Stereo garage security and protection management and control system and method based on fuzzy control

Abstract

The invention provides a stereo garage security management and control system and method based on fuzzy control, and belongs to the technical field of security system monitoring. Comprising a plurality of cameras, a router, a host and a fuzzy controller, the number of the cameras is consistent with the number of garages in the stereo garage, each camera shoots RGB images according to a preset shooting interval, and the shot RGB images are uploaded to the host through the router; the host is used for performing color cast factor difference prediction on the received RGB image and sending a prediction result to the fuzzy controller; and the fuzzy controller is used for outputting a corresponding adjustment value according to the set fuzzy control rule and controlling security and protection equipment in the stereo garage. Whether a fire disaster exists in the stereo garage or not can be effectively monitored based on the security and protection management and control system, meanwhile, fire extinguishing can be conducted in different control modes according to the actual situation of the fire disaster, and resource waste is reduced while effective fire extinguishing is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of security system monitoring, and in particular relates to a fuzzy control-based stereo garage security management and control system and method. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As electric vehicles have gradually become an important part of urban transportation, the number of charging piles, as "energy supply stations" for electric vehicles, has also increased rapidly. Especially in smart multi-story parking garages, charging piles are an indispensable infrastructure.

[0004] However, while providing charging services, charging piles also face certain fire risks. Since charging piles need to withstand high voltage and high current, once the equipment fails or is improperly operated, it may cause a fire. In addition, electric vehicle batteries are also prone to high temperatures during the charging process. If the temperature is too high or the battery itself has defects, it may also cause a fire. These fires will not only cause property losses, but may also threaten the safety of people's lives. Therefore, it is extremely necessary to design a security monitoring system that can determine whether a fire has occurred in a stereo garage.

[0005] At present, there are some monitoring systems or methods for the safety protection of stereo garages in the prior art, but these systems or methods still have some technical problems, such as: (1) Existing security control systems generally use some sensors to monitor whether there is smoke or temperature near the charging piles in the stereo garage to determine whether a fire has occurred. However, when the initial fire is small, the smoke or temperature will not change significantly; therefore, this method has a delay and cannot accurately and timely monitor the occurrence of fire.

[0006] (2) Existing security control systems directly extinguish fires when they detect a fire, but are unable to control the extent of the fire, which easily results in a waste of fire-fighting resources. At the same time, when such systems detect a fire, they need to wait until security personnel arrive at the designated location before they can extinguish the fire, resulting in low efficiency and safety.

[0007] (3) Although some existing fire extinguishing monitoring systems have embedded image processing methods to solve the problem of immediacy, they only perform feature analysis on a single image type when analyzing images, but lack attention to image details, resulting in weak image features. Therefore, the actual changes in images over a continuous period of time are not clearly reflected, resulting in unsatisfactory fire monitoring results. Summary of the invention

[0008] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a security management and control system and method for a three-dimensional parking garage based on fuzzy control, which can effectively monitor whether there is a fire in the three-dimensional parking garage based on the security management and control system, and can adopt different control methods to extinguish the fire according to the actual situation of the fire, thereby ensuring effective fire extinguishing while reducing resource waste.

[0009] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: A first aspect of the present invention provides a stereo garage security management and control system based on fuzzy control.

[0010] A fuzzy control-based stereo garage security management and control system, comprising: a plurality of cameras and a router, a host and a fuzzy controller connected in sequence; The number of cameras is consistent with the number of garages in the three-dimensional garage, that is, each camera corresponds to a garage; each camera shoots RGB images according to a preset shooting interval, and uploads the shot RGB images to the host through a router; The host is used to predict the color cast factor difference of the received RGB image, and send the color cast factor difference prediction result to the fuzzy controller; The fuzzy controller is used to output corresponding adjustment values ​​according to the set fuzzy control rules to control the security equipment in the three-dimensional parking garage.

[0011] Furthermore, a charging pile is arranged in front of each garage, and each camera is arranged in the upper front of the corresponding garage, so that the shooting range of each camera covers the garage corresponding to the camera and the charging pile corresponding to the garage.

[0012] Furthermore, each camera is configured with a separate serial number. If the number of cameras is s, the serial numbers configured for the cameras are camera 1, camera 2, ..., camera s; the garages and charging piles in the multi-story parking garage are numbered in the same configuration, and the configured serial numbers are consistent with the camera serial numbers.

[0013] Furthermore, the host includes an image acquisition unit, an image enhancement unit and a color cast factor difference prediction unit; wherein the image acquisition unit is used to receive an RGB image taken by a camera, the image enhancement unit is used to enhance the image effect of the received RGB image, and the color cast factor difference prediction unit is used to predict the color cast factor difference of the RGB image after image enhancement.

[0014] Furthermore, the security equipment is an electrically driven fire extinguisher, and the electrically driven fire extinguisher is provided with an electric valve, and the electric valve is connected to a dry powder tube on the electrically driven fire extinguisher.

[0015] A second aspect of the present invention provides a security management and control method for a stereo garage based on fuzzy control.

[0016] A fuzzy control-based stereo garage security management and control method, comprising: Obtain two adjacent frames of RGB images to be detected; Perform HSI space conversion on two adjacent RGB images, use homomorphic filtering to enhance the color of the images, and then convert the images back to RGB images. The color ratio of the number of pixels in the three channels of two adjacent RGB images is counted respectively when providing the maximum value and the minimum value in the whole image; the component difference of the three channels of the two adjacent RGB images is obtained at the same time; the difference between the color cast factors of the two adjacent RGB images is calculated based on the obtained color ratio and component difference, and the color cast threshold is set; When the difference between the color cast factors of two adjacent RGB image frames is greater than the set color cast threshold, the difference between the color ratios and the component difference of the two adjacent RGB image frames are input into the fuzzy controller, and the fuzzy controller outputs an adjustment value based on the set control rules to control the security equipment in the stereo garage.

[0017] Furthermore, the color ratio difference and component difference between two adjacent RGB image frames have three levels, that is, when the color ratio difference and component difference between two adjacent RGB image frames are input into the fuzzy controller, nine different level combinations will be generated, and each level combination corresponds to a fire extinguishing control method; specifically, the fuzzy control rules corresponding to the three levels of the color ratio difference are: extinguishing fire with low spray volume, extinguishing fire with medium spray volume, and extinguishing fire with high spray volume; the fuzzy control rules corresponding to the three levels of the component difference are: continuous spraying E duration, continuous spraying F duration, and continuous spraying G duration; wherein, the relationship between the durations of the three sprays is: .

[0018] Furthermore, after the RGB image is converted into HSI space, the I component in the HSI image is Fourier transformed, and the block effect is removed based on the domain mean before Gaussian filtering is performed for image enhancement; after filtering, the I component in the HSI image is inversely Fourier transformed to obtain a color-enhanced RGB image.

[0019] Furthermore, the component difference of the three channels of the RGB image is obtained, including: selecting any one of the three channels of the RGB image as the target channel, and recording the remaining two channels as auxiliary channels; when the target channel provides a maximum value, the average amplitude difference obtained by dividing the sum of the amplitude value of the target channel and the difference between the amplitude values ​​of the two auxiliary channels by the number of pixels when the target channel provides the maximum value is the component difference.

[0020] Furthermore, a Bayesian fusion algorithm is used to calculate the color cast factor of the RGB image according to the obtained color ratio and component difference.

[0021] One or more of the above technical solutions have the following beneficial effects: (1) The security control system provided by the present invention includes multiple cameras and a router, a host and a fuzzy controller connected in sequence; each camera corresponds to a garage and takes RGB images according to a preset shooting interval, and uploads the taken RGB images to the host through the router; the host predicts the color cast factor difference of the received RGB images. The present invention uses the size of the color cast factor difference as the basis for judging whether a fire has occurred. Compared with traditional judgment methods such as smoke and temperature, it has higher sensitivity and stronger real-time performance, and can monitor the occurrence of fire more accurately and timely.

[0022] (2) When the security control system provided by the present invention detects a fire, the fuzzy controller can output an adjustment value based on the built-in control rules to control the opening and closing and spray volume of the electric-driven fire extinguisher on the charging pile. When the fire is small, a low spray volume can be used to extinguish the fire; when the fire is large, a medium spray volume can be used to extinguish the fire; when the fire is very large, a high spray volume can be used to extinguish the fire. Therefore, the present invention can adopt different control methods to extinguish the fire according to the actual situation of the fire, while ensuring effective fire extinguishing and reducing resource waste; moreover, the security control can alarm when a fire is detected, and perform fire extinguishing operations before the arrival of security personnel. After the security personnel arrive at the scene, the fire extinguishing effect can be secondary verified to further ensure the control effect.

[0023] (3) The security control system provided by the present invention performs image information analysis based on an internal host, wherein the host includes an image acquisition unit, an image enhancement unit, and a color cast factor difference prediction unit. The host is based on various image processing units: first, an RGB image is acquired; then, the RGB image is converted to HSI space, and the image is color enhanced using homomorphic filtering; then the image is converted back to the form of an RGB image. Compared with the existing method of performing feature analysis based on a single image type, the present invention can better capture the actual changes of the image in a continuous time, and has a better effect on fire monitoring.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0026] Figure 1The present invention is a block diagram of a fuzzy control-based security management and control system for a three-dimensional parking garage in the first embodiment of the present invention.

[0027] Figure 2 The present invention is a flowchart of a method for security control of a stereoscopic parking garage based on fuzzy control in the second embodiment of the present invention. DETAILED DESCRIPTION

[0028] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0029] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0030] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0031] Embodiment 1 This embodiment discloses a stereo garage security management and control system based on fuzzy control.

[0032] like Figure 1 As shown, a fuzzy control-based three-dimensional parking garage security management and control system includes: Multiple cameras and the routers, hosts and fuzzy controllers connected in sequence; The number of cameras is consistent with the number of garages in the three-dimensional garage, that is, each camera corresponds to a garage; each camera shoots RGB images according to a preset shooting interval, and uploads the shot RGB images to the host through a router; The host is used to predict the color cast factor difference of the received RGB image, and send the color cast factor difference prediction result to the fuzzy controller; The fuzzy controller is used to output corresponding adjustment values ​​according to the set fuzzy control rules to control the security equipment in the three-dimensional parking garage.

[0033] Based on the above process, the security control system of the present invention can effectively monitor whether there is a fire in the stereo garage, and can use different control methods to extinguish the fire according to the actual situation of the fire, thereby ensuring effective fire extinguishing while reducing resource waste. To facilitate understanding of the technical solution of the present invention, the following further explains and illustrates each step of this embodiment, specifically: Furthermore, a charging pile is set in front of each garage for charging new energy vehicles parked in the garage; in order to ensure the charging safety of the garage, charging pile and electric vehicles, each charging pile is equipped with a security device to be ready for timely fire extinguishing in case of fire. In the specific implementation process, each camera is set in the upper front of the corresponding garage, so that the shooting range of each camera can just cover the garage corresponding to the camera and the charging pile corresponding to the garage. It can be understood that the installation position of the camera can be adjusted according to actual needs, as long as it can ensure that the shooting area of ​​the camera can meet the shooting requirements.

[0034] In this embodiment, the security equipment used in the security control system is an electric-driven fire extinguisher, which is provided with an electric valve, and the electric valve is connected to the dry powder tube on the electric-driven fire extinguisher. In the specific implementation process, the opening and closing degree and opening and closing time of the electric valve are controlled by the adjustment value output by the fuzzy controller, and the opening and closing degree and opening and closing time of the electric valve determine the injection time and injection amount when the dry powder in the electric-driven fire extinguisher can be ejected from the dry powder tube.

[0035] Furthermore, the camera used in this embodiment is a high-definition camera, and each camera is configured with a separate serial number. Specifically, if the number of cameras is s, the serial numbers configured for the cameras are camera No. 1, camera No. 2, ..., camera No. s; the garages, charging piles and electric-driven fire extinguishers in the three-dimensional parking garage are numbered in the same configuration, and the configured serial numbers are consistent with the camera serial numbers, that is: the serial numbers configured for the garages in the three-dimensional parking garage are garage No. 1, garage No. 2, ..., garage No. s, the serial numbers configured for the charging piles are charging pile No. 1, charging pile No. 2, ..., charging pile No. s; the serial numbers configured for the electric-driven fire extinguishers are electric-driven fire extinguisher No. 1, electric-driven fire extinguisher No. 2, ..., electric-driven fire extinguisher No. s. Among them, camera No. s is used to shoot new energy vehicles and charging pile No. s in garage No. s. When a fire is detected, the electric-driven fire extinguisher No. s is controlled to perform fire extinguishing.

[0036] like Figure 1As shown, the security control system provided in this embodiment also includes an alarm and an LED display, and both the alarm and the display are connected to the host. Specifically, when the host detects a fire, it will send an alarm signal to the alarm, and at this time, the alarm performs an alarm operation; at the same time, when the host detects a fire, it will also send a fire position signal to the LED display, for example: when the host detects a fire within the shooting range of camera No. 3, it will send an electrical signal with a position signal of "3" to the LED display, and at this time, the number "3" will be displayed on the LED display, and the security personnel can go to the corresponding position of the three-dimensional parking garage according to the digital display on the LED display; therefore, the security control provided by the present invention can directly alarm when a fire is detected, and can perform fire extinguishing operations before the arrival of security personnel. After the security personnel arrive at the scene, the fire extinguishing effect can be secondary verified, thereby better ensuring the control effect.

[0037] Furthermore, the electrical signal sent by the host to the LED display is sent in the form of binary code. For example, the electrical signal corresponding to the position signal "3" is "011", the electrical signal corresponding to the position signal "2" is "010", and the electrical signal corresponding to the position signal "1" is "001".

[0038] Furthermore, the host in the security control system includes an image acquisition unit, an image enhancement unit and a color cast factor difference prediction unit; wherein the image acquisition unit is used to receive the RGB image taken by the camera, the image enhancement unit is used to enhance the image effect of the received RGB image, and the color cast factor difference prediction unit is used to predict the color cast factor difference of the RGB image after image enhancement, and send the color cast factor difference prediction result to the fuzzy controller; then, the fuzzy controller is used to output the corresponding adjustment value according to the set fuzzy control rule to control the security equipment in the stereo garage; wherein, in this embodiment, the adjustment value output by the fuzzy controller is a current value. The fuzzy controller controls the working state of the electric valve on the electric-driven fire extinguisher based on the output current value, thereby realizing the control of the opening and closing and spraying amount of the electric-driven fire extinguisher, and finally realizing fire extinguishing.

[0039] Embodiment 2 This embodiment discloses a security management and control method for a stereoscopic parking garage based on fuzzy control.

[0040] like Figure 2 As shown, a fuzzy control-based three-dimensional parking garage security control method includes: Step S1, obtaining two adjacent frames of RGB images to be detected; Step S2, performing HSI space conversion operation on two adjacent RGB images respectively, and using homomorphic filtering method to perform color enhancement on the images, and then reconverting the images into RGB images; Step S3, respectively counting the color ratio of the number of pixels in the entire image when the three channels of the two adjacent frames of RGB images provide the maximum value and the minimum value; simultaneously obtaining the component difference of the three channels of the two adjacent frames of RGB images; calculating the difference between the color cast factors of the two adjacent frames of RGB images based on the obtained color ratio and component difference, and setting the color cast threshold; Step S4: When the difference between the color cast factors of two adjacent RGB image frames is greater than the set color cast threshold, the difference between the color ratios and the component difference of the two adjacent RGB image frames are input into the fuzzy controller. The fuzzy controller outputs an adjustment current based on the set control rule to control the opening and closing and spray volume of the electric-driven fire extinguisher on the charging pile, thereby realizing fire extinguishing control.

[0041] In step S1, two adjacent frames of RGB images to be detected are obtained.

[0042] Specifically, when acquiring RGB images, a high-definition camera with a high degree of restoration can be selected. Each camera is set in the upper front of the corresponding garage, so that the shooting range of each camera can just cover the garage corresponding to the camera and the charging pile corresponding to the garage. When analyzing RGB images, two adjacent RGB images are used as analysis objects. For example, assuming that there are 4 images received, recorded as , , and , then first obtain two adjacent frames of RGB images from and , and then obtain the other two adjacent RGB images and , and then obtain two adjacent RGB image frames and , and so on. It should be noted that the specific installation position of the camera and the wide-angle range of the shooting can be adjusted as needed, and this embodiment does not limit this. At the same time, a small micro camera with high definition can also be directly used and embedded in a fixed position, as long as it can obtain a clear image; in addition, when setting the camera's shooting interval, it can also be set according to needs. The shooting interval selected in this embodiment is to automatically take a picture every 10 seconds.

[0043] In step S2, two adjacent frames of RGB images are respectively subjected to HSI space conversion operation, and the homomorphic filtering method is used to perform color enhancement on the image, and then the image is converted back into the form of an RGB image, that is, after the RGB image is subjected to HSI space conversion, the I component (brightness) in the HSI image is subjected to Fourier transformation, and the block effect is removed based on the domain mean before Gaussian filtering is performed for image enhancement; after filtering, the I component in the HSI image is subjected to inverse Fourier transformation, thereby obtaining a color-enhanced RGB image. Compared with the existing method of performing feature analysis based on a single image type, the present invention can better capture the actual changes of the image in a continuous time, and has a better effect on fire detection.

[0044] Specifically, in order to highlight the characteristics of the flame in the image, this embodiment introduces a dual function to perform a secondary representation of the image. The HSI image after the secondary representation is: ; in, Represents the HSI image represented by a dual function, Represents the illumination function The light intensity component in Reflection function The range of the illumination component is (0,∞), which is very large but causes very little change, so it is mainly concentrated in the low-frequency part of the image; correspondingly, the range of the reflection component is (0,1), which is very small but causes very large change, so it is mainly concentrated in the high-frequency part of the image.

[0045] Subsequently, in order to avoid distortion when the HSI image is subsequently subjected to Fourier transform, the HSI image after the secondary representation is logarithmically transformed. The HSI image after logarithmic transformation is expressed as: ; Therefore, the light intensity component and the reflection component become an additive form in the HSI spatial domain; at the same time, the HSI image can be simplified by applying Fourier transform in the frequency domain, that is: ; in, represents the Fourier transform of the HSI image, represents the Fourier transform of the illumination component, represents the Fourier transform of the reflected component. Using the transfer function The Gaussian high-pass filter is used to filter the HSI image after Fourier transformation, and the transfer function is expressed as: ; in, represents the high frequency gain and , represents the low frequency gain and ; c represents the sharpening factor, n represents the order of the filter, represents the cut-off frequency, Represents the frequency plane from the origin to the point To highlight the brightness of the image, this embodiment sets the high-frequency gain to 2, the low-frequency gain to 1, the cutoff frequency to 6, and the sharpening factor to 1 to enhance the image. After filtering, the HSI image is subjected to inverse Fourier transform and exponential transform to obtain a color-enhanced RGB image, namely: ; in, represents the RGB image after color enhancement, Represents the illumination component in the spatial domain of the RGB image formed after the inverse Fourier transform, Represents the reflection component in the spatial domain of the RGB image formed after inverse Fourier transform.

[0046] In step S3, the color ratio of the number of pixels in the entire image when providing the maximum and minimum values ​​for the three channels of two adjacent frames of RGB images is counted respectively; the component difference of the three channels of the two adjacent frames of RGB images is obtained at the same time; the difference between the color cast factors of the two adjacent frames of RGB images is calculated based on the obtained color ratio and component difference, and the color cast threshold is set. For ease of understanding, this embodiment is described here with one of the two adjacent frames of RGB images as the processing object, and the other frame can be processed in the same way. Specifically, step S3 can be implemented by the following steps: Step S3-1, calculate the color ratio. First, calculate the current frame image T The maximum and minimum value matrices of , specifically: ; in, and Respectively represent the current frame image T The maximum and minimum matrices of Respectively represent the current frame image T The red component image, green component image and blue component image of the current frame RGB image are counted. The color ratio of the number of pixels in the entire image when the three channels provide the maximum and minimum values ​​is: ; ; ; in, and Respectively The color ratio of the number of pixels in the entire image when the channel provides the maximum and minimum values. and Respectively The color ratio of the number of pixels in the entire image when the channel provides the maximum and minimum values. and Respectively The color ratio of the number of pixels in the entire image when the channel provides the maximum and minimum values. Represents the number of pixels that can meet the conditions in the statistical matrix, and They represent the current frame image respectively T The height and width of the

[0047] Step S3-2: Calculate the current frame image T Component difference. Component difference is the difference in amplitude between the components in the image. Therefore, the component difference of the three channels of the RGB image is obtained. Specifically, any one of the three channels of the RGB image is selected as the target channel, and the remaining two channels are recorded as auxiliary channels. When the target channel provides the maximum value, the average amplitude difference obtained by dividing the sum of the difference between the amplitude value of the target channel and the amplitude values ​​of the two auxiliary channels by the number of pixels when the target channel provides the maximum value is the component difference. The mathematical representation of component difference is as follows: ; in, and Respectively represent the RGB image in the current frame aisle, Channel and Component difference of the channel; Indicates when When the channel reaches the maximum value Channel at pixel The amplitude value on Indicates when When the channel reaches the maximum value Channel at pixel The amplitude value on Indicates when When the channel reaches the maximum value Channel at pixel The amplitude value on , otherwise it is 0; and Respectively aisle, Channel and The number of pixels when the channel reaches its maximum value. To facilitate the representation and calculation of component differences, the obtained component differences are normalized, that is: ; in, represents the normalized component difference, ; and represent a constant respectively, and and The value can be adjusted according to the actual requirements for the brightness and darkness of the image.

[0048] Step S3-3, based on the obtained color ratio and component difference, the difference between the color cast factors of two adjacent RGB images is calculated and a color cast threshold is set. Specifically, a Bayesian fusion algorithm is used to calculate the color cast factor of the RGB image based on the obtained color ratio and component difference, that is: ; in, The specific value of the color cast factor is used to indicate the degree of color cast of the image. Compared with the image of the previous frame, the greater the difference in the value of the color cast factor, the higher the degree of color change of the image, which means the greater the possibility of a fire at the location contained in the image; conversely, the smaller the difference in the value of the color cast factor, the lower the degree of color change of the image compared with the image of the previous frame, which means the less likely the fire is at the location contained in the image. In this regard, a color cast threshold can be set, and the decision on whether to execute fire extinguishing control is made by comparing the set color cast threshold with the difference between the color cast factors of two adjacent frames of RGB images. In this embodiment, the color cast threshold is set to 1.5.

[0049] In step S4, when the difference between the color cast factors of two adjacent RGB image frames is greater than the set color cast threshold, the difference between the color ratios and the component difference of the two adjacent RGB image frames are input into the fuzzy controller, and the fuzzy controller outputs an adjustment current based on the set control rule to control the opening and closing and spray volume of the electric-driven fire extinguisher on the charging pile, thereby realizing fire extinguishing control.

[0050] Furthermore, the color ratio difference and component difference between two adjacent RGB images have three levels, namely, the levels included in the color ratio difference are recorded as A, B, and C, and the levels included in the component difference are recorded as a, b, and c; each level represents a fuzzy scale, as shown in Table 1: Table 1 Corresponding relationship between fuzzy levels of color ratio difference and component difference

[0051] Furthermore, the fuzzy control rules corresponding to the three levels (A, B, C) of the color ratio difference are: using low spray volume to extinguish fire, using medium spray volume to extinguish fire, and using high spray volume to extinguish fire; the fuzzy control rules corresponding to the three levels (a, b, c) of the component difference are: continuous spray E duration, continuous spray F duration, and continuous spray G duration; the relationship between the durations of the three sprays is It is understandable that the three different levels of spraying duration can be set according to actual needs. After a complete spraying is completed, the fire detection operation is performed again to detect whether the fire is extinguished. In addition, when performing spraying fire extinguishing, the fire extinguishing medium used in ordinary electric-driven fire extinguishers can be selected, or other media that can be used to extinguish fire by spraying can be selected.

[0052] Therefore, when the color ratio difference and component difference between two adjacent RGB images are input to the fuzzy controller, nine different level combinations will be generated, and each level combination corresponds to a fire extinguishing control method, as shown in Table 2: Table 2 Fire extinguishing control method of charging pile in intelligent stereo garage based on fuzzy control

[0053] It can be seen that the present invention can not only accurately identify fires, but also adopt different control methods to extinguish fires according to the actual situation of the fire, thereby reducing resource waste while ensuring effective fire extinguishing. The steps involved in the device of the above embodiment 1 correspond to the method of embodiment 2. For the specific implementation, please refer to the relevant description part of embodiment 2.

[0054] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0055] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A fuzzy control-based stereo garage security management and control system, characterized in that: include: Multiple cameras and the routers, hosts and fuzzy controllers connected in sequence; The number of cameras is consistent with the number of garages in the three-dimensional garage, that is, each camera corresponds to a garage; each camera shoots RGB images according to a preset shooting interval, and uploads the shot RGB images to the host through a router; The host is used to predict the color cast factor difference of the received RGB image, and send the color cast factor difference prediction result to the fuzzy controller; The fuzzy controller is used to output corresponding adjustment values ​​according to the set fuzzy control rules to control the security equipment in the three-dimensional parking garage.

2. A fuzzy control-based stereo garage security management and control system as claimed in claim 1, characterized in that: A charging pile is arranged in front of each garage, and each camera is arranged in the upper front of the corresponding garage, so that the shooting range of each camera covers the garage corresponding to the camera and the charging pile corresponding to the garage.

3. A fuzzy control-based stereo garage security management and control system as claimed in claim 2, characterized in that: Each camera is configured with a separate serial number. If the number of cameras is s, the serial numbers configured for the cameras are camera 1, camera 2, ..., camera s; the garages and charging piles in the stereo garage are numbered in the same configuration, and the configured serial numbers are consistent with the camera serial numbers.

4. A fuzzy control-based stereo garage security management and control system as claimed in claim 1, characterized in that: The host includes an image acquisition unit, an image enhancement unit and a color cast factor difference prediction unit; wherein the image acquisition unit is used to receive an RGB image taken by a camera, the image enhancement unit is used to enhance the image effect of the received RGB image, and the color cast factor difference prediction unit is used to predict the color cast factor difference of the RGB image after image enhancement.

5. The fuzzy control-based stereo garage security management and control system according to claim 1, characterized in that: The security equipment is an electric-driven fire extinguisher, on which an electric valve is arranged, and the electric valve is connected to a dry powder pipe on the electric-driven fire extinguisher.

6. A fuzzy control-based stereo garage security management method, characterized in that: include: Obtain two adjacent frames of RGB images to be detected; Perform HSI space conversion on two adjacent RGB images, use homomorphic filtering to enhance the color of the images, and then convert the images back to RGB images. The color ratio of the number of pixels in the three channels of two adjacent RGB images is counted respectively when providing the maximum value and the minimum value in the whole image; the component difference of the three channels of the two adjacent RGB images is obtained at the same time; the difference between the color cast factors of the two adjacent RGB images is calculated based on the obtained color ratio and component difference, and the color cast threshold is set; When the difference between the color cast factors of two adjacent RGB image frames is greater than the set color cast threshold, the difference between the color ratios and the component difference of the two adjacent RGB image frames are input into the fuzzy controller, and the fuzzy controller outputs an adjustment value based on the set control rules to control the security equipment in the stereo garage.

7. A fuzzy control-based security control method for a stereo garage as claimed in claim 6, characterized in that: The color ratio difference and component difference between two adjacent RGB image frames have three levels, that is, when the color ratio difference and component difference between two adjacent RGB image frames are input into the fuzzy controller, nine different level combinations will be generated, and each level combination corresponds to a fire extinguishing control method; Specifically, the fuzzy control rules corresponding to the three levels of the color ratio difference are: using low spray volume to extinguish fire, using medium spray volume to extinguish fire, and using high spray volume to extinguish fire; the fuzzy control rules corresponding to the three levels of the component difference are: continuous spray E duration, continuous spray F duration, and continuous spray G duration; among them, the relationship between the durations of the three sprays is .

8. A fuzzy control-based security control method for a stereo garage as claimed in claim 6, characterized in that: After the RGB image is converted to HSI space, the I component in the HSI image is Fourier transformed, and the block effect is removed based on the domain mean before Gaussian filtering is performed for image enhancement; After filtering, the I component in the HSI image is inversely transformed to obtain a color-enhanced RGB image.

9. A fuzzy control-based security control method for a stereo garage as claimed in claim 6, characterized in that: Get the component differences of the three channels of the RGB image, including: Select any one of the three channels of the RGB image as the target channel, and the remaining two channels are recorded as auxiliary channels; when the target channel provides the maximum value, the average amplitude difference obtained by dividing the sum of the amplitude value of the target channel and the amplitude values ​​of the two auxiliary channels by the number of pixels when the target channel provides the maximum value is the component difference.

10. A fuzzy control-based security control method for a stereo garage as claimed in claim 6, characterized in that: The Bayesian fusion algorithm is used to calculate the color cast factor of the RGB image based on the obtained color ratio and component difference.

Images