CN116563719A - Fire identification prediction method, system and medium based on air volume data - Google Patents
Fire identification prediction method, system and medium based on air volume data Download PDFInfo
- Publication number
- CN116563719A CN116563719A CN202310850187.3A CN202310850187A CN116563719A CN 116563719 A CN116563719 A CN 116563719A CN 202310850187 A CN202310850187 A CN 202310850187A CN 116563719 A CN116563719 A CN 116563719A
- Authority
- CN
- China
- Prior art keywords
- wind
- data
- fire
- clusters
- observation
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 33
- 230000002093 peripheral effect Effects 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims abstract description 15
- 230000007480 spreading Effects 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims abstract description 11
- 230000005484 gravity Effects 0.000 claims description 21
- 238000012876 topography Methods 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 12
- 238000009434 installation Methods 0.000 claims description 9
- 230000001788 irregular Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 241000791900 Selene vomer Species 0.000 claims 1
- 230000008569 process Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The application discloses a fire behavior identification prediction method, a fire behavior identification prediction system and a fire behavior identification prediction medium based on air volume data, which relate to the field of fire behavior trend prediction; modeling the wind speed sensor and the observation data to generate a plane model comprising wind clusters, fire points and an observation map; and processing the acting force of wind vectors corresponding to peripheral wind groups of the fire point at the current frame moment to the fire point, calculating the resultant force of all the peripheral wind groups to the acting force of the fire point, and outputting the current frame fire trend under the influence of the resultant force of multiple wind groups and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple wind groups comprises the direction of the resultant force and the propagation speed variable to the fire point. The method and the device combine the change condition of the air volume data in the local area to conduct in real time, predict the direction, speed and trend of the fire spreading, and can assist rescue work to be completed more quickly and effectively.
Description
Technical Field
The application relates to the field of fire trend prediction, in particular to a fire identification prediction method, a fire identification prediction system and a fire identification prediction medium based on air volume data.
Background
After the existing forest fire prevention camera finds out fire, elements such as surface vegetation condition, altitude, temperature, humidity, wind direction and the like of the place where the fire happens can be combined to predict the spreading direction and trend of the fire;
as the conventional wind power data is regional wind power observation data, the regional wind power observation data is influenced by vegetation coverage or topography factors, and the wind power data has large difference, so that inaccurate prediction of fire neighborhood is caused, and the analysis of fire trend is indirectly influenced.
Disclosure of Invention
The application provides a fire identification prediction method, a fire identification prediction system and a fire identification prediction medium based on air volume data, which solve the problems in the prior art.
In a first aspect, the present application provides a method for predicting fire behavior recognition based on air volume data, including:
collecting wind speed sensor data and looking down camera observation data;
modeling the wind speed sensor and the observation data to generate a plane model comprising wind clusters, fire points and an observation map;
and processing the acting force of wind vectors corresponding to peripheral clusters of the fire point on the fire point at the current frame moment, calculating the resultant force of all the peripheral clusters on the acting force of the fire point, and outputting the current frame fire trend under the influence of the resultant force of multiple clusters and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple clusters comprises the direction of the resultant force and the propagation speed variable of the fire point.
Further, the collecting wind speed sensor data and collecting the observation data of the down-looking camera includes:
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera;
and collecting fire position data and coordinate data of the fire position.
Further, the modeling wind speed sensor and the observed data generate a plane model including a wind group, a fire point and an observed map, and the method comprises the following steps:
generating a planar model comprising an observation map:
according to the height data, adjusting the scale of the observed image data, and simultaneously adjusting the inclination angle data of the observed image and the horizontal plane according to the position data of the identified wind speed sensor and the read installation position data of the corresponding wind speed sensor, and calculating the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located, wherein the included angle is the same as the inclination angle of the observed image and the horizontal plane;
generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, and projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the adjustment is carried out according to the wind quantity values and the wind direction angles of the adjacent wind clusters to be linear adjustment according to wind direction tracks and linear adjustment according to the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
Further, the method includes the steps of processing the acting force of wind vectors corresponding to peripheral wind clusters of a fire point on the fire point at the current frame time, calculating the resultant force of all the peripheral wind clusters on the acting force of the fire point, and outputting the trend of the fire of the current frame and the expected arrival area of the fire at the next frame time under the influence of the resultant force of multiple wind clusters, wherein the resultant force of multiple wind clusters comprises the direction of the resultant force and the propagation speed variable of the fire point, and the method includes the steps of:
rasterizing observation map data, and assigning values to grids occupied by the wind clusters, wherein the contents of the assignment are quantized wind volume data and angle values of wind directions;
and carrying out data fitting on blank grids of the area gaps occupied by the wind clusters in an observation map, wherein the data fitting mode is to take each blank grid as a starting point, travel to grids occupied by the adjacent assigned wind clusters in an equal step length, calculate the step length of the grids occupied by the wind clusters for realizing different assignment contents, calculate the numerical gradient change rate brought by the step length, and calculate the content values of the blank grids meeting the step length travel relation according to the numerical gradient change rate.
Further, the method includes the steps of processing the acting force of wind vectors corresponding to peripheral wind clusters of a fire point on the fire point at the current frame time, calculating the resultant force of all the peripheral wind clusters on the acting force of the fire point, and outputting the trend of the fire of the current frame and the expected arrival area of the fire at the next frame time under the influence of the resultant force of multiple wind clusters, wherein the resultant force of multiple wind clusters comprises the direction of the resultant force and the propagation speed variable of the fire point, and further comprises the following steps: judging the belonging blank grid or the grid occupied by the wind cluster according to the global coordinate of the gravity center position of the thermal value of the fire, calling the assigned data content in the corresponding grid, analyzing the fire direction and the fire spreading speed of the current frame according to the data content, and analyzing the global coordinate reached by the fire at the next frame time, and analyzing the fire direction and the fire spreading speed at the next frame time.
In a second aspect, the present application provides a fire identification prediction system based on air volume data, including:
the acquisition module is used for acquiring the data of the wind speed sensor and the observation data of the downward-looking camera;
the modeling module is used for modeling the wind speed sensor and the observation data and generating a plane model comprising a wind cluster, a fire point and an observation map;
the processing module is used for processing the acting force of wind power vectors corresponding to peripheral wind clusters of the fire point at the current frame moment to the fire point, calculating the resultant force of all the peripheral wind clusters to the acting force of the fire point, and outputting the trend of the fire of the current frame under the influence of the resultant force of multiple wind clusters and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple wind clusters comprises the direction of the resultant force and the propagation speed variable to the fire point.
Preferably, the acquisition module is specifically configured to:
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera;
and collecting fire position data and coordinate data of the fire position.
Preferably, the modeling module is specifically configured to:
generating a planar model comprising an observation map:
according to the height data, adjusting the scale of the observed image data, and simultaneously adjusting the inclination angle data of the observed image and the horizontal plane according to the position data of the identified wind speed sensor and the read installation position data of the corresponding wind speed sensor, and calculating the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located, wherein the included angle is the same as the inclination angle of the observed image and the horizontal plane;
generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, and projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the adjustment is carried out according to the wind quantity values and the wind direction angles of the adjacent wind clusters to be linear adjustment according to wind direction tracks and linear adjustment according to the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
Preferably, the processing module has a processing module for:
rasterizing observation map data, and assigning values to grids occupied by the wind clusters, wherein the contents of the assignment are quantized wind volume data and angle values of wind directions;
and carrying out data fitting on blank grids of the area gaps occupied by the wind clusters in an observation map, wherein the data fitting mode is to take each blank grid as a starting point, travel to grids occupied by the adjacent assigned wind clusters in an equal step length, calculate the step length of the grids occupied by the wind clusters for realizing different assignment contents, calculate the numerical gradient change rate brought by the step length, and calculate the content values of the blank grids meeting the step length travel relation according to the numerical gradient change rate.
In another aspect, the present application provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, which when executed by a processor, are configured to implement the method according to any one of the first aspects.
The beneficial effects of this application are:
the method and the device for analyzing the fire trend based on the air quantity data have the advantages that the change condition, distribution and fire image recognition of the air quantity data in the local area are combined, the fire trend is analyzed, the analysis on the fire trend can be improved, the fire trend is reasonably avoided, the real-time guidance is realized, the fire spreading direction, speed and trend are predicted, and the rescue work can be assisted to be completed more quickly and effectively.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the principle of the present application. In the drawings:
fig. 1 is a flowchart of a fire identification and prediction method based on air volume data according to an exemplary embodiment of the present application.
Fig. 2 is a view of a lower view angle in a fire behavior recognition and prediction method based on air volume data according to an exemplary embodiment of the present application.
Fig. 3 is a perspective transformation processing projection schematic diagram in a fire behavior recognition prediction method based on air volume data according to an exemplary embodiment of the present application.
Fig. 4 is a graph of assigning values to a blank grid in a fire identification prediction method based on air volume data according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of systems and methods that are consistent with aspects of the present application as detailed in the accompanying claims.
After the existing forest fire prevention camera finds out fire, elements such as surface vegetation condition, altitude, temperature, humidity, wind direction and the like of the place where the fire happens can be combined to predict the spreading direction and trend of the fire;
from multiparty studies, it is shown that the wind volume data dominates the spread speed of the arriving fire; the auxiliary effect on fire disaster is weakened due to the fact that the error of regional measurement and calculation of the air volume data on the prediction of the spreading speed and the direction is large, and possible preventive measures are invalid, and the preventive position is invalid, so that the trend influence of the fire disaster led by the air volume data is strengthened, and the technical scheme is needed to be realized;
therefore, the technology is considered to be combined with the camera and the image recognition process, the collected air volume data is combined with the prediction model to predict the trend of the fire, and the rescue work can be assisted to be completed more quickly and effectively.
The technical application scene of the method is used for predicting and developing fire behaviors of plain, forest or basin areas aiming at the downward vision of the camera, and is suitable for fire scenes containing air volume detection data under multiple scenes.
The utility model provides a look down camera realizes the whole collection of data to the position data of wind speed sensor in the correlation picture, go to indirectly acquire the pitch angle of looking down camera when gathering image data, the space view angle of the observation image data that the correction pitch angle brought, adjust the detection scope of wind speed sensor simultaneously and be oval or circular in two-dimensional projection plane's shape, for example, because the look down camera of slope detects ground image data, the perspective transformation's that gathers two discerns wind speed sensor distance data and known installation distance data are inconsistent, through two pair of known installation distance data, be the distance data of two wind speed sensors in the picture that the triangle-shaped correction looks down camera detected.
The recognition algorithm mentioned in the present application may be a neural network algorithm, or may adopt a plurality of neural network algorithm recognition models capable of achieving the effects in the present application, and may adopt a regression method including but not limited to a deep learning-based regression method including but not limited to YOLO series algorithm, and the invention point of the present application is not in the model and the recognition operation, so that the description is omitted here.
The application provides a fire identification prediction method, a fire identification prediction system and a fire identification prediction medium based on air volume data, which aim at solving the technical problems in the prior art.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a fire identification and prediction method based on air volume data according to an exemplary embodiment of the present application, and as shown in fig. 1, the present application provides a fire identification and prediction method based on air volume data, including:
s1, acquiring wind speed sensor data and downward-looking camera observation data;
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera, wherein the topography data comprises the position of a wind speed sensor;
acquiring fire position data and coordinate data of the acquired fire position, namely adopting an identification algorithm to identify a fire starting point, shielding smoke, displaying a unidirectional irregular graph in an image under the influence of wind power, only selecting the starting position of a unidirectional side to be specified as the fire starting point, wherein the starting point is the fire position in a current frame, and marking the highest temperature value by a temperature step value by means of thermal data corresponding to the infrared detection fire position on a camera, and selecting a local area obviously higher than the surrounding environment temperature as a fire spreading area;
s2, modeling the wind speed sensor and observation data to generate a plane model comprising a wind cluster, a fire point and an observation map;
generating a planar model comprising an observation map:
according to the height data, the scale of the observed image data is adjusted, meanwhile, the observed image and the horizontal plane inclination angle data are adjusted according to the identified position data of the wind speed sensor and the read corresponding installation position data of the wind speed sensor, the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located is calculated, the included angle is identical to the inclination angle of the observed image and the horizontal plane, for example, fig. 2 is a downward-looking angle chart in the fire behavior identification prediction method based on the wind volume data, as shown in fig. 2, the distance between projections of the horizontal planes of the two wind speed sensors is known to be d1, the distance data acquired by the downward-looking camera is the projection distance d2, the camera does not deflect, the position of the downward-looking camera is shot horizontally, when d2 is larger than d1, the included angle between the downward-looking camera and the vertical plane is arcco (d 1/d 2) calculated, the perspective image is acquired by adjusting the projection angle data of the whole camera, and the corrected image is acquired by the perspective image.
Generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle, namely, the projection direction of an image acquired by a lower vision camera is adjusted according to arccos (d 1/d 2), and after perspective transformation, the perfect circle of the measurement range falling at the installation position of the wind speed sensor is projected to the horizontal plane to form an ellipse or perfect circle, as shown in fig. 3;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the wind quantity values and the wind direction angles of the adjacent wind clusters are linearly adjusted according to wind direction tracks and the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
S3, processing the acting force of wind vectors corresponding to peripheral wind clusters of the fire point on the fire point at the current frame moment, calculating the resultant force of all the peripheral wind clusters on the acting force of the fire point, and outputting the trend of the fire of the current frame and the expected arrival area of the fire at the next frame moment under the influence of the resultant force of multiple wind clusters, wherein the resultant force of multiple wind clusters comprises the direction of the resultant force and the propagation speed variable of the fire point.
Rasterizing the observation map data, and assigning a value to a grid occupied by the wind cluster, wherein the assigned value is the quantized wind volume data and the angle value of the wind direction;
performing data fitting on blank grids of the area gap occupied by the wind cluster in an observation map, and assigning values, wherein the data fitting is performed in a mode that each blank grid is taken as a starting point, the blank grids travel to adjacent grids occupied by assigned wind clusters in an equal step length, step lengths of a plurality of grids occupied by wind clusters reaching different assigned contents are calculated, the numerical gradient change rate caused by the step lengths is calculated, and the content values of the blank grids meeting the step length travel relation are calculated according to the numerical gradient change rate;
for example, fig. 4 is a graph of assigning a blank grid in a fire identification prediction method based on air volume data according to an exemplary embodiment of the present application, as shown in fig. 4, the blank grid x is used as a starting point to diverge all around, a path reaching the assignment grid is found, in the process of finding the path, two types of variables of multiple assignment grids reach the blank grid x in a nonlinear manner, meanwhile, the multiple blank grids x (1, 2, … …, N) are the number of blank grids in a range of an irregular graph formed by occupying and connecting the assignment grids, the multiple paths are fitted into continuous multiple paths, the expected values are solved and assigned for the values of the corresponding same grid in the fitted multiple paths, and the two types of variables are quantized air volume data and angle values of wind directions. Further, the method further comprises the following steps: judging the belonging blank grid or the grid occupied by the wind cluster according to the global coordinate of the gravity center position of the thermal value of the fire, calling the assigned data content in the corresponding grid, analyzing the fire direction and the fire spreading speed of the current frame according to the data content, and analyzing the global coordinate reached by the fire at the next frame time, and analyzing the fire direction and the fire spreading speed at the next frame time.
In yet another embodiment provided herein, the present application provides a fire identification prediction system based on air volume data, including:
the acquisition module is used for acquiring the data of the wind speed sensor and the observation data of the downward-looking camera;
the modeling module is used for modeling the wind speed sensor and the observation data and generating a plane model comprising a wind cluster, a fire point and an observation map;
the processing module is used for processing the acting force of wind power vectors corresponding to peripheral wind clusters of the fire point at the current frame moment to the fire point, calculating the resultant force of all the peripheral wind clusters to the acting force of the fire point, and outputting the trend of the fire of the current frame under the influence of the resultant force of multiple wind clusters and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple wind clusters comprises the direction of the resultant force and the propagation speed variable to the fire point.
Preferably, the acquisition module is specifically configured to:
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera;
and collecting fire position data and coordinate data of the fire position.
Preferably, the modeling module is specifically configured to:
generating a planar model comprising an observation map:
according to the height data, adjusting the scale of the observed image data, and simultaneously adjusting the observed image and the horizontal plane inclination angle data according to the position data of the identified wind speed sensor and the read corresponding wind speed sensor installation position data, and calculating the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located, wherein the included angle is the same as the inclination angle of the observed image and the horizontal plane;
generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, and projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the wind quantity values and the wind direction angles of the adjacent wind clusters are linearly adjusted according to wind direction tracks and the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
Preferably, the processing module has a processing module for:
rasterizing the observation map data, and assigning a value to a grid occupied by the wind cluster, wherein the assigned value is the quantized wind volume data and the angle value of the wind direction;
and carrying out data fitting on blank grids of the area gap occupied by the wind cluster in the observation map, wherein the data fitting mode is to take each blank grid as a starting point, travel to grids occupied by the adjacent assigned wind cluster in an equal step length, calculate the step length of the grids occupied by the wind clusters for realizing different assignment contents, calculate the numerical gradient change rate brought by the step length, and calculate the content value of the blank grid meeting the step length travel relation according to the numerical gradient change rate.
The method and the device for analyzing the fire trend based on the air quantity data have the advantages that the change condition, distribution and fire image recognition of the air quantity data in the local area are combined, the fire trend is analyzed, the analysis on the fire trend can be improved, the fire trend is reasonably avoided, the real-time guidance is realized, the fire spreading direction, speed and trend are predicted, and the rescue work can be assisted to be completed more quickly and effectively.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in hardware plus software functional modules.
It will be appreciated by those skilled in the art that embodiments of the invention may be provided as methods or systems. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The fire behavior recognition and prediction method based on the air volume data is characterized by comprising the following steps of:
collecting wind speed sensor data and looking down camera observation data;
modeling the wind speed sensor and the observation data to generate a plane model comprising wind clusters, fire points and an observation map;
and processing the acting force of wind vectors corresponding to peripheral clusters of the fire point on the fire point at the current frame moment, calculating the resultant force of all the peripheral clusters on the acting force of the fire point, and outputting the current frame fire trend under the influence of the resultant force of multiple clusters and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple clusters comprises the direction of the resultant force and the propagation speed variable of the fire point.
2. The method of claim 1, wherein the acquiring wind speed sensor data, acquiring look-down camera observations, comprises:
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera;
and collecting fire position data and coordinate data of the fire position.
3. The method of claim 2, wherein modeling the wind speed sensor with the observed data generates a planar model comprising a cluster of winds, a fire point, and an observation map, comprising the steps of:
generating a planar model comprising an observation map:
according to the height data, adjusting the scale of the observed image data, and simultaneously adjusting the inclination angle data of the observed image and the horizontal plane according to the position data of the identified wind speed sensor and the read installation position data of the corresponding wind speed sensor, and calculating the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located, wherein the included angle is the same as the inclination angle of the observed image and the horizontal plane;
generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, and projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the adjustment is carried out according to the wind quantity values and the wind direction angles of the adjacent wind clusters to be linear adjustment according to wind direction tracks and linear adjustment according to the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
4. A method according to claim 3, wherein the processing of the force of the wind vectors corresponding to the peripheral clusters of the fire point at the current frame time to the fire point force calculates the resultant force of all the peripheral clusters to the fire point force, and outputs the current frame trend under the influence of the resultant force of multiple clusters including the direction of the resultant force and the propagation speed variation to the fire point and the area expected to arrive at the next frame time, comprises:
rasterizing observation map data, and assigning values to grids occupied by the wind clusters, wherein the contents of the assignment are quantized wind volume data and angle values of wind directions;
and carrying out data fitting on blank grids of the area gaps occupied by the wind clusters in an observation map, wherein the data fitting mode is to take each blank grid as a starting point, travel to grids occupied by the adjacent assigned wind clusters in an equal step length, calculate the step length of the grids occupied by the wind clusters for realizing different assignment contents, calculate the numerical gradient change rate brought by the step length, and calculate the content values of the blank grids meeting the step length travel relation according to the numerical gradient change rate.
5. The method of claim 4, wherein the processing the force of the wind vector corresponding to the peripheral clusters of the fire point at the current frame time to the fire point force calculates the resultant force of all the peripheral clusters to the fire point force, and outputs the current frame trend under the influence of the resultant force of multiple clusters including the direction of the resultant force and the propagation speed variation to the fire point and the area expected to arrive at the fire point at the next frame time, further comprising: judging the belonging blank grid or the grid occupied by the wind cluster according to the global coordinate of the gravity center position of the thermal value of the fire, calling the assigned data content in the corresponding grid, analyzing the fire direction and the fire spreading speed of the current frame according to the data content, and analyzing the global coordinate reached by the fire at the next frame time, and analyzing the fire direction and the fire spreading speed at the next frame time.
6. A fire identification prediction system based on air volume data, comprising:
the acquisition module is used for acquiring the data of the wind speed sensor and the observation data of the downward-looking camera;
the modeling module is used for modeling the wind speed sensor and the observation data and generating a plane model comprising a wind cluster, a fire point and an observation map;
the processing module is used for processing the acting force of wind power vectors corresponding to peripheral wind clusters of the fire point at the current frame moment to the fire point, calculating the resultant force of all the peripheral wind clusters to the acting force of the fire point, and outputting the trend of the fire of the current frame under the influence of the resultant force of multiple wind clusters and the expected arrival area of the fire at the next frame moment, wherein the resultant force of the multiple wind clusters comprises the direction of the resultant force and the propagation speed variable to the fire point.
7. The system according to claim 6, wherein the acquisition module is specifically configured to:
collecting height data of the down-looking observation data and collecting data of a wind speed sensor;
the method also comprises the steps of collecting position data of the wind speed sensor and reading mounting position data of the wind speed sensor;
collecting topography data of a downward-looking observation area, and acquiring topography data by calling known topography data or carrying out image recognition on the collected observation data of a downward-looking camera;
and collecting fire position data and coordinate data of the fire position.
8. The system according to claim 7, wherein the modeling module is specifically configured to:
generating a planar model comprising an observation map:
according to the height data, adjusting the scale of the observed image data, and simultaneously adjusting the inclination angle data of the observed image and the horizontal plane according to the position data of the identified wind speed sensor and the read installation position data of the corresponding wind speed sensor, and calculating the included angle between the current downward-looking observation direction and the vertical plane where the downward-looking camera is located, wherein the included angle is the same as the inclination angle of the observed image and the horizontal plane;
generating a planar model comprising a wind mass:
calculating global coordinate data of a wind speed sensor in an observation image, and projecting a horizontal plane on the observation image according to an actual measurement range of a predicted wind speed sensor to form an elliptical or circular wind cluster, wherein the wind cluster is obtained by rotating the actual measurement range according to the included angle;
the wind directions in the wind clusters are consistent and the wind quantity is the same, and data integration is carried out between adjacent wind clusters, wherein the data integration is that the wind quantity of the wind clusters is digitalized and the wind direction of the wind clusters is angulated, the wind quantity and the wind direction in an irregular pattern gap between the two wind clusters are adjusted according to the wind quantity values and the wind direction angles of the adjacent wind clusters, and the adjustment is carried out according to the wind quantity values and the wind direction angles of the adjacent wind clusters to be linear adjustment according to wind direction tracks and linear adjustment according to the wind quantity sizes;
generating a planar model including fire points:
and carrying out data processing on the downward-looking observed fire area, processing image recognition of the fire area, acquiring a thermodynamic diagram with temperature difference measured by infrared, calculating the gravity center position of the thermal value of the fire point by taking the intensity of the thermal value as a target value, correlating the gravity center position of the fire point with the acquired fire position data, and calculating the coordinate data of the fire position as the global coordinate of the gravity center position of the thermal value of the fire point.
9. The system of claim 8, wherein the processing module has a logic for:
rasterizing observation map data, and assigning values to grids occupied by the wind clusters, wherein the contents of the assignment are quantized wind volume data and angle values of wind directions;
and carrying out data fitting on blank grids of the area gaps occupied by the wind clusters in an observation map, wherein the data fitting mode is to take each blank grid as a starting point, travel to grids occupied by the adjacent assigned wind clusters in an equal step length, calculate the step length of the grids occupied by the wind clusters for realizing different assignment contents, calculate the numerical gradient change rate brought by the step length, and calculate the content values of the blank grids meeting the step length travel relation according to the numerical gradient change rate.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310850187.3A CN116563719B (en) | 2023-07-12 | 2023-07-12 | Fire identification prediction method, system and medium based on air volume data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310850187.3A CN116563719B (en) | 2023-07-12 | 2023-07-12 | Fire identification prediction method, system and medium based on air volume data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116563719A true CN116563719A (en) | 2023-08-08 |
| CN116563719B CN116563719B (en) | 2023-10-20 |
Family
ID=87503933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310850187.3A Active CN116563719B (en) | 2023-07-12 | 2023-07-12 | Fire identification prediction method, system and medium based on air volume data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116563719B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9977963B1 (en) * | 2017-03-03 | 2018-05-22 | Northrop Grumman Systems Corporation | UAVs for tracking the growth of large-area wildland fires |
| CN114757387A (en) * | 2022-03-07 | 2022-07-15 | 南京林业大学 | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence |
| CN114819310A (en) * | 2022-04-14 | 2022-07-29 | 安徽工业大学 | Building cluster fire spread prediction method and system based on minimum spanning tree |
| CN114936502A (en) * | 2022-07-25 | 2022-08-23 | 四川开澜科技有限公司 | Forest fire spreading situation boundary analysis method, system, terminal and medium |
| CN115330957A (en) * | 2022-10-10 | 2022-11-11 | 南京信息工程大学 | Method for simulating diffusion of fire smoke in building and emergency scheme calling method |
| CN115577830A (en) * | 2022-09-16 | 2023-01-06 | 浙江大华技术股份有限公司 | Fire spread range prediction method and device, computer equipment and storage medium |
| CN116189371A (en) * | 2023-02-10 | 2023-05-30 | 南京林业大学 | Forest fire prevention and fire control facility linkage management system and method based on Internet of things |
| CN116415754A (en) * | 2023-04-19 | 2023-07-11 | 华东理工大学 | Forest fire spread prediction method and system |
-
2023
- 2023-07-12 CN CN202310850187.3A patent/CN116563719B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9977963B1 (en) * | 2017-03-03 | 2018-05-22 | Northrop Grumman Systems Corporation | UAVs for tracking the growth of large-area wildland fires |
| CN114757387A (en) * | 2022-03-07 | 2022-07-15 | 南京林业大学 | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence |
| CN114819310A (en) * | 2022-04-14 | 2022-07-29 | 安徽工业大学 | Building cluster fire spread prediction method and system based on minimum spanning tree |
| CN114936502A (en) * | 2022-07-25 | 2022-08-23 | 四川开澜科技有限公司 | Forest fire spreading situation boundary analysis method, system, terminal and medium |
| CN115577830A (en) * | 2022-09-16 | 2023-01-06 | 浙江大华技术股份有限公司 | Fire spread range prediction method and device, computer equipment and storage medium |
| CN115330957A (en) * | 2022-10-10 | 2022-11-11 | 南京信息工程大学 | Method for simulating diffusion of fire smoke in building and emergency scheme calling method |
| CN116189371A (en) * | 2023-02-10 | 2023-05-30 | 南京林业大学 | Forest fire prevention and fire control facility linkage management system and method based on Internet of things |
| CN116415754A (en) * | 2023-04-19 | 2023-07-11 | 华东理工大学 | Forest fire spread prediction method and system |
Non-Patent Citations (4)
| Title |
|---|
| ZHONG ZHENG 等: "Forest fire spread simulating model using cellular automaton with extreme learning machine", 《ECOLOGICAL MODELLING》, pages 33 - 43 * |
| 姜文宇 等: "基于元胞自动机的以火灭火动态建模方法", 《清华大学学报（自然科学版）》, pages 926 - 933 * |
| 李建微 等: "虚拟森林景观中林火蔓延模型及三维可视化表达", 《应用生态学报》, pages 838 - 842 * |
| 淮永建北京林业大学信息学院 等: "森林场景可视化和林火模拟仿真技术研究综述", 《中国图象图形学报》, pages 1891 - 1908 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116563719B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110441791B (en) | Ground obstacle detection method based on forward-leaning 2D laser radar | |
| Nouri et al. | Cloud height and tracking accuracy of three all sky imager systems for individual clouds | |
| CN110658518B (en) | Target intrusion detection method and device | |
| CN107924461B (en) | Method, circuit, equipment, system and the correlation computer executable code for being registrated and tracking for multifactor characteristics of image | |
| WO2015104281A1 (en) | Solar irradiance forecasting | |
| CN109934844A (en) | A kind of multi-object tracking method and system merging geospatial information | |
| CN106485868B (en) | Monitoring method, the monitoring server of system and fire behavior of fire behavior | |
| CN110514298B (en) | Solar radiation intensity calculation method based on foundation cloud picture | |
| CA2947138A1 (en) | Object detection device, object detection method, and object detection system | |
| US20130272578A1 (en) | Information processing apparatus, information processing method, and program | |
| CN104954747B (en) | Video monitoring method and device | |
| CN111339826B (en) | Landslide unmanned aerial vehicle linear sensor network frame detecting system | |
| CN109238227B (en) | Method for representing ground settlement space-time evolution | |
| WO2017051480A1 (en) | Image processing device and image processing method | |
| CN109614948B (en) | Abnormal behavior detection method, device, equipment and storage medium | |
| KR102272369B1 (en) | Apparatus for predicting solar power based on satellite image and method thereof | |
| CN109681786A (en) | A kind of harmful influence leak position method | |
| Dolloff et al. | An assessment of WorldView-1 positional accuracy based on fifty contiguous stereo pairs of imagery | |
| CN110823899A (en) | Fault positioning method, device and system | |
| CN111337011A (en) | Indoor positioning method based on laser and two-dimensional code fusion | |
| KR101469099B1 (en) | Auto-Camera Calibration Method Based on Human Object Tracking | |
| CN113506340A (en) | Method and equipment for predicting cloud deck pose and computer readable storage medium | |
| JP2022013152A (en) | Cloud height measuring device, measuring point determination method, and cloud type determination method | |
| US11594035B2 (en) | Monitoring device, and method for monitoring a man overboard situation | |
| CN111652314A (en) | Temperature detection method and device, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |