CN112287849A - Fire early warning method and device for high-rise building - Google Patents
Fire early warning method and device for high-rise building Download PDFInfo
- Publication number
- CN112287849A CN112287849A CN202011197533.5A CN202011197533A CN112287849A CN 112287849 A CN112287849 A CN 112287849A CN 202011197533 A CN202011197533 A CN 202011197533A CN 112287849 A CN112287849 A CN 112287849A
- Authority
- CN
- China
- Prior art keywords
- fire
- river
- image segmentation
- segmentation threshold
- stream
- 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 37
- 230000007480 spreading Effects 0.000 claims abstract description 49
- 238000003709 image segmentation Methods 0.000 claims abstract description 42
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 21
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 17
- 238000001704 evaporation Methods 0.000 claims description 10
- 230000008020 evaporation Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 239000002184 metal Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 6
- 239000000284 extract Substances 0.000 abstract 1
- 206010000369 Accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a fire early warning method and a device for a high-rise building, wherein the method comprises the following steps: acquiring infrared image data in a high-rise building, and preprocessing the acquired image; calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting a flame region according to the image segmentation threshold value set; extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire exists, positioning the fire and starting fire alarm; predicting the fire spreading situation according to the fire location and the building structure; and sending the fire occurrence position and the fire spreading situation to a command center, and broadcasting the escape route guidance by voice. The invention adopts an improved water circulation algorithm to calculate the optimal image segmentation threshold, accurately extracts the flame area through multi-threshold segmentation, and accurately identifies and warns the fire at the initial stage of the fire.
Description
Technical Field
The invention belongs to the field of fire safety, and particularly relates to a fire early warning method and device for a high-rise building.
Background
With the deep advance of the urbanization process in China, high-rise buildings become the inevitable choice for urban development. Meanwhile, high-rise buildings have the characteristics of multiple use functions, complex building structures, multiple combustible decorations, large fire load, multiple electrical equipment, dense population and the like, so that the fire-causing factors of the buildings are multiple, once a fire disaster occurs, if the fire disaster is not effectively controlled in the early stage, the fire disaster can be rapidly spread, the fire fighting difficulty is high, and the serious casualties and property loss are easily caused. In recent years, a plurality of high-rise building fire accidents which have great influence occur in China successively, and great casualties, property loss and negative social influence are caused.
The high-rise building fire early-stage fire detection, the fire spreading pre-judgment and the internal fire threat reminding are important aspects of fire safety. At the present stage, image or video-based fire identification is effectively utilized, wherein fire image segmentation is an important premise for early fire identification, and the problems of low fire identification accuracy and the like caused by inaccurate flame segmentation still exist in the prior art.
Disclosure of Invention
In view of the above, the invention provides a high-rise building fire early warning method, which is used for solving the problem that a fire identification accuracy rate is not high due to the fact that a flame area cannot be accurately divided when a high-rise building fire occurs, so that accurate identification and positioning can be achieved at the initial stage of the fire.
The invention discloses a fire early warning method for a high-rise building, which comprises the following steps:
acquiring infrared image data in a high-rise building, and preprocessing the acquired image;
calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting a flame region according to the image segmentation threshold value set;
extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire disaster exists, if the fire disaster occurs, positioning the fire disaster, and starting a fire disaster alarm; predicting the fire spreading situation according to the fire location and the building structure;
and sending the fire occurrence position and the fire spreading situation to a command center, and broadcasting the escape route guidance by voice.
Preferably, the step of calculating the optimal image segmentation threshold set by using the improved water circulation algorithm specifically comprises:
initialization: let N be the total number of populations, NstreamIs the number of streams, NriverThe number of rivers and oceans is 1, Nsr=Nriver+1,Nstream=N-NsrThe number of the image segmentation threshold values is D; the upper and lower boundary range of the image segmentation threshold is [ LB, UB];
And (3) fitness calculation: calculating a fitness value through a fitness function, and screening out the current optimal ocean, river and stream according to the fitness value;
a confluence process: calculating the quantity of streams flowing to the ocean and the quantity of streams flowing to the corresponding river in the current population:
Nsrnfor the number of streams flowing into a river or ocean, round () is a round-down operation, fnIs the fitness value of the current individual, fmaxThe maximum value of the fitness in the current stream is obtained;
the stream flows to the river, the stream flows to the ocean, and the river flows to the ocean, and the position updating is respectively carried out:
the positions of the streams at the t-th iteration and the t + 1-th iteration are respectively,the positions of the river at the t-th iteration and the t +1 th iteration respectively,the positions of the ocean at the t th iteration and the t +1 th iteration are respectively, rand is a random number between (0,1), and C1, C2 and C3 are constants between (0, 2);
after the stream is updated every time, calculating a corresponding fitness value, if the current fitness value is superior to the fitness value of the river connected with the current fitness value, exchanging the position of the stream with the position of the river, and otherwise, keeping the position unchanged, and exchanging the river with the ocean and exchanging the stream with the ocean through the same rule;
evaporation and rainfall process: checking the relative positions of rivers and streams and oceans, and setting that if the judgment condition of the evaporation process is met, new streams or rivers are formed based on Laevice flight at different positions:
and storing the ocean position in the current population, recalculating the fitness value, and iteratively updating until the end condition is reached, wherein the obtained ocean position is the optimal position, namely the optimal image segmentation threshold value set.
Preferably, the conditions for determining the evaporation process are as follows:
dmaxis a constant close to 0;
the formula for forming a new stream or river based on the ravin flight at different positions is as follows:
alpha is the step size and is the length of the step,for point-to-point multiplication, Levy (β) represents the lewy distribution with a parameter of β,wherein the content of the first and second substances,gamma is a standard gamma function, and u and v are both subjected to normal distribution; when in useOrThe value of (b) exceeds the upper and lower boundary ranges [ LB, UB ] of the image segmentation threshold]In time, the stream or river is regenerated within the boundaries:
Preferably, the fitness function is the information entropy of the image, and the gray scale range of the infrared image is set as [0, K ]]And the image segmentation threshold value is set to be k1,k2,…,kDDividing pixel points in the image into a plurality of intervals, namely [0, k ], according to each image segmentation threshold value1-1]、[k1,k2-1]、…、[kD,K]Separately calculating the signal in each interval rangeEntropy and sum as fitness function:
wherein P isiIs the probability that a certain gray i appears in the image.
Preferably, the fire spreading situation prediction specifically includes:
extracting a spherical area which takes a fire position as a center and is within a set radius according to a building structure of a high-rise building, and extracting objects which cause a main spreading path of the fire of the high-rise building in the spherical area, wherein the main spreading path comprises a horizontal spreading path and a vertical spreading path, and the objects on the horizontal spreading path comprise an inner wall, a door and a window, a corridor, a suspended ceiling, a room partition wall and a horizontal dry type metal pipeline; objects on the vertical spreading path comprise staircases, vertical pipe shafts and cavities and gaps of floor slabs in the building;
identifying large-area inflammables in a main spreading path according to image data in a building, wherein the large-area inflammables comprise plastic wall cloth, wallpaper, curtains, large garbage cans and inflammable deposits;
and extracting a communication area consisting of objects and large-area inflammable matters on the horizontal spreading path and the vertical spreading path, and predicting the fire spreading situation according to the communication area.
In a second aspect of the present invention, a fire early warning device for high-rise buildings is disclosed, the device comprising:
a data acquisition module: the system is used for acquiring infrared image data in a high-rise building in real time, acquiring and storing a corresponding building structure;
an image segmentation module: the system comprises a water circulation module, a flame region extraction module and a flame region extraction module, wherein the water circulation module is used for carrying out pretreatment on an acquired image, calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting the flame region according to the image segmentation threshold value set;
flame discernment and orientation module: extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire exists, and if the fire occurs, positioning the fire;
a fire spread prediction module: the system is used for predicting the fire spreading situation according to the fire location and the building structure;
fire early warning module: the system is used for starting fire alarm, sending the fire occurrence position and the fire spreading situation to the command center, and broadcasting escape route guidance by voice.
Compared with the prior art, the invention has the following beneficial effects:
1) an improved water circulation algorithm is adopted to calculate an optimal image segmentation threshold value set, and a new stream or river is formed at different positions based on Levy flight to simulate the rainfall process, so that the population diversity is increased, and the search efficiency is ensured; the flame area is subjected to multi-threshold segmentation according to the optimal image segmentation threshold value set, so that the flame segmentation accuracy is improved, accurate fire identification and positioning at the initial stage of a fire are realized, and fire early warning is timely carried out;
2) the method can effectively pre-judge the fire situation spreading in advance according to the fire location and the building structure, and provides a judgment basis for personnel escape and fire fighting.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a fire early warning method for high-rise buildings according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the present invention provides a fire early warning method for a high-rise building, the method comprising:
s1, acquiring infrared image data in the high-rise building, and preprocessing the acquired image;
and acquiring infrared image data in the high-rise building by adopting an infrared camera, and performing gray level conversion, filtering and drying removal and other treatment on the acquired infrared image.
S2, calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting a flame region according to the image segmentation threshold value set;
an improved water circulation algorithm is adopted to calculate an optimal image segmentation threshold value set, and the method specifically comprises the following steps:
an initialization process: let N be the total number of populations, NstreamIs the number of streams, NriverThe number of rivers and oceans is 1, Nsr=Nriver+1,Nstream=N-NsrThe number of the image segmentation threshold values is D; the upper and lower boundary range of the image segmentation threshold is [ LB, UB];
And (3) fitness calculation process: calculating a fitness value through a fitness function, and screening out the current optimal ocean, river and stream according to the fitness value;
the fitness function is the information entropy of the image, and the gray scale range of the infrared image is set as [0, K ]]And the image segmentation threshold value is set to be k1,k2,…,kDDividing pixel points in the image into a plurality of intervals, namely [0, k ], according to each image segmentation threshold value1-1]、[k1,k2-1]、…、[kD,K]And respectively calculating the information entropy in each interval range and summing the information entropy as a fitness function:
wherein P isiIs the probability that a certain gray i appears in the image.
The best fitness is ocean, then river, and the worse remaining fitness is stream.
A confluence process: calculating the quantity of streams flowing to the ocean and the quantity of streams flowing to the corresponding river in the current population:
Nsrnfor the number of streams flowing into a river or ocean, round () is a round-down operation, fnIs the fitness value of the current individual, fmaxThe maximum value of the fitness in the current stream is obtained;
the stream flows to the river, the stream flows to the ocean, and the river flows to the ocean, and the position updating is respectively carried out:
the positions of the streams at the t-th iteration and the t + 1-th iteration are respectively,the positions of the river at the t-th iteration and the t +1 th iteration respectively,the positions of the ocean at the t th iteration and the t +1 th iteration are respectively, rand is a random number between (0,1), and C1, C2 and C3 are constants between (0, 2);
after the stream is updated at each position, calculating a corresponding fitness value, if the current fitness value is superior to the fitness value of the river connected with the current fitness value, exchanging the position of the stream with the position of the river, otherwise, keeping the position unchanged, and exchanging the river with the ocean and exchanging the stream with the ocean through the same rule;
evaporation and rainfall process: checking the relative positions of rivers and streams and oceans, and setting that if the relative positions meet the judgment condition of an evaporation process, new streams or rivers are formed at different positions based on Laiwei flight;
taking a stream as an example, the judgment conditions of the evaporation process are as follows:
dmaxis a constant close to 0;
the formula for forming a new stream or river based on the ravin flight at different positions is as follows:
alpha is the step size and is the length of the step,for point-to-point multiplication, Levy (β) represents the lewy distribution with a parameter of β,wherein the content of the first and second substances,gamma is a standard gamma function, and u and v are both subjected to normal distribution; when in useOrThe value of (b) exceeds the upper and lower boundary ranges [ LB, UB ] of the image segmentation threshold]In time, the stream or river is regenerated within the boundaries:
And storing the ocean position in the current population, recalculating the fitness value, and iteratively updating until the end condition is reached, wherein the obtained ocean position is the optimal position, namely the optimal image segmentation threshold value set.
According to the invention, an optimal threshold segmentation set is searched through an improved water circulation algorithm, and a new stream or river is formed at different positions based on Levy flight by utilizing the evaporation and rainfall processes of the water circulation algorithm, so that the population diversity is increased, the search efficiency is ensured, and the flame area can be accurately segmented, thereby performing flame identification and ensuring the accuracy of flame identification.
S3, extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire exists, if so, positioning the fire, and starting a fire alarm;
specifically, the characteristic parameters of the flame include circularity, area change rate, stroboscopic characteristics, layered characteristics, and the like.
S4, forecasting fire spreading situation according to the fire location and the building structure; the fire spreading situation prediction specifically comprises the following steps:
extracting a spherical area which takes a fire position as a center and is within a set radius according to a building structure of a high-rise building, and extracting objects which cause a main spreading path of the fire of the high-rise building in the spherical area, wherein the main spreading path comprises a horizontal spreading path and a vertical spreading path, and the objects on the horizontal spreading path comprise an inner wall, a door and a window, a corridor, a suspended ceiling, a room partition wall and a horizontal dry type metal pipeline; objects on the vertical spreading path comprise staircases, vertical pipe shafts and cavities and gaps of floor slabs in the building;
identifying large-area inflammables in a main spreading path according to image data in a building, wherein the large-area inflammables comprise plastic wall cloth, wallpaper, curtains, large garbage cans and inflammable deposits;
and extracting a communication area consisting of objects and large-area inflammable matters on the horizontal spreading path and the vertical spreading path, and predicting the fire spreading situation according to the communication area.
And S5, sending the fire occurrence position and the fire spreading situation to a command center, and broadcasting the escape route guidance by voice.
Based on infrared image data, the invention adopts an improved water circulation algorithm to search an optimal threshold segmentation set, can accurately segment a flame region for fire identification, accurately identify and position the fire at the initial stage of the fire, effectively pre-judge the fire situation spread in advance, pointedly remind and suppress the fire threat in the building, and reduce the casualties and property loss caused by the fire of the building.
Corresponding to the embodiment of the method, the invention also provides a high-rise building fire early warning device, which comprises:
a data acquisition module: the system is used for acquiring infrared image data in a high-rise building in real time, acquiring and storing a corresponding building structure;
an image segmentation module: the system comprises a water circulation module, a flame region extraction module and a flame region extraction module, wherein the water circulation module is used for carrying out pretreatment on an acquired image, calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting the flame region according to the image segmentation threshold value set;
flame discernment and orientation module: the system is used for extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire exists and positioning the fire;
a fire spread prediction module: the system is used for predicting the fire spreading situation according to the fire location and the building structure;
fire early warning module: the system is used for starting fire alarm, sending the fire occurrence position and the fire spreading situation to the command center, and broadcasting escape route guidance by voice.
The above method embodiments and device embodiments are briefly described with reference to the method embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A fire early warning method for high-rise buildings is characterized by comprising the following steps:
acquiring infrared image data in a high-rise building, and preprocessing the acquired image;
calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting a flame region according to the image segmentation threshold value set;
extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire disaster exists, if the fire disaster occurs, positioning the fire disaster, and starting a fire disaster alarm;
predicting the fire spreading situation according to the fire location and the building structure;
and sending the fire occurrence position and the fire spreading situation to a command center, and broadcasting the escape route guidance by voice.
2. The fire early warning method for the high-rise building according to claim 1, wherein the step of calculating the optimal image segmentation threshold set by adopting the improved water circulation algorithm specifically comprises the following steps:
initialization: let N be the total number of populations, NstreamIs the number of streams, NriverThe number of rivers and oceans is 1, Nsr=Nriver+1,Nstream=N-NsrThe number of the image segmentation threshold values is D; the upper and lower boundary range of the image segmentation threshold is [ LB, UB];
And (3) fitness calculation: calculating a fitness value through a fitness function, and screening out the current optimal ocean, river and stream according to the fitness value;
a confluence process: calculating the quantity of streams flowing to the ocean and the quantity of streams flowing to the corresponding river in the current population:
for the number of streams flowing into a river or ocean, round () is a round-down operation, fnIs the fitness value of the current individual, fmaxThe maximum value of the fitness in the current stream is obtained;
the stream flows to the river, the stream flows to the ocean, and the river flows to the ocean, and the position updating is respectively carried out:
the positions of the streams at the t-th iteration and the t + 1-th iteration are respectively,the positions of the river at the t-th iteration and the t +1 th iteration respectively,the positions of the ocean at the t th iteration and the t +1 th iteration are respectively, rand is a random number between (0,1), and C1, C2 and C3 are constants between (0, 2);
after the stream is updated every time, calculating a corresponding fitness value, if the current fitness value is superior to the fitness value of the river connected with the current fitness value, exchanging the position of the stream with the position of the river, and otherwise, keeping the position unchanged, and exchanging the river with the ocean and exchanging the stream with the ocean through the same rule;
evaporation and rainfall process: checking the relative positions of rivers and streams and oceans, and setting that if the judgment condition of the evaporation process is met, new streams or rivers are formed based on Laevice flight at different positions:
and storing the ocean position in the current population, recalculating the fitness value, and iteratively updating until the end condition is reached, wherein the obtained ocean position is the optimal position, namely the optimal image segmentation threshold value set.
3. The fire early warning method for high-rise buildings according to claim 3, wherein the judgment conditions of the evaporation process are as follows:
dmaxis a constant close to 0;
the formula for forming a new stream or river based on the ravin flight at different positions is as follows:
alpha is the step size and is the length of the step,for point-to-point multiplication, Levy (β) represents the lewy distribution with a parameter of β,wherein the content of the first and second substances,gamma is a standard gamma function, and u and v are both subjected to normal distribution; when in useOrThe value of (b) exceeds the upper and lower boundary ranges [ LB, UB ] of the image segmentation threshold]In time, the stream or river is regenerated within the boundaries:
4. The fire early warning method for high-rise buildings according to claim 3, wherein the fitness function is the information entropy of the image, and the gray scale range of the infrared image is set as [0, K ]]And the image segmentation threshold value is set to be k1,k2,…,kDDividing pixel points in the image into a plurality of intervals, namely [0, k ], according to each image segmentation threshold value1-1]、[k1,k2-1]、…、[kD,K]And respectively calculating the information entropy in each interval range and summing the information entropy as a fitness function:
wherein P isiIs the probability that a certain gray i appears in the image.
5. The fire early warning method for high-rise buildings according to claim 2, wherein the fire spreading situation prediction is specifically:
extracting a spherical area which takes a fire position as a center and is within a set radius according to a building structure of a high-rise building, and extracting objects which cause a main spreading path of the fire of the high-rise building in the spherical area, wherein the main spreading path comprises a horizontal spreading path and a vertical spreading path, and the objects on the horizontal spreading path comprise an inner wall, a door and a window, a corridor, a suspended ceiling, a room partition wall and a horizontal dry type metal pipeline; objects on the vertical spreading path comprise staircases, vertical pipe shafts and cavities and gaps of floor slabs in the building;
identifying large-area inflammables in a main spreading path according to image data in a building, wherein the large-area inflammables comprise plastic wall cloth, wallpaper, curtains, large garbage cans and inflammable deposits;
and extracting a communication area consisting of objects and large-area inflammable matters on the horizontal spreading path and the vertical spreading path, and predicting the fire spreading situation according to the communication area.
6. A fire early warning apparatus for a high-rise building, the apparatus comprising:
a data acquisition module: the system is used for acquiring infrared image data in a high-rise building in real time, acquiring and storing a corresponding building structure;
an image segmentation module: the system comprises a water circulation module, a flame region extraction module and a flame region extraction module, wherein the water circulation module is used for carrying out pretreatment on an acquired image, calculating an optimal image segmentation threshold value set by adopting an improved water circulation algorithm, and extracting the flame region according to the image segmentation threshold value set;
flame discernment and orientation module: the system is used for extracting characteristic parameters of a flame area, identifying flame through multi-characteristic fusion, judging whether a fire exists and positioning the fire;
a fire spread prediction module: the system is used for predicting the fire spreading situation according to the fire location and the building structure;
fire early warning module: the system is used for starting fire alarm, sending the fire occurrence position and the fire spreading situation to the command center, and broadcasting escape route guidance by voice.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011197533.5A CN112287849A (en) | 2020-10-30 | 2020-10-30 | Fire early warning method and device for high-rise building |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011197533.5A CN112287849A (en) | 2020-10-30 | 2020-10-30 | Fire early warning method and device for high-rise building |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112287849A true CN112287849A (en) | 2021-01-29 |
Family
ID=74354274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011197533.5A Pending CN112287849A (en) | 2020-10-30 | 2020-10-30 | Fire early warning method and device for high-rise building |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112287849A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116612440A (en) * | 2023-07-21 | 2023-08-18 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103394171A (en) * | 2013-08-02 | 2013-11-20 | 重庆大学 | Large high-rise building indoor fire urgent evacuation indication escape method and system |
CN107730517A (en) * | 2017-11-10 | 2018-02-23 | 公安部天津消防研究所 | A kind of fire video image analysis algorithm based on adaption brightness segmentation |
CN109147259A (en) * | 2018-11-20 | 2019-01-04 | 武汉理工光科股份有限公司 | A kind of remote fire detection system and method based on video image |
CN109472411A (en) * | 2018-11-09 | 2019-03-15 | 武汉理工光科股份有限公司 | The adaptive emergency evacuation navigation system of large scale business synthesis |
CN111143983A (en) * | 2019-12-19 | 2020-05-12 | 南京理工大学 | Low sidelobe comprehensive optimization method of sparse antenna array based on improved water circulation algorithm |
-
2020
- 2020-10-30 CN CN202011197533.5A patent/CN112287849A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103394171A (en) * | 2013-08-02 | 2013-11-20 | 重庆大学 | Large high-rise building indoor fire urgent evacuation indication escape method and system |
CN107730517A (en) * | 2017-11-10 | 2018-02-23 | 公安部天津消防研究所 | A kind of fire video image analysis algorithm based on adaption brightness segmentation |
CN109472411A (en) * | 2018-11-09 | 2019-03-15 | 武汉理工光科股份有限公司 | The adaptive emergency evacuation navigation system of large scale business synthesis |
CN109147259A (en) * | 2018-11-20 | 2019-01-04 | 武汉理工光科股份有限公司 | A kind of remote fire detection system and method based on video image |
CN111143983A (en) * | 2019-12-19 | 2020-05-12 | 南京理工大学 | Low sidelobe comprehensive optimization method of sparse antenna array based on improved water circulation algorithm |
Non-Patent Citations (4)
Title |
---|
PANKAJ KANDHWAY 等: "A Water Cycle Algorithm-Based Multilevel Thresholding A Water Cycle Algorithm-Based Multilevel Thresholding System for Color Image Segmentation Using Masi Entropy", 《CIRCUITS, SYSTEMS, AND SIGNAL PROCESSING》 * |
SOHEYL KHALILPOURAZARI 等: "An efficient hybrid algorithm based on Water Cycle and Moth-Flame Optimization algorithms for solving numerical and constrained engineering optimization problems", 《METHODOLOGIES AND APPLICATION》 * |
WEIGUO ZHANG 等: "Improved Water Cycle Algorithm with Chaotic Levy Distribution Applied to Engineering Problem", 《ADVANCES IN ENGINEERING RESEARCH》 * |
金肖 等: "多特征融合视频火灾识别研究", 《电气与自动化》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116612440A (en) * | 2023-07-21 | 2023-08-18 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
CN116612440B (en) * | 2023-07-21 | 2023-09-29 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111079663B (en) | High-altitude parabolic monitoring method and device, electronic equipment and storage medium | |
CN103903008B (en) | A kind of method and system of the mist grade based on image recognition transmission line of electricity | |
CN111488799B (en) | Falling object identification method and system based on image identification | |
CN110335294B (en) | Mine water pump house water leakage detection method based on frame difference method and 3D convolutional neural network | |
CN108629935B (en) | Method and system for detecting burglary of climbing stairs and turning windows based on video monitoring | |
CN106448431A (en) | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode | |
CN111325947B (en) | Storm surge flood early warning method and system based on long-term and short-term memory network | |
CN104463253B (en) | Passageway for fire apparatus safety detection method based on adaptive background study | |
WO2023273010A1 (en) | High-rise littering detection method, apparatus, and device, and computer storage medium | |
WO2023273011A1 (en) | Method, apparatus and device for detecting object thrown from height, and computer storage medium | |
CN114881381B (en) | Urban ponding water level prediction method and system based on improved convolutional neural network | |
CN114689058B (en) | Fire evacuation path planning method based on deep learning and hybrid genetic algorithm | |
CN106023199B (en) | A kind of flue gas blackness intelligent detecting method based on image analysis technology | |
CN115775085A (en) | Smart city management method and system based on digital twin | |
CN116664359A (en) | Intelligent fire early warning decision system and method based on multi-sensor fusion | |
CN111325292B (en) | Object behavior recognition method and device | |
CN116434325A (en) | Method, device, equipment and storage medium for detecting specific action | |
CN112287849A (en) | Fire early warning method and device for high-rise building | |
CN116227362A (en) | Municipal drainage pipe network state prediction method based on graph and deep learning | |
CN115311623A (en) | Equipment oil leakage detection method and system based on infrared thermal imaging | |
Luo | Research on fire detection based on YOLOv5 | |
CN114332739A (en) | Smoke detection method based on moving target detection and deep learning technology | |
CN116993745B (en) | Method for detecting surface leakage of water supply pipe based on image processing | |
CN111898440B (en) | Mountain fire detection method based on three-dimensional convolutional neural network | |
CN110852174A (en) | Early smoke detection method based on video monitoring |
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: 20210129 |