CN114333207A - Fire overall process monitoring method and device based on remote sensing data - Google Patents
Fire overall process monitoring method and device based on remote sensing data Download PDFInfo
- Publication number
- CN114333207A CN114333207A CN202111664769.XA CN202111664769A CN114333207A CN 114333207 A CN114333207 A CN 114333207A CN 202111664769 A CN202111664769 A CN 202111664769A CN 114333207 A CN114333207 A CN 114333207A
- Authority
- CN
- China
- Prior art keywords
- fire
- remote sensing
- sensing data
- area
- early warning
- 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 85
- 238000012544 monitoring process Methods 0.000 title claims abstract description 65
- 230000008569 process Effects 0.000 title claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims abstract description 59
- 230000007480 spreading Effects 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 238000005094 computer simulation Methods 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 11
- 238000012806 monitoring device Methods 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000006378 damage Effects 0.000 abstract description 9
- 238000011156 evaluation Methods 0.000 description 9
- 238000007781 pre-processing Methods 0.000 description 9
- 244000025254 Cannabis sativa Species 0.000 description 6
- 241000196324 Embryophyta Species 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008832 photodamage Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 230000009526 moderate injury Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001012 protector Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Alarm Systems (AREA)
Abstract
The application relates to a fire overall process monitoring method and device based on remote sensing data, wherein the method comprises the following steps: acquiring first remote sensing data at a monitoring area in real time, and analyzing the first remote sensing data; when the first remote sensing data containing the abnormal temperature region is analyzed, the abnormal temperature region is extracted from the first remote sensing data, and the current fire spreading trend is predicted based on the abnormal temperature region to obtain the corresponding fire spreading trend; and when the first remote sensing data is analyzed to have no abnormal temperature region, carrying out fire early warning processing on the current monitoring region based on the first remote sensing data to obtain a corresponding fire early warning result. The method has the advantages that through setting a fire spreading area prediction flow and a fire early warning flow, and analyzing and calling different threads for the first remote sensing data of the monitoring area acquired in real time, the fire is monitored in the whole process of early warning before occurrence, near real-time monitoring during occurrence and disaster damage assessment after occurrence.
Description
Technical Field
The application relates to the technical field of remote sensing image disaster monitoring, in particular to a fire overall process monitoring method and device based on remote sensing data.
Background
Forest and grass fire risk assessment forewarning has been used as one of the important means of fire prevention in many countries worldwide where forest and grass fires are heavily attacked. At present, the mainstream forest and grassland fire early warning and monitoring mode mainly comprises means such as meteorological monitoring, manual patrol, sensor network arrangement, conventional satellite remote sensing and the like, but in the related technology of forest and grassland fire early warning, early warning before fire occurrence is carried out only based on remote sensing data and meteorological factors, so that the monitoring process of the fire is too single, and finally, the monitoring result is not fully served in the whole process of monitoring the fire.
Disclosure of Invention
In view of this, the present application provides a fire overall process monitoring method based on remote sensing data, which can realize the monitoring of the fire overall process.
According to one aspect of the application, a fire overall process monitoring method based on remote sensing data is provided, and comprises the following steps:
acquiring first remote sensing data at a monitoring area in real time, and analyzing the first remote sensing data;
when the first remote sensing data containing the abnormal temperature region is analyzed, extracting the abnormal temperature region from the first remote sensing data, and predicting the current fire spreading trend based on the abnormal temperature region to obtain the corresponding fire spreading trend;
and when the first remote sensing data is analyzed to be free of the abnormal temperature region, carrying out fire early warning processing on the current monitoring region based on the first remote sensing data to obtain a corresponding fire early warning result.
In a possible implementation manner, when the first remote sensing data is analyzed, a target identification network model is used for identifying the temperature abnormal area.
In a possible implementation manner, predicting a current fire spreading trend based on the temperature abnormal region to obtain a corresponding fire spreading trend includes:
determining location data of a current fire occurrence based on the temperature abnormality region;
acquiring and acquiring a fire area image corresponding to position data according to the position data of the current fire;
and according to the fire area image, taking a fire point as a center, integrating meteorological information and geographic information of the fire area, carrying out forest fire dynamic simulation, and generating a fire spreading trend result according to a dynamic simulation result.
In a possible implementation mode, a fire point is used as a center, meteorological information and geographic information of a fire area are integrated, and when forest fire dynamic simulation is carried out, forest fire dynamic simulation is directly carried out on an electronic map by calling the electronic map of the fire area.
In a possible implementation manner, performing fire early warning processing on a current monitoring area based on the first remote sensing data to obtain a corresponding fire early warning result, including:
classifying the ground features based on the first remote sensing data;
performing combustible analysis according to the ground object classification result of the first remote sensing data to obtain combustible background survey data;
and carrying out meshing on the monitoring area based on the combustible background survey data, and carrying out fire early warning processing based on meshing results.
In one possible implementation, the combustible analysis is performed based on the result of the ground feature classification performed on the first remote sensing data, and comprises analyzing at least one of the type of combustible, the spatial distribution of combustible, and the density of forest stand.
In one possible implementation manner, when performing fire early warning processing based on a grid division result, the method includes:
acquiring second remote sensing data at each grid area;
calculating a vegetation index of the second remote sensing data, and generating vegetation coverage according to the vegetation index obtained by calculation;
obtaining the water content of the vegetation combustible according to the vegetation coverage;
calculating the fire hazard comprehensive risk index according to the combustible background survey data, the vegetation combustible water content, the terrain elements and the meteorological elements;
and performing fire risk grade early warning according to the fire risk comprehensive risk index obtained by calculation.
In a possible implementation manner, when the first remote sensing data includes a temperature abnormal region, the method further includes:
acquiring first satellite remote sensing data before and after the fire in the temperature abnormal area;
comparing the first satellite remote sensing data before the fire with the first satellite remote sensing data after the fire, and identifying a final fire passing area;
and evaluating the damaged area after the fire disaster based on the identified fire disaster area.
In one possible implementation, when performing the evaluation of the post-disaster damaged area based on the identified fire passing area, the method includes:
acquiring a fire passing area boundary;
based on the boundary of the fire passing area, performing mask processing on the first satellite remote sensing data after the fire by using the fire passing area, and reserving an image of the fire passing area;
calculating to obtain a normalized vegetation index map of the image of the fire passing area, carrying out grade division on the normalized vegetation index map according to preset disaster degrees to obtain disaster areas of different levels, and generating vectors for the disaster areas of different levels to output a disaster degree distribution vector map;
and combining the vector diagram of the fire passing area boundary and the disaster degree distribution vector diagram with the established background basic database and fire scene ground survey data on a GIS platform to perform disaster statistical analysis.
According to another aspect of the application, the fire overall process monitoring device based on the remote sensing data comprises a remote sensing data analysis module, a fire spreading trend prediction module and a fire early warning module;
the remote sensing data analysis module is configured to acquire first remote sensing data at a monitoring area in real time and analyze the first remote sensing data;
the fire spreading trend prediction module is configured to extract a temperature abnormal region from the first remote sensing data when the first remote sensing data analyzed by the remote sensing data analysis module contains the temperature abnormal region, and predict the current fire spreading trend based on the temperature abnormal region to obtain a corresponding fire spreading trend;
and the fire early warning module is configured to perform fire early warning processing on the current monitoring area based on the first remote sensing data when the remote sensing data analysis module analyzes that the first remote sensing data does not have a temperature abnormal area, so as to obtain a corresponding fire early warning result.
By acquiring the first remote sensing data of the monitoring area in real time, setting a fire spreading area prediction flow and a fire early warning flow, after acquiring the first remote sensing data of the monitoring area in real time, analyzing the first remote sensing data, and calling different threads according to the analysis result, the monitoring of the whole process of the fire by early warning before and prediction after occurrence is realized, so that the probability of fire occurrence is greatly reduced, and the functions of fire prevention and fire trend prediction are realized.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the application and, together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart of a method for overall process monitoring of a fire based on remote sensing data according to an embodiment of the present application;
FIG. 2 shows a flow chart of fire early warning in the fire overall process monitoring method based on remote sensing data according to the embodiment of the present application;
FIG. 3 is a flow chart illustrating the prediction of the fire spreading tendency in the fire overall process monitoring method based on remote sensing data according to the embodiment of the present application;
FIG. 4 is a flow chart illustrating post-fire evaluation in a method for overall process monitoring of a fire based on remote sensing data according to an embodiment of the present application;
fig. 5 is a diagram illustrating an embodiment of a disaster situation statistics report generated when performing fire disaster situation statistics in the fire overall process monitoring method based on remote sensing data according to the embodiment of the present application;
fig. 6 shows a block diagram of a fire overall process monitoring device based on remote sensing data according to an embodiment of the present application.
Detailed Description
Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present application.
Fig. 1 shows a flowchart of a fire overall process monitoring method based on remote sensing data according to an embodiment of the application. As shown in fig. 1, the method includes: and S100, acquiring first remote sensing data in the monitoring area in real time, and analyzing the first remote sensing data. Here, the analysis of the first remote sensing data in this step is mainly performed to analyze whether or not a temperature abnormal region exists in the first remote sensing data. Here, the abnormal temperature region refers to whether there is a region where a fire is occurring at the monitoring region, as will be understood by those skilled in the art. Meanwhile, it is also noted that the first remote sensing data at the monitoring area can be directly acquired by adopting a satellite remote sensing technology.
And S200, when the first remote sensing data containing the abnormal temperature region is analyzed, extracting the abnormal temperature region from the first remote sensing data, and predicting the current fire spreading trend based on the extracted abnormal temperature region to obtain the corresponding fire spreading trend. That is, when the first remote sensing data including the abnormal temperature region is analyzed, it is indicated that a fire disaster is occurring in the currently monitored region, so that the abnormal temperature region is extracted from the first remote sensing data, and the current fire spreading trend is predicted based on the extracted abnormal temperature region to obtain a corresponding fire spreading trend prediction result, so that a corresponding fire fighting path can be planned according to the obtained prediction result, and the fire fighting can be performed in a more reasonable manner when the fire rescue is handled.
And step S300, when the first remote sensing data is analyzed to have no abnormal temperature region, carrying out fire early warning processing on the current monitoring region based on the first remote sensing data to obtain a corresponding fire early warning result. Namely, when the first remote sensing data is analyzed to have no abnormal temperature region, the current monitoring region is pre-warned based on the first remote sensing data, and the purpose of preventing fire is achieved.
Therefore, according to the fire overall process monitoring method based on the remote sensing data, whether a fire disaster happens in the monitoring area or not is detected by acquiring the first remote sensing data in the monitoring area in real time and analyzing the first remote sensing data. When the first remote sensing data is detected to contain the temperature abnormal area, namely when the situation that a fire disaster happens in the monitored area is detected, the temperature abnormal area is extracted from the first remote sensing data, the current fire disaster spreading trend is predicted based on the extracted temperature abnormal area, and therefore a corresponding fire disaster spreading trend prediction result is obtained, and further a fire disaster rescue plan is made according to the obtained fire disaster spreading trend prediction result, so that the planned fire disaster rescue plan can effectively improve the fire disaster rescue efficiency and reduce the situation of further development of the fire disaster.
When the first remote sensing data is detected to have no abnormal temperature region, namely, when the situation that no fire disaster occurs at the monitoring region is detected, fire early warning processing is carried out on the current monitoring region based on the first remote sensing data, and the purpose of preventing the fire disaster is achieved.
That is to say, according to the method provided by the embodiment of the application, by setting the fire spread area prediction process and the fire early warning process, after the first remote sensing data at the monitoring area is obtained in real time, the first remote sensing data is analyzed, and then different threads are called according to the analysis result, so that the overall process of early warning before occurrence and prediction after occurrence of a fire is monitored, the occurrence probability of the fire is greatly reduced, and the functions of fire prevention and fire trend prediction are realized.
It should be noted that, when analyzing the acquired first remote sensing data to obtain an analysis result of whether a fire is happening in the monitored area, a target identification network model may be used to identify a temperature abnormal area in the first remote sensing data. It should be noted that the adopted target recognition network model may be implemented by directly calling a neural network model that is conventional in the art, or a corresponding neural network model may be designed by itself, which is not specifically limited in this application.
Meanwhile, it should be noted that, when the first remote sensing data is analyzed in the temperature abnormal region, a conventional fire identification technical means in the field may also be adopted, and details are not described here.
Further, referring to fig. 2, in a possible implementation manner, when performing fire early warning processing on a current monitoring area based on the first remote sensing data and obtaining a corresponding fire early warning result, the following manner may be implemented.
That is, first, the feature classification is performed based on the first remote sensing data. And then, performing combustible analysis according to the result of ground object classification on the first remote sensing data to obtain combustible background survey data. And then, carrying out meshing on the monitoring area based on combustible background survey data, and carrying out fire early warning processing based on meshing results.
Specifically, in the above embodiment, when the combustible analysis is performed based on the result of the ground feature classification performed on the first remote sensing data, the analysis includes analyzing at least one of the type of combustible, the spatial distribution of combustible, the density of forest stand, and the like.
More specifically, when the obtained first remote sensing data is subjected to surface feature classification, the obtained first remote sensing data needs to be preprocessed, and then the surface feature classification is performed. The preprocessing of the first remote sensing data comprises at least one of fusion, mosaic and image cutting of a multispectral image and a panchromatic image. It should be noted that, the preprocessing of the first remote sensing data (i.e., fusion of the multispectral image and the panchromatic image, mosaicing, image cropping, etc.) may be performed by a conventional image preprocessing method in the art, and will not be described herein again.
Meanwhile, when the ground feature classification is performed on the preprocessed first remote sensing data, a conventional ground feature classification method in the field can be adopted to realize the ground feature classification, such as: supervised classification, unsupervised classification, knowledge-based decision tree classification, BP neural network classification, etc. may be employed, and are not specifically limited in the application.
After the ground feature classification of the first remote sensing data is realized through any one of the above manners, combustible analysis can be performed on the monitored area based on the ground feature classification result generated by the first remote sensing data. Specifically, the type, spatial distribution, forest stand density and the like of the combustible in the monitoring area are analyzed, and corresponding combustible background survey data are obtained.
Based on the ground feature classification result of the first remote sensing data, the type of the combustible, the spatial distribution of the combustible and the forest density information of the ground features in the monitoring area are determined according to LY/T1812-2009 forest land classification by combining with the second-class survey data of the forest resources, namely the combustible background survey data.
According to the species of the land, the soil can be divided into a dead branch and deciduous leaf layer (upper dead branch and deciduous leaf layer, lower dead branch and deciduous leaf layer), lichen, moss (on-forest moss and on-tree moss), herbaceous plants (inflammable herbaceous plants and incombustible herbaceous plants), shrubs (inflammable shrubs and incombustible shrubs), arbors (inflammable arbors and incombustible arbors) and a mixed and disorderly forest land.
Then, when the monitoring area is subjected to grid division based on the combustible background survey data, the method specifically comprises the following steps: based on information such as combustible background investigation, forest resource investigation, personnel, units, water sources and equipment, the monitoring area is subjected to grid division, responsibility and boundaries are determined, and fireproof area grid management is carried out. Therefore, regional management and analysis are carried out according to the grid division result, specific geographical regions, forest resource conditions and combustible material conditions of the patrol area can be checked for each grid area according to the grid division result, and forest maintainer data, patrol mountain forest protection task execution conditions, forestry disaster alarm information and the like can be inquired.
Meanwhile, when fire early warning processing is carried out based on the grid division result, the method comprises the following steps: acquiring second remote sensing data at each grid area; calculating the vegetation index of the second remote sensing data, and generating vegetation coverage according to the vegetation index obtained by calculation; obtaining the water content of the vegetation combustible according to the vegetation coverage; calculating the fire hazard comprehensive risk index according to the combustible background survey data, the vegetation combustible water content, the terrain elements and the meteorological elements; and performing fire risk grade early warning according to the fire risk comprehensive risk index obtained by calculation.
It should be noted here that the second remote sensing data and the first remote sensing data at each grid region that are acquired may be acquired by using different satellite acquisitions. Meanwhile, the resolution of the satellite used in acquiring the second remote sensing data at each grid region should be higher than the resolution of the satellite used in acquiring the first remote sensing data.
Specifically, in a possible implementation manner, the first remote sensing data may be acquired directly by using a high-score second satellite. The second remote sensing data at each grid region can be acquired by using MODIS satellite acquisition.
Meanwhile, before vegetation index calculation is performed on the acquired second remote sensing data at each grid region, the acquired second remote sensing data at each grid region also needs to be preprocessed. In this step, the preprocessing of the second remote sensing data may then comprise at least one of a radiation correction, a geometric correction, a projective transformation, etc. Moreover, the preprocessing method for the second remote sensing data can also directly adopt the conventional image preprocessing method in the field, and the details are not repeated here.
In addition, in the above possible implementation manner, the calculating the vegetation index based on the second remote sensing data may include the following steps:
the Normalized Difference Vegetation Index (NDVI) is calculated by the following formula:
wherein: rhoNIRAnd ρREDRespectively representing the reflectivity in the near infrared band and the red light band, and the NDVI value is between-1 and 1.
Furthermore, the vegetation coverage is generated according to the vegetation index obtained by calculation, and then the vegetation radiation transmission model can be directly adopted to realize the vegetation coverage when the water content of the vegetation combustible is generated based on the vegetation coverage data.
And when the fire risk comprehensive risk index is calculated according to the combustible background survey data, the vegetation combustible water content, the terrain elements and the meteorological elements, the terrain elements can comprise at least one of terrain, gradient, slope direction, elevation data and the like corresponding to the grid area. The meteorological elements may then include at least one of temperature data, humidity data, rainfall data, and the like. The resident data may include the number of residents at each grid area, and the like.
Meanwhile, the fire hazard comprehensive risk index calculation can also be carried out by adopting a conventional calculation mode in the field according to the combustible background survey data, the vegetation combustible water content, the terrain elements and the meteorological elements, and the detailed description is omitted here.
It should be further noted that, when the fire risk level early warning at the monitoring area is performed according to the calculated comprehensive fire risk index, the fire risk level early warning can be implemented by comparing the calculated comprehensive fire risk index with a preset fire risk level mapping table.
The fire risk grade preset table comprises corresponding relations between different fire risk comprehensive risk indexes and fire risk grades. That is, different fire ratings correspond to different ranges of fire risk composite risk indices. In a possible implementation manner, the fire risk levels can be set to 6 levels from low to high, and different levels correspond to different fire risk comprehensive risk index ranges. Meanwhile, in the method of the embodiment of the application, different fire risk grade preset tables can be correspondingly arranged in different areas.
Further, referring to fig. 3, in the method according to the embodiment of the present application, when the first remote sensing data is analyzed to include the abnormal temperature region, the abnormal temperature region is extracted from the first remote sensing data, and the current fire spreading tendency is predicted based on the abnormal temperature region, so as to obtain the corresponding fire spreading tendency, which can be implemented in the following manner.
First, location data of a current fire occurrence is determined based on the temperature abnormality region. And then, acquiring a fire area image corresponding to the acquired position data according to the position data of the current fire. And then according to the fire area image, taking the fire point as the center, synthesizing meteorological information and geographic information at the fire area, carrying out forest fire dynamic simulation, and generating a fire spreading trend result according to a dynamic simulation result.
The method comprises the steps of taking a fire point as a center, integrating meteorological information and geographic information of a fire area, and directly carrying out dynamic simulation of forest fire on an electronic map by calling the electronic map of the fire area when carrying out dynamic simulation of forest fire.
Specifically, after the current fire location is determined based on the temperature anomaly region, a fire region image corresponding to the location is acquired. Here, it should be noted that the acquired fire area image may be time-series remote sensing image data. Meanwhile, historical data, traffic data, administrative division data, earth surface coverage data and the like of a fire area, fire point pixel longitude and latitude, an administrative division to which a fire point belongs, open fire area, fire area information, underlying surface type and the like are obtained, and forest fire is monitored. The fire area historical data, the traffic data, the administrative division data and the earth surface coverage data can be directly obtained through a third-party interface. The fire point image element longitude and latitude, the administrative division to which the fire point belongs, the open fire area, the fire area information and the underlying surface type can be obtained according to the acquired fire area image. The fire monitoring purpose is realized through the acquired fire area historical data, traffic data, administrative division data, surface coverage data, fire point image element longitude and latitude, the administrative division to which the fire point belongs, open fire area, fire area information, underlying surface type and other information.
Meanwhile, the acquired fire area image can be used for analyzing information such as forest resource distribution conditions, residential points, fire prevention important facilities, forest protectors, fire fighting teams and the like in a certain range around the fire point, so that fire source analysis is realized, and a reference basis is provided for making fire fighting decisions.
For the prediction analysis of the fire spreading area, the forest fire dynamic simulation is directly carried out on an electronic map by taking the fire point determined in the front as the center and integrating meteorological factors such as wind direction, vegetation, combustible landforms, barriers and other factors, the prediction effect of fire development spreading is automatically generated by model dynamic calculation, and scientific basis is provided for the arrangement of fire fighting material equipment, the arrangement of fire fighting personnel and the erection of isolation zones.
In addition, based on the obtained fire spreading area prediction result, the safe and reasonable fire fighting route can be set and recommended to rescue workers according to the terrain and the distribution conditions of water sources, roads, disaster relief equipment and materials in the fire occurrence area, so that the fire can be efficiently and quickly extinguished.
In a possible implementation manner, when planning and making a rescue route is performed based on the obtained fire spreading area prediction result and in combination with the terrain and the distribution conditions of water sources, roads, disaster relief equipment and materials in a fire occurrence area, a modeling manner can be adopted to implement the method.
Namely, a fire occurrence area is modeled with high precision by leading information such as a satellite, aviation data, DEM data and the like, and a three-dimensional model of a fire scene can be constructed in a very short time by combining a cloud computing technology. And then based on the constructed three-dimensional model of the fire area, a corresponding rescue route is made by combining a fire spreading trend prediction result, the terrain and the distribution conditions of water sources, roads, disaster relief equipment and materials of the fire occurrence area. Meanwhile, corresponding emergency dispatching can be carried out according to the obtained fire spreading trend prediction result, and finally the purpose of reducing fire damage to the minimum is achieved.
Further, in the method of the embodiment of the present application, when the evaluation of the post-disaster damaged area is performed based on the identified fire passing area (i.e., the temperature abnormal area), it may be performed by:
first, the fire zone boundary is obtained. The boundary of the fire passing area can be determined according to the identified fire passing area, and after the boundary of the fire passing area is obtained, the obtained boundary of the fire passing area is output in a vector diagram mode.
Specifically, when identifying a fire passing area, the normalized vegetation index (NDVI) obtained by calculation may be used, and a threshold may be set in combination with the result of image enhancement, so as to implement a manner of distinguishing pixels of the fire passing area from pixels of a non-fire passing area.
The method comprises the steps of acquiring first satellite remote sensing data before and after a fire in a temperature abnormal area; and comparing the first satellite remote sensing data before the fire with the first satellite remote sensing data after the fire to identify a final fire passing area.
Specifically, the satellite remote sensing images before and after the fire can be acquired by a high-resolution second satellite. Moreover, preprocessing is also required before analyzing the first satellite remote sensing data before the fire and the first satellite remote sensing data after the fire. The preprocessing comprises operations such as mosaic splicing and image cutting.
And after preprocessing the acquired first satellite remote sensing data before and after the fire, comparing and analyzing the first satellite remote sensing data before and after the fire, and identifying a final fire passing area. Here, it should be noted that, by comparing and analyzing the first satellite remote sensing data before the fire and the first satellite remote sensing data before the fire, the final fire passing area is identified, and an object-oriented change detection method may be used.
Specifically, the process of using the object-oriented change detection method includes: firstly, image segmentation processing is carried out, characteristics such as spectrum, texture and space structure are further extracted from the ground object obtained by segmentation, whether the characteristics change or not is judged by comparing and analyzing the characteristics, and a change area, namely a fire passing area, is obtained.
Meanwhile, it should be noted that, referring to fig. 4, when the first remote sensing data includes the temperature abnormal region, the method further includes: and acquiring second satellite remote sensing images of the fire overfire area before and after the fire, and acquiring the normalized vegetation index of the fire overfire area based on the second satellite remote sensing images of the fire overfire area before and after the fire.
Here, the acquired second satellite remote sensing image before a fire and the acquired second satellite remote sensing image after the fire may be image data acquired by MODIS satellite acquisition.
Meanwhile, the normalized vegetation index of the fire overfire area is obtained based on the second satellite remote sensing images of the fire overfire area before and after the fire, and can be obtained through calculation in the following mode.
According to the foregoing, the Normalized Difference Vegetation Index (NDVI) is calculated as:
wherein: rhoNIRAnd ρREDRespectively representing the reflectivity in the near infrared band and the red light band, and the NDVI value is between-1 and 1.
After the temperature abnormal area is identified through the method, the temperature abnormal area is sealed through a manual method or an expansion algorithm and the like, so that the sealed temperature abnormal area is obtained, the fire passing area is generated and vector is output, and the fire passing area boundary vector diagram can be obtained.
And then, based on the acquired fire passing area boundary, masking the first satellite remote sensing data after the fire by using the fire passing area, and reserving an image of the fire passing area. Here, as can be understood by those skilled in the art, the masking processing of the first satellite remote sensing data after the fire disaster by using the fire passing area (i.e., the temperature abnormal area) can be implemented by using conventional technical means in the art, and is not described herein again.
And then, calculating by using a previous normalized index calculation mode to obtain a normalized vegetation index map of the image of the fire passing area, carrying out grade division on the normalized vegetation index map according to preset disaster degrees to obtain disaster areas of different levels, and generating vectors for the disaster areas of different levels to output a disaster degree distribution vector map. Here, when the normalized vegetation index map is graded according to the preset disaster degree, the preset disaster degree may include: no-damage, light damage, moderate damage and heavy damage. Meanwhile, when the normalized vegetation index map is divided according to different disaster-suffering degrees, corresponding threshold values can be set for division according to the result after image enhancement (namely, the normalized vegetation index map is enhanced by adopting the conventional technical means in the field) and the damaged state of the forest acquired on the ground.
In a possible implementation manner, the damaged state of the forest obtained on the ground specifically includes four levels of non-damage, light damage, moderate damage and severe damage, and the set threshold values for dividing different damage degrees can be referred to in table 1 below.
Wherein, dNTPI ═ is (NDVIpre-fire) - (NDVIpost-fire);
NDVIpre-fire is the normalized burn index value of the pre-fire image and NDVIpost-fire is the normalized burn index value of the post-fire image.
After the normalized vegetation index map of the temperature abnormal area is divided into 4 levels according to non-damage, light damage, medium damage and heavy damage by any one of the above methods, the normalized vegetation index map divided into different disaster-suffering degrees can be processed by small patch removal, expansion and the like to obtain a closed area, the different areas correspond to different disaster-suffering degrees, and then corresponding vectors are generated by the different disaster levels to output corresponding disaster-suffering degree distribution vector maps.
And finally, combining the vector diagram of the fire passing area boundary and the disaster degree distribution vector diagram with the established background basic database and the fire scene ground survey data on a GIS platform to perform disaster statistical analysis.
In the management of forest resources, the minimum business shift (or business shift) is usually used as the minimum business unit, so in the extraction of forest fire information, the statistical analysis of the fire can be performed in the unit of the small shift (or business shift).
Specifically, when carrying out disaster statistical analysis, the method mainly comprises the following aspects:
generating a disaster situation statistical unit diagram: by utilizing the space analysis function of the GIS system, the boundary map of the fire passing area, the distribution map of the degree of disaster and the forest map (or the forest distribution map) are processed by polygon intersection, segmentation and the like, and then a unit map which has a small shift (or business shift) investigation factor and is used for disaster statistics is generated. Meanwhile, the area proportion of the newly generated unit diagram to the original small shift (or business shift) is calculated as a disaster degree coefficient (R).
Calculating the disaster area and accumulation: and respectively counting the area of each newly generated unit graph by utilizing the space analysis function of the GIS system, and calculating the total area of each unit graph with the same minor shift number. Meanwhile, the accumulation amount of each class (if the forest is formed) or the number of sapling plants (if the forest is not formed) obtained in the second class investigation of each class is multiplied by the disaster degree coefficient to obtain the accumulation amount or the number of sapling plants in each unit area. Meanwhile, the damaged accumulation amount or the number of sapling plants of each class is counted.
Generating a disaster statistical report: in a geographic information system, various acquired disaster vector data and established background vector data are subjected to superposition analysis, different polygons can be generated according to characteristics of disaster grades, ground object types, administrative regions and the like, and accordingly the types of the forests suffering from disasters, the fire areas of various types and the like are obtained through statistical analysis. Fig. 5 is a diagram of an embodiment of a disaster statistics report generated in the method according to the embodiment of the present application.
Namely, by acquiring satellite remote sensing images before and after a fire (namely, first satellite remote sensing data before the fire and first satellite remote sensing data after the fire), forest and grass fire situations are analyzed and evaluated based on a fire loss evaluation mathematical model, wherein the forest and grass fire situations comprise fire area evaluation, biomass loss evaluation and combustion damage degree evaluation.
Therefore, by adopting the method of the embodiment of the application, the satellite image data at the monitoring area is acquired in real time by utilizing the satellite remote sensing technology, and the analysis of the whole stages of pre-disaster early warning, disaster suppression and post-disaster assessment is carried out on the monitoring area through the monitored satellite image data, so that early risk early warning before a fire disaster, near-real-time fire monitoring during the fire disaster, fire spread simulation and post-disaster loss assessment are realized; has the advantages of high efficiency, high speed and covering the whole process of forest and grass fire. The method can provide scientific data and decision support for forest and grass fire prevention, control, rescue and management under the global climate change background, improve the efficiency and precision of forest and grassland fire early warning in China, and reduce personal casualties and property loss caused by forest and grassland fires.
Correspondingly, based on any one of the fire overall process monitoring methods based on remote sensing data, the application also provides a fire overall process monitoring device based on remote sensing data. Because the working principle of the fire overall process monitoring device based on the remote sensing data is the same as or similar to that of the fire overall process monitoring method based on the remote sensing data, repeated parts are not repeated.
Referring to fig. 6, the fire overall process monitoring apparatus 100 based on remote sensing data provided by the present application includes a remote sensing data analysis module 110, a fire spreading trend prediction module 120, and a fire early warning module 130. The remote sensing data analysis module 110 is configured to obtain first remote sensing data in the monitoring area in real time and analyze the first remote sensing data. And the fire spreading trend prediction module 120 is configured to extract the temperature abnormal region from the first remote sensing data when the first remote sensing data is analyzed to include the temperature abnormal region, and predict the current fire spreading trend based on the temperature abnormal region to obtain a corresponding fire spreading trend. And the fire early warning module 130 is configured to perform fire early warning processing on the current monitoring area based on the first remote sensing data when the first remote sensing data is analyzed out that the temperature abnormal area does not exist, so as to obtain a corresponding fire early warning result.
In a possible implementation manner, the fire overall process monitoring device based on remote sensing data provided by the present application further includes a post-disaster evaluation module (not shown in the figure). The post-disaster evaluation module is configured to obtain first satellite remote sensing data before and after a fire in the temperature abnormal region when the first remote sensing data is analyzed by the remote sensing data analysis module to obtain a stored temperature abnormal region, compare the first satellite remote sensing data before the fire with the first satellite remote sensing data after the fire, identify a final fire over-fire region, and evaluate a post-disaster damaged area based on the identified fire over-fire region.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A fire overall process monitoring method based on remote sensing data is characterized by comprising the following steps:
acquiring first remote sensing data at a monitoring area in real time, and analyzing the first remote sensing data;
when the first remote sensing data containing the abnormal temperature region is analyzed, extracting the abnormal temperature region from the first remote sensing data, and predicting the current fire spreading trend based on the abnormal temperature region to obtain the corresponding fire spreading trend;
and when the first remote sensing data is analyzed to be free of the abnormal temperature region, carrying out fire early warning processing on the current monitoring region based on the first remote sensing data to obtain a corresponding fire early warning result.
2. The method according to claim 1, wherein the identification of the temperature anomaly region is performed using a target identification network model when analyzing the first remote sensing data.
3. The method of claim 1, wherein predicting a current fire spread trend based on the temperature anomaly region, and obtaining a corresponding fire spread trend comprises:
determining location data of a current fire occurrence based on the temperature abnormality region;
acquiring and acquiring a fire area image corresponding to position data according to the position data of the current fire;
and according to the fire area image, taking a fire point as a center, integrating meteorological information and geographic information of the fire area, carrying out forest fire dynamic simulation, and generating a fire spreading trend result according to a dynamic simulation result.
4. The method according to claim 3, wherein when a fire point is taken as a center, meteorological information and geographic information at the fire area are integrated, and the dynamic simulation of the forest fire is directly performed on the electronic map by calling the electronic map at the fire area.
5. The method according to any one of claims 1 to 4, wherein performing fire early warning processing on the current monitored area based on the first remote sensing data to obtain a corresponding fire early warning result comprises:
classifying the ground features based on the first remote sensing data;
performing combustible analysis according to the ground object classification result of the first remote sensing data to obtain combustible background survey data;
and carrying out meshing on the monitoring area based on the combustible background survey data, and carrying out fire early warning processing based on meshing results.
6. The method of claim 5, wherein analyzing combustibles based on the results of the ground feature classification of the first remotely sensed data comprises analyzing at least one of combustible type, spatial distribution of combustibles, and forest stand density.
7. The method of claim 5, wherein the fire early warning processing based on the gridding result comprises:
acquiring second remote sensing data at each grid area;
calculating a vegetation index of the second remote sensing data, and generating vegetation coverage according to the vegetation index obtained by calculation;
obtaining the water content of the vegetation combustible according to the vegetation coverage;
calculating the fire hazard comprehensive risk index according to the combustible background survey data, the vegetation combustible water content, the terrain elements and the meteorological elements;
and performing fire risk grade early warning according to the fire risk comprehensive risk index obtained by calculation.
8. The method according to any one of claims 1 to 4, wherein when the first remote sensing data is analyzed to include a temperature abnormal region, the method further comprises:
acquiring first satellite remote sensing data before and after the fire in the temperature abnormal area;
comparing the first satellite remote sensing data before the fire with the first satellite remote sensing data after the fire, and identifying a final fire passing area;
and evaluating the damaged area after the fire disaster based on the identified fire disaster area.
9. The method of claim 8, wherein the evaluating of the post-disaster damaged area based on the identified fire zone comprises:
acquiring a fire passing area boundary;
based on the boundary of the fire passing area, performing mask processing on the first satellite remote sensing data after the fire by using the fire passing area, and reserving an image of the fire passing area;
calculating to obtain a normalized vegetation index map of the image of the fire passing area, carrying out grade division on the normalized vegetation index map according to preset disaster degrees to obtain disaster areas of different levels, and generating vectors for the disaster areas of different levels to output a disaster degree distribution vector map;
and combining the vector diagram of the fire passing area boundary and the disaster degree distribution vector diagram with the established background basic database and fire scene ground survey data on a GIS platform to perform disaster statistical analysis.
10. A fire overall process monitoring device based on remote sensing data is characterized by comprising a remote sensing data analysis module, a fire spreading trend prediction module and a fire early warning module;
the remote sensing data analysis module is configured to acquire first remote sensing data at a monitoring area in real time and analyze the first remote sensing data;
the fire spreading trend prediction module is configured to extract a temperature abnormal region from the first remote sensing data when the first remote sensing data analyzed by the remote sensing data analysis module contains the temperature abnormal region, and predict the current fire spreading trend based on the temperature abnormal region to obtain a corresponding fire spreading trend;
and the fire early warning module is configured to perform fire early warning processing on the current monitoring area based on the first remote sensing data when the remote sensing data analysis module analyzes that the first remote sensing data does not have a temperature abnormal area, so as to obtain a corresponding fire early warning result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664769.XA CN114333207A (en) | 2021-12-30 | 2021-12-30 | Fire overall process monitoring method and device based on remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664769.XA CN114333207A (en) | 2021-12-30 | 2021-12-30 | Fire overall process monitoring method and device based on remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114333207A true CN114333207A (en) | 2022-04-12 |
Family
ID=81020800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111664769.XA Pending CN114333207A (en) | 2021-12-30 | 2021-12-30 | Fire overall process monitoring method and device based on remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114333207A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664048A (en) * | 2022-05-26 | 2022-06-24 | 环球数科集团有限公司 | Fire monitoring and fire early warning method based on satellite remote sensing monitoring |
| CN114758470A (en) * | 2022-06-16 | 2022-07-15 | 张家港金典软件有限公司 | Fire early warning method and system based on fire engineering |
| CN116030354A (en) * | 2023-03-29 | 2023-04-28 | 东华理工大学南昌校区 | Geological disaster analysis method and system based on remote sensing data fusion |
| CN116047546A (en) * | 2022-07-07 | 2023-05-02 | 北京玖天气象科技有限公司 | Mountain fire monitoring method based on multi-source satellite data |
| EP4283569A1 (en) * | 2022-05-26 | 2023-11-29 | Contec Co., Ltd. | Disaster response system using sattelite image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103869767A (en) * | 2012-12-07 | 2014-06-18 | 波音公司 | Forest sensor deployment and monitoring system |
| CN109785569A (en) * | 2019-01-28 | 2019-05-21 | 中科光启空间信息技术有限公司 | A kind of forest fire monitoring method based on 3S technology |
| CN110379113A (en) * | 2019-06-28 | 2019-10-25 | 北京中科锐景科技有限公司 | A method of based on satellite remote sensing date Forest Fire Alarm |
| CN112216052A (en) * | 2020-11-18 | 2021-01-12 | 北京航天泰坦科技股份有限公司 | Forest fire prevention monitoring and early warning method, device and equipment and storage medium |
| CN113111518A (en) * | 2021-04-15 | 2021-07-13 | 应急管理部四川消防研究所 | Fire simulation processing method based on Internet of things |
-
2021
- 2021-12-30 CN CN202111664769.XA patent/CN114333207A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103869767A (en) * | 2012-12-07 | 2014-06-18 | 波音公司 | Forest sensor deployment and monitoring system |
| CN109785569A (en) * | 2019-01-28 | 2019-05-21 | 中科光启空间信息技术有限公司 | A kind of forest fire monitoring method based on 3S technology |
| CN110379113A (en) * | 2019-06-28 | 2019-10-25 | 北京中科锐景科技有限公司 | A method of based on satellite remote sensing date Forest Fire Alarm |
| CN112216052A (en) * | 2020-11-18 | 2021-01-12 | 北京航天泰坦科技股份有限公司 | Forest fire prevention monitoring and early warning method, device and equipment and storage medium |
| CN113111518A (en) * | 2021-04-15 | 2021-07-13 | 应急管理部四川消防研究所 | Fire simulation processing method based on Internet of things |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664048A (en) * | 2022-05-26 | 2022-06-24 | 环球数科集团有限公司 | Fire monitoring and fire early warning method based on satellite remote sensing monitoring |
| EP4283569A1 (en) * | 2022-05-26 | 2023-11-29 | Contec Co., Ltd. | Disaster response system using sattelite image |
| CN114758470A (en) * | 2022-06-16 | 2022-07-15 | 张家港金典软件有限公司 | Fire early warning method and system based on fire engineering |
| CN116047546A (en) * | 2022-07-07 | 2023-05-02 | 北京玖天气象科技有限公司 | Mountain fire monitoring method based on multi-source satellite data |
| CN116047546B (en) * | 2022-07-07 | 2024-02-27 | 北京玖天气象科技有限公司 | Mountain fire monitoring method based on multi-source satellite data |
| CN116030354A (en) * | 2023-03-29 | 2023-04-28 | 东华理工大学南昌校区 | Geological disaster analysis method and system based on remote sensing data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114333207A (en) | Fire overall process monitoring method and device based on remote sensing data | |
| Gigović et al. | GIS multi-criteria analysis for identifying and mapping forest fire hazard: Nevesinje, Bosnia and Herzegovina | |
| Dong et al. | Forest fire risk zone mapping from satellite images and GIS for Baihe Forestry Bureau, Jilin, China | |
| CN114118677A (en) | Tailing pond risk monitoring and early warning system based on Internet of things | |
| KR102108754B1 (en) | Realtime forest fire danger rating system in north korea | |
| Kucuk et al. | Visibility analysis of fire lookout towers in the Boyabat State Forest Enterprise in Turkey | |
| CN111860205A (en) | Forest fire evaluation method based on multi-source remote sensing image and grid and storage medium | |
| KR102108752B1 (en) | Method for realtime forest fire danger rating forecasting in north korea | |
| CN116580532A (en) | Geological disaster early warning system based on radar remote sensing technology | |
| Farhadi et al. | Badi: a novel burned area detection index for sentinel-2 imagery using google earth engine platform | |
| Barrile et al. | Integrated GIS system for post-fire hazard assessments with remote sensing | |
| Yang et al. | Spatial layout siting method for fire stations based on comprehensive forest fire risk distribution | |
| Atesoglu | Forest fire hazard identifying. Mapping using satellite imagery-geographic information system and analytic hierarchy process: Bartin, Turkey | |
| Delparte | Avalanche Terrain Modeling in Glacier National Park, Canada | |
| Soundranayagam et al. | An analysis of land use pattern in the industrial development city using high resolution satellite imagery | |
| Nasanbat et al. | Wild fire risk map in the eastern steppe of Mongolia using spatial multi-criteria analysis | |
| Bisson et al. | LiDAR-based digital terrain analysis of an area exposed to the risk of lava flow invasion: the Zafferana Etnea territory, Mt. Etna (Italy) | |
| Maric et al. | Derivation of Wildfire Ignition Index using GIS-MCDA from High-Resolution UAV Imagery Data and Perception Analysis in Settlement Sali, Dugi Otok Island (Croatia). | |
| Caetano et al. | Fire risk mapping by integration of dynamic and structural variables | |
| Bilotta et al. | Wildfires: an application of remote sensing and OBIA | |
| Laneve et al. | SIGRI project: Products validation results | |
| Ahmed | Mapping the wildland-urban interfaces for forest fire prevention in the province of mila (Algeria) | |
| Mozgovoy et al. | Automated detection of deforestation based on multi-spectrum satellite data | |
| Tsidilina et al. | Developing a single system for comprehensive monitoring of catastrophic phenomena based on satellite and ground data | |
| Kumsa et al. | Applications of Geospatial Science and Technology in Disaster Risk Management. J Robot Auto Res, 3 (3), 270-281. 1Geospatial artificial intelligence researcher, Artificial In-telligence Institute of Ethiopia 2Machine Learning researcher |
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 |