CN111127810A - Automatic alarming method and system for open fire of machine room - Google Patents
Automatic alarming method and system for open fire of machine room Download PDFInfo
- Publication number
- CN111127810A CN111127810A CN201911343801.7A CN201911343801A CN111127810A CN 111127810 A CN111127810 A CN 111127810A CN 201911343801 A CN201911343801 A CN 201911343801A CN 111127810 A CN111127810 A CN 111127810A
- Authority
- CN
- China
- Prior art keywords
- area
- temperature
- zone
- flame
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000007613 environmental effect Effects 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000004044 response Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000010191 image analysis Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000003086 colorant Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 241001085205 Prenanthella exigua Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention relates to the technical field of flame detection, in particular to an automatic alarming method and system for machine room naked flame, wherein the automatic alarming method comprises the following steps: acquiring an environment image and a region temperature of a certain region of a computer room; analyzing whether the environmental image and the area temperature of a certain area of the computer room all meet the following judgment conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm. The method and the device can judge whether the fire occurs or not by simultaneously analyzing the environment image and the area temperature of a certain area of the machine room, can accurately position the fire point when the fire occurs, reduce the possibility of false alarm, improve the accuracy of open fire judgment, effectively help the staff to position the fire point at the first time, enable the staff to quickly perform related processing, and avoid the fire from becoming large, thereby causing further safety accidents and dangers.
Description
Technical Field
The invention relates to the technical field of flame detection, in particular to an automatic alarming method and system for machine room open fire.
Background
At present, the fire condition of a machine room is mainly monitored by a smoke sensor for alarming, and the alarm device is a smoke alarm device, cannot alarm in the fire starting state and the smoke-free state, and cannot find the fire hidden condition in the machine room in time. Once the equipment, facilities and the like in the machine room catch fire, the fire alarm cannot be sent out at the first time when the fire disaster starts, and the operators on duty in the machine room cannot deal with abnormal conditions at the first time, so that a large fire accident is easily caused.
Disclosure of Invention
The invention provides an automatic fire alarm method and system for a machine room, overcomes the defects of the prior art, and can effectively solve the problem that the fire cannot be found at the initial stage of fire and timely alarm exists in the conventional fire detection device for the machine room.
One of the technical schemes of the invention is realized by the following measures: an automatic alarm method for open fire of a machine room comprises the following steps:
acquiring an environment image and a region temperature of a certain region of a computer room;
analyzing whether the environmental image and the area temperature of a certain area of the computer room all meet the following judgment conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
The following is further optimization or/and improvement of the technical scheme of the invention:
the above-mentioned environmental image with a certain region of computer lab is input into flame color model and is analyzed, confirms that flame appears in the environmental image, includes:
inputting an environment image of a certain area of a machine room into a flame color model to obtain R, G, B three numerical values in the environment image;
a decision R, G, B is made as to whether the three values R > G and G > B, and in response, it is determined that a flame is present in the ambient image.
The flame color model is established based on a K-NN algorithm model, and comprises the following steps:
acquiring historical environment images of a machine room, establishing a training sample set, and preprocessing each environment image;
extracting the characteristics of the preprocessed environmental image, wherein the characteristics comprise flame area, flame perimeter and flame radian;
and repeatedly training the K-NN algorithm model by adopting a training sample set to obtain a flame color model.
The preprocessing is performed on each environment image, and the preprocessing includes noise reduction and segmentation of a suspected flame area.
The comparing the zone temperature of the zone with the zone set threshold to determine that the zone temperature has reached the lowest ignition point of the zone includes:
setting a set threshold value of each area in the machine room, wherein the set threshold value is the lowest ignition point of equipment or materials in the area;
acquiring the temperature of an area, wherein the temperature of the area is the temperature data acquired by a temperature acquisition device in the area;
the zone temperature is compared to a set threshold for the corresponding zone, a determination is made as to whether the set threshold is reached, and in response to reaching, it is determined that the zone temperature has reached the lowest ignition point for the zone.
The second technical scheme of the invention is realized by the following measures: an automatic open fire alarm system for a machine room comprises a control unit, a plurality of temperature acquisition devices and a plurality of image acquisition devices;
the temperature acquisition devices are arranged in each area of the machine room and used for acquiring temperature data in each area;
the image acquisition devices are arranged in each area of the machine room and are used for acquiring environment images of each area;
the control unit is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the following judgment conditions, judging that the area is on fire and giving an alarm in response to the fact that all meet the following judgment conditions, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
The following is further optimization or/and improvement of the technical scheme of the invention:
the control unit comprises a region image analysis module, a region temperature analysis module and a judgment module;
the regional image analysis module is used for inputting an environmental image of a certain region of the computer room into the flame color model for analysis and determining that flames appear in the environmental image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environmental image of the computer room and a flame label corresponding to the environmental image;
the area temperature analysis module is used for comparing the area temperature of the area with the area set threshold value and judging that the area temperature reaches the lowest ignition point of the area;
and the judging module is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the judging conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm.
The terminal also comprises an alarm unit used for sending the alarm signal to the terminal.
The temperature acquisition device is a dual-channel temperature sensor, and the image acquisition device is a high-definition camera.
According to the invention, the environment image and the area temperature of a certain area of the machine room are simultaneously analyzed to judge whether open fire occurs, the fire point can be accurately positioned when the fire occurs, the possibility of false alarm is reduced, the accuracy of open fire judgment is improved, and workers are effectively helped to position the fire point at the first time, so that the workers can quickly perform related processing, and further safety accidents and dangers are avoided due to the fact that the fire becomes large.
Drawings
FIG. 1 is a flow chart of example 1 of the present invention.
Fig. 2 is a flowchart of determining the presence of flames in an environmental image according to embodiment 1 of the present invention.
FIG. 3 is a flow chart of flame color modeling in example 1 of the present invention.
Fig. 4 is a diagram illustrating a data storage structure of a suspected flame area in embodiment 1 of the present invention.
Fig. 5 is a diagram showing a storage structure of boundary position data of a suspected flame area in embodiment 1 of the present invention.
Fig. 6 is a flowchart of the region temperature determination in embodiment 1 of the present invention.
Fig. 7 is a block diagram showing the structure of embodiment 2 of the present invention.
Detailed Description
The present invention is not limited by the following examples, and specific embodiments may be determined according to the technical solutions and practical situations of the present invention.
The invention is further described with reference to the following examples and figures:
example 1: as shown in the attached figure 1, the automatic open fire warning method for the machine room comprises the following steps:
s1, acquiring an environment image and an area temperature of a certain area of the computer room;
s2, analyzing whether the environmental image and the area temperature of a certain area of the computer room all meet the following judgment conditions, responding to all the conditions, judging that the area has been on fire, and giving an alarm, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
According to the steps, the environment image and the area temperature in one area of the computer room can be analyzed simultaneously by acquiring the environment image and the area temperature in the certain area, and if the environment image analysis result and the area temperature analysis result are both in fire, the area is determined to have an open fire, and an alarm is given. Therefore, the invention can judge whether the fire occurs by simultaneously analyzing the environmental image and the area temperature of a certain area of the machine room, can accurately position the fire point when the fire occurs, reduces the possibility of false alarm, improves the accuracy of open fire judgment, effectively helps the staff to position the fire point at the first time, enables the staff to quickly perform related treatment, and avoids the fire from becoming larger, thereby causing further safety accidents and dangers.
The following is further optimization or/and improvement of the technical scheme of the invention:
as shown in fig. 2, the inputting an environment image of a certain area of a machine room into a flame color model for analyzing to determine that flames appear in the environment image includes:
s211, inputting an environment image of a certain area of a machine room into a flame color model to obtain R, G, B three numerical values in the environment image;
s212, a decision R, G, B is made as to whether the three values R > G and G > B, and in response, it is determined that a flame is present in the ambient image.
The R, G, B numerical values respectively represent the colors of the red, green and blue channels; because the flame has distinctive color characteristics, the invention sets that any color in the RGB image can be regarded as a flame as long as R > -G and G > B are satisfied.
As shown in fig. 3, the flame color model is built based on a K-NN algorithm model, and the building process includes:
s2111, obtaining historical environment images of the machine room, establishing a training sample set, and preprocessing each environment image;
s2112, extracting the characteristics of the preprocessed environment image, wherein the characteristics comprise flame area, flame perimeter and flame radian;
s2113, repeatedly training the K-NN algorithm model by adopting the training sample set to obtain a flame color model.
Preprocessing each environmental image by the vertical training sample set, wherein the preprocessing comprises noise reduction and suspected flame area segmentation; because the acquired environment image contains a large amount of noise points, the image needs to be subjected to noise reduction processing so as to be convenient for subsequent segmentation of a flame region; and when the suspected flame area is segmented, an image segmentation algorithm is used for segmenting the suspected flame area, so that preparation is made for feature extraction.
When a suspected flame area is determined, because the flame color is not a determined value, the segmentation of the flame in the color space is performed by setting the value range of each component through a large number of experiments, and then intersection is obtained among the components, so as to obtain the suspected flame area, for example, the video image collected by a camera is based on an RGB color model, which obtains various colors by overlapping three colors of red (R), green (G), and blue (B), the flame center is bright white during combustion of the flame, yellow, orange, and red are sequentially arranged from the flame center to the outside, the saturation of the red is gradually increased from the inside to the outside, and the brightness is gradually decreased, so that the saturation, the brightness value, and the red component value of the flame can be used as a set of criteria for identifying the flame, assuming that the total number of pixel points in the environment image is N, wherein any point (x, y) and the luminance value Y (x, Y) are as follows:
Y(x,y)=0.22×R(x,y)+0.587×G(x,y)+0.114×V(x,y)
when the red saturation and the brightness of the point are both larger than the threshold red saturation set value and the threshold red brightness set value, the pixel point (x, y) is indicated to have the color characteristic of flame, and therefore the corresponding area is the area of the determined suspected flame.
The boundary of each suspected flame area is scanned clockwise to obtain the positions of all inner boundary points of each suspected flame area in an image memory, and the inner boundary points are stored in a storage form of a linked list sequence. The data storage format of the pseudo flame area is shown in fig. 4, where I represents the number of the pseudo flame area, and the following data are the minimum value of the abscissa, the minimum value of the ordinate, the maximum value of the abscissa, and the maximum value of the ordinate, respectively. The boundary position data is stored in a manner such that I represents the number of the pseudo-flame area, L represents the perimeter of the boundary of the current area and the number of boundary positions of the current pseudo-flame area, and then boundary position data is stored, and the boundary position data is stored after the boundary position data is returned to the starting point after scanning for one week from the scanning starting point of the current pseudo-flame area, as shown in fig. 5. The information from I to the second X0 is represented as a frame of information, each frame of information is divided by two 0 s, and the data between I and L, L and the boundary point is separated by one 0, so as to obtain the relevant data.
Performing feature extraction on the preprocessed environmental images, wherein two or more continuous environmental images are selected as a sample to perform feature extraction during extraction; the method is characterized by comprising the following steps of (1) calculating the flame area, the flame perimeter and the flame radian, wherein the flame area of continuous adjacent frames of images is continuously changed due to continuous flicker of the edge in the fire occurrence process when the flame area is calculated, but the change amplitude of the flame area in the early stage is not particularly large, so that the average value of the flame area in two or more continuous environment images can be calculated when the flame area is calculated; the circumference and the area of the flame are obtained in the same way; the flame radian is calculated according to the flame circumference and area by the following formula:
wherein A is the area of the zone flame; p is the zone flame perimeter.
The process of repeatedly training the K-NN algorithm model is the prior known technology, and the obtained flame color model can classify pixel points of the image by repeatedly training the K-NN algorithm model, so that R, G, B values in the environmental image are obtained.
As shown in fig. 6, the comparing the zone temperature of the zone with the zone set threshold to determine that the zone temperature has reached the lowest ignition point of the zone includes:
s221, setting a set threshold value of each area in the machine room, wherein the set threshold value is the lowest ignition point of equipment or materials in the area;
s222, acquiring the temperature of the area, wherein the temperature of the area is the temperature data acquired by the temperature acquisition device in the area;
and S223, comparing the zone temperature with the set threshold value of the corresponding zone, judging whether the set threshold value is reached, and judging that the zone temperature reaches the lowest ignition point of the zone in response to the set threshold value.
Example 2: as shown in fig. 7, the automatic open fire alarm system for the machine room comprises a control unit, a plurality of temperature acquisition devices and a plurality of image acquisition devices;
the temperature acquisition devices are arranged in each area of the machine room and used for acquiring temperature data in each area;
the image acquisition devices are arranged in each area of the machine room and are used for acquiring environment images of each area;
the control unit is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the following judgment conditions, judging that the area is on fire and giving an alarm in response to the fact that all meet the following judgment conditions, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
The following is further optimization or/and improvement of the technical scheme of the invention:
as shown in fig. 7, the control unit includes a region image analysis module, a region temperature analysis module, and a determination module;
the regional image analysis module is used for inputting an environmental image of a certain region of the computer room into the flame color model for analysis and determining that flames appear in the environmental image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environmental image of the computer room and a flame label corresponding to the environmental image;
the area temperature analysis module is used for comparing the area temperature of the area with the area set threshold value and judging that the area temperature reaches the lowest ignition point of the area;
and the judging module is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the judging conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm.
As shown in fig. 7, the terminal further comprises an alarm unit for sending an alarm signal to the terminal.
As shown in fig. 7, the temperature acquisition device is a dual-channel temperature sensor, and the image acquisition device is a high-definition camera.
Above-mentioned temperature acquisition device is binary channels temperature sensor, and binary channels temperature sensor can automatic angle regulation, gathers and corresponds the region temperature, and its collection region temperature process includes:
the object to be measured is imaged by the objective lens, and projected onto the spectroscope through the diaphragm and the light guide rod, so that the long-wave (infrared ray) radiation rays are transmitted, and the short-wave (visible light) part is reflected; the radiation rays penetrating through the spectroscope are filtered by the optical filter to remove residual short waves, and then are received by the infrared photoelectric element silicon photocell and converted into electric quantity to be output; the short wave radiation reflected by the spectroscope filters the long wave through the filter plate, and is received by the visible light silicon photocell and converted into electric quantity which has a functional relation with the wavelength brightness to be output; the two electric signals are input into an automatic balance display recorder to be compared to obtain a photoelectric signal ratio, and the temperature value of the measured object can be read.
The above technical features constitute the best embodiment of the present invention, which has strong adaptability and best implementation effect, and unnecessary technical features can be increased or decreased according to actual needs to meet the requirements of different situations.
Claims (10)
1. An automatic alarm method for open fire of a machine room is characterized by comprising the following steps:
acquiring an environment image and a region temperature of a certain region of a computer room;
analyzing whether the environmental image and the area temperature of a certain area of the computer room all meet the following judgment conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
2. The automatic fire alarm method for the computer room according to claim 1, wherein the step of inputting the environment image of a certain area of the computer room into a flame color model for analysis to determine that flames appear in the environment image comprises:
inputting an environment image of a certain area of a machine room into a flame color model to obtain R, G, B three numerical values in the environment image;
a decision R, G, B is made as to whether the three values R > G and G > B, and in response, it is determined that a flame is present in the ambient image.
3. The automatic alarming method for the open fire in the machine room according to claim 1 or 2, wherein the flame color model is established based on a K-NN algorithm model, and comprises the following steps:
acquiring historical environment images of a machine room, establishing a training sample set, and preprocessing each environment image;
extracting the characteristics of the preprocessed environmental image, wherein the characteristics comprise flame area, flame perimeter and flame radian;
and repeatedly training the K-NN algorithm model by adopting a training sample set to obtain a flame color model.
4. The automatic fire alarm method for the computer room according to claim 3, wherein each environmental image is preprocessed, and the preprocessing comprises noise reduction and segmentation of suspected flame areas.
5. The automatic fire alarm method for the machine room according to claim 1, 2 or 4, wherein the step of comparing the zone temperature of the zone with the zone set threshold to determine that the zone temperature has reached the lowest ignition point of the zone comprises:
setting a set threshold value of each area in the machine room, wherein the set threshold value is the lowest ignition point of equipment or materials in the area;
acquiring the temperature of an area, wherein the temperature of the area is the temperature data acquired by a temperature acquisition device in the area;
the zone temperature is compared to a set threshold for the corresponding zone, a determination is made as to whether the set threshold is reached, and in response to reaching, it is determined that the zone temperature has reached the lowest ignition point for the zone.
6. The automatic fire alarm method for the machine room according to claim 3, wherein the step of comparing the zone temperature of the zone with the zone set threshold to determine that the zone temperature has reached the lowest ignition point of the zone comprises:
setting a set threshold value of each area in the machine room, wherein the set threshold value is the lowest ignition point of equipment or materials in the area;
acquiring the temperature of an area, wherein the temperature of the area is the temperature data acquired by a temperature acquisition device in the area;
the zone temperature is compared to a set threshold for the corresponding zone, a determination is made as to whether the set threshold is reached, and in response to reaching, it is determined that the zone temperature has reached the lowest ignition point for the zone.
7. The automatic fire alarm system for the machine room according to any one of claims 1 to 6, characterized by comprising a control unit, a plurality of temperature acquisition devices and a plurality of image acquisition devices;
the temperature acquisition devices are arranged in each area of the machine room and used for acquiring temperature data in each area;
the image acquisition devices are arranged in each area of the machine room and are used for acquiring environment images of each area;
the control unit is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the following judgment conditions, judging that the area is on fire and giving an alarm in response to the fact that all meet the following judgment conditions, wherein the judgment conditions comprise:
A. inputting an environment image of a certain area of a machine room into a flame color model for analysis, and determining that flames appear in the environment image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environment image of the machine room and a flame label corresponding to the environment image;
B. comparing the zone temperature of the zone with the zone set threshold value, and judging that the zone temperature reaches the lowest ignition point of the zone.
8. The automatic fire alarm system for the machine room according to claim 7, wherein the control unit comprises a region image analysis module, a region temperature analysis module and a judgment module;
the regional image analysis module is used for inputting an environmental image of a certain region of the computer room into the flame color model for analysis and determining that flames appear in the environmental image, wherein the flame color model is obtained by using multiple groups of data through machine learning training, and each group of data comprises the environmental image of the computer room and a flame label corresponding to the environmental image;
the area temperature analysis module is used for comparing the area temperature of the area with the area set threshold value and judging that the area temperature reaches the lowest ignition point of the area;
and the judging module is used for analyzing whether the environment image and the area temperature of a certain area of the computer room all meet the judging conditions, responding to all the conditions, judging that the area is on fire, and giving an alarm.
9. The automatic fire alarm system for the machine room according to claim 8, further comprising an alarm unit for transmitting an alarm signal to the terminal.
10. The automatic fire alarm system for the machine room according to claim 7, 8 or 9, wherein the temperature acquisition device is a dual-channel temperature sensor, and the image acquisition device is a high-definition camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343801.7A CN111127810A (en) | 2019-12-24 | 2019-12-24 | Automatic alarming method and system for open fire of machine room |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343801.7A CN111127810A (en) | 2019-12-24 | 2019-12-24 | Automatic alarming method and system for open fire of machine room |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111127810A true CN111127810A (en) | 2020-05-08 |
Family
ID=70501622
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911343801.7A Pending CN111127810A (en) | 2019-12-24 | 2019-12-24 | Automatic alarming method and system for open fire of machine room |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111127810A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340746A (en) * | 2020-05-19 | 2020-06-26 | 深圳应急者安全技术有限公司 | Fire fighting method and fire fighting system based on Internet of things |
CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
CN113313907A (en) * | 2021-07-30 | 2021-08-27 | 东华理工大学南昌校区 | Emergency protection system based on cloud server |
CN114465849A (en) * | 2021-12-07 | 2022-05-10 | 华信咨询设计研究院有限公司 | Grain depot safety supervision cloud gateway based on AI image recognition and streaming media technology |
CN117173854A (en) * | 2023-09-13 | 2023-12-05 | 西安博深安全科技股份有限公司 | Coal mine open fire early warning method and system based on deep learning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08121757A (en) * | 1994-10-20 | 1996-05-17 | Kubota Corp | Combustion control device |
CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
CN103473788A (en) * | 2013-07-31 | 2013-12-25 | 中国电子科技集团公司第三十八研究所 | Indoor fire and flame detection method based on high-definition video images |
CN107944359A (en) * | 2017-11-14 | 2018-04-20 | 中电数通科技有限公司 | Flame detecting method based on video |
CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
CN109101882A (en) * | 2018-07-09 | 2018-12-28 | 石化盈科信息技术有限责任公司 | A kind of image-recognizing method and system of fire source |
CN109887221A (en) * | 2019-03-13 | 2019-06-14 | 杭州图析同创科技有限公司 | A kind of fire disaster intelligently detection system and its control method |
-
2019
- 2019-12-24 CN CN201911343801.7A patent/CN111127810A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08121757A (en) * | 1994-10-20 | 1996-05-17 | Kubota Corp | Combustion control device |
CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
CN103473788A (en) * | 2013-07-31 | 2013-12-25 | 中国电子科技集团公司第三十八研究所 | Indoor fire and flame detection method based on high-definition video images |
CN107944359A (en) * | 2017-11-14 | 2018-04-20 | 中电数通科技有限公司 | Flame detecting method based on video |
CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
CN109101882A (en) * | 2018-07-09 | 2018-12-28 | 石化盈科信息技术有限责任公司 | A kind of image-recognizing method and system of fire source |
CN109887221A (en) * | 2019-03-13 | 2019-06-14 | 杭州图析同创科技有限公司 | A kind of fire disaster intelligently detection system and its control method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340746A (en) * | 2020-05-19 | 2020-06-26 | 深圳应急者安全技术有限公司 | Fire fighting method and fire fighting system based on Internet of things |
CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
CN113313907A (en) * | 2021-07-30 | 2021-08-27 | 东华理工大学南昌校区 | Emergency protection system based on cloud server |
CN114465849A (en) * | 2021-12-07 | 2022-05-10 | 华信咨询设计研究院有限公司 | Grain depot safety supervision cloud gateway based on AI image recognition and streaming media technology |
CN117173854A (en) * | 2023-09-13 | 2023-12-05 | 西安博深安全科技股份有限公司 | Coal mine open fire early warning method and system based on deep learning |
CN117173854B (en) * | 2023-09-13 | 2024-04-05 | 西安博深安全科技股份有限公司 | Coal mine open fire early warning method and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111127810A (en) | Automatic alarming method and system for open fire of machine room | |
US20240005757A1 (en) | Method and device for smoke or fire recognition, computer apparatus, and storage medium | |
US20190279478A1 (en) | Fire monitoring system | |
TWI603074B (en) | Optical film defect detection method and system thereof | |
US20160260306A1 (en) | Method and device for automated early detection of forest fires by means of optical detection of smoke clouds | |
CN101882034B (en) | Device and method for discriminating color of touch pen of touch device | |
KR101822924B1 (en) | Image based system, method, and program for detecting fire | |
CN112069975A (en) | Comprehensive flame detection method based on ultraviolet, infrared and vision | |
CN109637068A (en) | Intelligent pyrotechnics identifying system | |
CN112394064B (en) | Point-line measuring method for screen defect detection | |
CN103761529A (en) | Open fire detection method and system based on multicolor models and rectangular features | |
CN112395928A (en) | Method for automatically detecting equipment state operation | |
KR101726786B1 (en) | System and method for real-time fire detection using color information of the image | |
KR101224494B1 (en) | Video based smoke detection method robust to light conditions | |
US20150169984A1 (en) | Flame detection system and method | |
CN101764999B (en) | Sub-camera video capture device | |
KR101196678B1 (en) | Real-time fire detection device and method | |
CN111899210A (en) | Arc detection method based on image recognition | |
KR101044903B1 (en) | Fire detecting method using hidden markov models in video surveillance and monitoring system | |
CN112364884B (en) | Method for detecting moving object | |
KR20050009135A (en) | Method and device for detecting flames | |
CN116828274A (en) | Camera identification method based on HSV and application thereof | |
KR20100032723A (en) | The device for detecting fire and method therefor | |
CN110624853A (en) | Online magic stick visual detection system | |
JP4715703B2 (en) | Optical flare inspection apparatus and inspection method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |