CN113628401A - Dense place intelligent escape facility based on smoke detection - Google Patents
Dense place intelligent escape facility based on smoke detection Download PDFInfo
- Publication number
- CN113628401A CN113628401A CN202010379399.4A CN202010379399A CN113628401A CN 113628401 A CN113628401 A CN 113628401A CN 202010379399 A CN202010379399 A CN 202010379399A CN 113628401 A CN113628401 A CN 113628401A
- Authority
- CN
- China
- Prior art keywords
- metal pipe
- smoke
- neural network
- smoke detection
- facility based
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 239000000779 smoke Substances 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 title claims abstract description 11
- 239000002184 metal Substances 0.000 claims abstract description 49
- 239000007787 solid Substances 0.000 claims abstract description 4
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 239000003973 paint Substances 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000011810 insulating material Substances 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000005452 bending Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
- G08B7/062—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources indicating emergency exits
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62B—DEVICES, APPARATUS OR METHODS FOR LIFE-SAVING
- A62B3/00—Devices or single parts for facilitating escape from buildings or the like, e.g. protection shields, protection screens; Portable devices for preventing smoke penetrating into distinct parts of buildings
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
- G08B7/066—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources guiding along a path, e.g. evacuation path lighting strip
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of fire safety, in particular to an intelligent escape facility for a dense place based on smoke detection; it includes a hollow metal pipe and one with metal pipe parallel arrangement nevertheless contactless solid rubber tube, and the metal pipe is located the right side of rubber tube on escaping the direction, and wherein one end of metal pipe is located crowd intensive place, and the other end is located outside the passway for escaping, one of them one end fixed mounting of hollow metal pipe has electric vibrator, and through two pipes, one vibrates not to vibrate, and the metal pipe of vibration is located the right side, utilizes the traditional chinese people to lean on right current custom guide crowd to grope these two pipes and escape from the scene of a fire.
Description
Technical Field
The invention relates to the technical field of fire safety, in particular to an intelligent escape facility for a dense place based on smoke detection.
Background
The very danger of fire is a well-known fact that many people are reasonably thought to be "burned" by a big fire due to their natural fear of fire, as a matter of deaths from a fire. However, research data show that in fact, in the fire, the fire directly burned out is only a few, real "fierce", and actually various strong smoke in the fire scene.
Particularly in places with dense crowds, once a fire disaster occurs, the crowds are necessarily confused, and if the crowds are heavily abused by smoke, the crowds are difficult to find a correct escape channel and escape from the fire scene along the escape channel under the condition of greatly obstructed vision.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent facility capable of guiding people to escape when a large amount of smoke occurs in a crowd-dense place.
The technical scheme of the invention is as follows:
dense place intelligence facility of fleing based on smog detects, its characterized in that: the device comprises a hollow metal pipe and a solid rubber pipe which is arranged in parallel with the metal pipe but is not in contact with the metal pipe, wherein the metal pipe is positioned on the right side of the rubber pipe in the escape direction, one end of the metal pipe is positioned in a crowd intensive place, the other end of the metal pipe is positioned outside an escape passage, one end of the hollow metal pipe is fixedly provided with an electric vibrator, the metal pipe and the rubber pipe are respectively supported by two groups of supports which do not interfere with each other, one group of the supports is also provided with a USB camera, the USB camera is connected with an upper computer through a USB data line, and the upper computer is connected with the control end of the electric vibrator through a data line;
the USB camera shoots a scene image, then data are uploaded to an upper computer, the upper computer identifies smoke through an indoor flame and smoke identification method based on a convolutional neural network, and once the situation that fire smoke occurs is judged, an electric vibrator is started. At this moment, because dense smoke cage cover, the crowd can't look for escape channel's correct direction through normal vision basically, even take place the personnel in the escape channel and get into the scene of a fire once more because of the direction of having made a mistake and lose the accident of the chance of fleing for one's life, so through two pipes, one vibrates not to vibrate, and the metal pipe of vibration is located the right side, utilizes chinese to lean on right current custom to guide the crowd to search for these two pipes and escape the scene of a fire.
Specifically, the convolutional neural network based indoor flame smoke identification method comprises the following steps:
detecting whether a target is a moving target or not by adopting an interframe difference method;
selecting a neural network, wherein the smoke identification adopts a mobilenet network;
extracting smoke features, and analyzing the smoke features by using geometric features, wherein the geometric features comprise wheel frame roughness, area growth rate and circularity;
training neural network characteristics, loading pictures, and then respectively using the pictures as training data set test data sets, wherein the training data sets of the test data sets are provided with labels for comparing with the identified structure, and then carrying out feedback transmission to change parameters of the neural network until a decision-making person considers that the loss and the acceracy of the neural network reach proper levels, thereby completing the training of the neural network;
and step five, importing the pictures shot by the camera in real time into the neural network model, judging the result, sending early warning to a decision maker if the result is fire smoke, and starting the electric vibrator.
Furthermore, the outer wall of the metal pipe is coated with a fireproof heat-insulating material, so that people are prevented from being burnt by the metal pipe when escaping.
Furthermore, the rubber tube is made of a fireproof rubber material, so that ignition and combustion in case of fire are avoided.
Furthermore, the height of the support is 1.2 meters, the height difference of individuals in the crowd is large, but all people should bend down to move forward after the fire occurs, so that the height of the support is the height which can be grasped by ordinary adults after bending down to lower the head, and the crowd can conveniently feel the metal pipe to escape.
Furthermore, the outer surface of the rubber tube is coated with fluorescent paint or thermal luminous paint, the visibility is greatly reduced due to the smoke cage, and the feeble light emitted by the rubber tube can slightly stabilize the emotion of people.
Furthermore, the metal pipe is located crowd's intensive place one end and still installs the speaker, and the speaker passes through the data line and connects the host computer for the decision maker shouts to the scene or plays the guidance of fleing, because on-the-spot visibility descends in addition, and sound is then not influenced, can do benefit to and attract crowd to draw close to the metal pipe fast and touch the metal pipe with sound and flee.
The invention has the beneficial effects that: firstly, the fire smoke in the crowded place is quickly and accurately judged through an information technology, and then the crowd is guided to walk out of the escape passage through a metal pipe or a rubber pipe which is groped for vibration, so that the direction of the crowd cannot be mistaken due to dense smoke, and the escape probability is improved.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
In the figure, 1, a metal tube; 2. a rubber tube.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
as shown in figure 1, the intelligent escape facility for the dense place based on smoke detection is characterized in that: the device comprises a hollow metal pipe and a solid rubber pipe which is arranged in parallel with the metal pipe but is not in contact with the metal pipe, wherein the metal pipe is positioned on the right side of the rubber pipe in the escape direction, one end of the metal pipe is positioned in a crowd intensive place, the other end of the metal pipe is positioned outside an escape passage, one end of the hollow metal pipe is fixedly provided with an electric vibrator, the metal pipe and the rubber pipe are respectively supported by two groups of supports which do not interfere with each other, one group of the supports is also provided with a USB camera, the USB camera is connected with an upper computer through a USB data line, and the upper computer is connected with the control end of the electric vibrator through a data line;
the USB camera shoots a scene image, then data are uploaded to an upper computer, the upper computer identifies smoke through an indoor flame and smoke identification method based on a convolutional neural network, and once the situation that fire smoke occurs is judged, an electric vibrator is started. At this moment, because dense smoke cage cover, the crowd can't look for escape channel's correct direction through normal vision basically, even take place the personnel in the escape channel and get into the scene of a fire once more because of the direction of having made a mistake and lose the accident of the chance of fleing for one's life, so through two pipes, one vibrates not to vibrate, and the metal pipe of vibration is located the right side, utilizes chinese to lean on right current custom to guide the crowd to search for these two pipes and escape the scene of a fire.
Specifically, the convolutional neural network based indoor flame smoke identification method comprises the following steps:
detecting whether a target is a moving target or not by adopting an interframe difference method;
selecting a neural network, wherein the smoke identification adopts a mobilenet network;
extracting smoke features, and analyzing the smoke features by using geometric features, wherein the geometric features comprise wheel frame roughness, area growth rate and circularity;
training neural network characteristics, loading pictures, and then respectively using the pictures as training data set test data sets, wherein the training data sets of the test data sets are provided with labels for comparing with the identified structure, and then carrying out feedback transmission to change parameters of the neural network until a decision-making person considers that the loss and the acceracy of the neural network reach proper levels, thereby completing the training of the neural network;
and step five, importing the pictures shot by the camera in real time into the neural network model, judging the result, sending early warning to a decision maker if the result is fire smoke, and starting the electric vibrator.
Furthermore, the outer wall of the metal pipe is coated with a fireproof heat-insulating material, so that people are prevented from being burnt by the metal pipe when escaping.
Furthermore, the rubber tube is made of a fireproof rubber material, so that ignition and combustion in case of fire are avoided.
Furthermore, the height of the support is 1.2 meters, the height difference of individuals in the crowd is large, but all people should bend down to move forward after the fire occurs, so that the height of the support is the height which can be grasped by ordinary adults after bending down to lower the head, and the crowd can conveniently feel the metal pipe to escape.
The invention can be used as a separation fence for separating people from entering and exiting at ordinary times, and when a fire disaster occurs, the escape personnel can jump on a metal pipe or a rubber pipe to escape from the subway transfer station and leave from the escape passage.
Example 2
The outer surface of the rubber tube is coated with fluorescent paint or thermal luminous paint, the visibility is greatly reduced due to the smoke cage, and the faint light emitted by the rubber tube can slightly stabilize the emotion of people. The other structure of this embodiment is the same as embodiment 1.
Example 3
The metal pipe is located crowd intensive place one end and still installs the speaker, and the speaker passes through the data line and connects the host computer for the decision maker shouts to the scene or plays and flee and guide, because on-the-spot visibility descends in addition, sound is then not influenced, can do benefit to and attracts the crowd to draw close to the metal pipe fast and touch the metal pipe with the sound and flee. The other structure of this embodiment is the same as embodiment 1.
The foregoing embodiments and description have been presented only to illustrate the principles and preferred embodiments of the invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention as hereinafter claimed.
Claims (7)
1. Dense place intelligence facility of fleing based on smog detects, its characterized in that: the device comprises a hollow metal pipe and a solid rubber pipe which is arranged in parallel with the metal pipe but is not in contact with the metal pipe, wherein the metal pipe is positioned on the right side of the rubber pipe in the escape direction, one end of the metal pipe is positioned in a crowd intensive place, the other end of the metal pipe is positioned outside an escape passage, one end of the hollow metal pipe is fixedly provided with an electric vibrator, the metal pipe and the rubber pipe are respectively supported by two groups of supports which do not interfere with each other, one group of the supports is also provided with a USB camera, the USB camera is connected with an upper computer through a USB data line, and the upper computer is connected with the control end of the electric vibrator through a data line;
the USB camera shoots a scene image, then data are uploaded to an upper computer, the upper computer identifies smoke through an indoor flame and smoke identification method based on a convolutional neural network, and once the situation that fire smoke occurs is judged, an electric vibrator is started.
2. The dense place intelligent escape facility based on smoke detection as claimed in claim 1, wherein: the convolutional neural network-based indoor flame smoke identification method comprises the following steps:
detecting whether a target is a moving target or not by adopting an interframe difference method;
selecting a neural network, wherein the smoke identification adopts a mobilenet network;
extracting smoke features, and analyzing the smoke features by using geometric features, wherein the geometric features comprise wheel frame roughness, area growth rate and circularity;
training neural network characteristics, loading pictures, and then respectively using the pictures as training data set test data sets, wherein the training data sets of the test data sets are provided with labels for comparing with the identified structure, and then carrying out feedback transmission to change parameters of the neural network until a decision-making person considers that the loss and the acceracy of the neural network reach proper levels, thereby completing the training of the neural network;
and step five, importing the pictures shot by the camera in real time into the neural network model, judging the result, sending early warning to a decision maker if the result is fire smoke, and starting the electric vibrator.
3. The dense place intelligent escape facility based on smoke detection as claimed in claim 2, wherein: the outer wall of the metal pipe is coated with a refractory heat-insulating material.
4. The dense place intelligent escape facility based on smoke detection as claimed in claim 3, wherein: the rubber tube is made of a fireproof rubber material.
5. The dense place intelligent escape facility based on smoke detection as claimed in claim 4, wherein: the height of the bracket is 1.2 meters.
6. The dense place intelligent escape facility based on smoke detection as claimed in claim 5, wherein: the outer surface of the rubber tube is coated with fluorescent paint or thermoluminescent paint.
7. The dense place intelligent escape facility based on smoke detection as claimed in claim 6, wherein: the metal pipe is located crowd intensive place one end and still installs the speaker, and the speaker passes through the data line and connects the host computer for the decision maker shouts to the scene or plays and flee for one's life and guide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010379399.4A CN113628401A (en) | 2020-05-07 | 2020-05-07 | Dense place intelligent escape facility based on smoke detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010379399.4A CN113628401A (en) | 2020-05-07 | 2020-05-07 | Dense place intelligent escape facility based on smoke detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113628401A true CN113628401A (en) | 2021-11-09 |
Family
ID=78377056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010379399.4A Pending CN113628401A (en) | 2020-05-07 | 2020-05-07 | Dense place intelligent escape facility based on smoke detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113628401A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2214681A (en) * | 1988-01-22 | 1989-09-06 | Neville Hamilton Birch | Emergency evacuation and guidance means |
| US5027741A (en) * | 1990-05-15 | 1991-07-02 | Smith John R | Fire escape device |
| CN2714700Y (en) * | 2004-07-02 | 2005-08-03 | 龚凯旋 | Escaping device for building |
| JP2007034671A (en) * | 2005-07-27 | 2007-02-08 | Shinohara Electric Co Ltd | Escape guiding system and evacuation indicator |
| JP2008194422A (en) * | 2007-02-13 | 2008-08-28 | Tnk:Kk | Evacuation guide system, guide device and guide device for visually handicapped person |
| JP2009102775A (en) * | 2007-10-24 | 2009-05-14 | Kik Associates:Kk | Wire, evacuation route-indicating device, protection fence for vehicle, handrail, and glass shelf |
| CN101441798A (en) * | 2008-03-05 | 2009-05-27 | 中科院嘉兴中心微***所分中心 | Safe monitoring and emergency commanding and controlling system based on wireless sensor network |
| CN105498105A (en) * | 2016-01-12 | 2016-04-20 | 胡士龙 | Emergency staircase armrest |
| CN106157515A (en) * | 2016-08-31 | 2016-11-23 | 成都君华睿道科技有限公司 | A kind of fire alarm installation |
| CN107481472A (en) * | 2017-09-22 | 2017-12-15 | 广州地铁设计研究院有限公司 | A kind of security protection and fire protection linkage control method |
| JP2018101317A (en) * | 2016-12-21 | 2018-06-28 | ホーチキ株式会社 | Abnormality monitoring system |
| CN109035642A (en) * | 2018-07-30 | 2018-12-18 | 辽宁工程技术大学 | Fire disaster escaping intelligently indicates floor tile and the escape method using the instruction floor tile |
| KR101958564B1 (en) * | 2017-09-12 | 2019-03-14 | 정현 | public address broadcasting system including |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
-
2020
- 2020-05-07 CN CN202010379399.4A patent/CN113628401A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2214681A (en) * | 1988-01-22 | 1989-09-06 | Neville Hamilton Birch | Emergency evacuation and guidance means |
| US5027741A (en) * | 1990-05-15 | 1991-07-02 | Smith John R | Fire escape device |
| CN2714700Y (en) * | 2004-07-02 | 2005-08-03 | 龚凯旋 | Escaping device for building |
| JP2007034671A (en) * | 2005-07-27 | 2007-02-08 | Shinohara Electric Co Ltd | Escape guiding system and evacuation indicator |
| JP2008194422A (en) * | 2007-02-13 | 2008-08-28 | Tnk:Kk | Evacuation guide system, guide device and guide device for visually handicapped person |
| JP2009102775A (en) * | 2007-10-24 | 2009-05-14 | Kik Associates:Kk | Wire, evacuation route-indicating device, protection fence for vehicle, handrail, and glass shelf |
| CN101441798A (en) * | 2008-03-05 | 2009-05-27 | 中科院嘉兴中心微***所分中心 | Safe monitoring and emergency commanding and controlling system based on wireless sensor network |
| CN105498105A (en) * | 2016-01-12 | 2016-04-20 | 胡士龙 | Emergency staircase armrest |
| CN106157515A (en) * | 2016-08-31 | 2016-11-23 | 成都君华睿道科技有限公司 | A kind of fire alarm installation |
| JP2018101317A (en) * | 2016-12-21 | 2018-06-28 | ホーチキ株式会社 | Abnormality monitoring system |
| KR101958564B1 (en) * | 2017-09-12 | 2019-03-14 | 정현 | public address broadcasting system including |
| CN107481472A (en) * | 2017-09-22 | 2017-12-15 | 广州地铁设计研究院有限公司 | A kind of security protection and fire protection linkage control method |
| CN109035642A (en) * | 2018-07-30 | 2018-12-18 | 辽宁工程技术大学 | Fire disaster escaping intelligently indicates floor tile and the escape method using the instruction floor tile |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190057696A1 (en) | Information processing apparatus, information processing method, and program | |
| US11257221B2 (en) | Apparatus and method for detecting falling object | |
| CN110313154A (en) | Intelligent assistant with the information discrimination based on intention | |
| EP3696624A1 (en) | Intelligent control system and method | |
| KR101953342B1 (en) | Multi-sensor fire detection method and system | |
| US11421610B2 (en) | Artificial intelligence apparatus for controlling auto stop system and method therefor | |
| JP2006236244A (en) | Face authenticating device, and entering and leaving managing device | |
| CN105007674A (en) | Intelligent lamp control system | |
| KR20190065200A (en) | Method and apparatus for recognizing a voice | |
| US11143156B2 (en) | Artificial intelligence apparatus for controlling auto stop system based on traffic information and method for the same | |
| JP6927234B2 (en) | Information processing equipment, information processing methods and programs | |
| CN110522617A (en) | Blind person's wisdom glasses | |
| KR102184728B1 (en) | Walk signal guide apparatus through object recognition based on image detection | |
| WO2018154900A1 (en) | Information processing device, information processing method, and program | |
| JP2013161145A (en) | Pedestrian guiding device | |
| CN109843771A (en) | Guide device, bootstrap technique and elevator | |
| CN104969542B (en) | Monitoring system | |
| JP2023095918A (en) | Robot, method for controlling robot, and program | |
| KR102624302B1 (en) | High auxiliary lighting system and lighting output control method for crime prevention | |
| CN113628401A (en) | Dense place intelligent escape facility based on smoke detection | |
| CN106850846B (en) | Remote learning system and method | |
| CN110472458A (en) | A kind of unmanned shop order management method and system | |
| CN105278426A (en) | Intelligent-surveying-ball-based fire situation investigation method and system | |
| CN113313895B (en) | Building escape self-adaptive guiding system and control method thereof | |
| KR102001782B1 (en) | Method of controlling air-cleaner using artificial intelligence based on input sound and air-cleaner implementing thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240524 |
|
| AD01 | Patent right deemed abandoned |