Remote fire automatic detection and early warning method, monitoring system and equipment

Abstract

The invention relates to a long-distance fire behavior automatic detection and early warning method, a monitoring system and equipment. The long-distance fire behavior automatic detection and early warning method comprises the following steps that whether a suspected fire point target exists or not is judged based on a collected first image of a preset position point; if yes, collecting a second image of the preset position point in the first imaging waveband and a third image of the preset position point in the second imaging waveband; calculating the two-color ratio of the first imaging band to the second imaging band of the target position based on the second image and the third image; and judging whether a fire exists at the target position based on the calculated two-color ratio. Whether a suspected fire point target exists at the preset position point can be preliminarily judged through the collected first image, whether a fire behavior exists can be further determined through double-color ratio calculation and logic judgment of the first imaging waveband and the second imaging waveband, false alarms in a natural scene are effectively eliminated, the fire point automatic detection efficiency is improved, and the fire detection efficiency is improved. The technical problems of high false alarm and easy false alarm in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of photoelectric imaging and security / fire prevention monitoring, and specifically to a remote fire automatic detection and early warning method, monitoring system and equipment. Background Art

[0002] With the development of modern society, how to quickly detect fire has become a problem that needs to be solved. In the field of security and forest fire prevention, if the fire can be detected as early as possible, casualties and property losses can be reduced.

[0003] In the related technology, traditional security / forest monitoring systems usually use conventional long-wave uncooled infrared detection or medium-wave cooled infrared detectors with visible light imaging as detection devices, combined with security pan / tilts to achieve wide-area coverage and routine inspections through preset position movement, and observe images to see if there are any abnormalities. In the field of fire prevention applications, monitoring is generally achieved by combining the characteristics of infrared being sensitive to temperature and being able to form strong contrast highlights on images.

[0004] However, when long-wave uncooled infrared is used for fire prevention, the radiation of the normal temperature background on the ground is high in the long-wave band, which can easily cause many false alarms, making the target point difficult to find, and there is a risk of sun burns in long-wave detectors. When traditional medium-wave infrared is used for fire prevention, there is also interference and false alarms caused by surface sunlight radiation, and there are problems of high false alarms and easy false alarms, making it difficult to achieve true automatic monitoring and unmanned on-duty application promotion.

[0005] Therefore, it is necessary to design a new long-distance fire automatic detection and early warning method to overcome the above problems. Summary of the invention

[0006] The present application provides a remote fire automatic detection and early warning method, monitoring system and equipment, which can solve the technical problems of high false alarm and easy false alarm in related technologies.

[0007] In a first aspect, an embodiment of the present application provides a remote fire automatic detection and early warning method, characterized in that it comprises the following steps:

[0008] Determine whether there is a suspected fire point target based on the first image collected at the preset position point;

[0009] If yes, collecting a second image of the preset position point in the first imaging band and a third image in the second imaging band;

[0010] Calculate the dual color ratio of the first imaging band to the second imaging band at the target position based on the second image and the third image;

[0011] Based on the calculated dual-color ratio, it is determined whether there is a fire at the target location.

[0012] In combination with the first aspect, in one embodiment, the wavelength of the first imaging band is 4.3 ± 0.2 um, and the wavelength of the second imaging band is 3.8 ± 0.2 um.

[0013] In combination with the first aspect, in one embodiment, calculating the two-color ratio of the first imaging band and the second imaging band at the target position based on the second image and the third image includes:

[0014] Calculating the ratio of the irradiance differences within the first imaging band and the second imaging band at the target position based on the second image and the third image, which is the two-color ratio of the first imaging band and the second imaging band.

[0015] In combination with the first aspect, in one embodiment, calculating the ratio of the irradiance differences within the first imaging band and the second imaging band at the target position based on the second image and the third image includes:

[0016] Calculating the ratio of the radiation gains of the first imaging band and the second imaging band;

[0017] Calculating the difference between the target gray value and the background gray value in the second image and the difference between the target gray value and the background gray value in the third image;

[0018] Based on the ratio of the radiation gains of the first imaging band and the second imaging band, and the differences between the target gray value and the background gray value in the second image and the third image, determining the ratio of the irradiance differences within the first imaging band and the second imaging band at the target position.

[0019] In combination with the first aspect, in one embodiment, determining whether there is a fire at the target position based on the calculated two-color ratio includes:

[0020] Judging whether the calculated two-color ratio is within the set two-color ratio threshold range. If so, there is a fire; otherwise, there is no fire.

[0021] In combination with the first aspect, in one embodiment, before determining whether there is a suspected fire target based on the first image of the preset position point collected, it further includes:

[0022] Controlling the fire intelligent monitoring system to move to the preset position point and switching to a filter with a wavelength of the third imaging band to collect the first image; wherein, the wavelength range of the third imaging band is 3.7 um to 4.8 um.

[0023] In a second aspect, an embodiment of the present application provides a fire intelligent monitoring system, which includes:

[0024] A pan-tilt head, on which an infrared thermal imager is installed;

[0025] A control module, which is connected to the pan-tilt, is used to control the pan-tilt to move to a preset position point and control the infrared thermal imager to collect images;

[0026] A first judgment module, which is used to judge whether there is a suspected fire target based on the first image of the preset position point collected;

[0027] The control module is further used to control the infrared thermal imager to collect a second image in the first imaging band and a third image in the second imaging band of the preset position point when it is judged that there is a suspected fire target;

[0028] A calculation module, which is used to calculate the two-color ratio of the first imaging band and the second imaging band of the target position based on the second image and the third image;

[0029] A second judgment module, which is used to judge whether there is a fire at the target position based on the calculated two-color ratio.

[0030] Combined with the second aspect, in an implementation manner, the infrared thermal imager includes a filter wheel device, the filter wheel device includes a first filter, a second filter and a third filter, the wavelength of the first filter is the first imaging band, the wavelength of the second filter is the second imaging band, and the wavelength of the third filter is the third imaging band.

[0031] Combined with the second aspect, in an implementation manner, the filter wheel device further includes:

[0032] An installation base, on which a transmission structural member is rotatably installed, and the transmission structural member has an external gear, and the first filter, the second filter and the third filter are all installed at different positions of the transmission structural member;

[0033] A DC motor, the output shaft of which is engaged with the external gear;

[0034] A position sensor, the rotating shaft gear of which is engaged with the external gear;

[0035] The infrared thermal imager further includes a controller, which is used to control the rotation of the DC motor based on the position information of the first filter, the second filter or the third filter fed back by the position sensor, so that the first filter, the second filter or the third filter moves to the theoretical position.

[0036] In a third aspect, an embodiment of the present application provides a long-distance fire automatic detection and early warning device, which includes a processor, a memory, and a long-distance fire automatic detection and early warning program stored on the memory and executable by the processor. When the long-distance fire automatic detection and early warning program is executed by the processor, the steps of the above-mentioned long-distance fire automatic detection and early warning method are implemented.

[0037] The beneficial effects brought by the technical solution provided by the embodiment of the present application include:

[0038] Based on the first image collected, it is possible to initially determine whether there is a suspected fire target at a preset position point. Further, through the second image in the first imaging band and the third image in the second imaging band, the two-color ratio of the first imaging band and the second imaging band of the target position can be calculated. Through the two-color ratio calculation and logical judgment, it is possible to further determine whether there is a fire, effectively eliminating false alarms in natural scenes, improving the efficiency of automatic fire detection, and solving the technical problems of high false alarms and easy misreporting in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0040] Figure 1 It is a flowchart of a long-distance fire automatic detection and early warning method provided by an embodiment of the present application;

[0041] Figure 2 It is a flowchart of another long-distance fire automatic detection and early warning method provided by an embodiment of the present application;

[0042] Figure 3 It is a schematic structural diagram of a filter wheel device provided by an embodiment of the present application;

[0043] Figure 4 It is a schematic diagram of the closed-loop control principle of the filter wheel device provided by an embodiment of the present application;

[0044] Figure 5 It is a schematic structural diagram of an infrared thermal imager provided by an embodiment of the present application;

[0045] Figure 6 It is a schematic structural diagram of a fire intelligent monitoring system provided by an embodiment of the present application.

[0046] In the figure:

[0047] 1, pan-tilt;

[0048] 2. Infrared thermal imager

[0049] 21. Filter wheel device; 211. Mounting base; 212. Transmission structure member; 213. First filter; 214. Second filter; 215. Third filter; 216. DC motor; 217. Position sensor

[0050] 22. Base plate; 23. Lens assembly; 24. Detector module assembly

[0051] 3. Thermal imager window; 4. Laser rangefinder window; 5. Laser illumination window; 6. Visible light window Specific implementation manners

[0052] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application

[0053] The embodiments of this application provide a long-distance fire automatic detection and warning method, a monitoring system and equipment, which can solve the technical problems of high false alarm and easy misreport in the related art

[0054] See Figure 1 As shown, a long-distance fire automatic detection and warning method provided by the embodiments of this application may include the following steps

[0055] S1: Judge whether there is a suspected fire target based on the first image of the preset position point collected

[0056] S2: If it is judged that there is a suspected fire target, collect the second image of the preset position point in the first imaging band and the third image in the second imaging band

[0057] S3: Calculate the two-color ratio of the first imaging band and the second imaging band of the target position based on the second image and the third image

[0058] S4: Judge whether there is a fire at the target position based on the calculated two-color ratio

[0059] In this embodiment, the above-mentioned long-distance fire automatic detection and warning method can be completed in the fire intelligent monitoring system. After the inspection task starts, the fire intelligent monitoring system is controlled to move according to the preset. When it is determined that the fire intelligent monitoring system moves to one of the preset position points, a first image will be collected at this preset position point to determine whether there is a suspected fire target at this preset position point. When it is determined that there is a suspected fire target at this preset position point, steps S2 to S4 will be continued; if it is determined that there is no suspected fire target at this preset position point, the fire intelligent monitoring system will be controlled to move to the next position point, and the judgment in step S1 above will be continued. The long-distance fire automatic detection and warning method in this embodiment is mainly used in the fields of security and forest fire prevention, and can realize the monitoring of fire points / fires in areas such as long-distance ground / forests.

[0060] In the above embodiment, the wavelength ranges of the first imaging band and the second imaging band are different, and different second images and third images can be obtained under the first imaging band and the second imaging band of different wavelengths. The ratio of the response signals of the fire intelligent monitoring system to the first imaging band and the second imaging band is the two-color ratio, and the two-color ratio is related to the temperature, emissivity, atmospheric attenuation, system response rate, etc. of the target.

[0061] In this embodiment, through the collected first image, it can be initially judged whether there is a suspected fire target at the preset position point, and further, through the second image under the first imaging band and the third image under the second imaging band, the two-color ratio of the first imaging band and the second imaging band of the target position can be calculated. Through the two-color ratio calculation and logical judgment, it can be further determined whether there is a fire, effectively eliminating false alarms in the natural scene, improving the fire point automatic detection efficiency, and solving the technical problems of high false alarms and easy misreporting in the related technology.

[0062] See Figure 2 As shown, further, after step S4, if it is confirmed that there is a fire at the target position, an alarm message will be output, the fire record will be started, and the fire point position will be tracked and locked. The distance information of the fire point will be obtained through laser ranging, and then the fire point position information will be output; if it is confirmed that there is no fire at the target position, the fire intelligent monitoring system will be controlled to move to the next position point, and the judgment in step S1 above will be continued.

[0063] Preferably, in the above embodiment, the wavelength of the first imaging band is 4.3 ± 0.2 um, and the wavelength of the second imaging band is 3.8 ± 0.2 um. In this embodiment, the typical wavelength range of mid-wave infrared detectors is usually 3.7 um to 4.8 um. According to a number of satellite remote sensing test data at home and abroad, for the spectral characteristics of fire, from the perspective of flame red ultraviolet spectral resolution, it is mainly in the three bands of 0.28 um, 4.3 um, and 4.6 um, and the surface solar radiation curves at these three bands happen to be at the trough positions. A filter with a central wavelength of 4.3 um can be adopted to effectively monitor the mid-infrared wavelength signals radiated by CO2 and CO gases released in the combustion flame of hydrocarbons. In addition, the radiation near the 3.8 um wavelength is relatively weak, which can be used to monitor the thermal radiation of non-fire hot bodies and solar radiation (sunlight) to avoid interference and false alarms.

[0064] Further, in one embodiment, calculating the two-color ratio of the first imaging band and the second imaging band of the target position based on the second image and the third image may include: calculating the ratio of the irradiance difference of the target position in the first imaging band and the second imaging band based on the second image and the third image, which is the two-color ratio of the first imaging band and the second imaging band.

[0065] In this embodiment, an infrared thermal imager 2 is integrated in the fire intelligent monitoring system for collecting images. Since the spatial solid angle of a far-distance small target on the detector pixel is smaller than the instantaneous field of view of the device, the radiation energy at the entrance pupil of the infrared thermal imager 2 includes three parts: the self-radiation of the target, the background radiation, and the path radiation. At this time, the total irradiance at the entrance pupil of the infrared thermal imager 2 is:

[0066] E t =(I t / R 2 +L b (Ω s -Ω t ))τ(λ,R)+(1-τ(λ,R))L a (1).

[0067] Among them, I t is the radiation intensity in the target; L b is the background radiation intensity; L a is the radiation intensity on the atmospheric path; τ(λ, R) is the atmospheric transmittance; λ refers to the wavelength value; R is the distance between the target and the infrared detection system; Ω s is the field of view angle of the detector pixel; Ω t is the angle formed by the target relative to the detector pixel.

[0068] The irradiance difference formed by the target and the background on the infrared thermal imager 2 is:

[0069]

[0070] In the above formula, E b is the radiation of the background; the target radiation intensity can be obtained by integrating according to Planck's formula, and its definition is:

[0071]

[0072] where, C 1 is the first radiation constant, C 1 = 2πhC 2 = 3.7418×10 4 (W·cm -2 ·μm 4 ); C 2 is the second radiation constant, C 2 = h c / k = 1.4388×10 4 (μm·K); A S is the projected area of the thermal radiator (for the infrared thermal imager detection device), with the unit of cm -2 ; T is the temperature of the thermal radiator, with the unit of K; ε is the emissivity; λ 1 , λ 2 respectively represent the lower limit value and the upper limit value of the wavelength range, which are the variable integration ranges in the formula.

[0073] Considering that the radiation areas of the target with respect to the first imaging band (wavelength range λ 1 ~λ 2 ) and the second imaging band (wavelength range λ 3 ~λ 4 ) are basically the same, then the ratio of the irradiance differences within the two bands, that is, the two-color ratio, is:

[0074]

[0075] In the formula, M(λ 1 , λ 2 , T) and M(λ 3 , λ 4 , T) respectively represent the radiation intensities of the target in these two bands; ε 1 and ε 2 respectively represent the emissivities of the target in these two bands; τ 1 and τ 2 are the atmospheric transmittances of these two bands.

[0076] Therefore, in this embodiment, by calculating the ratio of the irradiance differences between the first imaging band and the second imaging band, the two-color ratio between the first imaging band and the second imaging band can be determined.

[0077] Further, based on the above embodiments, calculating the ratio of the irradiance differences of the target position in the first imaging band and the second imaging band based on the second image and the third image may include:

[0078] S31: Calculate the ratio of the radiation gains of the first imaging band and the second imaging band.

[0079] S32: Calculate the difference between the target gray value and the background gray value in the second image and the difference between the target gray value and the background gray value in the third image.

[0080] S33: Based on the ratio of the radiation gains of the first imaging band and the second imaging band, the difference between the target gray value and the background gray value in the second image, and the difference between the target gray value and the background gray value in the third image, determine the ratio of the irradiance differences of the target position in the first imaging band and the second imaging band.

[0081] In this embodiment, generally, an infrared thermal imager detection device can be approximated as a linear response system. The infrared image is the final output of this system, and the image gray value and the irradiance at the entrance pupil satisfy the following linear relationship:

[0082] E(i) = aG(i) + b (5).

[0083] Wherein, E(i) and G(i) are respectively the irradiance at the entrance pupil and the image gray value corresponding to a certain detection pixel, a is the radiation gain of the device, and b is the radiation offset of the device.

[0084] Thus, the target-background gray difference (i.e., the difference between the target gray value and the background gray value) on the infrared image can be expressed as:

[0085] ΔE(i) = a(G(i) t -G(i) bg ) (6).

[0086] In the above formula, G(i) t refers to the target gray value; G(i) bg refers to the background gray value.

[0087] Therefore, the two-color ratio at the entrance pupil can be calculated using the target gray value - background gray value in the infrared image:

[0088]

[0089] Among them, the target gray value - background gray value in the infrared image is obtained by extracting the target from the collected infrared image, and the gray values in the target and background image data are respectively statistically calculated; in addition, when calculating the two-color ratio, the radiation gain ratio of the first imaging band to the second imaging band needs to be obtained; after calculating the radiation gain ratio of the first imaging band to the second imaging band in Equation (7) and the difference between the target gray value and the background gray value in the second image (G(i) t1 -G(i) bg1 ) and the difference between the target gray value and the background gray value in the third image (G(i) t2 -G(i) bg2 ), the two-color ratio K can be calculated. The radiation gain is related to the optical system transmittance τ 光学 , the infrared detector response R(λ), the AD sampling σ AD , and the non-uniformity k, etc., and satisfies a multiplicative relationship, that is:

[0090] a = τ 光学 *R(λ)*σ AD *k (8).

[0091] Considering that the DC component b of the non-uniformity process can be subtracted during the process of finding the gray difference, the radiation gain ratio of the first imaging band (wavelength range λ 1 ~λ 2 ) and the second imaging band (wavelength range λ 3 ~λ 4 ) is:

[0092]

[0093] In the above formula, is the radiation gain of the first imaging band; is the radiation gain of the second imaging band; τ 光学1 is the optical system transmittance of the first imaging band; R(λ) 1 is the infrared detector response of the first imaging band; σ AD1 is the AD sampling of the first imaging band; k 1 is the non-uniformity of the first imaging band; τ 光学2 is the optical system transmittance of the second imaging band; R(λ) 2 is the infrared detector response of the second imaging band; σ AD2 is the AD sampling of the second imaging band; k 2 is the non-uniformity of the second imaging band.

[0094] The spectral response of the infrared detector is:

[0095]

[0096] Among them, D * is the specific detectivity; V n is the system noise; A d is the detector pixel area; Δf is the system equivalent noise bandwidth, Δf = 1 / 2τ d ; τ d is the integration time.

[0097] Substituting R(λ) into the above formula (9), we get:

[0098]

[0099] The AD analog-to-digital sampling process of the infrared thermal imager 2 core circuit can be described by the following formula:

[0100]

[0101] Among them, V s is the detector signal voltage, γ is the amplification factor, A is the AD chip sampling range, N is the number of digital signal bits, and formula (12) shows that AD sampling can be regarded as a linear conversion process.

[0102] According to the above derivation, under the condition of knowing the parameters of the first imaging band and the second imaging band of the fire intelligent monitoring system, the radiation gain ratio in the two bands can be calculated, and then the irradiance difference ratio of the target in the two bands, that is, the two-color ratio, can be obtained by using formula (7).

[0103] Further, in one embodiment, determining whether there is a fire at the target position based on the calculated two-color ratio may include: determining whether the calculated two-color ratio is within the set two-color ratio threshold range. If so, there is a fire; otherwise, there is no fire.

[0104] In this embodiment, according to Wien's displacement law, as shown in formula (13), the two-color ratio threshold range T 1 -T 2 can be set. Combining the large-scale infrared observation results, the fire point is further confirmed in the multi-spectral information of the first imaging band and the second imaging band. If the calculated two-color ratio is within the set two-color ratio threshold range T 1 -T 2 , it indicates that there is a fire at the target position. If it is not within the two-color ratio threshold range T 1 -T 2 , it indicates that there is no fire.

[0105]

[0106] In formula (13), b is Wien's displacement constant; λ max is the peak wavelength of blackbody radiation; T is the absolute temperature of the blackbody.

[0107] Further, in some embodiments, before determining whether there is a suspected fire target based on the first image of the preset position points collected, it may further include: controlling the fire intelligent monitoring system to move to the preset position points, and switching to a filter with a third imaging band wavelength to collect the first image; wherein, the wavelength range of the third imaging band is 3.7um to 4.8um. In this embodiment, the third imaging band is a mid-wave all-pass band. Switching to the mid-wave all-pass band to take a picture of the preset position points to obtain the first image, it is possible to preliminarily determine whether there is a suspected fire target at the preset position points based on the first image.

[0108] In this embodiment, the infrared thermal imager 2 integrated in the fire intelligent monitoring system may be a three-color infrared thermal imager 2. The infrared thermal imager 2 is provided with a filter wheel device 21. A first filter 213, a second filter 214, and a third filter 215 are installed on the filter wheel device 21. Among them, the wavelength of the first filter 213 is the first imaging band, the wavelength of the second filter 214 is the second imaging band, and the wavelength of the third filter 215 is the third imaging band; when imaging in the third imaging band is required, it can be switched to the third filter 215; when imaging in the first imaging band is required, it can be switched to the first filter 213; when imaging in the second imaging band is required, it can be switched to the second filter 214, and thus the acquisition of the above-mentioned first image, second image, and third image can be realized. And the fire intelligent monitoring system used in the above-mentioned long-distance fire automatic detection and early warning method may adopt the fire intelligent monitoring system provided in any of the following embodiments, which will not be elaborated here. The present application aims to combine the peak wavelength released by the combustion flame, the typical surface solar radiation wavelength, and the traditional imaging monitoring requirements to provide a new type of mid-wave three-color imaging, which can effectively reduce the false alarm of fire point detection and contribute to the realization of efficient unmanned automatic monitoring.

[0109] In the above embodiment, the filter wheel device 21 includes: a mounting base 211, a transmission structural member 212 is rotatably mounted on the mounting base 211, and the transmission structural member 212 has an external gear. The first filter 213, the second filter 214, and the third filter 215 are all installed at different positions of the transmission structural member 212; a DC motor 216, the output shaft of the DC motor 216 meshes with the external gear; a position sensor 217, the rotating shaft gear of the position sensor 217 meshes with the external gear; the infrared thermal imager 2 further includes a controller, which is used to control the rotation of the DC motor 216 based on the position information of the first filter 213, the second filter 214, or the third filter 215 fed back by the position sensor 217, so that the first filter 213, the second filter 214, or the third filter 215 moves to the theoretical position.

[0110] In the above-mentioned long-distance fire automatic detection and early warning method, according to the typical characteristics of natural scenes, fire point targets, solar radiation, etc. in three bands (i.e., the above-mentioned first imaging band, second imaging band, and third imaging band), a radiation feature model and comparison can be established to form a multi-dimensional spatial feature in the air-time-spectral domain. The sampling time of the three band images is not completely consistent, and considering that the equipment and the scene may have a certain degree of shaking relative to each other, and the rotation of the filter wheel device 21 will also bring about a slight optical axis error, the target coordinates of the image detection are mapped to the three-dimensional space coordinates based on the coordinate system of the mounting base 211, so as to achieve air-domain registration.

[0111] The target on the full-pass image (i.e., the first image) is extracted by the high-temperature target detection algorithm to obtain target-related features, including grayscale, shape, motion, etc.; and the target extreme points, grayscale values, signal-to-noise ratio, target size, etc. of the proposed target points in the first imaging band and the second imaging band (i.e., the second image and the third image) are obtained. Considering that the target radiation area and receiving optical aperture of the first imaging band and the second imaging band are the same, the ratio of the response signals of the two bands of the dual-band infrared detection system to the target, i.e., the dual-color ratio, is only related to the target temperature, emissivity, atmospheric attenuation, system response rate, etc. In a limited time period, the same equipment is used for multispectral observation, and the target dual-color ratio is only related to the target temperature. Therefore, the target temperature can be mapped by the dual-color ratio of the target to set the threshold logic judgment, and combined with the volatility of the target in the three bands (the first imaging band, the second imaging band, and the third imaging band), it can be judged whether there is a fire at the target location.

[0112] See also Figure 6 As shown, an intelligent fire monitoring system provided by an embodiment of the present application may include: a pan-tilt head 1, on which an infrared thermal imager 2 is installed; a control module, which is connected to the pan-tilt head 1, and is used to control the pan-tilt head 1 to move to a preset position point, and control the infrared thermal imager 2 to collect images; a first judgment module, which is used to judge whether there is a suspected fire point target based on the first image collected at the preset position point; the control module is also used to control the infrared thermal imager 2 to collect a second image of the preset position point in the first imaging band and a third image in the second imaging band when it is judged that there is a suspected fire point target; a calculation module, which is used to calculate the two-color ratio of the first imaging band to the second imaging band of the target position based on the second image and the third image; a second judgment module, which is used to judge whether there is a fire at the target position based on the calculated two-color ratio.

[0113] In this embodiment, the first image, the second image and the third image are all captured by the infrared thermal imager 2 .

[0114] Further, in one embodiment, the infrared thermal imager 2 includes a filter wheel device 21. The filter wheel device 21 includes a first filter 213, a second filter 214, and a third filter 215. The wavelength of the first filter 213 is the first imaging band, the wavelength of the second filter 214 is the second imaging band, and the wavelength of the third filter 215 is the third imaging band. In this embodiment, by providing the filter wheel device 21 on the infrared thermal imager 2 and providing multiple filters on the filter wheel device 21, the band ranges of different filters are different. When imaging in the corresponding band is required, the corresponding filter can be quickly switched to through the filter wheel, so that the infrared thermal imager 2 can achieve multiple imaging modes. In this embodiment, the wavelength of the first imaging band is 4.3 ± 0.2 um, the wavelength of the second imaging band is 3.8 ± 0.2 um, and the wavelength range of the third imaging band is 3.7 um to 4.8 um.

[0115] Preferably, in one embodiment, the filter wheel device 21 further includes: a mounting base 211, a transmission structural member 212 is rotatably mounted on the mounting base 211, and the transmission structural member 212 has an external gear. The first filter 213, the second filter 214, and the third filter 215 are all mounted at different positions on the transmission structural member 212; a DC motor 216, the output shaft of the DC motor 216 meshes with the external gear; a position sensor 217, the rotating shaft gear of the position sensor 217 meshes with the external gear; the infrared thermal imager 2 further includes a controller, which is configured to control the rotation of the DC motor 216 based on the position information of the first filter 213, the second filter 214, or the third filter 215 fed back by the position sensor 217, so that the first filter 213, the second filter 214, or the third filter 215 moves to the theoretical position.

[0116] In this embodiment, three filters are installed on a metal structural member with a gear-shaped outer ring (i.e., the transmission structural member 212). The outer gear of this structural member meshes with the pinion on the output shaft of the DC motor 216, and also synchronously meshes with the rotating shaft gear of a position sensor 217. The position sensor 217 can be a resistive or absolute encoder. The gear driven by the DC motor 216 drives the transmission structural member 212 where the filters are located to rotate, and synchronously drives the rotating shaft of the position sensor 217 to move, realizing synchronous movement among the three; the absolute feedback value of the position sensor 217 determines the real-time positions of the three filters (i.e., the first filter 213, the second filter 214, and the third filter 215) relative to the rotating shaft. Through the motor closed-loop control program of the digital controller, the position control of the filters can be achieved. Taking the theoretical position of the filters as the input, the real-time sampling value of the position sensor 217 as the feedback, and the DC motor 216 as the driving device, a PID controller is used to achieve closed-loop control. The composition of the filter wheel device 21 is as Figure 3 shown, and the closed-loop control principle of the filter wheel device 21 is as Figure 4 shown.

[0117] Refer to Figure 5 shown. The infrared thermal imager 2 further includes a bottom plate 22. A lens assembly 23 and a detector core assembly 24 are installed on the bottom plate 22. The filter wheel device 21 is designed and installed at the position between the lens assembly 23 and the detector core assembly 24, and the filter wheel device 21 is also fixed to the bottom plate 22. The lens optics adopts a mid-wave all-pass design. By rotating and switching the filter wheel device 21, three filters with different wavelength bands are cut into between the optics and the detector sensitive surface, which can change the imaging wavelength band characteristics of the entire infrared thermal imager 2, realizing time-sharing red (the first imaging wavelength band), blue (the second imaging wavelength band), and full (the third imaging wavelength band) three-color wavelength band imaging.

[0118] Refer to Figure 6 shown. The above-mentioned pan-tilt 1 is further provided with a thermal imager window 3, a laser rangefinder window 4, a laser illumination window 5, and a visible light window 6.

[0119] The above-mentioned infrared thermal imager 2 is integrated into Figure 6 the fire intelligent monitoring system shown. In order to achieve wide-area long-distance fire point detection, this application designs a multi-point preset and filter wheel device 21 automatic switching control logic to obtain three-color mid-wave infrared images at a single position point, which can suppress complex backgrounds, improve the detection ability and accuracy of the system, effectively eliminate false alarms through two-color ratio calculation and logical judgment, identify fire points, and improve the efficiency of automatic detection and warning.

[0120] Through the design of the three-color filter wheel device 21, this application realizes mid-wave infrared three-color imaging. By utilizing the response differences of different mid-wave bands to the scene and fire points, information is deeply fused. Through two-color ratio calculation and logical judgment, false alarms in natural scenes are effectively eliminated, and the efficiency of automatic fire point detection is improved. Moreover, by using a single infrared detector, without significantly increasing the design cost, the dimension and depth of image information can be effectively improved, which is beneficial to the combined application of intelligent algorithms and enhances the effect.

[0121] In a third aspect, an embodiment of this application provides a long-distance fire automatic detection and warning device. The long-distance fire automatic detection and warning device can be a device with data processing functions such as a personal computer (PC), a laptop computer, a server, etc.

[0122] In an embodiment of this application, the long-distance fire automatic detection and warning device may include a processor, a memory, a communication interface, and a communication bus.

[0123] Among them, the communication bus can be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0124] The communication interface includes interfaces such as input / output (I / O) interfaces, physical interfaces, and logical interfaces for interconnecting components inside the long-distance fire automatic detection and warning device, as well as interfaces for interconnecting the long-distance fire automatic detection and warning device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0125] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical memory, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0126] The processor may be a general-purpose processor, which can call the automatic long-distance fire detection and warning program stored in the memory and execute the automatic long-distance fire detection and warning method provided in the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). Among them, the method executed when the automatic long-distance fire detection and warning program is called may refer to the various embodiments of the automatic long-distance fire detection and warning method of the present application, which will not be elaborated here.

[0127] In the description of the present application, it should be noted that the orientation or positional relationship indicated by terms such as "upper" and "lower" is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application. Unless otherwise clearly specified and defined, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0128] It should be noted that in the present application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0129] The above description is only the specific implementation manners of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

Claims

1. A remote fire automatic detection and early warning method, characterized in that: It includes the following steps: Determine whether there is a suspected fire point target based on the first image collected at the preset position point; If yes, collecting a second image of the preset position point in the first imaging band and a third image in the second imaging band; Calculate the dual color ratio of the first imaging band to the second imaging band at the target position based on the second image and the third image; Based on the calculated dual-color ratio, it is determined whether there is a fire at the target location.

2. The remote fire automatic detection and early warning method according to claim 1, characterized in that: The wavelength of the first imaging band is 4.3±0.2 um, and the wavelength of the second imaging band is 3.8±0.2 um.

3. The remote fire automatic detection and early warning method according to claim 1, characterized in that: The method of calculating the dual color ratio of the first imaging band and the second imaging band of the target position based on the second image and the third image includes: The ratio of the irradiance difference between the first imaging band and the second imaging band at the target position is calculated based on the second image and the third image, that is, the dual-color ratio of the first imaging band to the second imaging band.

4. The remote fire automatic detection and early warning method according to claim 3, characterized in that: The step of calculating the ratio of the irradiance difference between the first imaging band and the second imaging band at the target position based on the second image and the third image includes: Calculating the ratio of the radiation gain of the first imaging band to the radiation gain of the second imaging band; Calculating the difference between the target grayscale value and the background grayscale value in the second image and the difference between the target grayscale value and the background grayscale value in the third image; Based on the ratio of the radiation gain of the first imaging band to the second imaging band, the difference between the target grayscale value and the background grayscale value in the second image, and the difference between the target grayscale value and the background grayscale value in the third image, the ratio of the irradiance difference of the target position in the first imaging band to the second imaging band is determined.

5. The remote fire automatic detection and early warning method according to claim 1, characterized in that: The step of judging whether there is a fire at the target location based on the calculated two-color ratio includes: It is determined whether the calculated two-color ratio is within the set two-color ratio threshold range. If so, there is a fire; otherwise, there is no fire.

6. The remote fire automatic detection and early warning method according to claim 1, characterized in that: Before judging whether there is a suspected fire point target based on the first image of the preset position point collected, the method further includes: The intelligent fire monitoring system is controlled to move to a preset position point, and is switched to a filter with a wavelength of the third imaging band to collect the first image; wherein the wavelength range of the third imaging band is 3.7um to 4.8um.

7. An intelligent fire monitoring system, characterized in that: It includes: A pan / tilt platform (1), wherein the pan / tilt platform (1) is equipped with an infrared thermal imager (2); A control module, connected to the pan / tilt platform (1), used to control the pan / tilt platform (1) to move to a preset position point, and to control the infrared thermal imager (2) to capture images; A first judgment module, which is used to judge whether there is a suspected fire point target based on the first image collected at the preset position point; The control module is also used to control the infrared thermal imager (2) to collect a second image of a preset position point in the first imaging band and a third image in the second imaging band when it is determined that there is a suspected fire point target; A calculation module, which is used to calculate the dual-color ratio of the first imaging band and the second imaging band of the target position based on the second image and the third image; The second judgment module is used to judge whether there is a fire at the target location based on the calculated two-color ratio.

8. The intelligent fire monitoring system according to claim 7, characterized in that: The infrared thermal imager (2) comprises a filter wheel device (21), the filter wheel device (21) comprising a first filter (213), a second filter (214) and a third filter (215), the wavelength of the first filter (213) being a first imaging band, the wavelength of the second filter (214) being a second imaging band, and the wavelength of the third filter (215) being a third imaging band.

9. The intelligent fire monitoring system according to claim 8, characterized in that: The filter wheel device (21) further comprises: A mounting base (211), wherein a transmission structure (212) is rotatably mounted on the mounting base (211), and the transmission structure (212) has an external gear, and the first optical filter (213), the second optical filter (214), and the third optical filter (215) are all mounted at different positions of the transmission structure (212); a DC motor (216), wherein an output shaft of the DC motor (216) is meshed with the external gear; a position sensor (217), wherein a rotating shaft gear of the position sensor (217) is meshed with the external gear; The infrared thermal imager (2) further comprises a controller for controlling the rotation of the DC motor (216) based on the position information of the first optical filter (213), the second optical filter (214) or the third optical filter (215) fed back by the position sensor (217), so as to move the first optical filter (213), the second optical filter (214) or the third optical filter (215) to a theoretical position.

10. A remote fire automatic detection and early warning device, characterized in that: The remote fire automatic detection and early warning device includes a processor, a memory, and a remote fire automatic detection and early warning program stored in the memory and executable by the processor. When the remote fire automatic detection and early warning program is executed by the processor, the steps of the remote fire automatic detection and early warning method as described in any one of claims 1 to 6 are implemented.

Images