Forest fire smoke automatic recognition system and method based on adaptive target detection

Abstract

The application discloses a forest fire smoke automatic identification system and method based on adaptive target detection, and belongs to the technical field of forestry engineering. The method comprises the following steps: setting a plurality of fire smoke information monitoring units in a forest area to be monitored, collecting forest state information, and the forest state information comprising a visible light image and a thermal infrared image; adaptively adjusting an initial feature threshold value based on the average brightness in the collected visible light image to obtain an adaptive feature threshold value, and simultaneously calculating image feature data; formulating a smoke identification standard, identifying pixel points meeting the smoke identification standard, regarding an image area formed by the identified pixel points as a smoke key area, extracting the smoke key area, and obtaining a regional temperature value through the thermal infrared image; generating a fire smoke evaluation value based on the texture feature, shape feature and corresponding temperature value of the smoke key area, and determining whether the smoke key area is a forest fire smoke based on the fire smoke evaluation value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of forestry engineering, in particular to a forest fire smoke automatic recognition system and method based on adaptive target detection. BACKGROUND

[0002] In the face of frequent forest fire events, timely and accurate detection and assessment of smoke become an important task in forest fire prevention. Traditional fire monitoring methods mainly rely on manual inspection and fixed monitoring points. This method not only consumes time and effort, but also is difficult to achieve real-time comprehensive coverage due to the vastness and complexity of the forest, which can easily lead to the failure of early detection of fires. Especially in the case of changing weather conditions and complex terrain, the limitations of manual inspection are increasingly apparent, and it cannot meet the needs of modern forest fire prevention. Therefore, the development of an efficient automatic monitoring system has become an urgent need.

[0003] Existing forest fire monitoring technologies mainly rely on single sensor data, such as visible light cameras or infrared sensors, which leads to instability in detection results under complex weather conditions (such as strong light, haze, and rain and fog). Visible light images are easily disturbed in strong sunlight or insufficient ambient light, resulting in false positives or false negatives. On the other hand, although thermal infrared sensors can effectively capture temperature changes, their ability to detect smoke formed under low temperature conditions is limited. Therefore, existing technologies lack the ability to integrate and analyze data, making it difficult to achieve efficient smoke detection and fire warning.

[0004] In the prior art, the publication number CN112686190A discloses a forest fire smoke automatic recognition method based on adaptive target detection, which specifically includes obtaining calibrated image data in a pre-established forest fire smoke image database as target training images; inputting the target training images into a pre-defined fire smoke detection and recognition model, and extracting image features through the region candidate network in the model; selecting indicators in a pre-established indicator model library to evaluate the recognition accuracy of image feature extraction. This method takes an improved adaptive target detection network as the main body, effectively improving the extraction ability of forest fire smoke features, thereby realizing real-time and high-precision detection and recognition of forest fire smoke. However, this method relies on a pre-established forest fire smoke image database, and if the image samples in the database are insufficient to cover different environmental conditions, light changes, smoke types, and background situations, the model may not perform well in certain situations. Lower diversity and representativeness can affect the generalization ability of the model, leading to false positives or false negatives in actual monitoring. At the same time, the model cannot continuously learn and optimize based on newly collected data, which may cause its performance to decline over time.

[0005] The above information disclosed in the Background section is only for enhancing the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art that is already known to those of ordinary skill in the art. SUMMARY

[0006] The present application aims to provide a forest fire smoke automatic identification system and method based on adaptive target detection to solve the problems raised in the background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0008] A forest fire smoke automatic identification system based on adaptive target detection, specifically comprising:

[0009] An information acquisition module for monitoring the entire forest area to be monitored, which is composed of a plurality of fire smoke information monitoring units for acquiring forest state information, the fire smoke information monitoring unit comprising a visual sensor and a thermal infrared sensor, and the forest state information comprising a visible light image and a thermal infrared image;

[0010] An adaptive detection adjustment module for adaptively adjusting an initial feature threshold based on the average brightness in the visible light image to obtain an adaptive feature threshold, and simultaneously calculating image feature data of each pixel point based on the visible light image, the image feature data comprising the hue, saturation and lightness of the pixel point, and the initial feature threshold comprising a hue range threshold, a saturation threshold and a lightness threshold;

[0011] A key area identification and extraction module for formulating a smoke identification standard based on the adaptive feature threshold, identifying the pixel points in the visible light image whose image feature data meet the smoke identification standard, regarding the image area composed of the identified pixel points as a smoke key area, extracting the smoke key area through a contour detection algorithm, and obtaining the temperature value of the smoke key area through the thermal infrared image;

[0012] A smoke identification and determination module for generating a fire smoke evaluation value based on the texture feature, shape feature and corresponding temperature value of the smoke key area, and determining whether the smoke key area is a forest fire smoke based on the fire smoke evaluation value, the texture feature comprising contrast and energy, and the shape feature comprising contour simplicity and circularity.

[0013] Further, the visual sensor and the thermal infrared sensor are a high-definition camera and a thermal infrared camera, the real-time video of the forest area to be monitored is acquired through the high-definition camera and the thermal infrared camera, and the forest state information including the visible light image and the thermal infrared image is obtained through the real-time video, wherein the method for obtaining the visible light image and the thermal infrared image is to acquire the visible light and thermal infrared frame images at the same time from the real-time video, and the acquisition interval is 30 frames.

[0014] Further, the initial feature threshold is adaptively adjusted according to the average brightness to obtain an adaptive feature threshold, including the following steps: calculating the average brightness L of the current visible light image according to the brightness of each pixel point in the collected visible light image; converting the visible light image from the RGB color space to the HSV color space, and calculating image feature data, the image feature data including the hue H, the saturation S and the lightness V of the pixel point.

[0015] The formula for adaptively adjusting the initial feature threshold according to the average brightness to obtain the adaptive feature threshold is:

[0016] H final =[H base (0)+α H *L,H base (1)-β H *L]

[0017] S final =S base -γ S *L

[0018] V final =V base +δ V *L

[0019] In the formula, H final represents the adaptive hue range threshold, S final represents the adaptive saturation threshold, and V final represents the adaptive lightness threshold. The adaptive feature threshold includes H final , S final and V final , H base (0) and H base (1) represent the lower limit and the upper limit of the hue range in the initial feature threshold, S base is the saturation threshold in the initial feature threshold, and V base is the lightness threshold in the initial feature threshold, wherein α H , β H , γ S and δ V respectively represent the adjustment coefficients of the lower limit and the upper limit of the hue range, the saturation threshold, and the lightness threshold. L is the average brightness of the current visible light image.

[0020] Further, the formula for calculating the average brightness L in the collected visible light image is:

[0021]

[0022] In the formula, M represents the total number of pixel points in the visible light image, and I represents the brightness of each pixel point in the visible light image.p I p represents the brightness value of the pth pixel point, and the first pixel point in the upper left corner of the visible light image is denoted as the first pixel point, which is sequentially arranged in row priority order, and a total of M pixel points are obtained, wherein p is the index of the pixel point, p = 1, 2, …, M;

[0023] The brightness value I p of the pth pixel point p is calculated by the following formula:

[0024] I p = 0.299R p + 0.587G p + 0.114B p

[0025] In the formula, R p represents the intensity value of the red channel of the pth pixel point, G p represents the intensity value of the green channel of the pth pixel point, and B p represents the intensity value of the blue channel of the pth pixel point.

[0026] Further, the visible light image is converted from the RGB color space to the HSV color space, and the image feature data is calculated including the following steps:

[0027] The image feature data is calculated according to the intensity values of the red, green and blue channels of each pixel point, and the specific calculation formula is as follows:

[0028]

[0029] In the formula, atan2 is an inverse tangent function for calculating the inverse tangent value of two variables, H p , S p and V p are the hue, saturation and lightness of the pth pixel point in the visible light image, respectively.

[0030] Further, a smoke recognition standard is formulated according to the adaptive feature threshold, and the logic on which the smoke recognition standard is based is:

[0031] When the pixel point satisfies the following conditions:

[0032] H p ∈ H final

[0033] S p < S final

[0034] V p > V final

[0035] Mark the pixel point, and mark the image region composed of all the pixel points meeting the smoke identification standard as a smoke key region, and based on a Canny edge detection algorithm, the smoke key region is extracted to obtain a temperature value of the corresponding smoke key region in the thermal infrared image, wherein the average temperature is calculated through the temperature value of each pixel point in the corresponding smoke key region of the thermal infrared image, and the average temperature is taken as the temperature value of the smoke key region.

[0036] Further, the formula based on the texture feature, shape feature and corresponding temperature value of the smoke key region for generating the fire smoke evaluation value is:

[0037]

[0038] In the formula, HY represents the fire smoke evaluation value, T is the temperature value of the smoke key region, Ct and En represent the contrast and energy in the texture feature respectively, Cm and Cl represent the contour simplicity and circularity in the shape feature respectively, and ω1, ω2, ω3, ω4 and ω5 are weight coefficients of T, En, Ct, Cm and Cl respectively.

[0039] The logic for determining whether the smoke key region is forest fire smoke based on the fire smoke evaluation value is that the fire smoke threshold is set as yz.

[0040] When HY<yz, it is determined that the current smoke key region is not forest fire smoke.

[0041] When HY≥yz, it is determined that the current smoke key region is forest fire smoke, and an alarm is issued.

[0042] Further, the shape feature of the texture feature of the smoke key region includes: calculating the texture feature including the contrast and energy of the smoke key region through a gray level co-occurrence matrix, and calculating the shape feature including the contour simplicity and circularity based on the contour length and area of the smoke key region.

[0043] The present application also provides a forest fire smoke automatic identification method based on adaptive target detection, which is used for controlling the forest fire smoke automatic identification system based on adaptive target detection.

[0044] A plurality of fire smoke information monitoring units are arranged in the forest area to be monitored to ensure that the entire forest area to be monitored can be monitored, and forest state information is collected, the fire smoke information monitoring unit includes a visual sensor and a thermal infrared sensor, and the forest state information includes a visible light image and a thermal infrared image.

[0045] Adaptively adjust the initial feature threshold based on the average brightness in the visible light image to obtain an adaptive feature threshold, and calculate the image feature data of each pixel point based on the visible light image, the image feature data including the hue, saturation and lightness of the pixel point, and the initial feature threshold including the hue range threshold, saturation threshold and lightness threshold;

[0046] Formulate the smoke recognition standard based on the adaptive feature threshold, mark the pixel points in the visible light image that meet the smoke recognition standard, and record the image region formed by the marked pixel points as a smoke key region, extract the smoke key region through a contour detection algorithm, and obtain the temperature value of the smoke key region through the thermal infrared image;

[0047] Generate a fire smoke evaluation value based on the texture feature, shape feature and corresponding temperature value of the smoke key region, and determine whether the smoke key region is forest fire smoke based on the fire smoke evaluation value, wherein the texture feature includes contrast and energy, and the shape feature includes contour simplicity and roundness.

[0048] Compared with the prior art, the present application has the following advantages:

[0049] The combination of visual sensors and thermal infrared sensors ensures coverage of the forest area to be monitored under various weather conditions, greatly improving the comprehensiveness and real-time performance of the monitoring. By adaptively adjusting the smoke key region recognition threshold based on the actual brightness condition, the applicability of the system is improved under complex weather conditions (such as strong light, haze and rain, etc.), and the smoke key region is determined, reducing the computational burden and improving the accuracy of identification. Combining the temperature information of the thermal infrared image with the texture and shape features of the smoke key region, the multi-modal data is deeply fused, overcoming the limitations of a single sensor in a specific environmental condition, thereby improving the stability and reliability of smoke detection. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 It is a schematic diagram of the overall system structure of the present application;

[0051] Figure 2 It is a schematic diagram of the overall method flow of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0053] It should be noted that the technical terms or scientific terms used in the present application should be understood as the general meaning understood by those skilled in the art unless otherwise defined. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationship, which may change accordingly when the absolute position of the described object changes.

[0054] Embodiments:

[0055] Please refer to Figure 1 The present application provides a system structure:

[0056] An automatic forest fire smoke recognition system based on adaptive target detection, specifically comprising:

[0057] An information acquisition module for monitoring the entire forest area to be monitored, which is composed of a plurality of fire smoke information monitoring units for acquiring forest state information, the fire smoke information monitoring unit comprising a visual sensor and a thermal infrared sensor, and the forest state information comprising visible light images and thermal infrared images;

[0058] The visual sensor and the thermal infrared sensor are high-definition cameras and thermal infrared cameras, which acquire real-time video of the forest area to be monitored through the high-definition cameras and the thermal infrared cameras, and acquire forest state information including visible light images and thermal infrared images through the real-time video. The method for acquiring visible light images and thermal infrared images is to collect visible light and thermal infrared frame images at the same time from the real-time video, and the collection interval is 30 frames.

[0059] An adaptive detection adjustment module for adaptively adjusting an initial feature threshold based on the average brightness in the visible light image to obtain an adaptive feature threshold, and simultaneously calculating image feature data of each pixel point in the visible light image, the image feature data including hue, saturation and lightness of the pixel point, and the initial feature threshold including hue range threshold, saturation threshold and lightness threshold;

[0060] Adaptively adjusting the initial feature threshold according to the average brightness to obtain an adaptive feature threshold comprises the following steps: calculating the average brightness L of the current visible light image according to the brightness of each pixel point in the collected visible light image; converting the visible light image from the RGB color space to the HSV color space, and calculating image feature data, wherein the image feature data comprises the hue H, the saturation S and the lightness V of the pixel point;

[0061] The formula for adaptively adjusting the initial feature threshold according to the average brightness to obtain the adaptive feature threshold is as follows:

[0062] H final =[H base (0)+α H *L,H base (1)-β H *L]

[0063] S final =S base -γ S *L

[0064] V final =V base +δ V *L

[0065] In the formula, H final represents the adaptive hue range threshold, S final represents the adaptive saturation threshold, and V final represents the adaptive lightness threshold, the adaptive feature threshold comprises H final , S final and V final , H base (0) and H base (1) represent the lower limit and the upper limit of the hue range in the initial feature threshold, S base is the saturation threshold in the initial feature threshold, V base is the lightness threshold in the initial feature threshold, wherein α H , β H , γ S and δ V respectively represent the adjustment coefficients of the lower limit and the upper limit of the hue range, the saturation threshold and the lightness threshold, and L is the average brightness of the current visible light image, wherein the initial feature threshold can be set according to the actual environmental conditions of the monitored forest area and expert experience;

[0066] In the formula, α H , β H , γ S and δ V can be set by expert experience, and the general range is generally between 0.01 and 0.3, which can be adjusted according to the actual situation.

[0067] The formula for calculating the average brightness L in the collected visible light image is:

[0068]

[0069] In the formula, M represents the total number of pixel points in the visible light image, I p represents the brightness value of the pth pixel point, and the first pixel point at the top left corner of the visible light image is numbered as the first pixel point, and the pixel points are numbered in row-major order, a total of M pixel points, where p is the index of the pixel point, p=1, 2, …, M.

[0070] The brightness value I p of the pth pixel point is calculated by the following formula:

[0071] I p =0.299R p +0.587G p +0.114B p

[0072] In the formula, R p represents the intensity value of the red channel of the pth pixel point, G p represents the intensity value of the green channel of the pth pixel point, and B p represents the intensity value of the blue channel of the pth pixel point.

[0073] The visible light image is converted from the RGB color space to the HSV color space, and the image feature data is calculated including the following steps:

[0074] The image feature data is calculated according to the intensity values of the red, green and blue channels of each pixel point, and the specific calculation formula is as follows:

[0075]

[0076] In the formula, atan2 is the inverse tangent function for calculating the inverse tangent value of two variables, H p , S p and V p are the hue, saturation and lightness of the pth pixel point in the visible light image, respectively.

[0077] The key area identification and extraction module is used to formulate smoke identification criteria based on adaptive feature threshold values, and the pixel points in the visible light image that meet the smoke identification criteria are identified, and the image area composed of the identified pixel points is recorded as a smoke key area. The smoke key area is extracted by a contour detection algorithm, and the temperature value of the smoke key area is obtained through a thermal infrared image;

[0078] The smoke recognition standard is formulated according to the adaptive feature threshold, and the logic on which the smoke recognition standard is based is:

[0079] When the pixel point meets the following conditions:

[0080] H p ∈H final

[0081] S p <S final

[0082] V p >V final

[0083] The pixel point is marked, and an image region composed of all pixel points meeting the smoke recognition standard is recorded as a smoke key region; the saturation of smoke is usually low. Due to the scattering of light by smoke, the color in the image appears not bright enough, and the saturation is reduced. The color of the smoke region often looks pale and blurred, and lacks vitality; smoke usually has a high lightness, especially under sunlight, and the scattering of light by smoke increases the brightness of the region. Therefore, the lightness value of the smoke region is usually higher than that of the surrounding environment.

[0084] Based on the Canny edge detection algorithm, the smoke key region is extracted, and the temperature value of the corresponding smoke key region in the thermal infrared image is obtained, wherein the average temperature is calculated through the temperature value of each pixel point in the thermal infrared image corresponding to the smoke key region, and the average temperature is taken as the temperature value of the smoke key region, and the formula for calculating the average temperature is:

[0085]

[0086] In the formula, T represents the average temperature, Q is the total number of pixels in the smoke key region in the infrared image, T d is the temperature value of the dth pixel, and d is the index of the pixel point in the smoke key region in the infrared image, d=1, 2, …, Q.

[0087] The smoke recognition determination module is configured to generate a fire smoke evaluation value based on the texture feature, shape feature and corresponding temperature value of the smoke key region, and determine whether the smoke key region is forest fire smoke based on the fire smoke evaluation value, wherein the texture feature includes contrast and energy, and the shape feature includes contour simplicity and roundness.

[0088] The formula for generating the fire smoke evaluation value based on the texture feature, shape feature and corresponding temperature value of the smoke key region is:

[0089]

[0090] In the formula, HY represents a fire smoke evaluation value, T is a temperature value of a smoke focus area, Ct and En represent contrast and energy in texture features respectively, Cm and Cl represent contour simplicity and circularity in shape features respectively, and ω1, ω2, ω3, ω4 and ω5 are weight coefficients of T, En, Ct, Cm and Cl respectively; wherein the temperature value T is proportional to HY, the higher the temperature, the greater the probability that the smoke focus area is forest fire smoke, Ct and En are inversely proportional to HY, a lower contrast value and energy value are usually associated with a smoke area, Cm and Cl are also inversely proportional to HY, usually the smaller the value of Cm and Cl, the more irregular the shape, indicating that the probability that the smoke focus area is forest fire smoke is greater, and since the temperature value T has the greatest impact on HY, Ct and En are smaller than the temperature value T, therefore ω1>ω2≥ω3>ω4≥ω5 and ω1, ω2, ω3, ω4 and ω5 are greater than 0.

[0091] The logic for determining whether the smoke focus area is forest fire smoke based on the fire smoke evaluation value is as follows: set a fire smoke threshold value yz;

[0092] When HY<yz, it is determined that the current smoke focus area is not forest fire smoke;

[0093] When HY≥yz, it is determined that the current smoke focus area is forest fire smoke, and an alarm is issued.

[0094] The shape feature of the texture feature of the smoke focus area includes: calculating the texture features of the smoke focus area including contrast and energy through a gray level co-occurrence matrix, and calculating the shape features including contour simplicity and circularity based on the contour length and area of the smoke focus area;

[0095] Wherein, the texture features of the smoke focus area including contrast and energy calculated through the gray level co-occurrence matrix are mature existing technologies, and the specific calculation method is not described here; the shape features including contour simplicity and circularity calculated based on the contour length and area of the smoke focus area are based on the following formulas respectively:

[0096]

[0097] In the formula, A is the area of the smoke focus area, and L represents the contour length of the smoke focus area; a smaller value of Cm may indicate a more irregular shape, a value of Cl close to 1 indicates a more regular shape, and the smaller the value, the more irregular the shape.

[0098] Please refer to Figure 2The application further provides a forest fire smoke automatic identification method based on adaptive target detection, which is used for controlling the forest fire smoke automatic identification system based on adaptive target detection.

[0099] Step 1: A plurality of fire smoke information monitoring units are arranged in the forest area to be monitored, so as to ensure that the entire forest area to be monitored can be monitored, and forest state information is collected, the fire smoke information monitoring unit comprises a visual sensor and a thermal infrared sensor, and the forest state information comprises a visible light image and a thermal infrared image.

[0100] Step 2: Based on the average brightness in the visible light image, the initial feature threshold is adaptively adjusted to obtain an adaptive feature threshold, and based on the visible light image, image feature data of each pixel point is calculated, the image feature data comprises hue, saturation and lightness of the pixel point, and the initial feature threshold comprises a hue range threshold, a saturation threshold and a lightness threshold.

[0101] Step 3: Based on the adaptive feature threshold, a smoke identification standard is formulated, the pixel points in the visible light image that meet the smoke identification standard are marked, an image region composed of the marked pixel points is recorded as a smoke key region, the smoke key region is extracted through a contour detection algorithm, and a temperature value of the smoke key region is obtained through the thermal infrared image.

[0102] Step 4: A fire smoke evaluation value is generated based on the texture feature, shape feature and corresponding temperature value of the smoke key region, and whether the smoke key region is forest fire smoke is determined based on the fire smoke evaluation value, the texture feature comprises contrast and energy, and the shape feature comprises contour simplicity and roundness.

[0103] The above formula is a dimensionless value calculation, the formula is obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0104] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present text can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0105] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, and may be located in one place, or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0106] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. An automatic forest fire smoke recognition system based on adaptive target detection, characterized in that: Specifically include: An information collection module, used to monitor the entire forest area to be monitored, is composed of several fire and smoke information monitoring units that collect forest status information. The fire and smoke information monitoring units include visual sensors and thermal infrared sensors. The forest status information includes visible light images and thermal infrared images. an adaptive detection and adjustment module, configured to adaptively adjust an initial feature threshold based on the average brightness of the visible light image to obtain an adaptive feature threshold, and simultaneously calculate image feature data for each pixel of the visible light image, wherein the image feature data includes the hue, saturation, and lightness of the pixel, and the initial feature threshold includes a hue range threshold, a saturation threshold, and a lightness threshold; Adaptively adjusting the initial feature threshold according to the average brightness to obtain the adaptive feature threshold includes the following steps: calculating the average brightness L of the current visible light image based on the brightness of each pixel in the collected visible light image; converting the visible light image from the RGB color space to the HSV color space, and calculating image feature data, wherein the image feature data includes the hue H, saturation S, and lightness V of the pixel; The initial feature threshold is adaptively adjusted according to the average brightness, and the formula for the adaptive feature threshold is obtained as follows: H final =[H base (0)+a H *L, H base (1)-b H *L] S final =S base -γs*L V final =V base +δ V *L Where H final Represents the adaptive hue range threshold, S final Represents the adaptive saturation threshold, V final Represents the adaptive brightness threshold, the adaptive feature threshold includes H final 、S final and V final , H base (0) and H base (1) represents the lower and upper limits of the hue range in the initial feature threshold, S base is the saturation threshold in the initial feature threshold, V base is the brightness threshold in the initial feature threshold, where α H , β H , γ S and δ V They represent the lower and upper limits of the hue range, the saturation threshold, and the adjustment coefficient of the brightness threshold, respectively. L is the average brightness of the current visible light image; The key area identification and extraction module is used to establish smoke recognition standards based on adaptive feature thresholds, identify pixels in the visible light image whose image feature data meets the smoke recognition standards, record the image area composed of the identified pixels as the smoke key area, extract the smoke key area through the contour detection algorithm, and obtain the temperature value of the smoke key area through the thermal infrared image; The smoke identification and determination module is used to generate a fire smoke assessment value based on the texture features, shape features and corresponding temperature values ​​of the smoke key area, and determine whether the smoke key area is forest fire smoke based on the fire smoke assessment value. The texture features include contrast and energy, and the shape features include contour simplicity and roundness.

2. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 1, characterized in that: The visual sensor and thermal infrared sensor are high-definition cameras and thermal infrared cameras, which collect real-time videos of the forest area to be monitored. Forest status information is obtained through real-time videos, including visible light images and thermal infrared images. The method for obtaining visible light images and thermal infrared images is to collect visible light and thermal infrared frame images at the same time from the real-time video, with an acquisition interval of 30 frames.

3. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 2, characterized in that: The formula for calculating the average brightness L in the collected visible light image is: Where M represents the total number of pixels in the visible light image, I p Represents the brightness value of the p-th pixel. The first pixel in the upper left corner of the visible light image is denoted as the first pixel. The numbers are arranged in order of row priority to obtain a total of M pixels, where p is the index of the pixel, p = 1, 2, ..., M; The brightness value of the p-th pixel I p Calculated by the following formula: I p =0.299R p +0.587G p +0.114B p Where R p Represents the intensity value of the red channel of the p-th pixel, G p Indicates the intensity value of the green channel of the p-th pixel, B p Represents the intensity value of the blue channel of the p-th pixel.

4. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 3 is characterized by: Converting a visible light image from RGB color space to HSV color space and calculating image feature data includes the following steps: The image feature data is calculated based on the intensity values ​​of the red, green, and blue channels of each pixel. The specific calculation formula is as follows: Where atan2 is the inverse tangent function, which is used to calculate the inverse tangent value of two variables, H p 、S p and V p are the hue, saturation, and brightness of the p-th pixel in the visible light image, respectively.

5. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 4 is characterized in that: A smoke recognition standard is formulated based on the adaptive feature threshold. The logic behind the smoke recognition standard is as follows: When a pixel satisfies the following conditions at the same time: H p ∈H final S p <S final V p >V final Mark the pixel point, and denote the image area composed of all pixel points that fully meet the smoke recognition criteria as the smoke key area. Then, based on the Canny edge detection algorithm, extract the smoke key area and obtain the temperature value corresponding to the smoke key area in the thermal infrared image. Among them, calculate the average temperature through the temperature values of each pixel point in the smoke key area corresponding to the thermal infrared image, and use this average temperature as the temperature value of the smoke key area.

6. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 1, characterized in that: The formula for generating the fire smoke evaluation value based on the texture feature, shape feature, and corresponding temperature value of the smoke key area is: In the formula, HY represents the fire smoke evaluation value, T is the temperature value of the smoke key area, Ct and En respectively represent the contrast and energy in the texture feature, Cm and Cl respectively represent the contour simplicity and roundness in the shape feature, and ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of T, En, Ct, Cm, and Cl respectively, where ω1>ω2≥ω3>ω4≥ω5 and ω1, ω2, ω3, ω4, and ω5 are all greater than 0; The logic for determining whether the smoke key area is forest fire smoke based on the fire smoke evaluation value is: Set the fire smoke threshold as yz; When HY < yz, it is judged that the current smoke key area is not forest fire smoke; When HY ≥ yz, it is judged that the current smoke key area is determined to be forest fire smoke and an alarm is issued.

7. The automatic forest fire smoke recognition system based on adaptive target detection according to claim 6, characterized in that: The steps for obtaining the shape feature of the texture feature of the smoke key area include: Calculate the texture feature of the smoke key area including contrast and energy through the gray-level co-occurrence matrix, and calculate the shape feature including contour simplicity and roundness based on the contour length and area of the smoke key area.

8. A method for automatic identification of forest fire smoke based on adaptive target detection, characterized by: The automatic recognition method for forest fire smoke based on adaptive target detection is used to control the automatic recognition system for forest fire smoke based on adaptive target detection described in any one of claims 1-7. The specific steps include: Set several fire smoke information monitoring units in the forest area to be monitored to ensure that the entire forest area to be monitored can be monitored and collect forest status information. The fire smoke information monitoring unit includes a visual sensor and a thermal infrared sensor, and the forest status information includes visible light images and thermal infrared images; Based on the average brightness in the visible light image, adaptively adjust the initial feature threshold to obtain the adaptive feature threshold. At the same time, calculate the image feature data of each pixel point based on the visible light image. The image feature data includes the hue, saturation, and lightness of the pixel point, and the initial feature threshold includes the hue range threshold, saturation threshold, and lightness threshold; Based on the adaptive feature threshold, formulate the smoke recognition standard, mark the pixel points in the visible light image whose image feature data meet the smoke recognition standard, denote the image area composed of the marked pixel points as the smoke key area, extract the smoke key area through the contour detection algorithm, and obtain the temperature value of the smoke key area through the thermal infrared image; A fire smoke assessment value is generated based on the texture features, shape features and corresponding temperature values ​​of the smoke key area, and whether the smoke key area is forest fire smoke is determined based on the fire smoke assessment value. The texture features include contrast and energy, and the shape features include contour simplicity and roundness.

Images