Flame detection method, flame detection device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of computers, in particular to a binocular image flame detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first parameter of a first camera, and determining a second parameter according to the first parameter and a preset corresponding relation; adjusting the current second parameter of the second camera into the determined second parameter, and obtaining an image collected by the adjusted second camera; whether flame information exists or not is recognized according to the image, and if yes, a prompt message is sent out. Visibly, according to the flame detection method and the flame detection device for the binocular image, the electronic equipment and the computer readable storage medium, the second parameter of the second camera is determined and adjusted by using the binocular camera and utilizing the high-energy characteristic of the flame according to the first parameter of the first camera and the preset corresponding relation; therefore, flame identification requirements in different environments can be met, flame identification difficulty is reduced, and fire early warning efficiency and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a flame detection method of binocular images, a flame detection device, an electronic device and a computer-readable storage medium. Background Art

[0002] At present, the common surveillance cameras on the market generally use monocular cameras. The shutter speed and gain of the monocular camera will be adjusted adaptively as the brightness of the use environment changes. When the brightness of the use environment is high, the shutter speed and gain will be reduced accordingly to avoid overexposure and improve image quality. When the brightness of the use environment is low, the shutter speed and gain will be increased accordingly to enhance the brightness and clarity of the image. Through this adaptive adjustment feature, the surveillance camera can capture clear images in real time and realize effective monitoring functions.

[0003] Generally speaking, surveillance cameras have the function of flame recognition while ensuring the normal audio and video acquisition and display monitoring functions. That is, the image of the monitoring area is acquired through a monocular camera, and the flame information of the acquired image is identified through image analysis technology. Under normal circumstances, these cameras can effectively analyze whether there is a real flame in the monitoring area, thereby realizing fire warning. However, the application environment of surveillance cameras is somewhat complex. Under the premise of ensuring the normal monitoring function of the surveillance camera, if there is a flame in the monitoring area, and the background of the flame is white, bright or similar to the flame, the surveillance camera will not be able to successfully separate and identify the flame due to the high brightness and the background white wall or the close environment. At the same time, some reflective or partially yellow or red objects will be mistakenly identified as flames, which ultimately leads to difficulty in flame recognition. The following are specific manifestations of flame recognition difficulties, including:

[0004] 1. When the camera is used during the day, the flame usually appears bright in color. When the background of the monitored area is a white wall or a similar color, it is difficult to separate the flame and the similar background during the analysis of the collected images. This is likely to result in the inability to accurately identify the presence of flames in the monitored area, resulting in missed fire reports.

[0005] 2. The image analysis method used by the camera to identify flames is mainly through spectral color analysis. However, if the original image taken by the camera cannot be segmented, that is, the flame and the background cannot be clearly distinguished, the analysis may be hindered.

[0006] 3. When there are some red or yellow objects with colors close to flames in the images collected by the camera, these objects may lead to misjudgment of flames and false fire alarms because they are similar to the flame colors in the spectrum.

[0007] 4. By introducing hardware circuits such as infrared thermal imaging sensors to detect the heat radiation of the target object, the accuracy of flame identification can be improved, but this will greatly increase the cost of surveillance cameras.

[0008] In view of the above situation, there is an urgent need for a flame detection method that can reduce false alarms and missed alarms. Summary of the invention

[0009] In view of this, the present invention proposes a flame detection method of binocular images, a flame detection device, an electronic device and a computer-readable storage medium, aiming to solve the problem of difficulty in flame recognition in existing surveillance cameras.

[0010] In order to solve the above problems, the present invention adopts the following technical solutions:

[0011] In a first aspect, the present invention provides a flame detection method of binocular images, which is applied to a flame detection system, wherein the flame detection system includes a first camera and a second camera;

[0012] The flame detection method comprises:

[0013] Acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed, and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter;

[0014] Adjusting the current second parameter of the second camera to the determined second parameter, and obtaining an image captured by the second camera after the adjustment;

[0015] It is identified whether there is flame information based on the image, and a prompt message is issued when it is confirmed that there is flame information.

[0016] Furthermore, the preset corresponding relationship includes an index table of preset first parameters and second parameters and a preset functional relationship between the first parameters and the second parameters.

[0017] Furthermore, before obtaining the first parameter of the first camera, the method further includes: obtaining a first image captured by the first camera, and identifying and confirming the existence of flame information according to the first image.

[0018] Further, the first shutter speed and the first gain are both inversely correlated with the brightness.

[0019] Furthermore, the first camera and the second camera have the same specifications.

[0020] Further, when the first parameter is brightness, the second parameter is a second shutter speed;

[0021] When the first parameter includes a first shutter speed and a first gain, the second parameter is a second shutter speed.

[0022] In a second aspect, the present invention further provides a binocular image flame detection device, which is applied to a flame detection system, wherein the flame detection system includes a first camera and a second camera;

[0023] The flame detection device comprises an acquisition unit, an adjustment unit and an identification unit; wherein,

[0024] The acquisition unit is used to acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter;

[0025] The adjusting unit is used to adjust the current second parameter of the second camera to the determined second parameter, and obtain the image captured by the second camera after the adjustment;

[0026] The identification unit is used to identify whether there is flame information based on the image, and send a prompt message when it is confirmed that there is flame information.

[0027] Furthermore, the flame detection device also includes a starting unit, and the starting unit is used to obtain a first image captured by the first camera, and recognize and confirm the existence of flame information based on the first image.

[0028] In a third aspect, the present invention further provides an electronic device, comprising:

[0029] a memory for storing program instructions; and

[0030] A processor is used to execute the program instructions to implement the steps of the binocular image flame detection method as described above.

[0031] In a fourth aspect, the present invention further proposes a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the binocular image flame detection method as described above are implemented.

[0032] Compared with the prior art, the beneficial effects of the present invention are: a flame detection method of binocular images, a flame detection device, an electronic device and a computer-readable storage medium, applied to a flame detection system, the flame detection system comprising a first camera and a second camera; the flame detection method comprises: obtaining a first parameter of the first camera, determining a second parameter according to the first parameter and a preset corresponding relationship; adjusting the current second parameter of the second camera to the determined second parameter, and obtaining the image collected by the adjusted second camera; identifying whether there is flame information according to the image, and issuing a prompt message when it is confirmed that there is. Wherein, the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter. It can be seen that the flame detection method of binocular images, the flame detection device, the electronic device and the computer-readable storage medium use binocular cameras, wherein the first camera is used to realize the original monitoring function, and the second parameter of the second camera is determined and adjusted according to the first parameter of the first camera and the preset corresponding relationship, and combined with the high energy characteristics of the flame itself, to adapt to the flame recognition needs in different environments. In the process of flame recognition, especially when there is a background of a white wall or an object with a color close to the flame in the monitoring area, the shutter speed and / or gain of the second camera can be adaptively adjusted according to the first parameter of the first camera, so that the image captured by the second camera becomes darker or almost invisible as a whole. However, the flame itself usually generates high heat and brightness. Even if the image becomes darker or almost invisible as a whole, the flame area will still present a bright flame shape, so that the flame can still be accurately captured and recognized against a dim background. By analyzing the image collected after such adjustment, the flame and the background can be effectively separated to reduce the missed fire report caused by the monocular camera due to the too bright background, and the false fire report caused by misjudging the red or yellow objects close to the flame color as flames. This method helps to better adapt to the flame recognition needs in different environments, reduce the difficulty of flame recognition, and improve the efficiency and reliability of fire warning. In addition, the flame detection method is simple to implement, low cost, and does not affect the original monitoring function of the camera. It is suitable for various monitoring scenarios and provides an economical and effective solution for fire safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0034] Figure 1 It is a schematic flow chart of a first embodiment of a binocular image flame detection method of the present invention;

[0035] Figure 2 It is a flow chart of a second embodiment of the binocular image flame detection method of the present invention;

[0036] Figure 3 It is a structural block diagram of a first embodiment of a binocular image flame detection device of the present invention;

[0037] Figure 4 It is a structural block diagram of a second embodiment of a binocular image flame detection device of the present invention;

[0038] Figure 5 It is a schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0041] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0042] See also Figure 1 As shown, it is a flow chart of the first embodiment of the flame detection method of binocular images of the present invention.

[0043] In this embodiment, the flame detection method of binocular images is applied to a flame detection system, and the flame detection system includes a first camera and a second camera;

[0044] The flame detection method comprises:

[0045] Step S100: obtaining a first parameter of the first camera, and determining a second parameter according to a preset corresponding relationship between the first parameter and the first camera.

[0046] Among them, the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter.

[0047] Specifically, the flame detection system includes a first camera and a second camera. The flame detection system under this configuration uses a binocular camera. A binocular camera usually includes two cameras (each camera includes a lens and an image sensor matched thereto), a lens system, a processor and a connection interface. The camera is used to capture optical signals; the lens system is responsible for focusing light and directing it to the corresponding image sensor; the processor is responsible for processing image data; and the connection interface is used to transmit the processed data to a computer or other device. These components work together to enable the binocular camera to achieve various visual tasks, such as capturing images.

[0048] Specifically, a general camera will adaptively adjust the shutter speed and gain under changes in external brightness to avoid overexposure and improve image quality. Therefore, the second camera can theoretically perform adaptive shutter speed and gain adjustment based on the brightness information collected by itself. However, when there is a flame in the monitoring area, if the background is a white wall or a close environment, or there are reflective, yellow or red objects, the second camera cannot achieve the best shutter speed and gain by adaptive adjustment alone, resulting in poor image separation effect and affecting the accuracy of flame recognition. Therefore, choosing to use the first parameter of the first camera to guide the adjustment of the second parameter of the second camera can better adapt to different flame shooting environments, ensure that the collected image can accurately separate the flame and the background, and improve the accuracy and reliability of flame recognition. This adjustment process cannot be completed by the first camera, because if the first camera adjusts the shutter speed and gain to adapt to the flame shooting environment, it will affect its own audio and video monitoring function. This adjustment process can only be completed by the second camera, and the second camera only needs to complete the shooting of the flame image on the basis of adjustment, so as to perform accurate flame recognition later. The second parameter includes the second shutter speed and / or the second gain, which can be adjusted according to the brightness change of the first camera, or according to the change of the first shutter speed and the first gain, but their change process is opposite. That is, the brighter the external brightness, the smaller the second shutter speed and the second gain; the darker the external brightness, the larger the second shutter speed and the second gain; the smaller the first shutter speed and the first gain, the smaller the second shutter speed and the second gain; the larger the first shutter speed and the first gain, the larger the second shutter speed and the second gain. Such a design can better adapt to the flame recognition needs in different environments and improve the flexibility of the system.

[0049] Step S200: adjusting the current second parameter of the second camera to the determined second parameter, and obtaining an image captured by the second camera after the adjustment.

[0050] Specifically, adjusting the second parameter is a process of optimizing the parameter settings of the second camera, with the purpose of obtaining a setting that is more suitable for capturing flame images and completing image acquisition of the flame area.

[0051] Specifically, in a bright environment, the brightness of the image will be darker than the first image captured by the first camera; while in a dim environment, the brightness of the image may be slightly darker than the first image captured by the first camera (corresponding to the situation where the brightness of the first image is already very dark). The specific setting depends on the specific use environment. The key is to achieve a detection effect in which the flame and the background can be easily separated after adjustment.

[0052] Step S300: Identify whether there is flame information based on the image, and send a prompt message if it is confirmed to exist.

[0053] Specifically, according to the image recognition, whether there is flame information, it is usually necessary to perform image separation first. Since the analyzed image is collected after the second camera adjusts the second parameter setting, the image can more effectively separate the flame from the background during the image separation process. Subsequently, the separated image is analyzed by a flame recognition algorithm to identify whether there is flame information therein. The flame recognition algorithm includes a variety of methods such as color analysis, shape analysis, texture analysis, spectral analysis, motion detection and deep learning methods. Among them, spectral color analysis is a common flame recognition method. This method uses the spectral characteristics of flame radiation, that is, the light of a specific wavelength emitted by the flame to identify the flame. Different types of flames will produce spectra of different wavelengths, so by analyzing the spectral color characteristics of flame radiation, the flame can be effectively identified. Once the flame information is confirmed to be recognized, a prompt message can be issued by sound, text, alarm, etc. to remind the user or relevant personnel to take necessary safety measures in time to reduce the potential fire hazard.

[0054] Compared with the prior art, the flame detection method of binocular images in the embodiment of the present invention uses a binocular camera, wherein the first camera is used to realize the original monitoring function, and the second parameter of the second camera is determined and adjusted according to the first parameter of the first camera and the preset corresponding relationship, and combined with the high energy characteristics of the flame itself, to adapt to the flame recognition needs in different environments. In the flame recognition process, especially when there is a background of a white wall or an object with a color close to the flame in the monitoring area, the shutter speed and / or gain of the second camera can be adaptively adjusted according to the first parameter of the first camera, so that the image collected by the second camera becomes darker or almost invisible as a whole. However, the flame itself usually generates high heat and brightness. Even if the image becomes darker or almost invisible as a whole, the flame area will still present a bright flame shape, so that the flame can still be accurately captured and recognized under the dim background. By analyzing the image collected after such adjustment, the flame and the background can be effectively separated to reduce the missed fire report caused by the monocular camera due to the too bright background, and the false fire report caused by misjudging the red or yellow object close to the color of the flame as a flame. This method helps to better adapt to the flame recognition needs in different environments, reduce the difficulty of flame recognition, and improve the efficiency and reliability of fire warning. In addition, the flame detection method is simple to implement, low cost, and does not affect the original monitoring function of the camera. It is suitable for various monitoring scenarios and provides an economical and effective solution for fire safety management.

[0055] See also Figure 2 As shown, it is a flow chart of the second embodiment of the flame detection method of binocular images of the present invention.

[0056] Compared with other embodiments of the flame detection method using binocular images, this embodiment adds a step of using a second camera to perform re-inspection on the premise that the first camera recognizes the flame.

[0057] In this embodiment, the flame detection method of binocular images is applied to a flame detection system, and the flame detection system includes a first camera and a second camera;

[0058] The flame detection method comprises:

[0059] Step S400: obtaining a first image captured by the first camera, and identifying and confirming the presence of flame information based on the first image.

[0060] Specifically, the first camera is used for regular image display and video recording, and transmits the image to the main control chip for regular flame detection. The second camera of the same specification is specifically used to transmit the image to the intelligent algorithm unit of the main control chip for flame detection. If the first camera recognizes a flame, the second camera can be started at the same time to recheck the flame information to reduce the probability of false fire alarms.

[0061] Step S100: obtaining a first parameter of the first camera, and determining a second parameter according to a preset corresponding relationship between the first parameter and the first camera.

[0062] Among them, the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter.

[0063] In some embodiments of the present application, the preset corresponding relationship includes an index table of preset first parameters and second parameters and a preset functional relationship between the first parameters and the second parameters.

[0064] Specifically, the index table includes a first parameter, a second parameter, and a one-to-one correspondence between the first parameter and the second parameter. An index table can be made according to different brightness to achieve the setting of the shutter speed and / or gain of the second camera, and further achieve a better image separation effect. An index table can be made according to different first shutter speeds to achieve the setting of the shutter speed and / or gain of the second camera, and further achieve a better image separation effect. An index table can be made according to different first shutter speeds and first gains to achieve the setting of the shutter speed and / or gain of the second camera, and further achieve a better image separation effect. The index table can also include other forms, which are not given one by one here. The functional relationship includes a positively correlated or negatively correlated functional relationship established between the first parameter and the second parameter. Positive correlation means that the values ​​of the first parameter and the second parameter increase or decrease together, that is, when one parameter increases, the other parameter also increases, and vice versa; while negative correlation means that when the values ​​of the two parameters increase, the other decreases, or when one decreases, the other increases. Among them, the positive correlation function relationship can be represented by a positive proportional function or a linear function, and the negative correlation function relationship can be represented by an inverse proportional function or a negative correlation of a linear function. Specifically, a negatively correlated functional relationship is established between the brightness and the second parameter. A positively correlated functional relationship is established between the first shutter speed and the second parameter. A positively correlated functional relationship is established between the first gain and the second parameter.

[0065] In some embodiments of the present application, both the first shutter speed and the first gain are inversely correlated with the brightness.

[0066] Specifically, the shutter speed indicates the length of time the camera shutter is open, usually in seconds. If the external brightness is bright, the shutter speed can be shortened accordingly, and if the external brightness is dark, the shutter speed can be extended accordingly, so as to ensure the image quality captured in different brightness environments. Gain refers to the degree to which the camera amplifies the image signal, which is used to enhance the brightness of the image. The brightness refers to the brightness of the outside world, that is, the light intensity in the environment, which affects the light intensity received by the camera's image sensor. When the external brightness is low, the brightness of the image can be enhanced by increasing the shutter speed and gain; on the contrary, when the external brightness is high, the shutter speed and gain can be reduced to avoid overexposure to obtain a suitable exposure effect. Therefore, the shutter speed, gain and external brightness are mutually influential and mutually adjusted. The three work together to control the clarity and exposure effect of the image.

[0067] In some embodiments of the present application, the first camera and the second camera have the same specifications.

[0068] Specifically, the first camera and the second camera have the same specifications, which can maintain the similarity and comparability of the image data. Because under the premise that the second camera recognizes the flame, the shutter speed and gain of the first camera and the second camera are different. Under this premise, if the specifications of the two cameras are different, such as the number of pixels, the type of image sensor, the lens parameters, etc., there will be obvious differences in the collected image data, making it difficult to accurately compare and analyze. By keeping the specifications of the two cameras the same, it can be ensured that the images they collect have certain similar characteristics, so that it is easier to perform subsequent analysis and processing, such as evaluating the accuracy of flame recognition of the first camera, and evaluating the accuracy of flame recognition after the second camera adjusts the second parameter. Therefore, keeping the specifications of the first camera and the second camera the same can better provide data support for subsequent analysis.

[0069] In some embodiments of the present application, when the first parameter is brightness, the second parameter is a second shutter speed;

[0070] When the first parameter includes a first shutter speed and a first gain, the second parameter is a second shutter speed.

[0071] Specifically, the brightness of the outside world is usually the parameter that users perceive most intuitively, so using it as the first parameter can more directly reflect the brightness of the image shooting environment. Shutter speed and gain are two important parameters that affect image brightness and exposure. Putting them in the first parameter can more comprehensively affect and control the exposure effect of the image collected by the second camera. In addition, the second parameter is set to the second shutter speed, so that the exposure time and brightness of the image collected by the second camera can be further affected by adjusting the shutter speed. This setting method can make it easier for users to understand and adjust system parameters, and can also improve the ease of use and reliability of the system, so as to more effectively perform image separation and flame recognition.

[0072] In some embodiments of the present application, when the brightness is 100 lux, the second shutter speed is 1 / 4000 second;

[0073] When the first shutter speed is 1 / 1000 second and the first gain is 1 times, the second shutter speed is 1 / 8000 second;

[0074] When the first shutter speed is 1 / 25 second and the first gain is greater than 1 times, the second shutter speed is 1 / 2000 second.

[0075] Specifically, when the brightness is 100 lux, the second shutter speed is set to 1 / 4000 second in order to control the exposure time through a shorter shutter speed in a brighter environment to avoid overexposure. When the first shutter speed is 1 / 1000 second and the first gain is 1 times, the second shutter speed is set to 1 / 8000 second in order to control the exposure time through a shorter shutter speed in a brighter environment to avoid overexposure. When the first shutter speed is 1 / 25 second and the first gain is greater than 1 times, the second shutter speed is set to 1 / 2000 second in order to increase the exposure time by increasing the shutter speed in a darker environment to increase the image brightness and clarity. Such settings can adjust the second shutter speed according to different shooting scenes and parameter values ​​to obtain more suitable exposure effects and image quality. Through reasonable parameter settings, the image separation effect can be further improved.

[0076] Step S200: adjusting the current second parameter of the second camera to the determined second parameter, and obtaining an image captured by the second camera after the adjustment.

[0077] Step S300: Identify whether there is flame information based on the image, and send a prompt message if it is confirmed to exist.

[0078] The flame detection method of binocular images of the embodiment of the present invention discloses a method for improving the accuracy of flame recognition by combining the flame spectrum and energy characteristics with a binocular camera. The flame detection method utilizes the high energy characteristics of flames, and by adding a second camera and increasing the adjustment parameters of the second camera, the background and flame images are separated and detected even when they are close and difficult to separate. At the same time, a large number of false alarms are avoided by mutual verification detection of different cameras of the binocular camera. The flame detection method is simple and easy to use, and can greatly reduce the false alarm rate and missed detection rate at a low cost.

[0079] The following is an embodiment of the binocular image flame detection device provided by the present invention. The embodiment of the binocular image flame detection device and the embodiment of the binocular image flame detection method described above belong to the same concept, and the details not described in detail in the embodiment of the binocular image flame detection device can refer to the embodiment of the binocular image flame detection method described above.

[0080] See also Figure 3 As shown, it is a structural block diagram of the first embodiment of the binocular image flame detection device of the present invention.

[0081] In this embodiment, a binocular image flame detection device is applied to a flame detection system, and the flame detection system includes a first camera and a second camera;

[0082] The flame detection device comprises an acquisition unit 10, an adjustment unit 20 and an identification unit 30; wherein,

[0083] The acquisition unit 10 is used to acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter.

[0084] The adjusting unit 20 is used to adjust the current second parameter of the second camera to the determined second parameter, and obtain the image captured by the second camera after the adjustment.

[0085] The identification unit 30 is used to identify whether there is flame information according to the image, and send a prompt message when it is confirmed that there is flame information.

[0086] The binocular image flame detection device of the embodiment of the present invention provides an efficient and easy-to-use binocular device to achieve separate detection of flames and similar backgrounds, and eliminate false alarms of reflective objects or similar objects with colors close to flames. Specifically, because the white wall or reflected forehead or red cloth around the flame are not luminous bodies, they will appear dark or completely invisible at a certain shutter speed and / or gain; but the flame can still present a bright form of flame at this shutter speed and / or gain. By analyzing such an image, the recognition accuracy of the flame can be greatly improved, and while reducing false alarms, it can also reduce missed alarms due to effective background stripping.

[0087] See also Figure 4 As shown, it is a structural block diagram of the second embodiment of the binocular image flame detection device of the present invention.

[0088] Compared with other embodiments of the binocular image flame detection device, this embodiment adds a starting unit 40.

[0089] In this embodiment, the flame detection device of binocular image is applied to a flame detection system, and the flame detection system includes a first camera and a second camera;

[0090] The flame detection device comprises an acquisition unit 10, an adjustment unit 20 and an identification unit 30; wherein,

[0091] The acquisition unit 10 is used to acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter;

[0092] The adjusting unit 20 is used to adjust the current second parameter of the second camera to the determined second parameter, and obtain the image captured by the second camera after the adjustment;

[0093] The identification unit 30 is used to identify whether there is flame information according to the image, and send a prompt message when it is confirmed that there is flame information.

[0094] The flame detection device further includes a starting unit 40, and the starting unit 40 is used to obtain a first image captured by the first camera, and recognize and confirm the existence of flame information according to the first image.

[0095] The binocular image flame detection device of the embodiment of the present invention adopts a binocular camera, and matches the adaptive shutter speed and / or gain of the second parameter of the second camera according to the first parameter of the first camera; (for example, if the external brightness collected by the first camera is about 100 lux, the shutter speed of the second camera is set to 1 / 4000 second). A fire or flame with impurities will appear mainly red and yellow, and then release a large amount of energy. When the matched second camera is used to collect images, when the shutter speed is short enough, the clear outline and color of the flame can be displayed, and the surrounding similar environment will become a gray background to achieve complete separation of the background and the flame. After the flame recognition system adds a second camera, the monitoring properties of the first camera are not affected, and the normal audio and video monitoring function is still exercised. If the first camera recognizes the flame, the second camera will perform a re-inspection at the same time, which can reduce false alarms of fire. If the first camera does not recognize the flame, and the second camera recognizes the flame alone, it can reduce the situation of missed fire reports.

[0096] The binocular image flame detection device of the embodiment of the present invention is very easy to implement, because a large number of chips of flame detection systems currently support binocular detection, and image processing technology is very mature. In addition, the flame detection device utilizes the spectral characteristics and energy characteristics of the flame, and relies on the method of adjusting the shutter speed and / or gain of one of the cameras to directly separate the background and the flame, while not changing the original image monitoring properties of the other camera, which not only reduces many false alarms of the monocular camera, but also avoids the omission of fires with similar image backgrounds. This is a very economical and practical method that combines the characteristics of the camera and the energy spectrum characteristics of the flame itself, and improves the accuracy and sensitivity of the entire image flame recognition through simple means.

[0097] The following is an embodiment of the electronic device provided by the present invention. The embodiment of the electronic device and the embodiment of the flame detection method and flame detection device of the above-mentioned binocular image belong to the same concept, and the details not described in detail in the embodiment of the electronic device can refer to the embodiment of the flame detection method and flame detection device of the above-mentioned binocular image.

[0098] See also Figure 5 As shown, it is a schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention.

[0099] In this embodiment, an electronic device includes:

[0100] Memory 1005, used to store program instructions; and

[0101] The processor 1001 is used to execute the program instructions to implement the steps of the binocular image flame detection method as described above.

[0102] The electronic device of the embodiment of the present invention can be a computing device such as a desktop computer, a notebook, a palm computer, and a server. Figure 5 As shown, the electronic device may include: a processor 1001 (e.g., a CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit, such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0103] Those skilled in the art will understand that Figure 5 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0104] like Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and a computer program.

[0105] exist Figure 5 In the electronic device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the computer program stored in the memory 1005. When the computer program is called and executed by the processor 1001, the steps of the above-mentioned binocular image flame detection method are implemented.

[0106] The following is an embodiment of the computer-readable storage medium provided by the present invention. The embodiment of the computer-readable storage medium and the embodiment of the above-mentioned binocular image flame detection method, flame detection device and electronic device belong to the same concept, and the details not described in detail in the embodiment of the computer-readable storage medium can refer to the above-mentioned binocular image flame detection method, flame detection device and electronic device.

[0107] In this embodiment, a computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the binocular image flame detection method described above are implemented.

[0108] Since the electronic device and computer-readable storage medium of the present invention can both implement the steps of the above-mentioned binocular image flame detection method, they at least have all the beneficial effects brought about by the technical solutions of the above-mentioned binocular image flame detection method step embodiments, which will not be described one by one here.

[0109] The above description is only a partial or preferred embodiment of the present invention. Neither the text nor the drawings can limit the scope of protection of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the overall concept of the present invention, or direct / indirect application in other related technical fields are included in the scope of protection of the present invention.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0111] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A flame detection method using binocular images, characterized in that: Applied to a flame detection system, the flame detection system comprising a first camera and a second camera; The flame detection method comprises: Acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed, and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter; Adjusting the current second parameter of the second camera to the determined second parameter, and obtaining an image captured by the second camera after the adjustment; It is identified whether there is flame information based on the image, and a prompt message is issued when it is confirmed that there is flame information.

2. The flame detection method of binocular image according to claim 1, characterized in that: The preset corresponding relationship includes an index table of preset first parameters and second parameters and a preset functional relationship between the first parameters and the second parameters.

3. The flame detection method of binocular image according to claim 1, characterized in that: Before obtaining the first parameter of the first camera, the method further includes: obtaining a first image captured by the first camera, and identifying and confirming the existence of flame information according to the first image.

4. The flame detection method of binocular image according to claim 3, characterized in that: The first shutter speed and the first gain are both inversely correlated with the brightness.

5. The flame detection method of binocular image according to claim 1, characterized in that: The first camera and the second camera have the same specifications.

6. The flame detection method of binocular image according to claim 1, characterized in that: When the first parameter is brightness, the second parameter is a second shutter speed; When the first parameter includes a first shutter speed and a first gain, the second parameter is a second shutter speed.

7. A binocular image flame detection device, characterized in that: Applied to a flame detection system, the flame detection system comprising a first camera and a second camera; The flame detection device comprises an acquisition unit, an adjustment unit and an identification unit; wherein, The acquisition unit is used to acquire a first parameter of the first camera, and determine a second parameter according to a preset corresponding relationship between the first parameter; wherein the first parameter includes at least one of brightness, a first shutter speed and a first gain, and the second parameter includes a second shutter speed and / or a second gain; in the preset corresponding relationship, the brightness is inversely correlated with the second parameter, and the first shutter speed and the first gain are both positively correlated with the second parameter; The adjusting unit is used to adjust the current second parameter of the second camera to the determined second parameter, and obtain the image captured by the second camera after the adjustment; The identification unit is used to identify whether there is flame information based on the image, and send a prompt message when it is confirmed that there is flame information.

8. The binocular image flame detection device according to claim 7, characterized in that: The flame detection device further includes a starting unit, which is used to obtain a first image captured by the first camera, and to identify and confirm the existence of flame information based on the first image.

9. An electronic device, characterized in that: include: A memory for storing program instructions; as well as A processor is used to execute the program instructions to implement the steps of the binocular image flame detection method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the binocular image flame detection method according to any one of claims 1 to 6 are implemented.

Images