Fire location method, system and equipment based on photon radar

Abstract

The present application relates to the field of three-dimensional fire positioning technology, and specifically to a method, system and device for positioning a fire based on a photon radar, the method comprising: real-time acquisition of three-dimensional point cloud data detected by each photon radar on a fire monitoring area; the three-dimensional point cloud data contains a fire point; according to the position difference of different fire points at the same time and the position difference of the same fire point at different times, the positioning deviation is obtained; according to the clustering of all fire points at the current time and the similarity of the position change of all fire points in the local area of ​​each fire point over time, the position true coefficient is obtained; the positioning accuracy coefficient of each photon radar is obtained by combining the position true coefficient and the positioning deviation; according to the positioning accuracy coefficient of all photon radars, the three-dimensional point cloud data of the photon radar is selected for three-dimensional modeling, and the three-dimensional model of the fire monitoring area is obtained to locate the fire source. The present application can improve the accuracy of fire positioning.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional fire positioning, and in particular to a fire positioning method, system and equipment based on photon radar. Background Art

[0002] The working principle of photon radar is to obtain target information by emitting a single photon and detecting the photons reflected back. This method has extremely high sensitivity and resolution, and can detect very weak signals, thereby achieving accurate detection of targets in the early stages of a fire or in other complex environments. Then, a three-dimensional model is established through three-dimensional geographic information system technology to quickly visualize and warn the fire location, thereby achieving efficient fire location.

[0003] In the process of using photonic quantum radar to locate fires, there are many interference factors in the scene. For example, the complex weather environment in the outdoor environment causes smoke deviation of the fire point, and there are many moving targets in the complex field scene. These will cause the fire points collected by the photonic quantum radar to have certain position deviations, resulting in low accuracy of the model during three-dimensional modeling, which in turn affects the accuracy of fire location. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a fire location method, system and equipment based on optical quantum radar. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a fire location method based on a photon radar, the method comprising the following steps:

[0006] S1, real-time acquisition of three-dimensional point cloud data of the fire monitoring area detected by each photon radar; the three-dimensional point cloud data includes a fire point;

[0007] S2, according to the position difference of different fire points at the same time and the position difference of the same fire point at different times, obtain the positioning deviation of each fire point at each time;

[0008] S3, according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time, the true position coefficient of each fire point at the current moment is obtained;

[0009] S4, comprehensively analyzing the true position coefficient and positioning deviation of the fire point detected by each photon radar at the current moment, and obtaining the positioning accuracy coefficient of each photon radar at the current moment;

[0010] S5, according to the positioning accuracy coefficients of all photon radars at the current moment, the three-dimensional point cloud data of the photon radar is selected for three-dimensional modeling, and the three-dimensional model of the fire monitoring area is obtained to locate the fire source.

[0011] Furthermore, the method for obtaining the positioning deviation of each fire point at each moment includes:

[0012] For the current time t, calculate the mean of the Euclidean distances between the i-th fire point and all other fire points at time t, recorded as the first mean; calculate the mean of the Euclidean distances of all the fire points except the i-th fire point at time t, recorded as the second mean; and take the difference between the first mean and the second mean as the spatial offset of the i-th fire point at time t;

[0013] The positioning deviation of the i-th fire point at time t is calculated by comprehensively considering the spatial offset of the i-th fire point at time t and the difference in the position of the i-th fire point at time t relative to its position before the preset time period.

[0014] Furthermore, the method for calculating the positioning deviation of the i-th fire point at time t includes:

[0015] Set the offset observation time Q; record the positioning deviation of the i-th fire point at time t as , ;in, is the Euclidean distance between the position of the i-th fire point at time t and its position at time tQ; is the spatial offset of the i-th fire point at time t; A preset constant greater than 0.

[0016] Furthermore, the position true coefficient of each fire point at the current moment is obtained according to the clustering of all fire points at the current moment and the similarity of the position change of all fire points in the local area of ​​each fire point over time, including:

[0017] Density clustering is performed on all fire points at all times to obtain clusters;

[0018] Obtain the mean of the Euclidean distances between the clusters to which each fire point belongs and the cluster centers of all other clusters at the current moment, recorded as the average inter-cluster distance; obtain the cumulative sum of the Euclidean distances between any two fire points in the clusters to which each fire point belongs at the current moment; and use the ratio of the average inter-cluster distance to the cumulative sum as the multi-source characteristic coefficient of each photon radar at the current moment;

[0019] According to the similarity between the position changes of all fire points in the cluster to which each fire point belongs at the current moment and the previous moment, the change approximation of each photon radar fire point at the current moment is obtained;

[0020] By integrating the multi-source characteristic coefficients and change approximation of each photon radar at the current moment, the true position coefficient of each fire point at the current moment is obtained.

[0021] Furthermore, the method for obtaining the change approximation of each photon radar fire point at the current moment includes:

[0022] Calculate the average and variance of the Euclidean distance between all fire points in the cluster to which each photon radar fire point belongs at the current moment and the previous moment; take the reciprocal of the sum of the average, the variance and a preset constant greater than 0 as the change approximation of each photon radar fire point at the current moment.

[0023] Furthermore, the multi-source characteristic coefficients and the variation approximation of each photon radar at the current moment are integrated to obtain the true position coefficient of each fire point at the current moment, including:

[0024] The product of the multi-source characteristic coefficient of each photon radar at the current moment and the variation approximation is taken as the true position coefficient of each fire point at the current moment.

[0025] Furthermore, the method for obtaining the positioning accuracy coefficient of each photon radar at the current moment includes: calculating the sum of the positioning deviation of the fire point detected by each photon radar at the current moment and a preset constant greater than 0; taking the ratio of the true position coefficient of the fire point detected by each photon radar at the current moment to the sum as the positioning accuracy coefficient of each photon radar at the current moment.

[0026] Further, the three-dimensional point cloud data of the photon radar is selected according to the positioning accuracy coefficient of all photon radars at the current moment to perform three-dimensional modeling, and the three-dimensional model of the fire monitoring area is obtained to locate the fire source, including:

[0027] A threshold analysis is performed on the positioning accuracy coefficients of all photon radars at the current moment to obtain a segmentation threshold; the three-dimensional point cloud data detected by the photon radar whose positioning accuracy coefficient is greater than the segmentation threshold is recorded as precise point cloud data; three-dimensional modeling is performed on all precise point cloud data to obtain a three-dimensional model of the fire monitoring area.

[0028] In a second aspect, an embodiment of the present application provides a fire location system based on a photon radar, the fire location system comprising:

[0029] A positioning data acquisition module is used to obtain in real time the three-dimensional point cloud data detected by each photon radar on the fire monitoring area; the three-dimensional point cloud data includes a fire point;

[0030] The data accuracy assessment module is used to obtain the positioning deviation of each fire point at each moment according to the position differences of different fire points at the same moment and the position differences of the same fire point at different moments; obtain the true position coefficient of each fire point at the current moment according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time; and obtain the positioning accuracy coefficient of each photon radar at the current moment by combining the true position coefficient and positioning deviation of the fire points detected by each photon radar at the current moment;

[0031] The real-time fire source positioning module is used to select the three-dimensional point cloud data of the photon radar according to the positioning accuracy coefficient of all photon radars at the current moment for three-dimensional modeling, and obtain the three-dimensional model of the fire monitoring area to locate the fire source.

[0032] In a third aspect, an embodiment of the present application further provides a fire location device based on optical quantum radar, the device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

[0033] It can be seen from the above embodiments that the fire location method, system and device based on photon radar provided in the embodiments of the present application have at least the following beneficial effects:

[0034] This application aims at the influence of the smoke environment generated when a fire occurs on the accuracy of fire point identification, analyzes the differences in the three-dimensional data of fire points collected at different times by using photon radar and the position differences of different fire points at the same time, calculates the positioning deviation, and indicates the degree of positioning deviation caused by smoke interference; further analyzes the situation where fire sources appear at multiple locations at the same time, and obtains the position true coefficient according to the similarity of the position changes of the fire points collected by each photon radar over time, so as to characterize the authenticity of the three-dimensional data of the fire points collected by the current photon radar; further locates the deviation degree and the position true coefficient, constructs the positioning accuracy coefficient of a single photon radar, comprehensively characterizes the accuracy of the three-dimensional data of the fire points collected by the photon radar, and then selects the three-dimensional data of the fire points with higher accuracy for three-dimensional modeling. This application solves the problem that in the process of using photon radar to locate fire, the three-dimensional data of the fire points collected by the photon radar has a certain position deviation due to environmental factors, resulting in low accuracy of the model when modeling, and improves the accuracy of fire location. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 A flowchart of a method for locating a fire based on a photon radar according to an embodiment of the present application;

[0037] Figure 2 A schematic diagram of fire point distribution provided for one embodiment of the present application;

[0038] Figure 3 A structural block diagram of a fire location device based on photon radar provided in one embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the fire location method, system and device based on the photon radar proposed in the present application, its specific implementation, structure, features and effects are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0040] Unless otherwise specified and limited, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application.

[0041] The specific scheme of the fire location method, system and equipment based on photon radar provided by the present application is described in detail below with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flow chart of the steps of a fire location method based on a photon radar provided by an embodiment of the present application, the method comprising the following steps:

[0043] S1, real-time acquisition of the three-dimensional point cloud data of the fire monitoring area detected by each photon radar.

[0044] A specific implementation scenario of the embodiment of the present application is to use a photon radar for fire location. Taking a nature reserve as a fire monitoring area as an example, the principle of using a photon radar for fire source detection is to use a quantum radar to emit a laser beam, detect the reflected light signal, and determine whether there is a fire source by analyzing the signal characteristics. The photon radar can provide higher spatial resolution, which helps to generate a more detailed three-dimensional model to accurately locate the fire source.

[0045] Therefore, this embodiment uses each photon radar in the fire monitoring area to obtain three-dimensional point cloud data once every time interval T, T=0.1s. The three-dimensional point cloud data contains fire points and non-fire points, the fire points are locations where fires may occur, and the non-fire points are natural landform locations where fires have not occurred. Among them, using photon radar to detect fire sources and identify fire points and non-fire points is a well-known technology, and the specific implementation process will not be repeated.

[0046] In the process of using photon radar to locate fire, due to environmental factors, the recognition accuracy of photon radar for fire points and non-fire points is poor. Figure 2 As shown, this is a schematic diagram of the fire point distribution, which maps the three-dimensional data of fire points collected by all photon radars onto a two-dimensional plane.

[0047] In order to improve the quality of three-dimensional point cloud data, this embodiment determines the recognition accuracy of each photon radar for the fire point by analyzing the distinguishing features of the fire origin location and the surrounding smoke state environment, and selects fire points with higher accuracy to participate in the calculation of fire location.

[0048] S2, according to the position difference of different fire points at the same time and the position difference of the same fire point at different times, the positioning deviation degree of each fire point at each time is obtained.

[0049] When the photon radar acquires the fire point, the origin of the fire will spread to a certain range, and the fire point is relatively small, so the 3D data of the smoke area will be highlighted faster than the 3D data of the fire source area. Therefore, the location of the fire point will be affected by the larger smoke environment factors, and when collecting data on the fire point location, there may be a large difference in the location of the fire point.

[0050] When a fire point collected by a photon radar may have a certain deviation, the position of the fire point will change greatly over time, and the three-dimensional position data of the fire point collected by different photon radars will be quite different. Therefore, this embodiment determines the degree of positioning deviation of each fire point at each moment based on the position difference of different fire points at the same moment and the position deviation of the same fire point at different moments.

[0051] Specifically, for the current moment t, taking the i-th fire point at time t as an example, first, calculate the mean Euclidean distance between the i-th fire point and all other fire points at time t, recorded as the first mean; the mean Euclidean distance of all pairwise combinations of all fire points except the i-th fire point at time t is recorded as the second mean; the difference between the first mean and the second mean is taken as the spatial offset of the i-th fire point at time t; the difference is the absolute value of the difference between the first mean and the second mean.

[0052] When there is a certain deviation in the i-th fire point, the greater the difference in position between the current moment and the other fire points, and the positions of the other fire points are more dense, it means that the fire point is more isolated than the other photonic quantum radars. The larger the spatial offset obtained, the more likely it is that the detection error will be caused by environmental factors.

[0053] First, according to the driving effect of wind direction on smoke drift, the fire point will have a relatively obvious offset at each interval. Therefore, this embodiment comprehensively considers the spatial offset of the i-th fire point at time t and the difference between the position of the i-th fire point at time t and its position before the preset time period, and calculates the positioning deviation of the i-th fire point at time t. The calculation formula is:

[0054]

[0055] in, is the positioning deviation of the i-th fire point at time t; is the Euclidean distance between the position of the i-th fire point at time t and its position at time tQ; is the spatial offset of the i-th fire point at time t; To preset a constant greater than 0 to prevent the denominator from being 0, this embodiment ; Q is the offset observation time pre-set according to the weather conditions in this embodiment, Q=0.5s.

[0056] If the fire point collected by the i-th photon radar at the current moment is not the actual location of the fire point, the greater the degree of position change of the fire point over time; when the spatial offset of the i-th fire point is larger, it means that the fire point is more outlier than the other photon radars, and is more likely to be affected by environmental factors and cause detection errors. The larger the final positioning deviation, the more likely the fire point collected by the photon radar is to be a location with thick smoke around the fire point, rather than the actual fire point location, and it needs to be excluded during the positioning process.

[0057] S3, according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time, the true position coefficient of each fire point at the current moment is obtained.

[0058] Since the environment in which a fire occurs is relatively complex and there are many different situations in which a fire occurs, environmental factors may cause multiple fires to occur simultaneously, resulting in multiple and scattered fire sources. At this time, if the accuracy of the fire point location is determined only by the positioning deviation calculated in the above manner, the fire sources may appear at multiple locations at the same time, and the fire point locations are distributed more discretely, resulting in a higher calculated positioning deviation. As a result, fire points that may be the real fire source locations are excluded, ultimately leading to misjudgment or missed fire points. Therefore, further analysis is needed.

[0059] When there are multiple fire points, the overall distribution of the fire point locations collected by the photon radar is relatively discrete, but the local convergence degree is relatively high. Therefore, this embodiment performs density clustering on all fire points at all times to obtain clusters; specifically, all fire points are used as input, the DPC clustering algorithm is used, the Euclidean distance between the fire points is used as the metric distance, the cutoff distance is set to 3, and several clusters are output. The DPC clustering algorithm is a well-known technology and will not be described in detail in this application.

[0060] Based on the distribution characteristics of the fire points when there are multiple fire sources, the multi-source characteristic coefficient of the i-th photon radar at the current moment is calculated by determining the distribution between clusters and the distribution within clusters. , calculated as follows:

[0061]

[0062] in, is the multi-source characteristic coefficient of the i-th photon radar at the current moment; is the mean Euclidean distance between the cluster to which the i-th fire point belongs and the cluster centers of all other clusters, recorded as the average distance between clusters; It is the cumulative sum of the Euclidean distances between any two fire points in the cluster to which the i-th fire point belongs.

[0063] When there are multiple fire points, the fire points are locally clustered and overall dispersed. The larger the average distance between clusters, the smaller the distance between fire points within the cluster, that is, the larger the multi-source characteristic coefficient, indicating that it is more likely that there are multiple fire points.

[0064] When there are multiple fire points, the changes in the positions of the fire points within the same fire point over time are relatively similar, and the overall change amplitude is small. Specifically, the change amplitudes of the fire points in the same cluster are relatively similar over the sampling time, and the mean change amplitude is small.

[0065] Therefore, this embodiment obtains the change approximation of each photon radar fire point at the current moment based on the similarity between the position changes of all fire points in the cluster to which each fire point belongs at the current moment and the previous moment. The specific calculation method is:

[0066]

[0067] in, is the change approximation of the i-th photon radar fire point at the current moment; is the variance of the Euclidean distance between the current moment and the previous moment of all fire points in the cluster to which the i-th photon radar fire point belongs; is the mean Euclidean distance between the current moment and the previous moment of all fire points in the cluster to which the i-th photon radar fire point belongs; To preset a constant greater than 0 to prevent the denominator from being 0, this embodiment .

[0068] When there are multiple fire points, the smaller the mean distance of the fire points within the same fire point changes over time, the greater the approximation of the position change, that is, the smaller the variance, the smaller the change amplitude, and the higher the change approximation, indicating that the fire point collected by the i-th photon radar is more likely to be the fire source location data under the condition of multiple fire points.

[0069] The above multi-source characteristic coefficients indicate the degree of obviousness of the existence of multiple fire source characteristics; the change approximation reflects the degree of synchronization of the fire points that may belong to the same fire source over time; therefore, the accuracy of fire point positioning can be determined by combining the multi-source characteristic coefficients and change approximation of each photon radar at the current moment, and the true position coefficient of each fire point at the current moment is constructed.

[0070] In this embodiment, the true position coefficient is obtained by calculating the product of the multi-source characteristic coefficients of each photon radar at the current moment and the variation approximation.

[0071] If there are multiple fire points, the overall distribution of fire points collected by the optical quantum radar is relatively discrete but the local distribution is relatively dense, that is, the multi-source characteristic coefficient is larger; and the greater the approximation of the change of local fire points, that is, the greater the approximation of the change; the larger the obtained position true coefficient, the higher the authenticity of the fire point, and the more likely the location of the fire point is to be the source of the fire.

[0072] S4, comprehensively analyzing the true position coefficient and positioning deviation of the fire point detected by each photon radar at the current moment, and obtaining the positioning accuracy coefficient of each photon radar at the current moment.

[0073] Through the above analysis, the positioning accuracy of the photon radar is mainly judged by two aspects of characteristics. On the one hand, the positioning offset caused by smoke interference is represented by the positioning deviation degree; on the other hand, all fire points caused by multiple fire points present the characteristics of local density distribution, which is represented by the position true coefficient. Therefore, based on the positioning deviation degree and the position true coefficient, the positioning accuracy coefficient of a single photon radar is constructed.

[0074] In this embodiment, the positioning deviation and The sum of the values; the ratio of the true coefficient of the position of the fire point detected by each photon radar at the current moment to the sum is used as the positioning accuracy coefficient of each photon radar at the current moment. To preset a constant greater than 0 to prevent the denominator from being 0, this embodiment .

[0075] When the location of the fire point collected by a single photon radar is the actual fire source location, the smaller the positioning offset caused by smoke interference, that is, the smaller the positioning deviation; and the larger the position truth coefficient, the more likely the fire point collected by the photon radar is to be the actual location of the fire source, the more accurate the positioning, and the larger the final positioning accuracy coefficient, the more the three-dimensional coordinates of the fire point should be used to construct a three-dimensional model.

[0076] S5, according to the positioning accuracy coefficients of all photon radars at the current moment, the three-dimensional point cloud data of the photon radar is selected for three-dimensional modeling, and the three-dimensional model of the fire monitoring area is obtained to locate the fire source.

[0077] In summary, the positioning accuracy coefficient can accurately determine the accuracy of the fire point; in order to further improve the detection accuracy of the fire source in the fire monitoring area using three-dimensional point cloud data, this embodiment uses the positioning accuracy coefficient to screen fire points with higher accuracy to participate in the construction of the three-dimensional model.

[0078] Specifically, a threshold analysis is performed on the positioning accuracy coefficients of all photon radars at the current moment to obtain a segmentation threshold; the three-dimensional point cloud data detected by the photon radar whose positioning accuracy coefficient is greater than the segmentation threshold is recorded as precise point cloud data; and three-dimensional modeling is performed on all precise point cloud data to obtain a three-dimensional model of the fire monitoring area.

[0079] Among them, all positioning accuracy coefficients are used as input, and the segmentation threshold W of the positioning accuracy coefficient is output by cross-validation. The cross-validation method is a well-known technology and will not be described in detail in this application. A three-dimensional model of the fire monitoring area is established for all accurate point cloud data using three-dimensional geographic information system technology to locate the fire source location area. Among them, the specific implementation process of three-dimensional modeling of point cloud data using three-dimensional geographic information system technology is a well-known technology and will not be described in detail in this application.

[0080] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a fire location system based on a photon radar provided in an embodiment of the present application. In this embodiment, each unit included in the terminal is used to execute each step in the embodiment corresponding to the fire location method based on a photon radar. Figure 3 ,The fire location system includes: a positioning data acquisition module, a data ,accuracy evaluation module, and a fire source real-time ,location module.

[0081] A positioning data acquisition module is used to obtain in real time the three-dimensional point cloud data detected by each photon radar on the fire monitoring area; the three-dimensional point cloud data includes a fire point;

[0082] The data accuracy assessment module is used to obtain the positioning deviation of each fire point at each moment according to the position differences of different fire points at the same moment and the position differences of the same fire point at different moments; obtain the true position coefficient of each fire point at the current moment according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time; and obtain the positioning accuracy coefficient of each photon radar at the current moment by combining the true position coefficient and positioning deviation of the fire points detected by each photon radar at the current moment;

[0083] The real-time fire source positioning module is used to select the three-dimensional point cloud data of the photon radar according to the positioning accuracy coefficient of all photon radars at the current moment for three-dimensional modeling, and obtain the three-dimensional model of the fire monitoring area to locate the fire source.

[0084] Based on the same inventive concept as the above method, an embodiment of the present application also provides a fire location device based on photon radar, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned fire location methods based on photon radar are implemented.

[0085] It is to be understood that the sequence of the embodiments of the present application described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0087] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the protection scope of the present application.

Claims

1. A fire location method based on photon radar, characterized in that: The method comprises the following steps: S1, real-time acquisition of three-dimensional point cloud data of the fire monitoring area detected by each photon radar; the three-dimensional point cloud data includes a fire point; S2, according to the position difference of different fire points at the same time and the position difference of the same fire point at different times, obtain the positioning deviation of each fire point at each time; S3, according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time, the true position coefficient of each fire point at the current moment is obtained; S4, comprehensively analyzing the true position coefficient and positioning deviation of the fire point detected by each photon radar at the current moment, and obtaining the positioning accuracy coefficient of each photon radar at the current moment; S5, according to the positioning accuracy coefficients of all photon radars at the current moment, the three-dimensional point cloud data of the photon radar is selected for three-dimensional modeling, and the three-dimensional model of the fire monitoring area is obtained to locate the fire source.

2. The fire location method based on photon radar as claimed in claim 1, characterized in that: The method for obtaining the positioning deviation of each fire point at each moment includes: For the current time t, calculate the mean of the Euclidean distances between the i-th fire point and all other fire points at time t, recorded as the first mean; calculate the mean of the Euclidean distances of all the fire points except the i-th fire point at time t, recorded as the second mean; and take the difference between the first mean and the second mean as the spatial offset of the i-th fire point at time t; The positioning deviation of the i-th fire point at time t is calculated by comprehensively considering the spatial offset of the i-th fire point at time t and the difference in the position of the i-th fire point at time t relative to its position before the preset time period.

3. The fire location method based on photon radar as claimed in claim 2, characterized in that: The method for calculating the positioning deviation of the i-th fire point at time t includes: Set the offset observation time Q; record the positioning deviation of the i-th fire point at time t as , ;in, is the Euclidean distance between the position of the i-th fire point at time t and its position at time tQ; is the spatial offset of the i-th fire point at time t; A preset constant greater than 0.

4. The fire location method based on photon radar as claimed in claim 1, characterized in that: The position true coefficient of each fire point at the current moment is obtained according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time, including: Density clustering is performed on all fire points at all times to obtain clusters; Obtain the mean of the Euclidean distances between the clusters to which each fire point belongs and the cluster centers of all other clusters at the current moment, recorded as the average inter-cluster distance; obtain the cumulative sum of the Euclidean distances between any two fire points in the clusters to which each fire point belongs at the current moment; and use the ratio of the average inter-cluster distance to the cumulative sum as the multi-source characteristic coefficient of each photon radar at the current moment; According to the similarity between the position changes of all fire points in the cluster to which each fire point belongs at the current moment and the previous moment, the change approximation of each photon radar fire point at the current moment is obtained; By integrating the multi-source characteristic coefficients and change approximation of each photon radar at the current moment, the true position coefficient of each fire point at the current moment is obtained.

5. The fire location method based on photon radar as claimed in claim 4, characterized in that: The method for obtaining the change approximation of each photon radar fire point at the current moment includes: Calculate the average and variance of the Euclidean distance between all fire points in the cluster to which each photon radar fire point belongs at the current moment and the previous moment; take the reciprocal of the sum of the average, the variance and a preset constant greater than 0 as the change approximation of each photon radar fire point at the current moment.

6. The fire location method based on photon radar as claimed in claim 4, characterized in that: The multi-source characteristic coefficients and the change approximation of each photon radar at the current moment are integrated to obtain the true position coefficient of each fire point at the current moment, including: The product of the multi-source characteristic coefficient of each photon radar at the current moment and the variation approximation is taken as the true position coefficient of each fire point at the current moment.

7. The fire location method based on photon radar as claimed in claim 1, characterized in that: The method for obtaining the positioning accuracy coefficient of each photon radar at the current moment includes: calculating the sum of the positioning deviation of the fire point detected by each photon radar at the current moment and a preset constant greater than 0; taking the ratio of the true position coefficient of the fire point detected by each photon radar at the current moment to the sum as the positioning accuracy coefficient of each photon radar at the current moment.

8. The fire location method based on photon radar as claimed in claim 1, characterized in that: The method of selecting the three-dimensional point cloud data of the photon radar according to the positioning accuracy coefficients of all photon radars at the current moment to perform three-dimensional modeling, and obtaining a three-dimensional model of the fire monitoring area to locate the fire source, includes: A threshold analysis is performed on the positioning accuracy coefficients of all photon radars at the current moment to obtain a segmentation threshold; the three-dimensional point cloud data detected by the photon radar whose positioning accuracy coefficient is greater than the segmentation threshold is recorded as precise point cloud data; three-dimensional modeling is performed on all precise point cloud data to obtain a three-dimensional model of the fire monitoring area.

9. A fire location system based on a photon radar, which implements a fire location method based on a photon radar as claimed in any one of claims 1 to 8, characterized in that: The fire location system comprises: A positioning data acquisition module is used to obtain in real time the three-dimensional point cloud data detected by each photon radar on the fire monitoring area; the three-dimensional point cloud data includes a fire point; The data accuracy assessment module is used to obtain the positioning deviation of each fire point at each moment according to the position differences of different fire points at the same moment and the position differences of the same fire point at different moments; obtain the true position coefficient of each fire point at the current moment according to the clustering of all fire points at the current moment and the similarity of the position changes of all fire points in the local area of ​​each fire point over time; and obtain the positioning accuracy coefficient of each photon radar at the current moment by combining the true position coefficient and positioning deviation of the fire points detected by each photon radar at the current moment. The real-time fire source positioning module is used to select the three-dimensional point cloud data of the photon radar according to the positioning accuracy coefficient of all photon radars at the current moment for three-dimensional modeling, and obtain the three-dimensional model of the fire monitoring area to locate the fire source.

10. A fire location device based on a photon radar, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the fire location method based on photon radar as described in any one of claims 1 to 8 are implemented.

Images