Method, apparatus, system and electronic device for fire detection

ES3084353T3Undetermined Publication Date: 2026-11-12HANGZHOU HIKMICRO SENSING TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
ES2021900067T
Authority / Receiving Office
ES · ES
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-12-03
Filing Date
2021-12-02
Publication Date
2026-11-12
Estimated Expiration
2041-12-02

AI Technical Summary

Technical Problem

In complex monitored scenes, factors other than fire behavior can cause targets to present excessively high temperatures in thermal imaging images, leading to a high false alarm rate in fire detection systems.

Method used

A fire behavior detection method that utilizes both thermal imaging and visible light imaging to determine if a high-temperature target is caused by a fire phenomenon or an infrared light source, reducing false alarms by analyzing visible light images for smoke or specific machine types and infrared light emission characteristics.

Benefits of technology

Effectively reduces the false alarm rate in fire detection by distinguishing between fire behavior and non-fire sources of high temperature through combined thermal and visible light image analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000014_0000
    Figure 00000014_0000
  • Figure 00000014_0001
    Figure 00000014_0001
  • Figure 00000014_0002
    Figure 00000014_0002
Patent Text Reader

Abstract

A method, apparatus, system, and electronic device for fire detection is provided.The method comprises: obtaining a visible light image of a high-temperature target (S101), said target being an element in a monitored scene whose temperature exceeds a pre-established threshold, determined from an infrared light signal collected in the monitored scene; if, according to the visible light image, the high-temperature target is determined to be compatible with a fire condition or not with an infrared light source condition, then determining that a fire has occurred in the high-temperature target (S102), the fire condition being the occurrence of a pre-established fire in said target, the infrared light source condition being that the high-temperature target is a pre-established infrared light source, said infrared light source being capable of emitting infrared light when a fire does not occur.Based on the temperature determination, it is possible to determine, according to the information presented in the visible light image, whether the cause of the high temperature is a fire, thus effectively reducing the false alarm rate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of optoelectronic detection, and in particular to a fire behavior detection method, system and computer readable storage medium.Background

[0002] In order to take timely response measures to avoid the spread of fire behavior, it is necessary to detect the fire behavior timely. In the related technology, the thermal imaging camera can be used to acquire a thermal imaging image in a monitored scene according to the characteristic of high temperature of the target at which a fire behavior occurs, and the thermal imaging image can be analyzed to determine whether there is a target with an excessively high temperature in the monitored scene. If there is a target with an excessively high temperature in the monitored scene, it is determined that a fire behavior occurs at the target.

[0003] US20090315722A1 discloses a multi-wavelength video image fire detecting system, which consists of a multi-wavelength video image fire detector, which is comprised of a color and near IR dual-mode camera, a color and B / W dual-mode camera, an image capture module, a processor and controller, an I / O module, a housing and a visible light and near IR view window, an alarm and indicate equipment, a setting and debugging system, a communication equipment, an area alarm and monitor system, and a pan & title and control system.

[0004] CN111899460A discloses a remote fire detection system and method based on video images, and the method comprises the following steps: S1, periodically acquiring infrared images in a current scene; S2, extracting image features of the infrared image via a DSP, recognizing flame or smoke of the extracted image features by an identification algorithm, and acquiring a suspected fire occurrence area; S3, acquiring a visible light image in a suspected fire behavior area, and identifying whether visible flame or visible smoke exists in the visible light image; if yes, a fire behavior occurs, obtaining visible light images of other areas except the suspected fire behavior area, and executing step S4; if not, performing a deep learning based on the deep learning module, and re-performing step S1 after the learning is completed; S4. the identification result is transmitted to the remote control center, and at the same time, a first-class fire alarm is given in the suspected fire behavior area, and a second-class indicating alarm is given in other areas except the suspected fire behavior area.

[0005] US10847009B1 discloses a monitoring system that is configured to monitor a property is disclosed. The monitoring system includes a thermal camera that is configured to generate a thermal image of the property. The monitoring system further includes a monitor control unit that is configured to receive, from the thermal camera, the thermal image. The monitor control unit is further configured to, based on the thermal image, determine a temperature of a portion of the property depicted in the thermal image. The monitor control unit is further configured to determine that the temperature of the portion of the property depicted in the thermal image satisfies a temperature threshold. The monitor control unit is further configured to, based on determining that the temperature of the portion of the property depicted in the thermal image satisfies the temperature threshold, select and perform a monitoring system action.

[0006] US2020054905A1 discloses a fire safety system particularly adapted for commercial kitchen applications provides control of exhaust levels for energy efficiency and intelligently responds to fires or fire risks. In embodiments, systems may provide early warning of fire hazards or impending fires. Embodiments employ probabilistic estimates with alarms that can be canceled. Embodiments employ classifiers that can make use of alarm cancellations as a mechanism for supervised learning.

[0007] However, in some complex monitored scenes, other factors than a fire behavior may cause the target to present an excessively high temperature in the thermal imaging image, so that a false alarm rate of a fire behavior in these monitored scenes is high.Summary

[0008] The present application provides a fire behavior detection method, apparatus, system and electronic device, which can reduce a false alarm rate of a fire behavior in complex monitored scenes.

[0009] The invention is set out in the appended set of claims.Brief Description of the Drawings

[0010] In order to describe the technical solutions of embodiments of the present application or of the prior art more clearly, a simple introduction of the drawings required in the description of the embodiments and of the prior art will be given. Obviously, the drawings described below are just for some embodiments of the present application and other drawings may be obtained by those of ordinary skills in the art based on these drawings without any creative effort. Fig. 1 is a schematic flowchart of a fire behavior detection method provided by an embodiment of the present application; Fig. 2 is a schematic flowchart of a determination method provided by an embodiment of the present application, which is not according to the present invention and is present for only illustration purposes; Fig. 3a is a schematic diagram of a structure of a fire behavior detection system provided by an embodiment of the present application; Fig. 3b is another schematic diagram of a structure of a fire behavior detection system provided by an embodiment of the present application; Detailed Description

[0011] In order to make objectives, technical solutions and advantages of the present application more apparent, the present application now will be described in detail with reference to the accompanying drawings and by way of examples. Obviously, the embodiments described are only some of the embodiments of the present application instead of all of them. All other embodiments obtained by those ordinary skilled in the art based on the embodiments of the present application fall within the scope of the present application.

[0012] The technical solution in the embodiments of the application will be described clearly in detail with reference to the drawings in the embodiments of the present application. Obviously, the embodiments described herein are only some instead of all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those ordinary skilled in the art based on of the present application without any creative effort fall within the scope of the present application.

[0013] In some areas, straws may be destroyed by burning it. The burning of straws will generate a lot of toxic substances that pollute the air and soil and may cause bigger fires, therefore the burning of straws needs to be managed. To facilitate the management of the burning of straws, in the related technology, the presence of a fire behavior caused by burning straws can be detected by the following methods: using a cruising device, such as an aircraft, arranged with a thermal imaging camera to cruise through a monitored scene and acquire a thermal imaging image of the monitored scene; analyzing the grayscale of a target in the thermal imaging image. Since the higher the temperature the higher the grayscale of the target in the thermal imaging image, it can be assumed that a fire behavior occurs at the target if there is the target with excessively high grayscale in the thermal imaging image.

[0014] However, the burning of straws often occurs in rural areas, and there may be targets such as a house, an agricultural machinery vehicle (seeder, tractor, etc.), a factory, etc. Therefore, due to the reflection of the roof of the house, the heat emitted by the engine of the agricultural machinery vehicle, and the heat emitted by the heat engine in the factory and so on, there may be targets with excessively high grayscale values in the thermal imaging image of the monitored scene when there is no fire behavior. Therefore, it is possible to mistakenly determine that a fire behavior occurs at these targets. It follows that this method may have a high false alarm rate in such monitored scene of the rural areas.

[0015] In view of this, in an embodiment of the present application a fire behavior detection method is provided, which can be applied to any electronic device with a fire behavior detection function. As shown in Fig. 1, the method includes: S101, obtaining a visible light image of a high-temperature target; S102, when the high-temperature target is determined to not meet an infrared light source condition according to the visible light image, determining that a fire behavior has occurred at the high-temperature target.

[0016] By choosing this embodiment, on the basis of a determination of temperature, it is possible to further determine, according to the information presented by the visible light image, whether the cause of the high temperature is a fire behavior, thus effectively reducing the false alarm rate in complex application scenes.

[0017] In S101, the high-temperature target is a target in a monitored scene having a temperature higher than a preset temperature threshold, as determined according to an infrared light signal acquired from the monitored scene. The target in the present application can refer to a target object, such as haystack, tree, etc., or can refer to a target location.

[0018] It is understood that any object with a temperature exceeding absolute zero will theoretically radiate infrared light, and the higher the temperature of the object, the higher the energy of the radiated infrared light. Therefore, theoretically, according to the infrared light signal acquired from the monitored scene, the target with a temperature higher than the preset temperature threshold in the monitored scene can be determined. The temperature of the target may be obtained by analyzing an thermal imaging image or may be measured by other non-contact temperature measurement methods, which are not limited by this embodiment. The preset temperature threshold may be set according to the application scene, for example, in the aforementioned application scene of detecting the burning of straws, the preset temperature threshold may be the burning point of the straws.

[0019] It is understood that since some parameters are associated with temperature, such as the temperature of the target is associated with the grayscale of the target in the thermal imaging image, the method of determining whether the temperature of the target is higher than the preset temperature threshold may be achieved by directly comparing the temperature of the target with the preset temperature threshold or by other parameters associated with the temperature, for example, by comparing the grayscale of the target in the thermal imaging image with a preset grayscale threshold to determine whether the temperature of the target is higher than the preset temperature threshold.

[0020] In S102, the fire behavior phenomenon condition is the occurrence of a preset fire behavior phenomenon at the high-temperature target, and the infrared light source condition is that the high-temperature target is a preset infrared light source. The preset fire behavior phenomenon may be a phenomenon caused by the occurrence of a fire behavior, such as smoke generation, flame generation, refractive index change of the air around the high-temperature target, etc.

[0021] The preset infrared light source can be an infrared light source pre-set according to the application scene. In the application scene of detecting the burning of straw, for example, the preset infrared light source may include an agricultural machinery vehicle, a roof of a house, etc. In other possible application scenes, the preset infrared light source may also include other infrared light sources other than an agricultural machinery vehicle and a roof of a house. The infrared light source in the present application refers to an object with the ability to emit an infrared light outward. The emitted infrared light can be an infrared light radiated by the object or an infrared light reflected by the object. It is understood that all objects with a temperature above absolute zero can radiate an infrared light. Therefore, the infrared light source that emits an infrared light by reflecting an infrared light in the present application does not specifically mean that the infrared light source can only emit an infrared light by reflecting an infrared light, and the infrared light source can also radiate an infrared light. In an embodiment of the present application, the preset infrared light source should not include an infrared light source generated by a fire behavior, such as an infrared light source generated by burning straws.

[0022] It is understood that the preset fire behavior phenomenon is a phenomenon caused by the occurrence of a fire behavior, so compared to a high-temperature target that does not meet a fire behavior phenomenon condition, a high-temperature target that meets a fire behavior phenomenon condition has a higher probability of occurrence of a fire behavior.

[0023] Furthermore, since the preset infrared light source can emit an infrared light when no fire behavior occurs, if the high-temperature target is the preset infrared light source, the reason for the temperature of the high-temperature target being higher than a preset temperature threshold, as determined according to an infrared light signal acquired from the monitored scene may not be a fire behavior at the high-temperature target. Therefore, compared to a high-temperature target that does not meet an infrared light source condition, a high-temperature target that meets a fire behavior phenomenon condition has a lower probability of occurrence of a fire behavior.

[0024] Therefore, when the high-temperature target does not meet an infrared light source condition, it is determined that a fire behavior has occurred at the high-temperature target. According to different application scenes, situations where the high-temperature target is determined to meet a fire behavior phenomenon condition and / or to not meet an infrared light source condition can refer to the following four different situations: Situation 1: the high-temperature target meets a fire behavior phenomenon condition; Situation 2: the high-temperature target does not meet an infrared light source condition; Situation 3: the high-temperature target meets a fire behavior phenomenon condition and does not meet an infrared light source condition; Situation 4: the high-temperature target does not meet an infrared light source condition;

[0025] Exemplary, it is assumed that in some application scenes, the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition refers to Situation 1. In these application scenes, if the high-temperature target meet a fire behavior phenomenon, it is determined that a fire behavior has occurred at the high-temperature target; if the high-temperature target does not meet a fire behavior phenomenon, it is determined that no fire behavior has occurred at the high-temperature target.

[0026] In these application scenes, the conditions of the high-temperature target for determining whether a fire behavior has occurred at the high-temperature target or whether no fire behavior has occurred at the high-temperature target can be shown in Table 1: Table 1meeting a fire behavior phenomenon conditionnot meeting a fire behavior phenomenon conditionmeeting an infrared light source conditiondetermining that a fire behavior has occurred at the high-temperature targetdetermining that no fire behavior has occurred at the high-temperature targetnot meeting an infrared light source conditiondetermining that a fire behavior has occurred at the high-temperature targetdetermining that no fire behavior has occurred at the high-temperature target

[0027] The "determining that a fire behavior has occurred at the high-temperature target" in the second row and second column of Table 1 indicates that: if the high-temperature target meets a fire behavior phenomenon condition and also meets an infrared light source condition, it is determined that a fire behavior has occurred at the high-temperature target. The "determining that no fire behavior has occurred at the high-temperature target" in the second row and third column of Table 1 indicates that: if the high-temperature target does not meet a fire behavior phenomenon condition and meets an infrared light source condition, it is determined that no fire behavior has occurred at the high-temperature target. The "determining that a fire behavior has occurred at the high-temperature target" in the third row and second column of Table 1 indicates that: if the high-temperature target meets a fire behavior phenomenon condition and does not meet an infrared light source condition, it is determined that a fire behavior has occurred at the high-temperature target. The "determining that no fire behavior has occurred at the high-temperature target" in the third row and third column of Table 1 indicates that: if the high-temperature target does not meet a fire behavior phenomenon condition and also does not meet an infrared light source condition, it is determined that no fire behavior has occurred at the high-temperature target.

[0028] The situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition refers to Situation 2. In these application scenes, the conditions of the high-temperature target for determining whether a fire behavior has occurred at the high-temperature target or whether no fire behavior has occurred at the high-temperature target can be shown in Table 2: Table 2meeting a fire behavior phenomenon conditionnot meeting a fire behavior phenomenon conditionmeeting an infrared light source conditiondetermining that no fire behavior has occurred at the high-temperature targetdetermining that no fire behavior has occurred at the high-temperature targetnot meeting an infrared light source conditiondetermining that a fire behavior has occurred at the high-temperature targetdetermining that a fire behavior has occurred at the high-temperature target

[0029] The explanation of each item in Table 2 can refer to the previous explanation of Table 1, which will not be repeated here. It is assumed that in some application scenes, the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition refers to Situation 3. In these application scenes, the conditions of the high-temperature target for determining whether a fire behavior has occurred at the high-temperature target or whether no fire behavior has occurred at the high-temperature target can be shown in Table 3: Table 3meeting a fire behavior phenomenon conditionnot meeting a fire behavior phenomenon conditionmeeting an infrared light source conditiondetermining that no fire behavior has occurred at the high-temperature targetdetermining that no fire behavior has occurred at the high-temperature targetnot meeting an infrared light source conditiondetermining that a fire behavior has occurred at the high-temperature targetdetermining that no fire behavior has occurred at the high-temperature target

[0030] The explanation of each item in Table 3 can refer to the previous explanation of Table 1, which will not be repeated here. It is assumed that in some application scenes, the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition refers to Situation 4. In these application scenes, the conditions of the high-temperature target for determining whether a fire behavior has occurred at the high-temperature target or whether no fire behavior has occurred at the high-temperature target can be shown in Table 4: Table 4meeting a fire behavior phenomenon conditionnot meeting a fire behavior phenomenon conditionmeeting an infrared lightdetermining that a fire behaviordetermining that no firesource conditionhas occurred at the high-temperature targetbehavior has occurred at the high-temperature targetnot meeting an infrared light source conditiondetermining that a fire behavior has occurred at the high-temperature targetdetermining that a fire behavior has occurred at the high-temperature target

[0031] The explanation of each item in Table 4 can refer to the previous explanation of Table 1, which will not be repeated here.

[0032] For a situation (hereinafter referred to Situation 5) of the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition referring to Situation 1, it can be only determined whether the high-temperature target meets a fire behavior phenomenon condition, without determining whether the high-temperature target meets an infrared light source condition. For a situation (hereinafter referred to Situation 6) of the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition referring to Situation 2, it can be only determined whether the high-temperature target meets an infrared condition, without determining whether the high-temperature target meets an infrared light source condition. For a situation (hereinafter referred to Situation 7) of the situation where the high-temperature target meets a fire behavior phenomenon condition and / or does not meet an infrared light source condition referring to Situation 3 or Situation 4, it can be determined whether the high-temperature target meets an infrared condition, and also be needed to determine whether the high-temperature target meets an infrared light source condition. The Situation 5, Situation 6, and Situation 7 will be explained in the following based on the application scene for detecting the burning of straws mentioned above:Situation 5:

[0033] For the convenience of description, it is assumed that the fire behavior phenomenon condition include the presence of a smoke within the preset range of the high-temperature target.

[0034] Then, the visible light image can be input into a pre-trained smoke detection model to obtain the output result of the smoke detection model. This result is used to indicate whether there is a smoke within the preset range of the high-temperature target. If this result indicates that there is a smoke within the preset range of the high-temperature target, the high-temperature target is considered to meet a fire behavior phenomenon condition. The model can be obtained based on deep learning or based on traditional machine learning, which is not limited by this embodiment.

[0035] It is understood that due to the high moisture content in straws, obvious smoke will be generated during burning, while the high-temperature target caused by other reasons other than fire behavior often do not generate smoke. For example, an internal combustion engine in an agricultural machinery vehicle has a high temperature during operation but do not generate obvious smoke. Therefore, it can be considered that if there is a smoke within the preset range of the high-temperature target, the high-temperature target is caused by burning straws. If there is no smoke within the preset range of the high-temperature target, the high-temperature target is not caused by burning straws. Therefore, in this embodiment, if it is determined that there is a smoke within the preset range of the high-temperature target according to the visible light image, it can be determined that a fire behavior has occurred at the high-temperature target. If it is determined that there is no smoke within the preset range of the high-temperature target according to the visible light image, it can be determined that no fire behavior has occurred at the high-temperature target.

[0036] The principle of a fire behavior phenomenon condition including other conditions, such as the preset occurrence of flames in high-temperature targets, is the same and can be inferred by analogy, which will not be repeated here.Situation 6:

[0037] The infrared light source condition includes that a high-temperature target is a preset type of machine. The preset type of machine can include an aforementioned agricultural machinery vehicle. Since smoke will be generated when burning straws, which has a certain blocking effect on light, the light emitted by the high-temperature target is blocked by the smoke if the high-temperature target is caused by burning straws, and only a small amount of light can be acquired by the image acquiring device that captures a visible light image. Therefore, the exposure level of the high-temperature target in the visible light image is theoretically low. The infrared light source should theoretically have a certain reflection effect on visible light at the same time, and since there is no block caused by a smoke, a large amount of the light emitted by the high-temperature target can be acquired by the image acquiring device that captures a visible light image, Therefore, the exposure level of the high-temperature target in the visible light image is theoretically high.

[0038] It is understood that the infrared light source is an object that emits an infrared light, so even if there is no fire behavior at the infrared light source, the energy of the infrared light emitted by the infrared light source is relatively high, leading to the infrared light source being determined as a high-temperature target. For example, a roof of a house may become a high-temperature target due to sunlight exposure.

[0039] The infrared light source condition includes that the high-temperature target is a preset type of machine, it is determined by image recognition of the visible light image to determine whether the high-temperature target is a preset type of machine. For example, the visible light image can be input into a pre-trained agricultural machinery vehicle detection model to obtain the output result of the agricultural machinery vehicle detection model. This result is used to indicate whether the high-temperature target is an agricultural machinery vehicle. The agricultural machinery vehicle detection model is a model used to identify an agricultural machinery vehicle. The model can be obtained based on deep learning or based on traditional machine learning, which is not limited by this embodiment.

[0040] It is understood that the infrared light source is an object that emits an infrared light, so even if there is no fire behavior at the infrared light source, the energy of the infrared light emitted by the infrared light source is relatively high, leading to the infrared light source being identified as a high-temperature target. For example, an agricultural machinery vehicle may become a high-temperature target due to the combustion of a fuel in an internal combustion engine. Therefore, it can be considered that if it is determined that the high-temperature target is a preset type of machine according to the visible light image, it can be determined that no fire behavior has occurred at the high-temperature target.

[0041] An infrared light source condition including other conditions, such as the high-temperature target being a factory chimney, can be inferred by analogy and will not be repeated here.Situation 7: the preset condition includes a fire behavior phenomenon condition and an infrared light source condition:

[0042] In this situation, it can be determined firstly whether the high-temperature target meets the fire behavior phenomenon condition, then whether the high-temperature target meets the infrared light source condition, or it can be determined firstly whether the high-temperature target meets the infrared light source condition, then whether the high-temperature target meets the fire behavior phenomenon condition, or it can be determined whether the high-temperature target meets the infrared light source condition and whether the high-temperature target meets the fire behavior phenomenon condition in a parallel or alternate manner, which is not limited by this embodiment.

[0043] Moreover, it is possible to determine all of the preset conditions or some of the preset conditions, for example, if it is possible to determine whether a fire behavior has occurred at the high-temperature target according to the determination result obtained after determining some of the preset conditions, it is possible not to continue determining the remaining preset conditions.

[0044] Exemplary, it is assumed that in a possible embodiment, if the high-temperature target meets the fire behavior phenomenon condition or does not meet the infrared light source condition, it is determined that a fire behavior has occurred at the high-temperature target. If the high-temperature target does not meet the fire behavior phenomenon condition and meets the infrared light source condition, it is determined that no fire behavior has occurred at the high-temperature target. In this embodiment, a possible determination process can be seen in Fig. 2. Fig. 2 is a schematic flowchart of a determination method provided by an embodiment of the present application, which can include: S201, determining whether there is a smoke within the preset range of the high-temperature target; if there is no smoke within the preset range of the high-temperature target, performing S202; if there is a smoke within the preset range of the high-temperature target, performing S204.

[0045] The determination method can refer to the relevant explanations mentioned above, and will not be repeated here.

[0046] S202, determining whether the high-temperature target is an infrared light source that emits an infrared light by reflecting an infrared light; if the high-temperature target is an infrared light source that emits an infrared light by reflecting an infrared light, performing S204; if the high-temperature target is not an infrared light source that emits an infrared light by reflecting an infrared light, performing S203.

[0047] The determination method can refer to the relevant explanations mentioned above, and will not be repeated here.

[0048] S203, determining whether the high-temperature target is a preset type of machine.

[0049] S204, generating a determination result.

[0050] In S201, if there is a smoke within the preset range of the high-temperature target, it can already be determined that a fire behavior has occurred at the high-temperature target. Therefore, a determination result can be generated to indicate the presence of a smoke within the preset range of the high-temperature target without performing the determinations on S202 and S203. Based on this determination result, it can be determined that a fire behavior has occurred at the high-temperature target.

[0051] Similarly, in S201, if there is no smoke within the preset range of the high-temperature target, and in S202, the high-temperature target is an infrared light source that emits an infrared light by reflecting an infrared light, it can already be determined that no fire behavior has occurred at the high-temperature target. Therefore, a determination result can be generated to indicate that there is no smoke within the preset range of the high-temperature target, and that the high-temperature target is an infrared light source that emits an infrared light by reflecting an infrared light without performing the determinations on S202 and S203. Based on this determination result, it can be determined that no fire behavior has occurred at the high-temperature target.

[0052] In S201, if there is no smoke within the preset range of the high-temperature target, and in S202, the high-temperature target is not an infrared light source that emits an infrared light by reflecting an infrared light, and in S203, the high-temperature target is a preset type of machine, a determination result can be generated to indicate that there is no smoke within the preset range of the high-temperature target, and that the high-temperature target is not an infrared light source that emits an infrared light by reflecting an infrared light, and the high-temperature target is a preset type of machine. Based on this determination result, it can be determined that no fire behavior has occurred at the high-temperature target.

[0053] In S201, if there is no smoke within the preset range of the high-temperature target, and in S202, the high-temperature target is not an infrared light source that emits an infrared light by reflecting an infrared light, and in S203, the high-temperature target is not a preset type of machine, a determination result can be generated to indicate that there is no smoke within the preset range of the high-temperature target, and that the high-temperature target is not an infrared light source that emits an infrared light by reflecting an infrared light , and the high-temperature target is not a preset type of machine. Based on this determination result, it can be determined that a fire behavior has occurred at the high-temperature target.

[0054] As shown in Fig. 3a, Fig. 3a is a schematic diagram of a structure of a fire behavior detection system provided by an embodiment of the present application, the fire behavior detection system may including: a data acquiring unit 310, a linkage unit 320 and an intelligence unit 330.

[0055] The data acquiring unit 310 is configured for acquiring a monitoring data in a monitored scene. The linkage unit 320 is configured for determining, according to the acquired monitoring data, a target in the monitored scene having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target, the monitoring data at least comprises an infrared light signal.

[0056] The data acquiring unit 310 is further configured for acquiring a visible light image of the high-temperature target; the intelligence unit 330 is configured for determining that a fire behavior has occurred at the high-temperature target, if, according to the visible-light image of the data acquiring unit 310, the high-temperature target is determined to meet a fire behavior phenomenon condition and / or not meet an infrared light source condition; wherein, the fire behavior phenomenon condition is that a preset fire behavior phenomenon occurs at the high-temperature target, and the infrared light source condition is that the high-temperature target is a preset infrared light source, the preset infrared light source being an infrared light source capable of emitting infrared light when no fire behavior is occurring.

[0057] Any two units of the data acquiring unit 310, the linkage unit 320, and the intelligence unit 330 can be two independent devices of each other, or be two integrated parts on the same device. For example, in an possible embodiment, the data acquiring unit 310 can be an aircraft, the linkage unit 320 can be a control server for the aircraft, and the intelligence unit 330 can be a back-end processing server for the aircraft. In another possible embodiment, the data acquiring unit 310, the linkage unit 320, and the intelligence unit 330 can be integrated on the same aircraft. In a further possible embodiment, the data acquiring unit 310 and the linkage unit 320 can be integrated on the same aircraft, and the intelligence unit 330 is a back-end processing server of the aircraft. Any unit in the embodiment of the present application can refer to one or more devices, or can refer to one or more components.

[0058] The steps performed by the intelligence unit 330 can refer to any of the aforementioned fire behavior detection methods, and will not be repeated here. The following will explain the data acquiring unit 310 and the linkage unit 320 respectively.

[0059] The data acquiring unit 310 can include a thermal imaging camera and a visible light camera which are pre-aligned, wherein the thermal imaging camera refers to a camera with the ability to capture a thermal imaging image, the visible light camera refers to a camera with the ability to capture a visible light image, and the thermal imaging camera and the visible light camera can be different cameras or the same camera. For example, the thermal imaging camera and the visible light camera can be the same binocular camera, that is, the same binocular camera serves as the thermal imaging camera and the visible light camera.

[0060] The thermal imaging camera is configured for capturing a thermal imaging image in the monitored scene; the linkage unit 320 is configured for determining, according to the thermal imaging image captured by the thermal imaging camera, a target having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target; and the visible light camera is configured for capturing the visible light image of the high-temperature target.

[0061] As an example, it can be used to determine the grayscale values of each pixel in the thermal imaging image. If at least one pixel has a grayscale value greater than the preset grayscale threshold, a target to which the pixel with a grayscale value greater than the preset grayscale threshold belongs will be served as the high-temperature target.

[0062] In another possible embodiment, the data acquiring unit 310 further includes a temperature and humidity sensor and a ranging component.

[0063] The temperature and humidity sensor is configured for acquiring the temperature and humidity information of the monitored scene, and the ranging component is configured for acquiring a distance information; wherein, the distance information is used to indicate the distance between the data acquiring unit and the target in the monitored scene. It can be understood that due to the possible position relationship between the data acquiring unit and other assemblies, although the distance information is used to indicate the distance between the data acquiring unit and the target in the monitored scene, the distance information can also be geometric parameters other than the distance between the data acquiring unit and the target in the monitored scene.

[0064] The ranging component can vary depending on the application scene. For example, in the data acquiring unit arranged on the aircraft as an example, the ranging component can be a pitch angle sensor configured for measuring the pitch angle relative to the aircraft when the thermal imaging camera captures the thermal imaging image. Based on this pitch angle and the height of the aircraft, the distance between the data acquiring unit and the target in the monitored scene can be calculated.

[0065] The linkage unit 320 can determine, according to the thermal imaging image captured by the thermal imaging camera, the temperature and humidity information and the distance information, a target having a temperature higher than a preset temperature threshold from the monitored scene.

[0066] For example, it can be based on the temperature and humidity information, the distance information (or if the data acquiring unit is arranged on an aircraft, it can also be based on the temperature and humidity information, the distance information, and cruise sensitivity information of the aircraft) to calculate the grayscale threshold and determine the grayscale value of each pixel in the thermal imaging image. If at least one pixel has a grayscale value greater than the grayscale threshold, the target to which the pixel with the grayscale value greater than the preset grayscale threshold belongs will be considered as the high-temperature target.

[0067] The linkage unit 320 can control the data acquiring unit 310. For example, the linkage unit 320 can adjust the data after determining the high-temperature target from the monitored scene.

[0068] In the data acquiring unit 310 arranged on the aircraft as an example, the linkage unit 320 can control the movement of the aircraft. For example, it is assumed that the linkage unit 320 determines a high-temperature target according to the data acquiring unit 310, the linkage unit 320 can control the aircraft to fly directly above the high-temperature target, and after the aircraft stabilizes above the high-temperature target, control the data acquiring unit 310 to capture a visible light image of the high-temperature target.

[0069] It is understood that there may be some areas in the monitored scene that may experience burning phenomenon even in the absence of a fire behavior. If the coal may be burnt in the factory and the firewood may be burnt in the chimney, such burning phenomenons with no fire behavior may be mistakenly detected as fire behaviors, leading to an increased false alarm rate. Therefore, in a possible embodiment, the linkage unit 320 can determine, according to the monitoring data, a target with a temperature higher than the preset temperature threshold from other areas other than a shielding area in the monitored scene, as a high-temperature target. The shielding area includes one or more areas within the preset factory area and the preset chimney area. The preset shielding area can be pre-set by the user or predetermined based on map information. This embodiment can further effectively reduce the false alarm rate.

[0070] As shown in Fig. 3b, Fig. 3b is another schematic diagram of a structure of a fire behavior detection system provided by an embodiment of the present application, the fire behavior detection system may including: a data acquiring unit 310, a linkage unit 320, an intelligence unit 340 and an alarm unit 340.

[0071] Regarding the data acquiring unit 310, the linkage unit 320, and intelligence unit 330, please refer to the relevant explanations mentioned above and the explanations thereof will not be repeated here. The alarm unit 340 is configured for sending an alarm when the intelligence unit 330 determines that a fire behavior has occurred at the high-temperature target.

[0072] The method of alarm can vary depending on the application situation. For example, it can be by emitting an alarm sound or sending an alarm information. The sent alarm information can be sent to the preset alarm center or to the preset user terminal, which is not limited by this embodiment.

[0073] The alarm information can include one or more of the following three types of information: Information 1: screenshots of the thermal imaging image and of the visible light image including the high-temperature target. Information 2: location information of the high-temperature target. Information 3: temperature information of the high-temperature target.

[0074] The inclusion of information 1 in the alarm information can facilitate relevant personnel to confirm the fire behavior situation and retain it as evidence. The inclusion of information 2 in the alarm information can facilitate relevant personnel to locate the unknown occurrence of the fire behavior. The inclusion of information in the alarm information can facilitate relevant personnel to grasp the fire behavior state and take appropriate response measures.

[0075] In the aforementioned embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The processes or functions described in accordance with the embodiments of the present application is produced in whole or in part, when the computer program instructions are loaded and executed on a computer. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or may be transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a web site, a computer, a server, or a data center to another web site, another computer, another server, or another data center via a cable (such as a coaxial cable, an optical fiber, a digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that may be accessed by a computer or a data storage device such as a server or a data center containing one or more available medium integrations. The available media may be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVD), or semiconductor media (such as solid state disk (SSD)), etc.

[0076] It should be noted that, the relationship terms herein such as "first", "second" and the like are only used to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply that there is actual relationship or order between these entities or operations. Moreover, the terms "comprise(s)", "include(s)" or any other variants thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles or devices including a series of elements include not only those elements listed but also those not specifically listed or the elements intrinsic to these processes, methods, articles, or devices. Without further limitations, elements defined by the sentences "comprise(s) a." or "include(s) a." do not exclude that there are other identical elements in the processes, methods, articles, or devices which include these elements.

[0077] All the embodiments are described in corresponding ways, same or similar parts in each of the embodiments can be referred to one another, and the parts emphasized are differences to other embodiments. In particular, for embodiments of the apparatus, system, electronic device, computer readable storage medium, and computer program product, since they are substantially similar to the embodiments of the method, their description is relatively simple, and for the related aspects, one only needs to refer to portions of the description of the embodiments of the method.

Claims

1. A fire behavior detection method, wherein the method comprises: obtaining a visible light image of a high-temperature target (S101), wherein the high-temperature target is a target in a monitored scene having a temperature higher than a preset temperature threshold, as determined according to an infrared light signal acquired from the monitored scene; determining that a fire behavior has occurred at the high-temperature target when the high-temperature target is determined to not meet an infrared light source condition according to the visible light image (S102), wherein when the high-temperature target is a preset type of machine, the high-temperature target meets the infrared light source condition, wherein whether the high-temperature target is the preset type of machine is determined by image recognition of the visible light image.

2. A fire behavior detection system, wherein the system comprises: a data acquiring unit (310), a linkage unit (320), an intelligence unit (330); wherein, the data acquiring unit (310) is configured for acquiring a monitoring data from a monitored scene, the monitoring data at least comprises an infrared light signal; the linkage unit (320) is configured for determining, according to the monitoring data acquired by the data acquiring unit (310), a target in the monitored scene having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target; the data acquiring unit (310) is further configured for acquiring a visible light image of the high-temperature target; the intelligence unit (330) is configured for determining that a fire behavior has occurred at the high-temperature target, when the high-temperature target is determined to not meet an infrared light source condition according to the visible light image, wherein when the high-temperature target is a preset type of machine, the high-temperature target meets the infrared light source condition, wherein whether the high-temperature target is the preset type of machine is determined by image recognition of the visible light image.

3. The system as claimed in claim 2, wherein, the data acquiring unit comprises a thermal imaging camera and a visible light camera which are pre-aligned; wherein, the thermal imaging camera is configured for capturing a thermal imaging image of the monitored scene; the linkage unit determining, according to the monitoring data acquired by the data acquiring unit, a target having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target, comprises: determining, according to the thermal imaging image captured by the thermal imaging camera, a target having a temperature higher than the preset temperature threshold from the monitored scene, as a high-temperature target; the visible light camera is configured for capturing the visible light image of the high-temperature target.

4. The system as claimed in claim 3, wherein, the linkage unit is further configured for adjusting the thermal imaging camera so that the high-temperature target is located in a center area of a field of view of the thermal imaging camera, after determining, according to the monitoring data acquired by the data acquiring unit, the target having a temperature higher than the preset temperature threshold from the monitored scene, as the high-temperature target; the visible-light camera capturing the visible light image of the high-temperature target, comprises: capturing the visible light image of the high-temperature target, after the linkage unit adjusts the thermal imaging camera so that the high-temperature target is located in the center area of the field of view of the thermal imaging camera.

5. The system as claimed in claim 3, wherein, the data acquiring unit further comprises a temperature and humidity sensor and a ranging component; wherein the temperature and humidity sensor is configured for acquiring temperature and humidity information of the monitored scene; the ranging component is configured for acquiring distance information, which indicates a distance between the data acquiring unit and the target in the monitored scene; the linkage unit determining, according to the thermal imaging image captured by the thermal imaging camera, a target having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target, comprises: the linkage unit determining, according to the thermal imaging image captured by the thermal imaging camera, the temperature and humidity information and the distance information, the target having a temperature higher than a preset temperature threshold from the monitored scene, as the high-temperature target.

6. The system as claimed in claim 2, wherein, the linkage unit determining, according to the monitoring data acquired by the data acquiring unit, a target having a temperature higher than a preset temperature threshold from the monitored scene, as a high-temperature target, comprises: determining, according to the monitoring data acquired by the data acquiring unit, a target having a temperature higher than the preset temperature threshold from the monitored scene, as the high-temperature target; determining, according to the monitoring data acquired by the data acquiring unit, a target having a temperature higher than the preset temperature threshold from an area other than a shielding area in the monitored scene, as the high-temperature target, wherein the shielding area comprises one or more of a preset factory area and a preset chimney area.

7. The system as claimed in claim 2, wherein, the fire behavior detection system further comprises an alarm unit; wherein the alarm unit is configured for sending an alarm when the intelligence unit determines that the fire behavior has occurred at the high-temperature target.

8. A computer readable storage medium having stored thereon a computer program which, when executed by a processor (502), causes the processor (502) to carry out the method of claim 1.