Ecological environment monitoring method, device and equipment based on GIS technology

Abstract

The present invention relates to the field of forest fire alarm, and specifically to an ecological environment monitoring method, device and equipment based on GIS technology. The method first obtains infrared images of each frame of the ecological area to be tested, and obtains the high temperature characteristic values ​​of the pixels in the infrared image and multiple high temperature areas according to the distribution of the gray values ​​of the pixels in each frame of the infrared image; obtains the high temperature coefficient of the high temperature area according to the high temperature characteristic values ​​of the pixels in each high temperature area in the infrared image and the gradient values ​​of the edge pixels of the high temperature area; analyzes the high temperature coefficient of the same high temperature area in infrared images of different frames, extracts the fire area, analyzes the degree of hazard of each fire area, and based on the degree of hazard, issues different levels of alarm information to each fire area in the ecological area to be tested. The present invention can accurately make different levels of alarms for different fire areas, thereby improving the effect of forest fire monitoring.

Description

Technical Field

[0001] The present invention relates to the field of forest fire alarm, and in particular to an ecological environment monitoring method, device and equipment based on GIS technology. Background Art

[0002] Forest fire monitoring is an important part of ecological and environmental protection. Forest fires are relatively hidden in the early stages. Early warning of forest fires can coordinate rescue personnel to put out forest fires in a timely manner and reduce the damage caused by fires to the ecological environment.

[0003] In related technologies, GIS technology is usually used to collect infrared images of the surface of forest areas, and visual analysis of the infrared images is performed to identify the location of fires in forest areas. However, as the fire develops dynamically, fires may occur in multiple areas, and there are large differences in the degree of fire urgency in different areas. Existing methods are unable to accurately analyze the fire urgency situation in different areas where fires occur, and thus are unable to accurately make different levels of alarms for different fire areas, reducing the effectiveness of forest fire monitoring. Summary of the invention

[0004] In order to solve the technical problem that the existing methods cannot accurately analyze the fire emergency situation in different areas where fire occurs, and thus cannot accurately make different levels of alarms for different fire areas, and the effect of forest fire monitoring is low, the purpose of the present invention is to provide an ecological environment monitoring method, device and equipment based on GIS technology, and the technical scheme adopted is as follows:

[0005] The present invention proposes an ecological environment monitoring method based on GIS technology, the method comprising:

[0006] Acquire infrared images of each frame of the ecological area to be tested within a preset time period;

[0007] According to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel, a high temperature characteristic value of each pixel and a plurality of high temperature areas in the infrared image are obtained;

[0008] According to the high temperature characteristic value of the pixel points in each high temperature area in the infrared image and the gradient value of the edge pixel points of the high temperature area, the high temperature coefficient of each high temperature area is obtained; the infrared image of the last frame is used as the target infrared image, and the other infrared images except the target infrared image are used as the historical infrared images, and according to the high temperature coefficient of each high temperature area in the target infrared image and the difference of the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared image, the fire possibility of each high temperature area in the target infrared image is obtained; based on the fire possibility, the fire area and the fire source point are extracted from the high temperature area in the target infrared image;

[0009] Performing straight line fitting on the centroids of all the fire areas in the target infrared image to obtain a fitting straight line; obtaining the degree of hazard of each fire area according to the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitting straight line;

[0010] Based on the degree of hazard, different levels of alarm information are issued to each fire area in the ecological area to be tested.

[0011] Furthermore, obtaining the high temperature characteristic value of each pixel point and the multiple high temperature areas in the infrared image includes:

[0012] Analyze the overall level of grayscale values ​​of all pixels in the infrared image to obtain the overall grayscale value of the infrared image;

[0013] Taking any pixel point in the infrared image as the pixel point to be tested, taking the gray value of the pixel point to be tested as the numerator, taking the overall gray value as the denominator, and taking the ratio as the first high temperature parameter value of the pixel point to be tested;

[0014] Analyze the overall level of the grayscale values ​​of all pixels in the preset window of the pixel to be tested to obtain a second high temperature parameter value of the pixel to be tested;

[0015] The first high temperature parameter value and the second high temperature parameter value are integrated and normalized to obtain a high temperature characteristic value of the pixel to be measured;

[0016] In the infrared image, a connected domain consisting of pixel points whose high temperature characteristic values ​​are greater than a preset first threshold is regarded as a high temperature area.

[0017] Further, obtaining the high temperature coefficient of each high temperature area includes:

[0018] Any high temperature area in the infrared image is used as the high temperature area to be measured, the average value of the high temperature characteristic values ​​of all the pixels in the high temperature area to be measured is used as the numerator, the average value of the high temperature characteristic values ​​of all the pixels in the infrared image is used as the denominator, and the ratio is used as the first temperature difference value of the high temperature area to be measured;

[0019] The average value of the gradient values ​​of all pixels on the edge of the high-temperature area to be measured is used as the numerator, the average value of the gradient values ​​of all pixels in the infrared image is used as the denominator, and the ratio is used as the second temperature difference value of the high-temperature area to be measured;

[0020] The first temperature difference value and the second temperature difference value are integrated to obtain a high temperature coefficient of the high temperature area to be measured.

[0021] Furthermore, obtaining the fire possibility of each high temperature area in the target infrared image includes:

[0022] Taking any high temperature area in the target infrared image as the target high temperature area, selecting a high temperature area with the same position as the target high temperature area from each frame of the historical infrared image as a reference high temperature area of ​​each frame of the historical infrared image;

[0023] The high temperature coefficient of the target high temperature area is used as a numerator, the average value of the high temperature coefficients of the reference high temperature areas of all historical infrared images is used as a denominator, and the ratio is used as the first fire possibility of the target high temperature area;

[0024] Obtaining a second fire possibility of the target high temperature area according to a difference in the high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image;

[0025] The first fire possibility and the second fire possibility are integrated and normalized to obtain the fire possibility of the target high temperature area.

[0026] Furthermore, obtaining the second fire possibility of the target high temperature area according to the difference in the high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of the historical infrared image includes:

[0027] The absolute value of the difference between the high temperature coefficient of the target high temperature region and the reference high temperature region in each frame of historical infrared image is used as the high temperature coefficient difference value between the target high temperature region and each reference high temperature region;

[0028] The accumulated value of the high temperature coefficient difference between the target high temperature area and all reference high temperature areas is used as the second fire possibility of the target high temperature area.

[0029] Furthermore, based on the fire possibility, extracting the fire area and the fire source from the high temperature area in the target infrared image includes:

[0030] In the target infrared image, the high temperature area where the fire possibility is greater than the preset second threshold is taken as the fire area of ​​the target infrared image; the centroid of the fire area corresponding to the maximum value of the fire possibility is taken as the fire source point.

[0031] Furthermore, obtaining the hazard level of each fire area includes:

[0032] Taking any fire area in the target infrared image as the target fire area, negatively correlating the angle between the line connecting the centroid of the target fire area and the fire source point with the fitting straight line to obtain the diffusion hazard parameter of the target fire area;

[0033] The fire probability of the target fire area is used as a numerator, the average value of the fire probability of all fire areas in the target infrared image is used as a denominator, and the ratio is used as a relative hazard parameter of the target fire area;

[0034] The diffusion hazard parameter and the relative hazard parameter are integrated and normalized to obtain the hazard level of the target fire area.

[0035] Furthermore, based on the degree of hazard, issuing different levels of alarm information to each fire area in the ecological area to be tested includes:

[0036] For any fire area, if the hazard level of the fire area is less than the preset first hazard threshold, a low-level emergency alarm message is issued to the fire area;

[0037] If the hazard level of the fire area is not less than the preset first hazard threshold and less than the preset second hazard threshold, an alarm message of a medium-critical level is issued to the fire area;

[0038] If the hazard level of the fire area is not less than a preset second hazard threshold, an alarm message of a high-level emergency level is issued to the fire area.

[0039] The present invention also proposes an ecological environment monitoring device based on GIS technology, the device comprising:

[0040] An image acquisition module is used to obtain infrared images of each frame of the ecological area to be tested within a preset time period;

[0041] The first analysis module is used to obtain a high temperature characteristic value of each pixel and a plurality of high temperature areas in the infrared image according to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel;

[0042] The second analysis module is used to obtain the high temperature coefficient of each high temperature area in the infrared image according to the high temperature characteristic value of the pixel points in each high temperature area in the infrared image and the gradient value of the edge pixel points of the high temperature area; take the last frame of infrared image as the target infrared image, take other infrared images except the target infrared image as the historical infrared image, and obtain the fire possibility of each high temperature area in the target infrared image according to the high temperature coefficient of each high temperature area in the target infrared image and the difference of the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared image; extract the fire area and the fire source point from the high temperature area in the target infrared image based on the fire possibility;

[0043] The third analysis module is used to perform straight line fitting on the centroids of all the fire areas in the target infrared image to obtain a fitting straight line; and obtain the degree of hazard of each fire area according to the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitting straight line;

[0044] The alarm module is used to send different levels of alarm information to each fire area in the ecological area to be tested based on the degree of hazard.

[0045] The present invention also proposes a computer electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any step of an ecological environment monitoring method based on GIS technology.

[0046] The present invention has the following beneficial effects:

[0047] The present invention takes into account that the existing methods cannot accurately analyze the fire emergency situation in different areas where a fire occurs, and thus cannot accurately make different levels of alarms for different fire areas, and the effect of forest fire monitoring is low. Therefore, the infrared image of each frame of the ecological area to be tested within a preset time period is first obtained. Considering that the temperature in the area where the fire occurs is relatively high, it is manifested as a pixel with a larger grayscale value in the infrared image. Therefore, the high temperature characteristic value obtained can be used to reflect the possibility that the pixel point in the infrared image is in the high temperature area, and thereby extract a plurality of high temperature areas from the infrared image. Since the temperature propagates in the air, the temperature of the non-fire area is also relatively high, which leads to the existence of non-fire areas in the high temperature area. Therefore, the present invention performs infrared image The temperature characteristics of each high temperature area in the image are analyzed, and the temperature characteristics of each high temperature area are reflected by the obtained high temperature coefficient. Considering that the temperature of the area where the fire occurs is high, and with the dynamic development of the fire, the temperature of the same area where the fire occurs in the infrared images of different frames will gradually increase. Therefore, the possibility of fire in each high temperature area can be reflected by the obtained fire possibility, and then the fire area and fire source can be accurately extracted. Considering that the diffusion path of the fire is affected by the wind direction, it is usually manifested as diffusion along a straight line. Therefore, the overall diffusion path of the fire can be reflected by fitting a straight line, and then different levels of alarm information can be accurately issued to each fire area according to the degree of hazard, thereby improving the effect of forest fire monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of an ecological environment monitoring method based on GIS technology provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a frame of infrared image provided by an embodiment of the present invention;

[0051] Figure 3 A flow chart of a method for obtaining the fire possibility of each high-temperature area in a target infrared image provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the ecological environment monitoring method, device and equipment based on GIS technology proposed by the present invention, its specific implementation method, structure, characteristics and effects, 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.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] The following is a detailed description of a specific scheme of an ecological environment monitoring method, device and equipment based on GIS technology provided by the present invention in conjunction with the accompanying drawings.

[0055] See also Figure 1 , which shows an ecological environment monitoring method based on GIS technology provided by an embodiment of the present invention, the method comprising:

[0056] Step S1: Acquire infrared images of each frame of the ecological area to be measured within a preset time period.

[0057] Forest fire monitoring is an important part of ecological environment protection. GIS technology is a comprehensive technology used to collect, store, manage, analyze and display geographic spatial data. When a fire occurs in an ecological area to be tested, such as a forest area, the surface temperature of the fire area is high and infrared radiation will be emitted outward. GIS technology can be used to collect infrared radiation information on the surface of the ecological area to be tested, so as to analyze the situation of fire in the ecological area to be tested. Therefore, the embodiment of the present invention first uses a drone equipped with infrared imaging equipment such as an infrared camera to collect infrared video of the ecological area to be tested within a preset time period, and imports the infrared video into professional video software such as Premiere software, and uses the single-frame image extraction function in the software to process the imported infrared video, so as to extract infrared images of each continuous frame in the infrared video. It should be noted that in order to reduce the computational complexity of subsequent image processing and improve the processing speed, the infrared image analyzed in the embodiment of the present invention is a grayscale image, and non-grayscale infrared images need to be grayscaled. Grayscale processing is a technical means well known to those skilled in the art and will not be described in detail here. Please refer to Figure 2 , which shows a schematic diagram of a frame of infrared image provided by an embodiment of the present invention, wherein the area with a larger gray value in the box may be the area where a fire occurs.

[0058] Among them, in order to ensure that the position and shape of the area where a fire may occur in the infrared video do not change significantly, so as to facilitate the smooth progress of subsequent analysis, it is usually necessary to ensure that the preset time period is within a smaller range, generally 5 to 10 seconds. In one embodiment of the present invention, the preset time period is set to 5 seconds. The specific value of the preset time period can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0059] At this point, the infrared image of each frame of the ecological area to be tested within the preset time period is obtained.

[0060] Step S2: According to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel, a high temperature characteristic value of each pixel and a plurality of high temperature areas in the infrared image are obtained.

[0061] The temperature of the area where the fire occurred is relatively high, and the above-mentioned multiple frames of infrared images are obtained. It is necessary to first analyze any frame of infrared image, take any frame of infrared image as the infrared image to be tested, and extract the high temperature area in each frame of infrared image. The higher the temperature, the greater the energy of its thermal radiation, which is manifested in the infrared image as a larger pixel grayscale value, and the local pixel grayscale value is also generally larger. Therefore, the grayscale value of each pixel in the infrared image to be tested and the distribution of the grayscale values ​​of each pixel in the preset window of each pixel can be analyzed. The high temperature characteristic value obtained reflects the high temperature characteristics of the pixel in the infrared image to be tested. The larger the high temperature characteristic value, the more obvious the high temperature performance of the pixel, and the greater the possibility that it is in the high temperature area, and then extract multiple high temperature areas from the infrared image to be tested. Subsequently, the high temperature area in each frame of infrared image can be analyzed, and combined with the high temperature characteristic value of the pixel, the area where the fire occurred can be further extracted, thereby improving the effect of fire alarm, wherein the size of the preset window is set to The specific size of the preset window can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0062] Preferably, in one embodiment of the present invention, the method for acquiring the high temperature characteristic value of each pixel in the infrared image to be measured and the multiple high temperature areas in the infrared image to be measured specifically includes:

[0063] First, the overall level of the grayscale values ​​of all pixels in the infrared image to be tested is analyzed to obtain the overall grayscale value of the infrared image to be tested. The overall grayscale value reflects the overall level of the grayscale values ​​of the pixels in the infrared image to be tested. Subsequently, the grayscale value of each pixel can be compared with the overall grayscale value to calculate the high temperature characteristic value of each pixel.

[0064] In an embodiment of the present invention, the average or median of the grayscale values ​​of all pixels in the infrared image to be tested can be used as the overall grayscale value of the infrared image to be tested to achieve the overall level analysis of the grayscale values ​​of all pixels in the infrared image to be tested, which is not limited here.

[0065] Then, any pixel point in the infrared image to be tested is analyzed, and any pixel point in the infrared image to be tested is used as the pixel point to be tested. Since the pixel point with higher temperature performance is larger than the overall grayscale value, the grayscale value of the pixel point to be tested can be used as the numerator, the overall grayscale value can be used as the denominator, and the ratio can be used as the first high temperature parameter value of the pixel point to be tested. The larger the first high temperature parameter value, the more obvious the high temperature performance of the pixel point to be tested. Subsequently, the high temperature characteristic value of the pixel point to be tested can be calculated based on the first high temperature parameter value.

[0066] Furthermore, the overall level of the grayscale values ​​of all pixels in the preset window of the pixel to be tested is analyzed to obtain the second high temperature parameter value of the pixel to be tested. The larger the second high temperature parameter value, the more obvious the high temperature performance of the local area of ​​the pixel to be tested. Then, the first high temperature parameter value and the second high temperature parameter value can be combined and normalized to obtain the high temperature characteristic value of the pixel to be tested.

[0067] In an embodiment of the present invention, the average value or median of the grayscale values ​​of all pixels in a preset window of the pixel to be tested can be used as the second high temperature parameter value of the pixel to be tested, so as to realize the analysis of the overall level of the grayscale values ​​of all pixels in the preset window of the pixel to be tested, and the combination of the first high temperature parameter value and the second high temperature parameter value can be realized by calculating the sum or product value of the two, which is not limited here.

[0068] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0069] As an example, in one embodiment of the present invention, the expression of the high temperature characteristic value of the pixel to be measured can be specifically, for example, as follows:

[0070]

[0071] in, Indicates the high temperature characteristic value of the pixel to be tested in the infrared image to be tested; Indicates the gray value of the pixel to be tested; Indicates the overall gray value of the infrared image to be tested; Represents the first high temperature parameter value of the pixel to be tested; Indicates the second high temperature parameter value of the pixel to be measured; Represents the normalization function.

[0072] By using the same method as above, the high temperature characteristic value of each pixel in the infrared image to be measured can be obtained.

[0073] Finally, since the larger the high temperature characteristic value is, the greater the possibility that the pixel point of the infrared image to be tested is in a higher temperature area, the connected domain composed of pixel points whose high temperature characteristic value is greater than the preset first threshold can be used as the high temperature area in the infrared image to be tested, so that multiple high temperature areas can be extracted from the infrared image to be tested. Among them, the connected domain is an existing concept and will not be elaborated here. The preset first threshold is set to 0.7. The specific value of the preset first threshold can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0074] Through the same method mentioned above, the high temperature area can be extracted from each frame of infrared image. It should be noted that since the duration of the infrared video collected by the embodiment of the present invention is short, the position and shape characteristics of a high temperature area in the infrared video will basically not change within a short period of time. The same high temperature area exists in each frame of infrared image. In other words, a specific high temperature area will appear in each frame of infrared image. The same high temperature area of ​​each frame of infrared image can be analyzed subsequently, so as to accurately extract the fire area, and analyze the critical conditions of different fire areas, thereby improving the effect of fire alarm.

[0075] Step S3: According to the high temperature characteristic values ​​of the pixels in each high temperature area in the infrared image and the gradient values ​​of the edge pixels of the high temperature area, the high temperature coefficient of each high temperature area is obtained; the last frame of the infrared image is used as the target infrared image, and the other infrared images except the target infrared image are used as the historical infrared images, and according to the high temperature coefficient of each high temperature area in the target infrared image and the difference in the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared images, the fire possibility of each high temperature area in the target infrared image is obtained; based on the fire possibility, the fire area and the fire source point are extracted from the high temperature area in the target infrared image.

[0076] When a fire occurs, the temperature in the air rises sharply, and as the temperature propagates in the air, the temperature of the non-fire area is also higher, which means that some high-temperature areas are non-fire areas, and their temperatures are high only because the temperature propagates in the air. For the real fire area in the high-temperature area, the temperature will rise sharply in a short time, and the temperature change is more obvious. For the non-fire area in the high-temperature area, since its high temperature feature is caused by the temperature propagation in the air, its temperature change in a short time is not obvious. Therefore, it is necessary to first analyze the temperature features of each high-temperature area in the infrared image to be tested. Since the high temperature feature value of the pixel point in the high-temperature area can reflect The temperature characteristics of the pixel point, the larger the high temperature characteristic value of the pixel point in the high temperature area, the higher the temperature expressed by the high temperature area, and the edge between the high temperature area and the background area is more obvious, and the gradient value of the edge pixel point is larger. Therefore, the high temperature characteristic value of the pixel point in each high temperature area in the infrared image to be tested, and the gradient value of the edge pixel point of each high temperature area can be analyzed, and the temperature characteristics of each high temperature area in the infrared image to be tested can be reflected by the obtained high temperature coefficient. The larger the high temperature coefficient, the higher the temperature of the temperature area. Subsequently, the difference in the high temperature coefficient of the same high temperature area in each frame of infrared image can be analyzed, so as to accurately extract the real fire area.

[0077] Preferably, in one embodiment of the present invention, the method for obtaining the high temperature coefficient of each high temperature area in the infrared image to be measured specifically includes:

[0078] First, any high temperature area in the infrared image to be tested is taken as the high temperature area to be tested, the average value of the high temperature characteristic values ​​of all pixels in the high temperature area to be tested is taken as the numerator, the average value of the high temperature characteristic values ​​of all pixels in the infrared image to be tested is taken as the denominator, and the ratio is taken as the first temperature difference value of the high temperature area to be tested. The larger the first temperature difference value is, the higher the temperature characteristics of the high temperature area to be tested are relative to the overall temperature characteristics of the infrared image to be tested.

[0079] Then, the gradient value of each pixel in the infrared image to be measured is calculated using an edge detection operator such as the Sobel operator or the Roberts operator, wherein the gradient is a vector, including a gradient value and a gradient direction. In the embodiment of the present invention, only the gradient value is selected for subsequent calculations, and the average value of the gradient values ​​of all pixels on the edge of the high-temperature area to be measured is used as the numerator, and the average value of the gradient values ​​of all pixels in the infrared image to be measured is used as the denominator, and the ratio is used as the second temperature difference value of the high-temperature area to be measured. The larger the second temperature difference value is, the larger the gradient value of the edge pixel of the high-temperature area to be measured is relative to the overall gradient value of the infrared image to be measured, indicating that the temperature of the high-temperature area to be measured is relatively high, and then the first temperature difference value and the second temperature difference value are combined to obtain the high temperature coefficient of the high-temperature area to be measured.

[0080] In the embodiment of the present invention, the sum or product of the first temperature difference value and the second temperature difference value may be used as the high temperature coefficient of the high temperature area to be measured, which is not limited here.

[0081] As an example, in one embodiment of the present invention, the expression of the high temperature coefficient of the high temperature area to be measured in the infrared image to be measured can be specifically, for example, as follows:

[0082]

[0083] in, Indicates the high temperature coefficient of the high temperature area to be measured in the infrared image to be measured; It represents the average value of the high temperature characteristic values ​​of all pixels in the high temperature area to be measured; Represents the average value of the high temperature characteristic values ​​of all pixels in the infrared image to be tested; Represents the average value of the gradient values ​​of all pixels on the edge of the high temperature area to be measured; Represents the average value of the gradient values ​​of all pixels in the infrared image to be tested; Indicates the first temperature difference value of the high temperature area to be measured; Indicates the second temperature difference value of the high temperature area to be measured.

[0084] The high temperature coefficient of each high temperature area in the infrared image to be measured and the high temperature coefficient of each high temperature area in each frame of infrared image can be obtained by the same method as above.

[0085] From the above analysis, it can be seen that compared with the non-fire area in the high-temperature area, as time goes by, the temperature of the real fire area in the infrared video will become higher and higher, and the temperature change is more obvious. Therefore, the infrared image of the last frame can be used as the target infrared image, and the infrared images other than the target infrared image can be used as the historical infrared image. For a specific high-temperature area where a fire actually occurs in the target infrared image, the temperature is higher, and the temperature difference with the same high-temperature area in the historical infrared image is large. Therefore, the high temperature coefficient of each high-temperature area in the target infrared image and the difference in the high temperature coefficient of the same high-temperature area between the target infrared image and the historical infrared image can be analyzed to obtain the fire possibility of each high-temperature area in the target infrared image. The greater the fire possibility, the more likely a fire is to occur in the high-temperature area, and the greater the severity of the fire, which is convenient for the subsequent extraction of the fire area and the fire source from the target infrared image. In addition, the critical conditions of different fire areas can be analyzed based on the fire possibility of the fire area to improve the effect of fire alarm.

[0086] Preferably, in one embodiment of the present invention, the method for obtaining the fire possibility of each high temperature area in the target infrared image specifically includes:

[0087] See also Figure 3 , which shows a flow chart of a method for obtaining the fire possibility of each high-temperature area in a target infrared image provided by an embodiment of the present invention.

[0088] Step S301: taking any high temperature area in the target infrared image as the target high temperature area, selecting a high temperature area with the same position as the target high temperature area from each frame of historical infrared image as a reference high temperature area of ​​each frame of historical infrared image.

[0089] The reference high temperature region in each historical infrared image and the target high temperature region in the target infrared image represent the same high temperature region in the infrared video.

[0090] Step S302: taking the high temperature coefficient of the target high temperature area as the numerator, taking the average value of the high temperature coefficients of the reference high temperature areas of all historical infrared images as the denominator, and taking the ratio as the first fire possibility of the target high temperature area.

[0091] The larger the high temperature coefficient of the target high temperature area is relative to the high temperature coefficient of the reference high temperature area of ​​each historical infrared image, the higher the temperature of the target high temperature area is, and thus the greater the possibility of a real fire in the target high temperature area is. Therefore, the high temperature coefficient of the target high temperature area can be used as the numerator, and the average value of the high temperature coefficients of the reference high temperature areas of all historical infrared images can be used as the denominator, and the ratio can be used as the first fire possibility of the target high temperature area. The larger the first fire possibility is, the greater the possibility of a real fire in the target high temperature area of ​​the target infrared image is.

[0092] Step S303: obtaining a second fire possibility of the target high temperature area according to the difference in high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image.

[0093] The greater the difference in high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image, the greater the difference in temperature between the target high temperature area and each reference high temperature area, which further indicates that the temperature change in the target high temperature area is more drastic, and the greater the possibility of a real fire in the target high temperature area. Therefore, the difference in high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image can be analyzed to obtain the second fire possibility of the target high temperature area. The greater the second fire possibility, the greater the possibility of a real fire in the target high temperature area of ​​the target infrared image.

[0094] Preferably, in one embodiment of the present invention, the method for obtaining the second fire possibility of the target high temperature area specifically includes:

[0095] The absolute value of the difference in high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image is taken as the high temperature coefficient difference value between the target high temperature area and each reference high temperature area. The larger the high temperature coefficient difference value, the greater the temperature difference between the target high temperature area and the reference high temperature area. Then the accumulated value of the high temperature coefficient difference values ​​between the target high temperature area and all reference high temperature areas is taken as the second fire possibility of the target high temperature area.

[0096] Step S304: The first fire possibility and the second fire possibility are integrated and normalized to obtain the fire possibility of the target high temperature area.

[0097] After the above analysis, the first fire possibility and the second fire possibility can be integrated and normalized to obtain the fire possibility of the target high temperature area.

[0098] In the embodiment of the present invention, the integration of the first fire possibility and the second fire possibility can be achieved by calculating the sum or product of the two, which is not limited here.

[0099] As an example, in one embodiment of the present invention, the expression of the fire possibility of the target high temperature area in the target infrared image can be specifically, for example, as follows:

[0100]

[0101] in, Indicates the fire possibility of the target high temperature area in the target infrared image; Indicates the high temperature coefficient of the target high temperature area; It represents the average value of the high temperature coefficient of the reference high temperature area of ​​all historical infrared images; Indicates High temperature coefficient of reference high temperature area of ​​frame history infrared image; Indicates the target high temperature area and the High temperature coefficient difference value between reference high temperature areas of frame history infrared images; Indicates the number of historical infrared images; Indicates the first fire probability of the target high temperature area; Indicates the potential for a second fire in the target high temperature area; Represents the normalization function.

[0102] The fire possibility of each high-temperature area in the target infrared image can be obtained by the same method as mentioned above. The greater the fire possibility, the more likely a fire is to occur in the high-temperature area and the more serious the fire situation is. Therefore, based on the fire possibility, the fire area and the fire source point can be extracted from the high-temperature area in the target infrared image. Among them, the fire source point can be considered as the starting point of the fire. Subsequently, based on the position and direction of each fire area in the target infrared image relative to the fire source point, the critical situation of each fire area can be accurately analyzed.

[0103] Preferably, in one embodiment of the present invention, the method for obtaining the fire area and the fire source point specifically includes:

[0104] In the target infrared image, the high temperature area where the fire possibility is greater than the preset second threshold is taken as the fire area of ​​the target infrared image. The greater the fire possibility of each fire area, the more serious the fire situation in the fire area is. Therefore, the centroid of the fire area corresponding to the maximum fire possibility can be taken as the fire source point. The method of obtaining the centroid of the area in the image is a technical field well known to technicians in this field and will not be elaborated here.

[0105] In one embodiment of the present invention, the preset second threshold is set to 0.7. The specific value of the preset second threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0106] Step S4: Perform straight line fitting on the centroids of all fire areas in the target infrared image to obtain a fitted straight line; obtain the degree of hazard of each fire area based on the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitted straight line.

[0107] Considering that the diffusion path of forest fire is affected by wind direction and usually diffuses along a straight line, we can first perform straight line fitting on the centroids of all fire areas in the target infrared image. The obtained fitting straight line reflects the overall diffusion path of the fire. The straight line fitting method can use the existing least squares method or other fitting methods, which are not limited or elaborated here. The more consistent the diffusion path of a fire area is with the overall diffusion path, that is, the smaller the angle between the line connecting the centroid of the fire area and the fire source point and the fitting straight line is, the fire area is very likely to cause a fire in the next area, indicating that the fire area is more harmful. Therefore, the angle between the line connecting the centroid of each fire area and the fire source point in the target infrared image and the fitting straight line can be analyzed, and the degree of harm of each fire area can be obtained in combination with the fire possibility of each fire area. Subsequently, different levels of alarm information can be issued to different fire areas based on the degree of harm, thereby improving the effect of fire alarm.

[0108] Preferably, in one embodiment of the present invention, the method for obtaining the hazard level of each fire area in the target infrared image specifically includes:

[0109] Take any fire area in the target infrared image as the target fire area, and negatively correlate the angle between the line connecting the centroid of the target fire area and the fire source point and the fitting straight line to obtain the diffusion hazard parameter of the target fire area. The larger the diffusion hazard parameter, the stronger the diffusion of the target fire area. The line connecting the centroid of the target fire area and the fire source point is a straight line determined by these two points, and the value range of the angle is .

[0110] It should be noted that when the target fire area is the fire area corresponding to the maximum value of the fire possibility in the target infrared image, the fire source point and the centroid of the target fire area are the same point, that is, the two points coincide with each other, and there are countless straight lines determined by the two coincident points. However, at this time, it can be considered that the diffusion hazard parameter of the target fire area has reached the maximum, that is, the straight line passing through the two coincident points and parallel to the fitted straight line can be considered to be the straight line determined by the two coincident points. At this time, the angle between the straight line and the fitted straight line is equal to 0.

[0111] The greater the fire possibility in the target fire area, the more serious the fire in the target fire area. Therefore, the fire possibility of the target fire area can be used as the numerator, and the average value of the fire possibility of all fire areas in the target infrared image can be used as the denominator. The ratio is used as the relative hazard parameter of the target fire area. The larger the relative hazard parameter, the more serious the fire situation in the target fire area is relative to other fire areas.

[0112] Then, the diffusion hazard parameters and relative hazard parameters are integrated and normalized to obtain the hazard degree of the target fire area.

[0113] In the embodiment of the present invention, the diffusion hazard parameter and the relative hazard parameter may be integrated by calculating the sum or product of the two, which is not limited here.

[0114] As an example, in one embodiment of the present invention, the expression of the hazard level of the target fire area in the target infrared image may be specifically, for example, as follows:

[0115]

[0116] in, Indicates the degree of hazard of the target fire area in the target infrared image; It represents the angle between the straight line determined by the centroid of the target fire area and the fire source point and the fitted straight line; Indicates the fire probability of the target fire area; It represents the average value of the fire probability of all fire areas in the target infrared image; A parameter representing the spread hazard of the target fire area; Relative hazard parameter representing the target fire area; represents the normalization function; Indicates the preset adjustment parameter, which is used to prevent the denominator from being 0. The value range is In one embodiment of the present invention, Set to 0.01, The specific value of can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0117] It should be noted that in other embodiments of the present invention, the positive and negative correlations may be represented by other basic mathematical operations, which will not be elaborated herein.

[0118] The hazard level of each fire area in the target infrared image can be obtained by the same method as above.

[0119] Step S5: Based on the degree of hazard, different levels of alarm information are issued to each fire area in the ecological area to be tested.

[0120] Since the degree of hazard in different fire areas varies, it is necessary to issue different levels of alarm information to different fire areas to improve the effectiveness of fire alarm and ecological environment monitoring, so that in subsequent rescue work, rescue resources can be reasonably allocated to each fire area based on different levels of alarm information to improve firefighting efficiency.

[0121] Preferably, in one embodiment of the present invention, for any fire area, if the hazard level of the fire area is less than a preset first hazard threshold, an alarm message of a low-level critical level is issued to the fire area; if the hazard level of the fire area is not less than the preset first hazard threshold and is less than the preset second hazard threshold, an alarm message of a medium-level critical level is issued to the fire area; if the hazard level of the fire area is not less than the preset second hazard threshold, an alarm message of a high-level critical level is issued to the fire area, wherein different levels of alarm information are reflected by marking the fire areas with different colors, for example, a fire area with a low-level critical level alarm message may be marked as blue, a fire area with a medium-level critical level alarm message may be marked as yellow, and a fire area with a high-level critical level alarm message may be marked as orange.

[0122] Among them, the preset first hazard threshold is smaller than the preset second hazard threshold. In one embodiment of the present invention, the preset first hazard threshold is set to 0.3, and the preset second hazard threshold is set to 0.7. The specific values ​​of the preset first hazard threshold and the preset second hazard threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0123] An embodiment of the present invention provides an ecological environment monitoring device based on GIS technology, the device comprising:

[0124] The image acquisition module is used to obtain infrared images of each frame of the ecological area to be tested within a preset time period.

[0125] The first analysis module is used to obtain the high temperature characteristic value of each pixel and multiple high temperature areas in the infrared image according to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel.

[0126] The second analysis module is used to obtain the high temperature coefficient of each high temperature area in the infrared image according to the high temperature characteristic value of the pixel points in each high temperature area in the infrared image and the gradient value of the edge pixel points of the high temperature area; take the last frame of infrared image as the target infrared image, take other infrared images except the target infrared image as the historical infrared image, and obtain the fire possibility of each high temperature area in the target infrared image according to the high temperature coefficient of each high temperature area in the target infrared image and the difference in the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared image; based on the fire possibility, extract the fire area and the fire source point from the high temperature area in the target infrared image.

[0127] The third analysis module is used to perform straight line fitting on the centroids of all fire areas in the target infrared image to obtain a fitted straight line; the degree of hazard of each fire area is obtained based on the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitted straight line.

[0128] The alarm module is used to issue different levels of alarm information to each fire area in the ecological area to be tested based on the degree of hazard.

[0129] An embodiment of the present invention provides a computer electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the method described in steps S1 to S5 when executing the computer program.

[0130] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. 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.

[0131] 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.

Claims

1. A GIS-based ecological environment monitoring method, applied to a fire alarm system, characterized in that: The method comprises: Acquire infrared images of each frame of the ecological area to be tested within a preset time period; According to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel, a high temperature characteristic value of each pixel and a plurality of high temperature areas in the infrared image are obtained; According to the high temperature characteristic value of the pixel points in each high temperature area in the infrared image and the gradient value of the edge pixel points of the high temperature area, the high temperature coefficient of each high temperature area is obtained; the infrared image of the last frame is used as the target infrared image, and the other infrared images except the target infrared image are used as the historical infrared images, and according to the high temperature coefficient of each high temperature area in the target infrared image and the difference of the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared image, the fire possibility of each high temperature area in the target infrared image is obtained; based on the fire possibility, the fire area and the fire source point are extracted from the high temperature area in the target infrared image; Performing straight line fitting on the centroids of all the fire areas in the target infrared image to obtain a fitting straight line; obtaining the degree of hazard of each fire area according to the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitting straight line; Based on the degree of hazard, different levels of alarm information are issued to each fire area in the ecological area to be tested.

2. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: The obtaining of the high temperature characteristic value of each pixel point and the multiple high temperature areas in the infrared image comprises: Analyze the overall level of grayscale values ​​of all pixels in the infrared image to obtain the overall grayscale value of the infrared image; Taking any pixel point in the infrared image as the pixel point to be tested, taking the gray value of the pixel point to be tested as the numerator, taking the overall gray value as the denominator, and taking the ratio as the first high temperature parameter value of the pixel point to be tested; Analyze the overall level of the grayscale values ​​of all pixels in the preset window of the pixel to be tested to obtain a second high temperature parameter value of the pixel to be tested; The first high temperature parameter value and the second high temperature parameter value are integrated and normalized to obtain a high temperature characteristic value of the pixel to be measured; In the infrared image, a connected domain consisting of pixel points whose high temperature characteristic values ​​are greater than a preset first threshold is regarded as a high temperature area.

3. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: The obtaining of the high temperature coefficient of each high temperature area comprises: Any high temperature area in the infrared image is used as the high temperature area to be measured, the average value of the high temperature characteristic values ​​of all the pixels in the high temperature area to be measured is used as the numerator, the average value of the high temperature characteristic values ​​of all the pixels in the infrared image is used as the denominator, and the ratio is used as the first temperature difference value of the high temperature area to be measured; The average value of the gradient values ​​of all pixels on the edge of the high-temperature area to be measured is used as the numerator, the average value of the gradient values ​​of all pixels in the infrared image is used as the denominator, and the ratio is used as the second temperature difference value of the high-temperature area to be measured; The first temperature difference value and the second temperature difference value are integrated to obtain a high temperature coefficient of the high temperature area to be measured.

4. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: The fire probability of each high temperature area in the target infrared image is obtained by: Taking any high temperature area in the target infrared image as the target high temperature area, selecting a high temperature area with the same position as the target high temperature area from each frame of the historical infrared image as a reference high temperature area of ​​each frame of the historical infrared image; The high temperature coefficient of the target high temperature area is used as a numerator, the average value of the high temperature coefficients of the reference high temperature areas of all historical infrared images is used as a denominator, and the ratio is used as the first fire possibility of the target high temperature area; Obtaining a second fire possibility of the target high temperature area according to a difference in the high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of historical infrared image; The first fire possibility and the second fire possibility are integrated and normalized to obtain the fire possibility of the target high temperature area.

5. The ecological environment monitoring method based on GIS technology according to claim 4 is characterized in that: The obtaining of the second fire possibility of the target high temperature area according to the difference of the high temperature coefficient between the target high temperature area and the reference high temperature area in each frame of the historical infrared image comprises: The absolute value of the difference between the high temperature coefficient of the target high temperature region and the reference high temperature region in each frame of historical infrared image is used as the high temperature coefficient difference value between the target high temperature region and each reference high temperature region; The accumulated value of the high temperature coefficient difference between the target high temperature area and all the reference high temperature areas is used as the second fire possibility of the target high temperature area.

6. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: The extracting of the fire area and the fire source from the high temperature area in the target infrared image based on the fire possibility includes: In the target infrared image, the high temperature area where the fire possibility is greater than the preset second threshold is taken as the fire area of ​​the target infrared image; the centroid of the fire area corresponding to the maximum value of the fire possibility is taken as the fire source point.

7. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: The hazard level of each fire area is obtained by: Taking any fire area in the target infrared image as the target fire area, negatively correlating the angle between the line connecting the centroid of the target fire area and the fire source point with the fitting straight line to obtain the diffusion hazard parameter of the target fire area; The fire probability of the target fire area is used as a numerator, the average value of the fire probability of all fire areas in the target infrared image is used as a denominator, and the ratio is used as a relative hazard parameter of the target fire area; The diffusion hazard parameter and the relative hazard parameter are integrated and normalized to obtain the hazard level of the target fire area.

8. The ecological environment monitoring method based on GIS technology according to claim 1 is characterized in that: Based on the degree of hazard, different levels of alarm information are issued to each fire area in the ecological area to be tested, including: For any fire area, if the hazard level of the fire area is less than the preset first hazard threshold, a low-level emergency alarm message is issued to the fire area; If the hazard level of the fire area is not less than the preset first hazard threshold and less than the preset second hazard threshold, an alarm message of a medium-critical level is issued to the fire area; If the hazard level of the fire area is not less than a preset second hazard threshold, an alarm message of a high-level emergency level is issued to the fire area.

9. An ecological environment monitoring device based on GIS technology, characterized in that: The device comprises: An image acquisition module is used to obtain infrared images of each frame of the ecological area to be tested within a preset time period; The first analysis module is used to obtain a high temperature characteristic value of each pixel and a plurality of high temperature areas in the infrared image according to the gray value of each pixel in the infrared image and the distribution of the gray values ​​of each pixel in a preset window of each pixel; The second analysis module is used to obtain the high temperature coefficient of each high temperature area in the infrared image according to the high temperature characteristic value of the pixel points in each high temperature area in the infrared image and the gradient value of the edge pixel points of the high temperature area; take the last frame of infrared image as the target infrared image, take other infrared images except the target infrared image as the historical infrared image, and obtain the fire possibility of each high temperature area in the target infrared image according to the high temperature coefficient of each high temperature area in the target infrared image and the difference of the high temperature coefficient of the same high temperature area between the target infrared image and the historical infrared image; extract the fire area and the fire source point from the high temperature area in the target infrared image based on the fire possibility; The third analysis module is used to perform straight line fitting on the centroids of all the fire areas in the target infrared image to obtain a fitting straight line; and obtain the degree of hazard of each fire area according to the fire possibility of each fire area in the target infrared image and the angle between the line connecting the centroid of each fire area and the fire source point and the fitting straight line; The alarm module is used to send different levels of alarm information to each fire area in the ecological area to be tested based on the degree of hazard.

10. A computer electronic device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images