KR102175419B1 - Building firefighting monitoring system using wide sprinkler - Google Patents

Abstract

The present invention relates to a fire-fighting system for monitoring a fire in a building using a wide sprinkler. According to the present invention, the fire-fighting system for monitoring a fire in a building using a wide sprinkler comprises at least one wide sprinkler, at least one CCTV, and a fire monitoring server, wherein the at least one wide sprinkler comprises a rail unit, a plurality of joint units, a motor unit, a plurality of sprinkler units, and a detection unit. According to the present invention, a fire can be accurately detected at an early stage.

Description

Building firefighting monitoring system using wide sprinkler}

The present invention relates to a fire monitoring system for buildings using a wide sprinkler.

In general, fire fighting piping systems applied to high-rise buildings are compulsory to be installed on each floor, and when a fire occurs, it is detected by a heat detector and an alarm is sounded. It was made to be able to digest.

It is branched into each household through the standing pipe connected to the main pipe connected to the fire extinguishing tank and each branch pipe.As the sprinkler head is opened by the fire heat, the fire extinguishing water is sprayed to the fire point, enabling the fire to be extinguished early. have.

The sprinkler head is normally sealed by a sealing part formed of lead-based fire extinguishing water, but in the event of a fire, heat is detected by a heat detector provided in the sprinkler head, and the sealing part that automatically seals the fire extinguishing water discharge is melted. A household in which a fire in an apartment house is caused by maintaining a predetermined pressure in the fire fighting water in each copper pipe, synthetic resin pipe, or stainless steel pipe that is connected to each other while the fire extinguishing water outlet is open. As the sprinkler head of is opened, the water pressurized in the fire extinguishing pipe is discharged and sprayed through the fire extinguishing water outlet of the sprinkler head, so that the fire is quickly extinguished.

In recent years, there is a need for technology to solve the problem that the fire extinguishing time is prolonged by uniformly spraying an extinguishing agent when a fire occurs in a building.

Therefore, there is a need for a fire detection system capable of early detection of fire while reducing malfunction by solving the problems of these conventional technologies, and furthermore, a plan to reduce damage by extinguishing early fire or slowing the spread of fire is required. have.

The object to be solved by the present invention is to provide a building fire fighting fire monitoring system using a wide sprinkler capable of extinguishing an early fire or slowing the spread of fire by spraying intensive extinguishing water at the point of fire through a wide sprinkler. To do.

Furthermore, by processing CCTV images to detect fires in the first stage and detecting fires in the second stage using deep learning-based artificial intelligence, image processing that can detect fires early and accurately, and building firefighting using deep learning-based wide sprinklers It aims to provide a surveillance system.

In addition, fire fighting fires in buildings using a wide sprinkler capable of detecting the presence of the victim and the location of the victim while monitoring the fire occurrence point and the progress of the fire more precisely through CCTV including a heat sensor and a location sensor. It aims to provide a surveillance system.

The problems of the present invention are not limited to the problems mentioned above, and other technical problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

In an embodiment for solving the above problem, a building fire fighting fire monitoring system using a wide sprinkler, in the building fire fighting fire monitoring system using AI including at least one wide sprinkler, at least one CCTV, and a fire monitoring server, The at least one wide sprinkler may include a rail part disposed on the ceiling, a plurality of joint parts fastened to the rail part, a motor part disposed between the plurality of joint parts and moving the plurality of joint parts, and the plurality of joint parts A plurality of sprinkler units disposed on the lower surface of the extinguisher and disposed on the motor unit to detect smoke, and a length of each of the plurality of joints is 65cm, and a thickness of each of the plurality of joints is 11cm And, a plurality of the motor parts are spaced apart from each other, the pitch of the motor part is 60cm to 210cm, the thickness of the motor part is 13cm, the pitch of the plurality of sprinkler parts is 40cm to 110cm, and the at least one CCTV A photographing unit for photographing, a fixing unit for fixing the photographing unit to the wall, a connection line unit for connecting the photographing unit and the fixing unit, and a first connection unit and a second connection unit for moving the photographing unit, and the second connection unit It extends in a first direction from the fixing part, one end of the first connection part extends in a second direction crossing the first direction from an end of the second connection part, and the other end of the first connection part is connected to the photographing part. In addition, a first sensor unit is disposed at the first connection unit, a second sensor unit is disposed at the second connection unit, and the first sensor unit surrounds an outer surface of the first connection unit and is spaced apart from each other. A fourth thermal sensor and a first thermal conductive barrier layer to a fourth thermal barrier layer disposed between the first thermal sensor to the fourth thermal sensor, and the second sensor unit recognizes a human voice frequency A voice recognition sensor and a GPS sensor that analyzes the GPS signal to obtain location information, and the fire monitoring server includes the at least one A communication unit receiving an image captured from CCTV, a fire determination unit determining whether a fire has occurred using deep learning-based artificial intelligence, and when the fire determination unit determines that a fire has occurred, the communication unit A fire notification unit for transmitting fire notification to the manager terminal, the at least one wide sprinkler, and the at least one CCTV, and guiding an evacuation route when receiving fire condition confirmation information from the manager terminal receiving the fire notification. An evacuation route guide unit, a person in the building determination unit that determines the presence of a person in the building and the location of the person by analyzing a CCTV image of a place where a person is detected through the second sensor unit, and the presence or absence of a person in the building, and A person location notification unit for transmitting the location of a person to the manager terminal, and a wide sprinkler control unit receiving the fire notification and generating a wide sprinkler control signal for operating the wide sprinkler adjacent to the fire occurrence location, the at least One CCTV further includes a microcontroller, and when heat exceeding a set value is sensed, the first to fourth heat sensor to detect the photographing unit in a direction in which heat exceeding the set value is detected. A first control signal for moving is transmitted to the microcontroller, and when a person is detected, the second sensor unit transmits a second control signal for moving the photographing unit in a direction in which the person is sensed to the microcontroller. .

The first to fourth thermal sensors have a thickness of 0.2cm to 0.4cm, the first to fourth thermal barriers have a thickness of 0.5cm to 0.7cm, and the second sensor The thickness of the part is made of 0.2cm to 0.4cm, and the first to fourth thermal barrier layers may include 75% by weight of glass fiber, 17% by weight of phenol resin, and 8% by weight of calcium carbonate.

According to the building fire fighting fire monitoring system using a wide sprinkler according to an embodiment, it is possible to extinguish an early fire or slow the spread of fire by accurately detecting the fire occurrence point and spraying intensive extinguishing water at the fire occurrence point. .

Effects according to the embodiments are not limited by the contents illustrated above, and more various effects are included in the present specification.

1 is a diagram schematically showing a building fire fighting fire monitoring system using a wide sprinkler according to an embodiment.
2 is a view schematically showing the operation of the wide sprinkler according to an embodiment.
3 is a view schematically showing the operation of a wide sprinkler according to an embodiment.
4 is a schematic diagram of a fire detection server according to an embodiment.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various forms different from each other, and only these embodiments make the disclosure of the present invention complete, and common knowledge in the technical field to which the present invention belongs It is provided to completely inform the scope of the invention to those who have it, and the invention is only defined by the scope of the claims.

Hereinafter, specific embodiments will be described with reference to the accompanying drawings.

1 is a view schematically showing a building fire fighting fire monitoring system using a wide sprinkler according to an embodiment, Figure 2 is a view schematically showing the operation of the wide sprinkler according to an embodiment, and Figure 3 is an embodiment It is a view schematically showing the operation of the wide sprinkler according to.

1 to 3, a building fire fighting fire monitoring system 100 using a wide sprinkler according to an embodiment of the present invention includes at least one CCTV 10 installed in a building space, a communication network 30, and It may include a fire monitoring server 50, a manager terminal 70, and a wide sprinkler 90.

At least one wide sprinkler 90 may be disposed on the ceiling of a building. In addition, at least one wide sprinkler 90 may be disposed on each ceiling of a building. For example, in the case of a multi-storey building, at least one wide sprinkler 90 may be installed for each floor of the ceiling, and at least one wide sprinkler 90 may be installed at various locations of the ceiling of each floor. May be.

At least one wide sprinkler 90 may communicate with the fire monitoring server 50 through a network such as the communication network 30. In addition, at least one wide sprinkler 90 may communicate with at least one CCTV 10.

In some embodiments, at least one wide sprinkler 90 may be controlled through the fire monitoring server 50. However, the present invention is not limited thereto, and in some embodiments at least one wide sprinkler 90 may be controlled through at least one CCTV 10, and in some embodiments, at least one wide sprinkler 90 may monitor fire. The server 50 and/or at least one CCTV 10 may receive fire information and location information of a person and operate directly.

At least one wide sprinkler 90 may determine whether smoke is detected. This process may be performed through the sensing unit 97 provided in at least one wide sprinkler 90. As an example, the detector 97 of the at least one wide sprinkler 90 may include a smoke detector such as a photoelectric detector or an ionization detector, and may detect whether a fire occurs through the smoke detector.

Specifically, the at least one wide sprinkler 90 is disposed on the ceiling, and the joint portion 91 and the motor unit 93 provide a space to be fastened and moved to the rail portion (RP), the rail portion (RP) It is disposed between a plurality of joints 91 and 91 to be fastened, the motor unit 93 for moving the plurality of joints 91 at a predetermined angle, and is disposed in the plurality of joints 91, It may include a plurality of sprinkler units 95 for injecting, and a detector 97 disposed on the motor unit 93 to detect smoke. The predetermined angle may be 1 to 85 degrees.

The rail part (RP) is disposed and fixed to the ceiling of the building, and provides a movement path for the joint part 91 and the motor part 93 while fixing the joint part 91 and the motor part 93.

The plurality of joints 91 may be inclined at a predetermined angle by the motor 93 as shown in FIGS. 2 and 3. The plurality of joints 91 may be respectively fastened to the motor 93. The length of each of the plurality of joints 91 may be 50cm to 200cm, and the length of each of the plurality of joints 91 may be preferably 65cm in consideration of precise movement and the arrangement of the sprinkler 95. The thickness of each of the plurality of joints 91 may be 7cm to 20cm in consideration of the convenience of operation and the role of a passage providing fire extinguishing water to the sprinkler 95, and the thickness of each of the plurality of joints 91 is preferable. It may be 11 cm. Here, the length refers to a length in which the plurality of joints 91 extend in a first direction (a direction extending between the motor parts 93), and the thickness refers to a length in a second direction perpendicular to the first direction.

The plurality of motor units 93 may have a rotation motor disposed therein, and may serve as a configuration in which the plurality of motor units 93 themselves rotate. The thickness of each of the plurality of motor units 93 may be 9cm to 25cm, and the thickness of each of the plurality of motor units 93 may be preferably 13cm. The pitch P1 of the plurality of motor units 93 is 60 cm to 210 cm. However, the present invention is not limited thereto, and may vary according to the length of the plurality of joints 91 connected to each of the plurality of motor units 93.

A plurality of sprinkler units 95 may be disposed on each of the plurality of joint units 91. The plurality of sprinkler units 95 may be disposed on the lower surfaces of the plurality of joints, and a jet hole (not shown) may be positioned so as to spray fire extinguishing water toward the floor. The pitch P2 of the plurality of sprinkler units 95 is 40cm to 110cm. However, the present invention is not limited thereto, and may vary according to the length of the plurality of joints 91.

As described above, the detection unit 97 may include a smoke detector such as a photoelectric detector or an ionization detector, and may detect whether a fire occurs. The sensing unit 97 may be disposed on each of the plurality of motor units 93. In this way, when the detection unit 97 disposed in each of the plurality of motor units 93 detects whether a fire has occurred, the fire occurrence location through the motor unit 93 in which the detection unit 97 that detects the occurrence of fire is disposed. And it is possible to determine the range of fire occurrence, and accordingly, the motor unit 93 can adjust the spray direction of the sprinkler unit 95 as shown in FIGS. 2 and 3 by adjusting the plurality of joints 91.

In addition, the motor unit 93 adjusts the plurality of joints 91 through information transmitted from the CCTV 10 through a network such as the communication network 30 as well as the detection unit 97 to control the sprinkler unit 95 The spraying direction may be adjusted, and the motor unit 93 controls the plurality of joints 91 through the information transmitted from the fire monitoring server 50 through a network such as the communication network 30 to spray the sprinkler unit 95 You can adjust the direction.

In addition, when determining the location of the fire and the extent of the fire through the detection unit 97, the information can be transmitted to the CCTV 10 to take an image in real time with the CCTV 10, and the captured image can be transmitted to the communication network 30 ) Is transmitted to the fire monitoring server 50 through a network such as) to determine whether a fire has occurred.

At least one CCTV 10 may be installed in each space of the building. For example, in the case of a multi-story building, at least one CCTV 10 may be installed on each floor, and at least one CCTV 10 may be installed at various locations on each floor. At least one CCTV 10 may be installed at a height of 190cm to 220cm from the floor in order to more precisely monitor the fire. In addition, at least one CCTV 10 may be inclined 15 degrees to 20 degrees downward.

At least one CCTV 10 may communicate with the fire monitoring server 50 through a network such as the communication network 30. In addition, at least one CCTV 10 may communicate with the wide sprinkler 90 through a network such as the communication network 30.

At least one CCTV 10 may determine whether fire or smoke is detected by processing the captured image. This process may be performed through an image processing unit (not shown) provided inside at least one CCTV 10. As an example, at least one CCTV 10 may analyze a captured image in real time using Open Source Computer Vision (OpenCV), a library for real-time image processing.

Specifically, at least one CCTV 10, a photographing unit 13 for photographing an image, a fixing unit 15 for fixing the photographing unit 13 to the wall, the photographing unit 13 and the fixing unit 15 It may include a connection line part 17 to connect, a first connection part 18A and a second connection part 18B for moving the photographing part 13.

As described above, the height of the at least one CCTV 10 may be determined by the fixing unit 15.

One end of the second connection part 18B may extend from the fixed part in a first direction, and one end of the first connection part 18A extends in a second direction crossing the first direction from the other end of the second connection part 18B, and 1 The other end of the connection part 18A may be connected to the photographing part 13. In addition, the photographing unit 13 can be moved up/down/left/right at a predetermined angle by the first connection part 18A and the second connection part 18B. In some embodiments, the first connection part 18A and the second connection part 18B may have a cylindrical shape. However, it is not limited thereto.

In some embodiments, the first sensor unit 19A may be disposed on the outer surface of the first connection unit 18A. For example, the first sensor unit 19A may include a plurality of heat detection sensors and a heat conduction blocking film HBL disposed between the plurality of heat detection sensors. In some embodiments, the first sensor unit 19A may include a first thermal sensor to a fourth thermal sensor surrounding the outer surface of the first connection unit 18A and spaced apart from each other, and the first thermal sensor to It may include first to fourth heat conduction barrier layers HBL disposed between the fourth thermal sensors, respectively.

As such, the first to fourth heat sensors arranged in four directions can accurately measure the direction in which heat exceeding a set value of heat is detected, and accordingly, the first sensor unit 19A is photographed. A first control signal for moving the direction of the unit 13 in a direction in which heat exceeding a set value is sensed may be transmitted to a microcontroller (not shown) of the CCTV 10. In addition, heat conduction between the first to fourth heat sensors is blocked by the first to fourth heat conduction shielding films (HBL) respectively disposed between the first to fourth heat sensors, thereby more precisely The direction in which this is sensed can be measured. In some embodiments, the thickness of the first to fourth thermal sensors may be 0.2cm to 0.4cm, and the thickness of the first to fourth heat conduction barrier layers HBL may be 0.5cm to 0.7cm. .

In some embodiments, the heat conduction barrier layer (HBL) may be a composition in which glass fire, a phenol resin, and calcium carbonate are mixed. For example, the heat conduction barrier layer (HBL) may include 75% by weight of glass fiber, 17% by weight of phenol resin, and 8% by weight of calcium carbonate.

In some embodiments, the second sensor unit 19B may be disposed on the outer surface of the second connection unit 18B. For example, the second sensor unit 19B may be disposed to surround the outer surface of the second connection unit 18B. The second sensor unit 19B is a sensor for detecting the position of a person in a building, and has a built-in Arduino voice recognition module to recognize urgent voice frequencies such as screaming and yelling, and a voice recognition sensor for It may include a GPS sensor that analyzes a GPS signal generated from a smart device to obtain current location information. Accordingly, the second sensor unit 19B may transmit a second control signal for moving the direction of the photographing unit 13 to a direction in which a person is sensed to the microcontroller (not shown) of the CCTV 10.

In some embodiments, the thickness of the second sensor unit 19B may be 0.2cm to 0.4cm.

In some embodiments, when at least one CCTV 10 detects at least one of flame and smoke from the captured image through real-time image processing, the captured image is transferred to the fire monitoring server 50 using the communication network 30. Can be transmitted.

As an example, at least one CCTV 10 may transmit a real-time image to the fire monitoring server 50 every predetermined frame when at least one of flame and smoke is detected in the captured image.

The fire monitoring server 50 may receive images captured from at least one CCTV 10. When at least one CCTV 10 transmits a real-time image to the fire monitoring server 50, it means that a flame or smoke is first detected in the real-time image. The fire monitoring server 50 may judge whether or not the image transmitted from the at least one CCTV 10 is fired using deep learning-based artificial intelligence.

The fire monitoring server 50 may transmit a fire notification to the manager terminal 70 when it is determined that a fire has occurred as a result of determining whether a fire has occurred using deep learning-based artificial intelligence. The fire monitoring server 50 may guide an evacuation route when receiving fire condition confirmation information from the manager terminal 70 that has received a fire notification. Here, the fire condition confirmation information may be information transmitted to the fire monitoring server 50 by confirming the fire occurrence as a result of directly checking after the manager receives the fire notification through the manager terminal 70. The fire monitoring server 50 may guide the evacuation route according to the location of the fire and the congestion rate analyzed from the image captured by the at least one CCTV 10.

The fire monitoring server 50 may transmit a fire notification to the microcontroller of the CCTV 10 when it is determined that a fire has occurred as a result of determining whether a fire has occurred using deep learning-based artificial intelligence. The microcontroller of the CCTV 10 that has received the fire notification from the fire monitoring server 50 can operate the first sensor unit 19A and the second sensor unit 19B, and the first sensor unit 19A is While controlling the photographing unit 13 by detecting the direction in which is generated, the second sensor unit 19B may control the photographing unit 13 by detecting the position of a person in the building. The location of the fire, the presence or absence of people in the building, and location information obtained through the control of the photographing unit 13 are transmitted to the fire monitoring server 50, and the fire monitoring server 50 transmits it to the manager terminal 70. You will be able to.

The fire monitoring server 50 may transmit a fire notification to the wide sprinkler 90 when it is determined that a fire has occurred as a result of determining whether a fire has occurred using deep learning-based artificial intelligence. The wide sprinkler 90 receiving the fire notification can focus the injection direction of the sprinkler unit 95 to the fire occurrence location by adjusting the plurality of joints 91 based on the fire location information.

When the fire detection server 50 receives the false fire detection information from the manager terminal 70 that has received the fire notification, the fire detection server 50 may recognize that the fire determination is wrong and feed back to the deep learning-based artificial intelligence. Here, the fire false detection information may be information transmitted to the fire monitoring server 50 by confirming that the fire has not occurred as a result of directly checking after receiving the fire notification through the manager terminal 700 by the manager.

The fire monitoring server 50 may automatically guide an evacuation route when it fails to receive fire condition confirmation information or fire false detection information within a predetermined time from the manager terminal 70 that has received the fire notification. In other words, if there is a reason such as the absence of the manager or the failure to check the fire notification, the evacuation route cannot be delayed continuously, so it is determined that the fire has occurred by trusting the results of the judgment of the artificial intelligence based on deep learning. Can guide you.

The communication network 30 is a communication network in which at least one CCTV 10, a fire monitoring server 50, an administrator terminal 70, and at least one wide sprinkler 90 can communicate with each other. Various communication networks such as short-distance communication network (PAN), local area network (LAN), metropolitan area network (MAN), and wide area network (WAN) It can be composed of. In addition, the communication network 30 may be a known World Wide Web (WWW), and may use a wireless transmission technology used for short-distance communication such as infrared (IrDA) or Bluetooth (Bluetooth). have. Since the communication network 30 is widely known to a person skilled in the art, a detailed description is omitted.

The manager terminal 70 is a terminal capable of receiving a fire notification from the fire monitoring server 50, and may be various types of terminals or electronic equipment capable of wired or wireless data communication such as a user computer or mobile terminal. Various changes can be made within the range known to the technician. The manager terminal 70 may be a user computer installed in a central control room or the like, or may be a mobile terminal directly possessed by the manager. The manager may receive a fire notification through the manager terminal 70, and when it is determined to be an actual fire situation, the manager may transmit fire situation confirmation information to the fire monitoring server 50. The manager may transmit false fire detection information to the fire monitoring server 50 when the fire notification is received through the manager terminal 70 but it is determined that it is not a fire.

4 is a schematic diagram of a fire detection server according to an embodiment.

Referring to FIG. 4, the fire monitoring server 50 using image processing and deep learning-based AI according to an embodiment of the present invention includes a communication unit 51, a fire determination unit 52, and a fire notification unit 53. , An evacuation route guide unit 54, a person presence/absence determination unit 55, a person location notification unit 56, a database unit 57, and a wide sprinkler control unit 59.

The communication unit 51 may receive an image captured from at least one CCTV 10 installed in each space of a building. In addition, the communication unit 51 may transmit the fire notification received from the fire notification unit 53 to the manager terminal 70, and the fire condition confirmation information and the fire false detection information transmitted from the manager terminal 70 It can be transmitted to 52 and the evacuation route guide (54). The server communication unit 51 can communicate with at least one wide sprinkler 90, at least one CCTV 10, and an administrator terminal 70 through the communication network 30, and is a communication module that supports various wired and wireless communication methods. It can be implemented and variously changed within a range known to a person skilled in the art.

In addition, the communication unit 51 may receive the location of the fire, the presence or absence of a person in the building, and location information from at least one CCTV 10. The communication unit 51 may transmit information received from the presence/absence determination unit 55 and the location notification unit 56 of a person in the building to the manager terminal 70.

In addition, the communication unit 51 may receive transmission of whether or not a fire is detected from the at least one wide sprinkler 90. The communication unit 51 may transmit the location information of the fire occurrence to the manager terminal 70.

The fire determination unit 52 may receive a real-time image in which flame or smoke is primarily detected from at least one CCTV 10, and use deep learning-based artificial intelligence for the image transmitted from at least one CCTV 10. It can be used to judge whether there is a fire.

Meanwhile, according to an embodiment, the fire determination unit 52 first determines whether fire or smoke has been detected by image processing the captured image, and when it is determined that fire or smoke is detected as a result of the first determination, the The captured image can be secondarily determined whether or not a fire has occurred using deep learning-based artificial intelligence. In this case, the at least one CCTV 10 may not perform real-time image processing for detecting flame or smoke in the captured image, and may transmit the captured image at regular frame intervals to the fire monitoring server 50. That is, according to the embodiment, the first determination of detecting flame or smoke in the captured image may be performed by at least one CCTV 10, or performed by the fire determination unit 52 of the fire monitoring server 50. May be.

The deep learning-based artificial intelligence performed by the fire determination unit 52 may operate in the following manner.

Image information photographed by at least one CCTV 10 installed in the building may be transmitted to the fire monitoring server 50, and the fire monitoring server 50 may store the received CCTV image in the database unit 57. .

In this way, the usual CCTV image accumulated in the database unit 57 may be a standard data value. The usual CCTV images may be classified and stored according to each of the at least one CCTV 10.

When fire or smoke is detected in the image captured by at least one CCTV 10 according to the result of the first real-time image processing, the fire determination unit 52 uses the previously learned data to determine the deep learning-based artificial intelligence. It can be determined once more whether the object of the captured image is definitely fire or smoke. As an example, TensorFlow may be used as the deep learning-based artificial intelligence engine, and Inception v3 model may be used. In order to achieve the goal of early fire detection, supervised learning, a method of learning a machine learning model using training data that knows the correct answer, can be used, and the structure, weight, parameter, and data set of the artificial intelligence model can be set in various ways. I can. The image transmitted from at least one CCTV 10 may be stored in the database unit 57 for each predetermined frame, and learning may be performed using various source codes.

The fire determination unit 52 compares the CCTV image that is primarily determined to have detected fire or smoke with the usual CCTV image accumulated in the database unit 57, so that the similarity with the usual CCTV image is significantly different. In this case, it can be judged as a fire. As an example, if the similarity between the CCTV image that is determined to have detected fire or smoke and the normal CCTV image is more than 90%, the result of the first determination is determined to be malfunctioning, feedback is given, and a fire notification may not occur. have. In addition, if the similarity between the CCTV image determined to have detected fire or smoke primarily and the normal CCTV image shows a low match rate of less than 90%, it is determined that it is a fire and the fire evacuation system can be operated. That is, the fire determination unit 52 may set a predetermined similarity reference value, and determine the primary fire by comparing the similarity between the CCTV image determined to have detected fire or smoke and the normal CCTV image with the similarity reference value. You can judge whether the results are correct. The predetermined similarity reference value may be variously changed according to each building, each area, and each CCTV 10.

Since the fire determination unit 52 uses artificial intelligence based on deep learning, the usual CCTV images of at least one CCTV 10 are continuously accumulated in the database unit 57 to provide a lot of training data and as the fire determination continues, There is an effect of increasing the accuracy of fire judgment. Therefore, the more the deep learning-based artificial intelligence of the fire determination unit 52 learns, the higher the accuracy and reliability of recognizing the fire situation of the corresponding building, and ultimately, the fire detection is unattended without a separate manager. And it may be possible to guide the evacuation route.

Meanwhile, according to an embodiment, the deep learning-based artificial intelligence performed by the fire determination unit 52 may operate by learning a flame or smoke image. That is, the database unit 57 can store a large amount of flame images and smoke images, and the deep learning-based artificial intelligence of the fire determination unit 52 uses the flame images and smoke images stored in the database unit 57. Improve your ability to recognize flames and smoke. The fire determination unit 52 can secondaryly determine whether flame or smoke is present in the CCTV image by analyzing the CCTV image that is primarily determined to have detected fire or smoke according to deep learning-based artificial intelligence. have.

The fire notification unit 53 may transmit a fire notification to the manager terminal 70 through the communication unit 51 when the fire determination unit 52 finally determines that a fire has occurred. The fire notification may be transmitted to the administrator terminal 70 in the form of a text message or a push message, and the location of the suspected fire area and the video of CCTV in which a fire was detected may be transmitted to the administrator terminal 70 together. .

In addition, the fire notification unit 53 may transmit a fire notification to the microcontroller of the CCTV 10 through the communication unit 51 when the fire determination unit 52 finally determines that a fire has occurred, and the CCTV 10 The microcontroller of may operate the first sensor unit 19A and the second sensor unit 19B. The first sensor unit 19A controls the photographing unit 13 by detecting the direction in which the fire occurred, and the second sensor unit 19B controls the photographing unit 13 by detecting the position of a person in the building. I can.

In addition, the fire notification unit 53 may transmit a fire notification to the wide sprinkler control unit 59 when the fire determination unit 52 finally determines that a fire has occurred, and the wide sprinkler control unit 59 is A control signal for operating the adjacent wide sprinkler 90 may be transmitted to the wide sprinkler 90 through the communication unit 51.

The manager terminal 70 may notify the manager of the reception of fire notification through a notification sound or the like. When the manager receives a fire notification, the manager can check the fire situation with one eye again to see if the fire situation is correct, and if the fire situation is correct, the fire evacuation route guidance system is activated so that personnel in the building can safely evacuate through the shortest route. You can do it.

The evacuation route guide unit 54 may guide the evacuation route according to the location of the fire and the congestion rate analyzed from the image captured by the at least one CCTV 10. The congestion rate may be calculated according to whether or not people are crowded by analyzing CCTV images and ease of movement.

The evacuation route guide unit 54 may guide the evacuation route when receiving fire condition confirmation information from the manager terminal 70 that has received the fire notification.

The evacuation route guide unit 54 may automatically guide the evacuation route when the fire condition confirmation information or the fire false detection information is not received within a predetermined time from the manager terminal 70 that has received the fire notification. That is, if the notification cannot be confirmed due to the absence of an administrator or the like, the evacuation route guide unit 54 may automatically guide the evacuation route after a specific time.

The fire determination unit 52 recognizes that the fire determination by the fire determination unit 52 is incorrect when receiving false fire detection information from the manager terminal 70 that has received the fire notification, and uses the deep learning-based artificial intelligence. You can give feedback. The deep learning-based artificial intelligence of the fire determination unit 52 recognizes that the CCTV image on which the five fire detection information was received was not a fire, and learns anew, and reflects it in the next fire determination.

According to an embodiment, in a state in which there is no response from the manager terminal 70 that has received the fire notification, the fire determination unit 52 when the degree of congestion in the suspected fire area increases or the movement speed of people in the suspected fire area is faster than the normal speed. ) May determine that a fire has occurred and guide the evacuation route through the evacuation route guide unit 54. That is, the fire determination unit 52 analyzes the image captured by the CCTV in the suspected fire area and detects that the number of people in the area increases and the degree of congestion increases or the movement speed of the people increases, a fire occurs and becomes urgent. Evacuation routes can be guided by judging the situation. That is, the fire determination unit 52 according to an embodiment of the present invention may guide an evacuation route by analyzing the congestion level of the suspected fire area and the moving speed of people analyzed through CCTV.

The presence/absence determination unit 55 in the building may receive a real-time image detected from at least one CCTV 10, and the image transmitted from at least one CCTV 10 is used in a building using deep learning-based artificial intelligence. I can judge whether I am my person or not. For example, it is estimated that there will be a person through a voice recognition sensor that recognizes urgent voice frequencies such as screaming and yelling of a person, and a GPS sensor that obtains current location information by analyzing a GPS signal generated by a person's smart device in a building. CCTV (10) video of the location can be transmitted, and the video can be judged whether there is a person in the building using deep learning-based artificial intelligence.

On the other hand, according to an embodiment, the presence/absence determination unit 55 in the building image-processes the captured image to first determine whether there is a person, and when it is determined that a person in the building is detected as a result of the first determination, The captured image may be secondarily determined to the location of a person using deep learning-based artificial intelligence. In this case, the at least one CCTV 10 may not perform real-time image processing for detecting a person in the captured image, and may transmit the captured image at regular frame intervals to the fire monitoring server 50. That is, depending on the embodiment, the primary determination of detecting a person in the captured image may be performed by at least one CCTV 10, or by the presence/absence determination unit 55 of the fire monitoring server 50 You may.

The deep learning-based artificial intelligence performed by the presence/absence determination unit 55 in the building may operate in the following manner.

The CCTV 10 receiving the fire notification from the fire monitoring server 50 operates the first sensor unit 19A and the second sensor unit 19B to detect the location of the fire and the presence or absence of people in the building, and (13) can be controlled so that the detected location can be photographed. Image information photographed by at least one CCTV 10 installed in the building may be transmitted to the fire monitoring server 50, and the fire monitoring server 50 may store the received CCTV image in the database unit 57. .

In this way, the usual CCTV image accumulated in the database unit 57 may be a standard data value. The usual CCTV images may be classified and stored according to each of the at least one CCTV 10.

When a person is detected in the image captured by at least one CCTV 10 according to the real-time image processing result, the fire determination unit 52 uses the previously learned data to allow the deep learning-based artificial intelligence to detect the captured image. You can determine once more whether the object is definitely a person. As an example, TensorFlow may be used as the deep learning-based artificial intelligence engine, and Inception v3 model may be used. In order to achieve the goal of early fire detection, supervised learning, a method of learning a machine learning model using training data that knows the correct answer, can be used, and the structure, weight, parameter, and data set of the artificial intelligence model can be set in various ways. I can. The image transmitted from at least one CCTV 10 may be stored in the database unit 57 for each predetermined frame, and learning may be performed using various source codes.

The presence/absence determination unit 55 in the building compares the CCTV image judged as being detected as a person with the usual CCTV image accumulated in the database unit 57, and if the similarity with the normal CCTV image is significantly different, It can be determined that the object is a person.

When it is determined that the object is a person, the presence/absence determination unit 55 may calculate the location of the person. For example, location information is calculated through the location of the CCTV 10 that transmitted the corresponding image, and a more precise location of the person using a GPS signal light detected through the second sensor unit 19B of the CCTV 10 Can be calculated.

The person location notification unit 56 may transmit the location of the person to the manager terminal 70 through the communication unit 51 when the presence/absence determination unit 55 in the building detects a person and identifies the location. The person's location notification may be transmitted to the manager terminal 70 in the form of a text message or a push message, and not only the location of the person, but also a CCTV image of the fire area can be transmitted to the manager terminal 70 together. have.

The database unit 57 may store photographed images transmitted from at least one CCTV 10, and may also store information on user terminals held by people in the building to guide an evacuation route.

The wide sprinkler control unit 59 may receive a fire notification from the fire determination unit 52. The wide sprinkler control unit 59 may transmit a wide sprinkler control signal for operating the wide sprinkler 90 adjacent to the fire location to the wide sprinkler 90 through the communication unit 51, and through the transmitted information, the adjacent wide sprinkler 90 can precisely concentrate the spraying direction of the sprinkler unit 95 at the location of the fire by adjusting the plurality of joints 91.

Embodiments of the present invention have been described above with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. You can understand. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting.

10: CCTV
13: Filming Department
15: fixed part
17: connection line part
18A: first connection
18B: second connection
19A: first sensor unit
19B: second sensor unit
30: communication network
50: fire monitoring server
70: administrator terminal
90: wide sprinkler
91: joint
93: motor unit
95: Scrinkle part
97: detection unit
100: Building fire monitoring system using AI
RP: rail part
HBL: Heat conduction barrier

Claims (2)

In the building fire fighting fire monitoring system using AI including at least one wide sprinkler, at least one CCTV and fire monitoring server,
The at least one wide sprinkler may include a rail part disposed on the ceiling, a plurality of joint parts fastened to the rail part, a motor part disposed between the plurality of joint parts and moving the plurality of joint parts, and the plurality of joint parts And a plurality of sprinkler units disposed on the lower surface of the unit and spraying fire extinguishing water and a sensing unit disposed on the motor unit to detect smoke,
The length of each of the plurality of joint portions is 65 cm, the thickness of each of the plurality of joint portions is 11 cm,
A plurality of the motor units are spaced apart from each other, the pitch of the motor unit is 60cm to 210cm, and the thickness of the motor unit is 13cm,
The pitch of the plurality of sprinkler parts is 40cm to 110cm,
The at least one CCTV includes: a photographing unit for photographing an image, a fixing unit for fixing the photographing unit to a wall, a connection line unit connecting the photographing unit and the fixing unit, and a first connection unit and a second connection unit for moving the photographing unit Including,
The second connection part extends in a first direction from the fixing part, one end of the first connection part extends in a second direction crossing the first direction from an end of the second connection part, and the other end of the first connection part Is connected to the photographing unit,
A first sensor unit is disposed at the first connection unit, and a second sensor unit is disposed at the second connection unit,
The first sensor unit includes first to fourth thermal sensors surrounding the outer surface of the first connection unit and spaced apart from each other, and first to fourth thermal sensors, respectively. Including a heat conduction barrier layer to a fourth thermal conduction barrier layer,
The second sensor unit includes a voice recognition sensor that recognizes a voice frequency of a person, and a GPS sensor that obtains location information by analyzing a GPS signal,
The fire monitoring server,
A communication unit receiving the image captured from the at least one CCTV;
A fire determination unit that judges whether the captured image is fired using deep learning-based artificial intelligence;
A fire notification unit for transmitting a fire notification to the manager terminal, the at least one wide sprinkler, and the at least one CCTV through the communication unit when the fire determination unit determines that a fire has occurred;
An evacuation route guide unit for guiding an evacuation route when receiving fire condition confirmation information from the manager terminal receiving the fire notification;
A presence/absence determination unit for determining the presence of a person and a location of a person by analyzing a CCTV image of a place where a person is detected through the second sensor unit;
A person location notification unit for transmitting the presence or absence of a person in the building and the location of the person to the manager terminal; And
A wide sprinkler control unit for receiving the fire notification and generating a wide sprinkler control signal for operating the wide sprinkler adjacent to the fire occurrence location
Including,
The at least one CCTV further comprises a microcontroller,
When heat exceeding a set value is detected, the first to fourth heat sensors may transmit a first control signal for moving the photographing unit in a direction in which heat exceeding the set value is sensed. Transfer to,
When a person is detected, the second sensor unit transmits a second control signal for moving the photographing unit in a direction in which the person is sensed to the microcontroller.
The method of claim 1,
The first to fourth thermal sensors have a thickness of 0.2cm to 0.4cm,
The thickness of the first to fourth thermal barrier layers is 0.5 cm to 0.7 cm,
The thickness of the second sensor part is made of 0.2cm to 0.4cm,
The first to fourth heat conduction barriers, glass fiber 75% by weight, phenolic resin 17% by weight, calcium carbonate is a building fire monitoring system using AI consisting of 8% by weight.

Images