Intelligent Firefighting System and Its Control Method, Processor and Processing Device

Abstract

An embodiment of the present invention provides a control method, a processor, a processing device, an intelligent fire-fighting system, and a machine-readable storage medium for an intelligent fire-fighting system. The control method includes: acquiring an image of the monitored environment collected by a monocular camera; when it is detected that the image contains a fire source, determining the coordinates of the flame center point of the fire source in the image according to the image; determining the actual coordinates of the flame center point according to the coordinates; determining the horizontal distance and the horizontal deflection angle between the fire source and the fire-fighting cannon according to the actual coordinates; determining the elevation angle required for the fire-fighting cannon to work according to the horizontal distance value; and controlling the fire-fighting cannon to perform a fire-extinguishing operation according to the horizontal deflection angle and the elevation angle. Through the above technical solution, the precise detection of the flame can be realized by using the deep learning object detection algorithm, and rapid response can be achieved. Only by using the monocular vision positioning method can the actual coordinates of the fire source be well obtained, so as to obtain the required horizontal rotation angle and vertical rotation angle for the fire-fighting cannon to work and complete the fire extinguishing.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire protection, and specifically relates to a control method, a processor, a processing device, an intelligent fire protection system, and a machine-readable storage medium for an intelligent fire protection system. Background Art

[0002] At present, in the development of automatic fire protection systems at home and abroad, the focus of research in various countries is on the rapid detection and response to fires, the accurate positioning of the fire source to achieve precise fire extinguishing, and the reliability and stability of the fire extinguishing system. Based on the above requirements, various types of fire protection systems have been designed, and the development of fire protection systems requires the integration of various technologies such as computer vision and fluid mechanics. Existing automatic fire extinguishing systems are characterized by large flow rates, long ranges, and intelligence.

[0003] Currently, the fire detection technologies used at home and abroad mainly include video detection technology based on images and scanning infrared flame detection technology, etc. These technologies have their own advantages and disadvantages, and the main problems are as follows:

[0004] 1. The flame detection technology based on image processing requires a large number of computational operations on color images, which places high requirements on the processing power of the computer. It is difficult to achieve real-time performance when the hardware conditions are poor.

[0005] 2. The scanning infrared flame detection system detects the direction of the ignition point by scanning in the horizontal and vertical directions. This method requires a long detection time, cannot give an early warning of the fire in time, and it is difficult to accurately detect small flames in the initial stage of the fire. Summary of the Invention

[0006] The purpose of the embodiments of the present invention is to provide a control method, a processor, a processing device, an intelligent fire protection system, and a machine-readable storage medium for an intelligent fire protection system.

[0007] To achieve the above purpose, in the first aspect of the present invention, a control method for an intelligent fire protection system is provided. The intelligent fire protection system includes a monocular camera, a processor, and a fire cannon. The monocular camera is arranged above the monitored environment. The control method includes:

[0008] Obtain an image of the monitored environment collected by the monocular camera;

[0009] In the case of detecting that the image contains a fire source, determine the coordinates of the flame center point of the fire source in the image according to the image;

[0010] Determine the actual coordinates of the flame center point in the actual space according to the coordinates, where the actual coordinates are the actual coordinates corresponding to the flame center point in the monitored image in the monitored environment;

[0011] Determine the horizontal distance between the fire source and the fire monitor according to the actual coordinates and the horizontal deflection angle required for the operation of the fire monitor;

[0012] Determine the elevation angle required for the operation of the fire monitor according to the horizontal distance; and

[0013] Control the fire monitor to perform fire extinguishing operations according to the horizontal deflection angle and the elevation angle.

[0014] In an embodiment of the present invention, when it is detected that the image contains a fire source, determining the coordinates of the flame center point of the fire source in the image according to the image includes:

[0015] Input the image into an object detection model based on deep learning;

[0016] When the image contains a fire source, the object detection model gives the position box of the fire source in the image;

[0017] Determine the coordinates of the center point of the position box relative to the reference point of the image as the coordinates of the flame center point of the fire source in the image.

[0018] In an embodiment of the present invention, the reference point is the upper left vertex of the image.

[0019] In an embodiment of the present invention, determining the actual coordinates of the flame center point in the actual space according to the coordinates includes:

[0020] Determine the actual coordinates according to the following formula:

[0021]

[0022] where, (x0, y0) are the coordinates of the flame center point in the image, (x1, y1) are the actual coordinates, D min is the horizontal distance from the near end of the field of view of the monocular camera to the monocular camera, D max is the horizontal distance from the far end of the field of view of the monocular camera to the monocular camera, B0 is half of the width of the far end of the field of view, h is the pixel height of the image, and w is the pixel width of the image.

[0023] In an embodiment of the present invention, determining the horizontal distance between the fire source and the fire monitor and the horizontal deflection angle required for the operation of the fire monitor according to the actual coordinates includes:

[0024] According to Determine the horizontal deflection angle, where, is the horizontal deflection angle; and

[0025] According to Determine the horizontal distance, where X is the horizontal distance.

[0026] In an embodiment of the present invention, determining the elevation angle required for the operation of the fire monitor according to the horizontal distance value includes:

[0027] The pitch angle is determined according to the following formula:

[0028]

[0029] where H is the installation height of the fire monitor, g is the acceleration due to gravity, v0 is the initial jet velocity of the fire monitor, and γ is the pitch angle.

[0030] A second aspect of the present invention provides a processor configured to execute the above control method for an intelligent fire protection system.

[0031] A third aspect of the present invention provides an intelligent fire protection system, comprising:

[0032] A monocular camera configured to collect images of the monitored environment;

[0033] A fire monitor for performing fire extinguishing operations; and

[0034] The above-mentioned processor.

[0035] In an embodiment of the present invention, the fire monitor is installed directly below the monocular camera, the axis of the fire monitor nozzle is coplanar with the optical axis of the monocular camera, and the initial horizontal rotation angle of the fire monitor is zero.

[0036] A fourth aspect of the present invention provides a processing device applied to an intelligent fire protection system. The intelligent fire protection system includes a monocular camera and a fire monitor. The monocular camera is arranged above the monitored environment. The processing device includes:

[0037] A flame detection module configured to obtain the images of the monitored environment collected by the monocular camera, and in the case of detecting that the image contains a fire source, determine the coordinates of the flame center point of the fire source in the image according to the image;

[0038] A spatial positioning module configured to receive the coordinates and determine the actual coordinates of the flame center point in the actual space according to the coordinates, where the actual coordinates are the actual coordinates of the flame center point projected onto the horizontal plane of the monitored environment;

[0039] A parameter calculation module configured to determine the horizontal distance between the fire source and the fire monitor and the required horizontal deflection angle for the operation of the fire monitor according to the actual coordinates; and

[0040] A jet trajectory calculation module configured to determine the required pitch angle for the operation of the fire monitor according to the horizontal distance value, and control the fire monitor to perform fire extinguishing operations according to the horizontal deflection angle and the pitch angle.

[0041] A fifth aspect of the present invention provides a machine-readable storage medium, on which instructions are stored, and when the instructions are executed by a processor, the processor implements the above control method for an intelligent fire protection system.

[0042] Through the above technical solution, the precise detection of flames can be achieved using a deep learning object detection algorithm, enabling fast response. By only using a monocular vision positioning method, the actual coordinates of the fire source can be well obtained, and based on this, the horizontal and vertical rotation angles required for the operation of the fire fighting cannon can be obtained to complete fire extinguishing.

[0043] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. Brief Description of the Drawings

[0044] The drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementation, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0045] Figure 1 Schematically shows an example flowchart of a control method for an intelligent fire fighting system according to an embodiment of the present invention;

[0046] Figure 2 Schematically shows a structural block diagram of a fire fighting system according to an embodiment of the present invention;

[0047] Figure 3 Schematically shows a schematic side view of monocular vision positioning used in an embodiment of the present invention; and

[0048] Figure 4 Schematically shows a schematic top view of monocular vision positioning used in an embodiment of the present invention.

[0049] Description of the Reference Numerals in the Drawings

[0050] 100 Monocular camera 200 Processor

[0051] 201 Flame detection module 202 Spatial positioning module

[0052] 203 Parameter calculation module 204 Jet trajectory calculation module

[0053] 300 Fire fighting cannon Detailed Description of the Specific Embodiments

[0054] The following will describe in detail the specific embodiments of the embodiments of the present invention with reference to the drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the present invention and are not used to limit the embodiments of the present invention.

[0055] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) in the embodiments of this application, the directional indications are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture (as shown in the attached drawings). If the specific posture changes, the directional indications will also change accordingly.

[0056] If there are descriptions such as "first", "second", etc. in the embodiments of this application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0057] Figure 1 Schematically shows an example flowchart of a control method for an intelligent fire protection system according to an embodiment of the present invention; Figure 2 Schematically shows a structural block diagram of a fire protection system according to an embodiment of the present invention.

[0058] As Figure 1 shown and referring to Figure 2 , in an embodiment of the present invention, a control method for an intelligent fire protection system is provided. The intelligent fire protection system may include a monocular camera 100, a processor 200, and a fire cannon 300. In an embodiment of the present invention, monocular vision positioning technology can be adopted to reduce the use of hardware (such as cameras) and possibly reduce the computing power requirements of the processor 200 when the positioning requirements are met. The resolution of the monocular camera 100 can be increased to make up for the inherent disadvantages of monocular vision positioning technology compared to binocular or multiocular vision positioning technology. The monocular camera 100 can be installed above the monitored environment and take pictures of the monitored environment downward at a certain downward viewing angle. For the convenience of subsequent data processing and calculation, the fire cannon 300 can be installed directly below the monocular camera 100. The initial pitch angle of the fire cannon 300 can be 0°, that is, horizontally installed, and the nozzle axis of the fire cannon 300 can be coplanar with the optical axis of the monocular camera 100, that is, the initial horizontal rotation angle of the fire cannon 300 is 0°.

[0059] The control method may include the following steps.

[0060] In step S101, an image of the monitored environment collected by the monocular camera 100 is obtained.

[0061] In step S102, when it is detected that the image contains a fire source, the coordinates of the flame center point of the fire source in the image are determined according to the image.

[0062] Specifically, for example, after the processor 200 obtains the image of the monitored environment collected by the monocular camera 100, it can detect whether there is a fire in the monitored environment according to the image, that is, detect whether there is a fire source. In one example, the processor 200 may include a flame detection module 201 or have a flame detection function (algorithm). In one example, the flame detection module 201 may be an object detection model of deep learning, such as an object detection model based on YOLOv4 applied in the field of computer vision. A large amount of data sets can be used to train the model, continuously adjust the parameters to make the model effect reach the optimal, and use the trained model for fire source (flame) detection. For example, a large number of picture data can be prepared as data sets, and the data sets are divided into training sets, test sets and validation sets according to a certain proportion, and all data include annotation files. During training, the data is trained in batches of a certain size and iterated for multiple rounds. The training method of the model can be known to those skilled in the art and will not be elaborated herein.

[0063] In this embodiment, the object detection model can preprocess the image, extract relevant feature information from the image, and comprehensively judge whether there is a fire source (flame) in the image based on the image information at different scales. If there is a fire source (flame), the object detection model can use a position box (such as a rectangular box) to mark the position of the fire source (flame) in the image. In this case, the object detection model can also calculate the coordinates (values) of the center point of the position box relative to the reference point in the image, and use this as the coordinates of the flame center point in the image. In one example, the reference point may include any one of the four vertices of the image. Preferably, the reference point may be the upper left vertex of the image.

[0064] In step S103, the actual coordinates of the flame center point in the actual space are determined according to the coordinates, where the actual coordinates are the actual coordinates corresponding to the flame center point in the monitored image in the monitored environment.

[0065] Specifically, the processor 200 may include a spatial positioning module 202 or have a spatial positioning function (algorithm). Figure 3 Schematically shows a schematic side view of monocular vision positioning used in an embodiment of the present invention. Figure 4 Schematically shows a schematic top view of monocular vision positioning used in an embodiment of the present invention. Refer to Figure 3 and Figure 4 , the monocular camera 100 monitors the on-site environment downward at a certain downward viewing angle. In Figure 3 , H represents the installation height of the monocular camera 100, AC represents the field of view range of the monocular camera 100, Dmin represents the actual horizontal distance from the near end of the field of view of the monocular camera 100 (the bottom edge, i.e., the near end where the field of view range of the monocular camera 100 intersects the horizontal plane of the monitored environment) to the monocular camera 100 (i.e., the distance between the near end of the field of view projected onto the horizontal plane of the monitored environment and the monocular camera 100), D max represents the actual horizontal distance from the far end of the field of view of the monocular camera 100 (the top edge, i.e., the far end where the field of view range of the monocular camera 100 intersects the horizontal plane of the monitored environment) to the monocular camera 100 (i.e., the distance between the far end of the field of view projected onto the horizontal plane of the monitored environment and the monocular camera 100), that is, OC. Here, the near end and the far end are defined relative to the position of the monocular camera 100. α represents the angle between the lower edge of the viewing angle of the monocular camera 100 and the vertical direction (i.e., the angle between the line connecting the near end and the lens of the monocular camera 100 and the vertical direction), and θ represents the angle between the upper edge and the lower edge of the viewing angle of the monocular camera 100 (i.e., the angle between the line connecting the far end and the monocular camera 100 and the line connecting the near end and the far end to the monocular camera 100). B is the monitored target point (i.e., the center point of the fire source), and Δθ represents the angle between the target point and the lower edge of the viewing angle of the monocular camera 100 (i.e., the angle between the line connecting the target point and the monocular camera 100 and the line connecting the lower edge and the monocular camera 100).

[0066] In Figure 4 , β represents the horizontal viewing angle of the monocular camera 100 (i.e., the horizontal field of view angle), h represents the height of the image pixels, and w represents the width of the image pixels. (x0, y0) represents the coordinate values of the target point (the center point of the fire source) in the image, and (x1, y1) represents the coordinate values of the target point (the center point of the fire source) in the actual space. B0 represents half of the width at the farthest point (i.e., the far end edge) of the viewing angle of the monocular camera 100, and B1 represents the distance in the x-axis direction at the position where the target point (the center point of the fire source) is located. Among all the parameters, the installation height of the monocular camera 100 is known, the resolution of the image is known, and B0, D min 、D max can be obtained by measurement.

[0067] Then the y1 coordinate of the center point of the fire source in the actual space is determined by the following formula

[0068]

[0069] The x1 coordinate of the center point of the fire source in the actual space is determined by the following formula

[0070]

[0071] Thus, the actual coordinates (x1, y1) of the center point of the fire source (flame) can be obtained.

[0072] In step S104, the horizontal distance between the fire source and the fire monitor 300 and the horizontal deflection angle required for the operation of the fire monitor 300 are determined according to the actual coordinates.

[0073] Specifically, the processor 200 may include a parameter calculation module 203 or have a parameter calculation function (algorithm). According to the actual coordinates (x1, y1) of the center point of the fire source obtained by the spatial positioning module 202 (function), the horizontal deflection angle of the fire monitor 300 can be determined by the following formula,

[0074]

[0075] where, represents the horizontal deflection angle.

[0076] According to the actual coordinates (x1, y1) of the center point of the fire source obtained by the spatial positioning module 202 (function), the horizontal distance between the fire source and the fire monitor 300 (i.e., the range of the fire monitor 300) can be determined by the following formula,

[0077]

[0078] where X is the above-mentioned horizontal distance.

[0079] In step S105, the elevation angle required for the operation of the fire monitor 300 is determined according to the horizontal distance value.

[0080] Specifically, the processor 200 may include a jet trajectory calculation module 204 or have a jet trajectory calculation function (algorithm). The jet trajectory calculation module 204 or the one with the jet trajectory calculation function (algorithm) can calculate the elevation angle required for the operation of the fire monitor 300 according to the horizontal distance, specifically:

[0081] After obtaining the horizontal distance between the fire source and the fire monitor 300, the initial jet velocity at the nozzle of the fire monitor 300 and the range value can be substituted into the relationship formula between the range and the elevation angle, and the required elevation angle γ can be deduced. The relationship formula between the range and the elevation angle can be determined by the following formula,

[0082]

[0083] In the formula, H represents the installation height of the fire monitor 300, g represents the acceleration due to gravity, v0 represents the initial jet velocity, and X represents the range of the fire monitor 300 (i.e., the horizontal distance).

[0084] In step S106, the fire monitor 300 is controlled to perform a fire extinguishing operation according to the horizontal deflection angle and the elevation angle.

[0085] Specifically, for example, after determining the horizontal deflection angle and the pitch angle, the processor 200 can send an instruction including the determined horizontal deflection angle and pitch angle to the fire cannon 300 to drive the fire cannon 300 to act according to the horizontal deflection angle and pitch angle for fire extinguishing operations (tasks).

[0086] In an embodiment of the present invention, a processor 200 is provided, which is configured to execute the control method for an intelligent fire protection system in any of the above embodiments.

[0087] Specifically, the processor 200 can be configured to:

[0088] Obtain an image of the monitored environment collected by the monocular camera 100;

[0089] In the case where a fire source is detected in the image, determine the coordinates of the flame center point of the fire source in the image according to the image;

[0090] Determine the actual coordinates of the flame center point in the actual space according to the coordinates, where the actual coordinates are the actual coordinates corresponding to the flame center point in the monitored image in the monitored environment;

[0091] Determine the horizontal distance between the fire source and the fire cannon 300 and the horizontal deflection angle required for the operation of the fire cannon 300 according to the actual coordinates;

[0092] Determine the pitch angle required for the operation of the fire cannon 300 according to the horizontal distance value; and

[0093] Control the fire cannon 300 to perform fire extinguishing operations according to the horizontal deflection angle and the pitch angle.

[0094] Examples of the processor 200 may include, but are not limited to, a single-chip microcomputer, a microprocessor, a field programmable gate array (FPGA), a programmable logic controller (PLC), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a state machine, etc.

[0095] Reference Figure 2 In an embodiment of the present invention, an intelligent fire protection system is provided, which may include:

[0096] A monocular camera 100, configured to collect an image of the monitored environment;

[0097] A fire cannon 300, used for fire extinguishing operations; and

[0098] The processor 200 is configured to execute the control method for the intelligent fire protection system according to any of the above embodiments.

[0099] The fire monitor 300 can be a device known to those skilled in the art, which may include a slewing device and a spraying device, etc. The spraying device can be used to spray a fire extinguishing medium, such as water or foam, and the slewing device is used to drive the spraying device to rotate, such as horizontal rotation and / or pitching rotation.

[0100] In an embodiment of the present invention, the fire monitor 300 can be installed directly below the monocular camera 100, and the initial pitching angle of the installation of the fire monitor 300 is 0, that is, it is installed horizontally. The axis of the nozzle of the fire monitor 300 and the optical axis of the monocular camera 100 are coplanar, and the initial horizontal rotation angle of the fire monitor 300 is zero.

[0101] In an embodiment of the present invention, a processing device is provided, which is applied to an intelligent fire protection system. The intelligent fire protection system includes a monocular camera 100 and a fire monitor 300. The processing device includes:

[0102] A flame detection module 201, configured to obtain an image of the monitored environment collected by the monocular camera 100, and in the case of detecting that the image contains a fire source, determine the coordinates of the flame center point of the fire source in the image according to the image;

[0103] A spatial positioning module 202, configured to receive the coordinates and determine the actual coordinates of the flame center point in the actual space according to the coordinates, where the actual coordinates are the actual coordinates of the flame center point projected onto the horizontal plane of the monitored environment;

[0104] A parameter calculation module 203, configured to determine the horizontal distance between the fire source and the fire monitor 300 and the horizontal deflection angle required for the operation of the fire monitor 300 according to the actual coordinates; and

[0105] A jet trajectory calculation module 204, configured to determine the pitching angle required for the operation of the fire monitor 300 according to the horizontal distance value, and control the fire monitor 300 to perform a fire extinguishing operation according to the horizontal deflection angle and the pitching angle.

[0106] In an embodiment of the present invention, a machine-readable storage medium is provided, and instructions are stored on the machine-readable storage medium. When the instructions are executed by the processor 200, the processor 200 implements the control method for the intelligent fire protection system according to any of the above embodiments.

[0107] The solution provided by the embodiments of the present invention can use deep learning object detection algorithms to achieve precise detection of flames, enabling rapid response. By using only a monocular vision positioning method, the actual coordinates of the fire source can be well obtained, and thus the horizontal and vertical rotation angles required for the operation of the fire fighting cannon can be obtained to complete fire extinguishing. Compared with binocular or multiocular vision positioning solutions, the use of hardware can be reduced and the computing power requirements can be lowered on the premise of meeting the positioning accuracy requirements.

[0108] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take 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 code.

[0109] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0110] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0112] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0113] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0114] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0115] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0116] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A control method for an intelligent fire protection system, characterized in that The intelligent fire-fighting system includes a monocular camera, a processor, and a fire cannon. The monocular camera is arranged above the monitored environment. The control method includes: Obtaining an image of the monitored environment collected by the monocular camera; When it is detected that the image contains a fire source, determining the coordinates of the flame center point of the fire source in the image according to the image; Determining the actual coordinates of the flame center point in the actual space according to the coordinates in the image, where the actual coordinates are the actual coordinates corresponding to the flame center point in the image in the monitored environment; Determining the horizontal distance between the fire source and the fire cannon and the horizontal deflection angle required for the operation of the fire cannon according to the actual coordinates; Determining the elevation angle required for the operation of the fire cannon according to the horizontal distance; Controlling the fire cannon to perform a fire extinguishing operation according to the horizontal deflection angle and the elevation angle; Wherein, the determining the actual coordinates of the flame center point in the actual space according to the coordinates in the image includes: determining the actual coordinates according to the following formula: Among them, is the coordinate of the center point of the flame in the image, is the actual coordinate, is the horizontal distance from the near end of the field of view of the monocular camera to the monocular camera, is the horizontal distance from the far end of the field of view of the monocular camera to the monocular camera, is half of the width of the far end of the field of view, h is the pixel height of the image, w is the pixel width of the image, and H is the installation height of the monocular camera.

2. The control method according to claim 1, wherein When it is detected that the image contains a fire source, determining the coordinates of the flame center point of the fire source in the image according to the image includes: Inputting the image into an object detection model based on deep learning; When the image contains the fire source, the object detection model gives the position box of the fire source in the image; Determining the coordinates of the center point of the position box relative to the reference point of the image as the coordinates of the flame center point of the fire source in the image.

3. The control method according to claim 2, wherein The reference point is the upper left vertex of the image.

4. The control method according to claim 1, wherein The determining the horizontal distance between the fire source and the fire cannon and the horizontal deflection angle required for the operation of the fire cannon according to the actual coordinates includes: According to determine the horizontal deflection angle, where is the horizontal deflection angle; and According to to determine the horizontal distance, where X is the horizontal distance.

5. The control method according to claim 4, wherein The determining the elevation angle required for the operation of the fire cannon according to the horizontal distance includes: Determining the elevation angle according to the following formula: Wherein, is the installation height of the fire monitor, is the acceleration of gravity, is the initial jet velocity of the fire monitor, is the elevation angle.

6. A processor, characterized in that, Configured to execute the control method for an intelligent fire-fighting system according to any one of claims 1 to 5.

7. An intelligent fire protection system, characterized in that, Including: A monocular camera configured to collect an image of the monitored environment; A fire cannon for performing a fire extinguishing operation; And The processor according to claim 6.

8. The intelligent fire protection system according to claim 7, characterized in that, The fire cannon is installed directly below the monocular camera. The axis of the fire cannon nozzle is coplanar with the optical axis of the monocular camera, and the initial horizontal rotation angle of the fire cannon is zero.

9. A processing device, characterized in that, Applied to an intelligent fire-fighting system, the intelligent fire-fighting system includes a monocular camera and a fire cannon. The monocular camera is arranged above the monitored environment. The processing device includes: A flame detection module configured to obtain an image of the monitored environment collected by the monocular camera, and when it is detected that the image contains a fire source, determining the coordinates of the flame center point of the fire source in the image according to the image; A space positioning module configured to receive the coordinates in the image and determine the actual coordinates of the flame center point in the actual space according to the coordinates in the image, where the actual coordinates are the actual coordinates of the flame center point projected onto the horizontal plane of the monitored environment; A parameter calculation module, configured to determine a horizontal distance between the fire source and the fire monitor according to the actual coordinates, and a horizontal deflection angle required for the operation of the fire monitor; and A jet trajectory calculation module, configured to determine a pitch angle required for the operation of the fire monitor according to the horizontal distance, and control the fire monitor to perform a fire extinguishing operation according to the horizontal deflection angle and the pitch angle; wherein, the spatial positioning module is further configured to determine the actual coordinates according to the following formula: Among them, is the coordinate of the center point of the flame in the image, is the actual coordinate, is the horizontal distance from the near end of the field of view of the monocular camera to the monocular camera, is the horizontal distance from the far end of the field of view of the monocular camera to the monocular camera, is half of the width of the far end of the field of view, h is the pixel height of the image, w is the pixel width of the image, and H is the installation height of the monocular camera.

10. A machine-readable storage medium, characterized in that, Instructions are stored on the machine-readable storage medium, and when the instructions are executed by a processor, the processor implements the control method for an intelligent fire protection system according to any one of claims 1 to 5.

Images