 인식부70: movement recognition unit
90 : 제어부90: control unit
910 : 데이터베이스910: database
930 : 수신부930: receiver
본 발명은 공조기를 제어하는 제어장치에 관한 것으로, 실내 공간 내에 위치한 재실자 존부를 기반으로 하는 공조기 제어장치에 관한 것으로, 실내 공간의 종류 또는 실내 공간의 상황에 따라 공조기가 제어됨으로써 쾌적한 실내 환경을 조성할 수 있으며, 에너지를 절감할 수 있는 효과가 있다.The present invention relates to a control device for controlling an air conditioner, and relates to an air conditioner control device based on occupant presence located in an indoor space, and creates a comfortable indoor environment by controlling the air conditioner according to the type of indoor space or the situation of the indoor space. It can be done, and it has the effect of saving energy.

Claims (11)

  1. 실내 공간에 위치한 복수의 객체들이 포함된 이미지를 촬영하는 촬영부;a photographing unit for capturing an image including a plurality of objects located in an indoor space;
    인공지능으로 기학습된 실내 장소별 특징을 이용하여 상기 촬영부에서 촬영된 이미지의 장소를 인식하는 장소 인식부;a place recognition unit for recognizing the place of the image taken by the photographing unit using the indoor place-by-place characteristics pre-learned by artificial intelligence;
    상기 촬영부의 이미지에서 재실자를 인식하는 재실자 인식부;an occupant recognizing unit recognizing occupants in the image of the photographing unit;
    상기 재실자 인식부의 인식 결과를 기반으로 시간에 따른 재실자의 위치 변화를 고려하여 재실자의 이동을 인식하는 이동 인식부; 및a movement recognition unit recognizing a movement of an occupant in consideration of a change in the occupant's position over time based on a recognition result of the occupant recognizing unit; and
    상기 장소 인식부, 상기 재실자 인식부 또는 상기 이동 인식부의 인식 결과를 통합하여 공조기의 운전을 제어하는 제어부를 포함하는 공조기 제어장치.and a control unit that controls operation of the air conditioner by integrating a recognition result of the location recognition unit, the occupant recognition unit, or the movement recognition unit.
  2. 제 1 항에 있어서,According to claim 1,
    상기 장소 인식부는,The location recognition unit,
    상기 촬영부를 통해 촬영된 이미지에서, 실내 공간을 복수의 영역으로 구분하여 인공지능으로 기학습된 실내 장소별 특징을 감지하며, 복수의 영역으로 인식되는 경우 각 영역을 별개의 장소로 인식하는 것을 특징으로 하는 공조기 제어장치.In the image captured by the photographing unit, the indoor space is divided into a plurality of areas, and the characteristics of each indoor place pre-learned by artificial intelligence are detected, and when recognized as a plurality of areas, each area is recognized as a separate place. Air conditioner control device to be.
  3. 제 1 항에 있어서,According to claim 1,
    상기 촬영부는,the filming unit,
    복수의 카메라, 거리 센서 또는 방향 센서를 포함하며,Includes multiple cameras, distance sensors or orientation sensors;
    상기 거리 센서는, The distance sensor,
    실내 공간의 규모를 센싱하고, Sensing the size of the indoor space,
    상기 거리 센서 또는 상기 방향 센서는,The distance sensor or the direction sensor,
    상기 카메라를 기준으로 재실자의 거리와 방향을 센싱하는 것을 특징으로 하는 공조기 제어장치.An air conditioner control device characterized in that for sensing the distance and direction of the occupant based on the camera.
  4. 제 1 항에 있어서,According to claim 1,
    상기 재실자 인식부는,The occupant recognition unit,
    상기 촬영부의 이미지 내에 포함된 복수의 객체를 인식하고, 인공지능으로 학습된 사람 이미지 데이터를 기반으로 재실자의 존부를 인식하는 것을 특징으로 하는 공조기 제어장치.The air conditioner control device characterized in that recognizing a plurality of objects included in the image of the photographing unit and recognizing the presence or absence of occupants based on human image data learned by artificial intelligence.
  5. 제 1 항에 있어서,According to claim 1,
    상기 재실자 인식부는,The occupant recognition unit,
    사람의 모션 변화를 학습한 결과를 이용하여, 상기 촬영부의 이미지에서 포착되는 모션 변화를 인식하여 재실자의 존부를 인식하는 것을 특징으로 하는 공조기 제어장치.The air conditioner control device characterized in that for recognizing the existence of an occupant by recognizing the motion change captured in the image of the photographing unit by using the result of learning the motion change of the person.
  6. 제 1 항에 있어서,According to claim 1,
    상기 이동 인식부는,The movement recognition unit,
    각 재실자에 대해 개별적으로 인식영역을 설정하고 개별 재실자의 이동을 추적하여, 재실자의 이동 방향 또는 이동 속도를 인식하는 것을 특징으로 하는 공조기 제어장치.An air conditioner control device characterized in that a recognition area is individually set for each occupant, and the movement direction or speed of the occupant is recognized by tracking the movement of the individual occupant.
  7. 제 1 항에 있어서,According to claim 1,
    상기 제어부는,The control unit,
    실내 장소의 종류, 재실자의 수 또는 재실자의 이동상황에 따른 공조기의 설정 기준을 저장하는 데이터베이스를 포함하여,Including a database that stores the air conditioner setting criteria according to the type of indoor place, the number of occupants, or the movement of occupants,
    상기 장소 인식부, 상기 재실자 인식부 또는 상기 이동 인식부에서의 인식 결과와 상기 설정 기준을 비교하여 공조기를 제어하는 것을 특징으로 하는 공조기 제어장치.The air conditioner control apparatus according to claim 1 , wherein the air conditioner is controlled by comparing a recognition result of the location recognition unit, the occupant recognition unit, or the movement recognition unit with the set standard.
  8. 제 2 항에 있어서,According to claim 2,
    상기 제어부는,The control unit,
    상기 장소 인식부에서 실내 공간을 별개의 장소로 구분하여 인식한 경우 장소에 따라 공조기를 개별적으로 제어하는 것을 특징으로 하는 공조기 제어장치.The air conditioner control device according to claim 1 , wherein the air conditioner control device individually controls the air conditioner according to the location when the location recognizing unit classifies and recognizes the indoor space as a separate location.
  9. 제 3 항에 있어서,According to claim 3,
    상기 제어부는,The control unit,
    실내 공간의 규모, 실내 공간 내에서의 재실자의 위치 또는 재실자의 수를 고려하여 공조기의 방향 또는 세기를 제어하는 것을 특징으로 하는 공조기 제어장치.An air conditioner control device characterized in that for controlling the direction or intensity of an air conditioner in consideration of the size of an indoor space, the position of occupants in the indoor space, or the number of occupants.
  10. 제 1 항에 있어서,According to claim 1,
    상기 제어부는,The control unit,
    실외의 기온 정보가 저장된 서버에서 실외 기온 데이터를 가져오는 수신부를 더 포함하여,Further comprising a receiving unit for obtaining outdoor temperature data from a server storing outdoor temperature information,
    공조기 제어 시, 실외 기온 상태 및 실내 공간 상황을 고려하는 것을 특징으로 하는 공조기 제어장치.An air conditioner control device characterized in that when controlling an air conditioner, considering outdoor temperature conditions and indoor space conditions.
  11. 제 1 항에 있어서,According to claim 1,
    상기 제어부는,The control unit,
    상기 재실자 인식부에서 재실자가 없는 것으로 인식되는 경우 공조기가 off 되도록 제어하고, 상기 재실자 인식부에서 재실자는 인식되지만 상기 이동 인식부에서 재실자의 움직임이 인식되지 않는 경우 공조기의 상태를 on으로 유지하면서 이동 인식부(70)의 이동 감지 시간을 제어하는 것을 특징으로 하는 공조기 제어장치.When the occupant recognizing unit recognizes that there is no occupant, the air conditioner is controlled to be turned off, and when the occupant is recognized by the occupant recognizing unit but the motion of the occupant is not recognized by the movement recognizing unit, the air conditioner moves while maintaining the on state. An air conditioner control device characterized in that for controlling the movement detection time of the recognition unit (70).
PCT/KR2021/020265 2021-12-29 2021-12-30 Air conditioner control apparatus for controlling air conditioner by recognizing occupant in room WO2023128014A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020210191490A KR102558090B1 (en) 2021-12-29 2021-12-29 An air conditioner control device that controls the air conditioner by recognizing the occupants of the room
KR10-2021-0191490 2021-12-29

Publications (1)

Publication Number Publication Date
WO2023128014A1 true WO2023128014A1 (en) 2023-07-06

Family

ID=86999324

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/020265 WO2023128014A1 (en) 2021-12-29 2021-12-30 Air conditioner control apparatus for controlling air conditioner by recognizing occupant in room

Country Status (2)

Country Link
KR (1) KR102558090B1 (en)
WO (1) WO2023128014A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160120607A (en) * 2015-04-08 2016-10-18 주식회사 태양씨앤엘 Air purification system and control method thereof
KR20190098101A (en) * 2019-03-20 2019-08-21 엘지전자 주식회사 Air conditioner
KR20190118337A (en) * 2018-04-10 2019-10-18 엘지전자 주식회사 Air-conditioner with region selective operation, cloud server, and method of operating thereof
KR20210045738A (en) * 2019-10-17 2021-04-27 주식회사 한국건설환경 A system for ventilating using artificial intelligence
KR102314903B1 (en) * 2021-05-25 2021-10-19 김유성 Method And Apparatus for Controlling Building Based on Image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160120607A (en) * 2015-04-08 2016-10-18 주식회사 태양씨앤엘 Air purification system and control method thereof
KR20190118337A (en) * 2018-04-10 2019-10-18 엘지전자 주식회사 Air-conditioner with region selective operation, cloud server, and method of operating thereof
KR20190098101A (en) * 2019-03-20 2019-08-21 엘지전자 주식회사 Air conditioner
KR20210045738A (en) * 2019-10-17 2021-04-27 주식회사 한국건설환경 A system for ventilating using artificial intelligence
KR102314903B1 (en) * 2021-05-25 2021-10-19 김유성 Method And Apparatus for Controlling Building Based on Image

Also Published As

Publication number Publication date
KR102558090B1 (en) 2023-07-24
KR20230101404A (en) 2023-07-06

Similar Documents

Publication Publication Date Title
US11151864B2 (en) System and method for monitoring a property using drone beacons
US6645066B2 (en) Space-conditioning control employing image-based detection of occupancy and use
JP7224527B2 (en) Elevator system and elevator control system
US20130293721A1 (en) Imaging apparatus, imaging method, and program
KR102481995B1 (en) On-device AI apparatus for detecting abnormal behavior automatically based on deep learning and operating method thereof
JP2011137589A (en) Air conditioner and control device of the same
CN110989387B (en) Intelligent household system, air conditioning equipment and intelligent door lock
KR102314903B1 (en) Method And Apparatus for Controlling Building Based on Image
KR20190044867A (en) Apparatus for elderly people who lives alone
WO2017135628A1 (en) Device for automatic ventilation and air conditioning and method for controlling same
CN116406058A (en) LED intelligent control system
WO2023128014A1 (en) Air conditioner control apparatus for controlling air conditioner by recognizing occupant in room
US20190272738A1 (en) System and method for preventing false alarms due to display images
KR20190108218A (en) Emergency Analysis Device and Method Using Digital Image
US20230252874A1 (en) Shadow-based fall detection
KR102395440B1 (en) Cloud-based building management system and method thereof
CN215954384U (en) Monitoring system and monitoring doorbell
US10045423B2 (en) Illuminating control system and method for controlling illuminating device
KR101778863B1 (en) Household security system using home network
KR102159088B1 (en) Method for managing energy consumption on smart building
US20210053795A1 (en) Sensor device, automated transportation system and operating method for the same
Suda et al. Robustness of machine learning pedestrian signal detection applied to pedestrian guidance device for persons with visual impairment
WO2020212644A1 (en) A home automation system
JP7513176B1 (en) Elevator image transmission system, learning device, inference device, image transmission method, and image transmission program
AU2022281095B2 (en) Door operating system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21970083

Country of ref document: EP

Kind code of ref document: A1