Flame smoke concentration detection method and device, computer device and storage medium

Abstract

The application relates to a flame smoke concentration detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring multiple visible light images of a to-be-detected area in the presence of a flame and smoke concentration represented by each visible light image through visible light camera devices arranged in multiple directions in the to-be-detected area; determining the weight corresponding to each visible light camera device based on the actual distance between each visible light camera device and the flame in the to-be-detected area; and performing fusion processing on the smoke concentration represented by the visible light images collected by each visible light camera device based on the weight corresponding to each visible light camera device, so as to obtain the actual smoke concentration of the flame in the to-be-detected area. The method can improve the detection accuracy of the flame smoke concentration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smoke concentration detection, and in particular to a flame smoke concentration detection method and device, computer equipment, a storage medium, and a computer program product. BACKGROUND

[0002] An overhead transmission line is usually arranged in the wild, such as a forest or the like. When a fire occurs in a vegetation-rich area, the high temperature generated by combustion and the smoke particles generated by combustion of the vegetation will change the conductive performance of the overhead transmission line to the ground gap, so that the overhead transmission line is prone to tripping accidents, resulting in large-scale power outages. Therefore, it is necessary to detect the flame smoke concentration in the vegetation-rich area to monitor the vegetation-rich area in real time.

[0003] In related technologies, a smoke detector is usually used to detect the flame smoke concentration. However, the smoke detector is easily affected by the air quality of the external environment, so that the detection accuracy of the flame smoke concentration is low. SUMMARY

[0004] Therefore, it is necessary to provide a flame smoke concentration detection method, device, computer equipment, computer readable storage medium, and computer program product capable of improving the detection accuracy of the flame smoke concentration to solve the technical problem of low detection accuracy of the flame smoke concentration.

[0005] In a first aspect, the present application provides a flame smoke concentration detection method. The method comprises:

[0006] obtaining a plurality of visible light images of the to-be-detected area in the presence of a flame and smoke concentration represented by each visible light image through a plurality of visible light camera devices arranged in different positions in the to-be-detected area;

[0007] determining a weight corresponding to each visible light camera device based on the actual distance between the visible light camera device and the flame in the to-be-detected area;

[0008] performing fusion processing on the smoke concentration represented by the visible light images collected by each visible light camera device based on the weight corresponding to each visible light camera device to obtain the actual smoke concentration of the flame in the to-be-detected area.

[0009] In one embodiment, the weight corresponding to each visible light camera device is determined based on the actual distance between the visible light camera device and the flame in the to-be-detected area, comprising:

[0010] determine, for each visible light camera device, area information of the smoke of the fire in a visible light image captured by the visible light camera device and a camera pixel of the visible light camera device;

[0011] determine a weight corresponding to the visible light camera device according to a distance ratio relationship between the actual distance and a distance threshold, the area information, and a pixel ratio relationship between the camera pixel and a camera pixel threshold;

[0012] The distance threshold is an actual distance corresponding to each visible light camera device, and a value of the actual distance is greater than values of the remaining actual distances. The camera pixel threshold is a camera pixel corresponding to each visible light camera device, and a value of the camera pixel is greater than values of the remaining camera pixels.

[0013] In one embodiment, the determination of the area information of the smoke of the fire in the visible light image captured by the visible light camera device includes:

[0014] identify a smoke image of the fire from the visible light image captured by the visible light camera device;

[0015] determine an area ratio relationship between an area of the smoke image and an area of the visible light image as the area information of the smoke of the fire in the visible light image captured by the visible light camera device.

[0016] In one embodiment, each visible light camera device is installed on a top of a power tower pole in the to-be-detected area.

[0017] The actual distance between each visible light camera device and the fire in the to-be-detected area is determined by:

[0018] For each visible light camera device, identify a power tower pole image of a power tower pole and a smoke image of the fire from the visible light image captured by the visible light camera device;

[0019] determine proportion information of the visible light image based on the power tower pole image and an actual height of the power tower pole, and determine an image distance between the visible light camera device and the smoke of the fire based on the smoke image; the image distance is used to represent a distance between the smoke of the fire in the visible light image and the visible light camera device;

[0020] determine the actual distance between the visible light camera device and the smoke of the fire in the to-be-detected area based on the proportion information and the image distance.

[0021] In one of the embodiments, the actual smoke concentration of the fire in the to-be-detected area is obtained by fusing the smoke concentrations represented by the visible light images collected by the visible light cameras based on the weights corresponding to the visible light cameras, including:

[0022] obtaining an initial smoke concentration represented by an initial visible light image collected by each visible light camera; the initial smoke concentration is obtained by each visible light camera in the absence of fire in the to-be-detected area;

[0023] determining, respectively, the smoke concentration difference information between the initial smoke concentration and the smoke concentration corresponding to each visible light camera as the target smoke concentration corresponding to each visible light camera;

[0024] fusing the target smoke concentrations corresponding to each visible light camera based on the weights corresponding to the visible light cameras to obtain the actual smoke concentration of the fire in the to-be-detected area.

[0025] In one of the embodiments, a flame detector is arranged in each area;

[0026] Before obtaining the multiple visible light images of the to-be-detected area in the presence of fire and the smoke concentration represented by each visible light image by the visible light cameras arranged in multiple directions in the to-be-detected area, the method further includes:

[0027] in the case of receiving the flame alarm information, determining the flame detector that sends the flame alarm information;

[0028] determining the area associated with the flame detector as the to-be-detected area in which the fire exists;

[0029] starting the visible light cameras arranged in multiple directions in the to-be-detected area.

[0030] In a second aspect, the present application further provides a flame smoke concentration detection device. The device includes:

[0031] a first smoke concentration determination module, configured to obtain the multiple visible light images of the to-be-detected area in the presence of fire and the smoke concentration represented by each visible light image by the visible light cameras arranged in multiple directions in the to-be-detected area;

[0032] a camera weight determination module, configured to determine the weight corresponding to each visible light camera based on the actual distance between each visible light camera and the fire in the to-be-detected area;

[0033] a second smoke concentration determination module configured to fuse smoke concentrations represented by visible light images collected by each visible light camera according to a weight corresponding to each visible light camera, to obtain an actual smoke concentration of the fire in the region to be detected.

[0034] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the following steps when executing the computer program:

[0035] a plurality of visible light cameras arranged at different positions in the region to be detected are used to obtain a plurality of visible light images of the region to be detected in the presence of the fire and smoke concentrations represented by each visible light image;

[0036] a weight corresponding to each visible light camera is determined according to an actual distance between the visible light camera and the fire in the region to be detected;

[0037] a weight corresponding to each visible light camera is determined according to an actual distance between the visible light camera and the fire in the region to be detected;

[0038] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0039] a plurality of visible light cameras arranged at different positions in the region to be detected are used to obtain a plurality of visible light images of the region to be detected in the presence of the fire and smoke concentrations represented by each visible light image;

[0040] a weight corresponding to each visible light camera is determined according to an actual distance between the visible light camera and the fire in the region to be detected;

[0041] a weight corresponding to each visible light camera is determined according to an actual distance between the visible light camera and the fire in the region to be detected;

[0042] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the following steps:

[0043] a plurality of visible light cameras arranged at different positions in the region to be detected are used to obtain a plurality of visible light images of the region to be detected in the presence of the fire and smoke concentrations represented by each visible light image;

[0044] determine a weight corresponding to each visible light camera device based on an actual distance between the each visible light camera device and the fire in the region to be detected;

[0045] fuse the smoke concentration represented by the visible light images collected by each visible light camera device based on the weight corresponding to each visible light camera device, to obtain the actual smoke concentration of the fire in the region to be detected.

[0046] The flame smoke concentration detection method, device, computer device, storage medium and computer program product can first obtain multiple visible light images of the region to be detected in the presence of a fire and the smoke concentration represented by each visible light image through the multiple visible light camera devices arranged in multiple directions in the region to be detected; then determine the weight corresponding to each visible light camera device based on the actual distance between the each visible light camera device and the fire in the region to be detected; and finally fuse the smoke concentration represented by the visible light images collected by each visible light camera device based on the weight corresponding to each visible light camera device, to obtain the actual smoke concentration of the fire in the region to be detected. In this way, the multiple visible light camera devices can collect the region to be detected from various angles to obtain multiple visible light images of the region to be detected and determine the smoke concentration represented by each visible light image. Then, the weight corresponding to each visible light camera device can be determined based on the actual distance between the each visible light camera device and the fire in the region to be detected, and the actual smoke concentration of the fire can be obtained by fusing the corresponding smoke concentration based on the weight corresponding to each visible light camera device. Compared with the flame smoke concentration detection method based on a smoke detector, the flame smoke concentration detection method can determine the actual smoke concentration of the fire in the region to be detected by comprehensively considering the smoke concentration detected by each visible light camera device in the region to be detected, and thus is less affected by the air quality of the external environment and improves the detection accuracy of the flame smoke concentration. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 FIG. 1 is a flowchart of a flame smoke concentration detection method according to an embodiment of the present disclosure;

[0048] Figure 2 FIG. 2 is an application diagram of the flame smoke concentration detection method according to an embodiment of the present disclosure;

[0049] Figure 3 FIG. 3 is a flowchart of a step of determining the weight corresponding to each visible light camera device according to an embodiment of the present disclosure;

[0050] Figure 4A flowchart of steps for determining the actual distance between each visible light camera and the flame in the region to be detected in one embodiment;

[0051] Figure 5 A flowchart of steps for obtaining the actual smoke concentration of the flame in the region to be detected in one embodiment;

[0052] Figure 6 A flowchart of a flame smoke concentration detection method in another embodiment;

[0053] Figure 7 A flowchart of a real-time flame smoke concentration observation method in one embodiment;

[0054] Figure 8 A block diagram of the structure of a flame smoke concentration detection device in one embodiment;

[0055] Figure 9 An internal structure diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0057] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0058] In an exemplary embodiment, as shown in Figure 1 A flame smoke concentration detection method is provided, and the present embodiment takes this method as an example applied to a server; it can be understood that this method can also be applied to a terminal, and can also be applied to a system including a server and a terminal, and is realized through the interaction between the server and the terminal. The server can be realized by an independent server or a server cluster composed of multiple servers, and the terminal can be but is not limited to various personal computers, notebook computers, smart phones, tablet computers, etc. In the present embodiment, the method includes the following steps:

[0059] In step S102, a plurality of visible light cameras arranged in multiple directions in the region to be detected are used to obtain a plurality of visible light images of the region to be detected in the presence of a flame and the smoke concentration represented by each visible light image.

[0060] Each visible light camera device is arranged on the top of one power tower pole in the to-be-detected area, and the visible light camera device is configured to collect a visible light image. It can be understood that there are visible light camera devices on the market that can calculate the surrounding smoke concentration according to the surrounding image. Therefore, the server can also determine the smoke concentration detected by the visible light camera device based on the visible light image collected by the visible light camera device. For example, the visible light camera device displays the detected smoke concentration in the visible light image and sends it to the server.

[0061] The smoke concentration represented by each visible light image is detected by the visible light camera device based on the visible light image.

[0062] As shown in Figure 2 The application provides a flame smoke concentration detection method. As shown in Figure 2 The visible light camera device can be installed on the top of each power tower pole in the forest, and the forest can be divided into multiple areas. When there is a flame in a certain area, multiple visible light images of the area can be collected from different angles by the visible light camera devices on the top of each power tower pole in the area.

[0063] Specifically, when the server detects that a fire occurs in the forest, i.e., there is a flame, the server starts multiple visible light camera devices in the to-be-detected area where the flame exists. After the multiple visible light camera devices are started, they will take pictures of the surrounding environment at the same time point at a preset time interval, and send the taken visible light images to the server. The server obtains multiple visible light images of the to-be-detected area and the smoke concentration represented by each visible light image by taking pictures of the to-be-detected area through the multiple visible light camera devices. For example, the server determines the smoke concentration corresponding to each visible light camera device as the smoke concentration marked on the visible light image sent by the visible light camera device.

[0064] In step S104, the weight corresponding to each visible light camera device is determined based on the actual distance between each visible light camera device and the flame in the to-be-detected area.

[0065] The actual distance is the distance between the visible light camera device and the flame in the to-be-detected area in the real world.

[0066] The weight is used to represent the influence of the smoke concentration represented by the visible light image collected by the visible light camera on the actual smoke concentration of the flame in the to-be-detected area.

[0067] Specifically, for each visible light camera device, the server determines an actual distance between each visible light camera device and the smoke in the to-be-detected region according to the visible light image collected by each visible light camera device, and then determines a weight corresponding to each visible light camera device according to the actual distance corresponding to each visible light camera device, where the weight represents a degree of influence of the smoke concentration represented by the visible light image collected by each visible light camera device on the actual smoke concentration of the flame in the to-be-detected region.

[0068] In step S106, the server fuses the smoke concentrations represented by the visible light images collected by the visible light camera devices based on the weights corresponding to the visible light camera devices, to obtain the actual smoke concentration of the flame in the to-be-detected region.

[0069] Specifically, the server fuses the smoke concentrations represented by the visible light images collected by the visible light camera devices based on the weights corresponding to the visible light camera devices, for example, weighted summation, to obtain the actual smoke concentration of the flame in the to-be-detected region. Based on the actual smoke concentration, the server can determine the size of the fire of the flame in the to-be-detected region, and then determine the severity of the fire, so as to realize real-time monitoring of the fire in the forest. Therefore, the server can issue a fire warning information when the actual smoke concentration exceeds a smoke concentration threshold, so as to enable the forest fire prevention personnel to control the fire, and enable the operation and maintenance personnel of the power transmission line to operate and maintain the power transmission line equipment in the to-be-detected region.

[0070] For example, the server can fuse the smoke concentrations based on formula 1 to obtain the actual smoke concentration:

[0071]

[0072] where P represents the actual smoke concentration, N represents the total number of visible light camera devices in the to-be-detected region, n represents the serial number of the visible light camera device in all visible light camera devices in the to-be-detected region, P n represents the smoke concentration represented by the visible light image collected by the nth visible light camera device, and λ n represents the weight corresponding to the nth visible light camera device.

[0073] For another example, the server can also fuse the smoke concentrations based on formula 2 to obtain the actual smoke concentration:

[0074]

[0075] The flame smoke concentration detection method provided by the above embodiment, first, when the server detects the presence of a flame, the server first acquires a plurality of visible light images of the to-be-detected area in the presence of a flame and the smoke concentration represented by each visible light image through the visible light camera devices arranged in multiple directions in the to-be-detected area; then, the server determines the weight corresponding to each visible light camera device based on the actual distance between each visible light camera device and the flame in the to-be-detected area; finally, the server fuses the smoke concentration represented by the visible light images collected by each visible light camera device based on the weight corresponding to each visible light camera device, to obtain the actual smoke concentration of the flame in the to-be-detected area. In this way, through the multiple visible light camera devices, the to-be-detected area can be collected from various angles to obtain multiple visible light images of the to-be-detected area by the server, and the smoke concentration represented by each visible light image can be determined. Then, based on the actual distance between each visible light camera device and the flame in the to-be-detected area, the server can determine the weight corresponding to each visible light camera device, and further fuse the corresponding smoke concentration based on the weight corresponding to each visible light camera device to obtain the actual smoke concentration of the flame. Compared with the flame smoke concentration detection method based on the smoke detector, the above flame smoke concentration detection method determines the actual smoke concentration of the flame in the to-be-detected area by comprehensively considering the smoke concentration detected by each visible light camera device in the to-be-detected area, and thus is less affected by the air quality of the external environment, thereby improving the detection accuracy of the flame smoke concentration.

[0076] As shown in Figure 3 In an exemplary embodiment, the step S104 of determining the weight corresponding to each visible light camera device based on the actual distance between each visible light camera device and the flame in the to-be-detected area specifically includes the following steps:

[0077] The step S302 determines, for each visible light camera device, the area information of the smoke of the flame in the visible light image collected by the visible light camera device and the camera pixels of the visible light camera device.

[0078] The step S304 determines the weight corresponding to the visible light camera device according to the distance ratio relationship between the actual distance and the distance threshold, the area information, and the pixel ratio relationship between the camera pixels and the camera pixel threshold.

[0079] The camera pixels of the visible light camera device can be determined according to the attribute information of the visible light image.

[0080] The area information is used to represent the area difference, such as the area difference value or the area ratio value, between the area of the smoke image of the flame in the visible light image and the area of the visible light image.

[0081] The distance threshold is the actual distance corresponding to each visible light camera device, and the value of the actual distance is greater than the values of the other actual distances, that is, the distance threshold is the maximum actual distance corresponding to each visible light camera device.

[0082] The camera pixel threshold is the camera pixel corresponding to each visible light camera device, and the value of the camera pixel is greater than the values of the other camera pixels, that is, the camera pixel threshold is the maximum camera pixel corresponding to each visible light camera device.

[0083] Specifically, for each visible light camera device, the server determines the actual distance, the area information, and the camera pixel corresponding to the visible light camera device through the following process: the server first determines the image distance of the visible light camera device and the flame in the detection area on the visible light image according to the visible light image collected by the visible light camera device, and obtains the actual distance of the visible light camera device and the flame in the detection area in the real world based on the image distance and the scale of the visible light image; then, the server identifies the smoke image of the flame from the visible light image, and calculates the area difference between the area of the smoke image and the area of the visible light image, thereby obtaining the area information of the smoke of the flame in the visible light image; then, the server determines the camera pixel of the visible light camera device according to the attribute information of the visible light image.

[0084] Based on the above process, the server can obtain the actual distance and the camera pixel corresponding to all visible light camera devices in the detection area, and then the server determines the maximum actual distance in all actual distances as the distance threshold, and determines the maximum camera pixel in all camera pixels as the camera pixel threshold.

[0085] Then, for each visible light camera device, the server determines the weight corresponding to the visible light camera device through the following process: the server first determines the distance ratio relationship between the actual distance corresponding to the visible light camera device and the distance threshold, and the pixel ratio relationship between the camera pixel corresponding to the visible light camera device and the camera pixel threshold; then, according to the distance ratio relationship, the pixel ratio relationship, and the area information corresponding to the visible light camera device, the weight corresponding to the visible light camera device is obtained according to formula 3:

[0086]

[0087] wherein λ n represents the weight corresponding to the nth visible light camera device; L n represents the actual distance between the nth visible light camera device and the flame in the detection area, L MAX represents the distance threshold; PI nPI represents the imaging pixels of the nth visible light camera device MAX S represents the imaging pixel threshold value n The area information of the smoke of the flame in the visible light image collected by the nth visible light camera device.

[0088] It can be understood that the server can also update the weight corresponding to the visible light camera device once every time the visible light image is acquired, to ensure the accuracy of the weight, and thus ensure the accuracy of the actual smoke concentration.

[0089] In this embodiment, the server can obtain the actual distance, area information and imaging pixels corresponding to each visible light camera device through the visible light image collected by each visible light camera device, so as to determine the smoke concentration corresponding to the visible light camera device based on the actual distance, area information and imaging pixels, the influence degree of the actual smoke concentration of the flame in the detection area, that is, the weight corresponding to the visible light camera device, so as to subsequently fuse the smoke concentrations corresponding to the visible light camera devices into the actual smoke concentration based on the weight; based on the above process, the server can determine the smoke concentration of the flame based on multiple visible light camera devices, thereby avoiding the inaccuracy caused by a single visible light camera device or a single smoke detector in smoke concentration detection, and thus improving the detection accuracy of the flame smoke concentration.

[0090] In an exemplary embodiment, in the step S302, the area information of the smoke in the visible light image is determined, specifically including the following contents: identifying the smoke image of the flame from the visible light image collected by the visible light camera device; determining the area ratio relationship between the area of the smoke image and the area of the visible light image as the area information of the flame in the visible light image.

[0091] Specifically, the server identifies the smoke image of the flame from the visible light image through a target detection algorithm, and determines the area of the smoke image and the area of the visible light image; then, the server determines the area ratio relationship between the area of the smoke image and the area of the visible light image, that is, the proportion of the smoke image in the visible light image, thereby obtaining the area information of the smoke of the flame in the visible light image.

[0092] In this embodiment, the server can obtain the area information of the smoke of the flame in the visible light image through the area of the smoke image and the area of the visible light image, and thus can represent the distribution range of the smoke of the flame in the detection area, thereby providing a basis for the subsequent determination of the weight of the visible light camera device.

[0093] In an exemplary embodiment, each visible light camera device is installed at the top of a power tower pole in the detection area.

[0094] As Figure 4As shown, the actual distance between each visible light camera and the flame in the to-be-detected region in step S104 is determined in the following manner:

[0095] In step S402, for each visible light camera, the power tower pole image of the power tower pole and the smoke image of the flame are identified from the visible light image collected by the visible light camera.

[0096] In step S404, the scale information of the visible light image is determined based on the power tower pole image and the actual height of the power tower pole, and the image distance between the visible light camera and the smoke of the flame is determined based on the smoke image.

[0097] In step S406, the actual distance between the visible light camera and the smoke of the flame in the to-be-detected region is determined based on the scale information and the image distance.

[0098] The image distance is used to represent the distance between the smoke of the flame and the visible light camera in the visible light image.

[0099] Specifically, the server identifies the power tower pole image of the remaining tower pole and the smoke image of the flame in the to-be-detected region from the visible light image collected by the visible light camera based on the target detection model; then, the server determines the height of the power tower pole image as the image height of the power tower pole, and measures the distance between the visible light camera and the smoke image in the visible light image as the image distance between the visible light camera and the flame; since the height of each power tower pole is the same and fixed, the server can calculate the scale information (i.e., the scale of the visible light image) of the visible light image according to the image height of the power tower pole and the actual height of the power tower pole, and finally derive the actual distance between the visible light camera and the flame according to the scale information and the image distance between the visible light camera and the smoke of the flame. The image height is used to represent the height of the power tower pole in the visible light image.

[0100] For example, assuming that the image height of the power tower pole is h, the actual height is H, and the image distance between the visible light camera and the smoke of the flame is l, the server can calculate the actual distance L between the visible light camera and the flame according to formula 4:

[0101]

[0102] H / h represents the scale information of the visible light image.

[0103] For another example, when there are multiple power tower pole images of the power tower pole in the visible light image, a scale can be determined based on each power tower pole image respectively, and the average of the scales is taken as the scale information of the visible light image.

[0104] In this embodiment, the server can obtain the scale information of the visible light image through the power tower in the visible light image, and further determine the actual distance between the visible light camera and the smoke of the flame, thereby providing a basis for determining the weight of the subsequent visible light camera.

[0105] As shown in Figure 5 In an exemplary embodiment, the step S106 fuses the smoke concentration represented by the visible light images collected by each visible light camera based on the weight corresponding to each visible light camera to obtain the actual smoke concentration of the flame in the detection area, and specifically includes the following steps:

[0106] Step S502: obtaining the initial smoke concentration represented by the initial visible light image collected by each visible light camera.

[0107] Step S504: determining the smoke concentration difference information between the initial smoke concentration and the smoke concentration corresponding to each visible light camera as the target smoke concentration corresponding to each visible light camera.

[0108] Step S506: fusing the target smoke concentration corresponding to each visible light camera based on the weight corresponding to each visible light camera to obtain the actual smoke concentration of the flame in the detection area.

[0109] The initial smoke concentration is obtained by each visible light camera in the case that there is no flame in the detection area. It can be understood that even in the case of no flame, there are still a certain number of smoke particles in the air. Therefore, in order to avoid the influence of the original smoke particles in the air on the smoke concentration detection, it is necessary to clear the smoke concentration detected by the visible light camera to correct the influence of the original smoke particles in the air on the smoke concentration detection.

[0110] Specifically, for each region, the server starts up each visible light camera device in the region in a case where it is determined according to the flame detector that there is no flame in the region, and acquires a plurality of initial visible light images of the region based on each visible light camera device, and takes the smoke concentration represented by each initial visible light image as the corresponding initial smoke concentration collected by the visible light device that takes the initial visible light image. Then, in a case where it is determined according to the flame detector that there is a flame in a certain region, the server determines the region as a to-be-detected region, and starts up each visible light camera device in the to-be-detected region. For each visible light camera device, the server determines the smoke concentration represented by the visible light image collected by the visible light camera device, and then determines the smoke concentration difference between the initial smoke concentration (in a flame-free environment) and the smoke concentration (in a flame environment) corresponding to the visible light camera device, thereby obtaining the target smoke concentration actually detected by the visible light camera device. Finally, the server performs fusion processing on the target smoke concentration corresponding to each visible light camera device based on the weight corresponding to each visible light camera device, and obtains the actual smoke concentration of the flame in the to-be-detected region.

[0111] For example, assuming that for a certain visible light camera device, the initial smoke concentration is 5 ppm (parts per million), and the smoke concentration is 50 ppm, the target smoke concentration corresponding to the visible light camera device is 50-5=45 (ppm).

[0112] In this embodiment, the server can detect the initial smoke concentration of each region in a flame-free case by starting up the visible light camera device in a flame-free case, thereby realizing the zeroing processing of the visible light camera device for detecting the smoke concentration. In addition, the initial smoke concentration of the visible light camera device in a flame-free environment and the smoke concentration in a flame environment can be used to detect the smoke concentration of the flame while excluding the influence of the originally existing smoke particles in the air, thereby improving the detection accuracy of the smoke concentration of the flame.

[0113] In an example embodiment, a flame detector is arranged in each region.

[0114] Before the step S102 of acquiring the plurality of visible light images of the to-be-detected region in a case where there is a flame and the smoke concentration represented by each visible light image, the following content is further included: in a case where the flame alarm information is received, determining the flame detector that sends the flame alarm information; determining the region associated with the flame detector as the to-be-detected region where there is a flame; and starting up the visible light camera device in multiple positions in the to-be-detected region.

[0115] The flame detector is an instrument for detecting whether there is a flame in the environment, such as a temperature sensor, a smoke detector, and can also be an infrared detector, an ultraviolet detector, etc.

[0116] Specifically, the server monitors in real time whether there is a flame in the area through the flame detector arranged in each area; when the flame detector detects that there is a flame in the area, the flame alarm information will be sent to the server; when the server receives the flame alarm information, the flame detector that sends the flame alarm information is determined based on the flame alarm information, and then the area to which the flame detector belongs is determined as the to-be-detected area where there is a flame, and the visible light camera device in multiple directions in the to-be-detected area is started.

[0117] For example, when the flame detector is a smoke detector, the smoke detector can determine whether to send the flame alarm information according to the degree of increase in smoke concentration within a certain period of time.

[0118] It can be understood that, since the flame detector is only used to detect whether there is a flame, the number of flame detectors in each area does not need to be too many, and can be one or more, so the flame alarm information received by the server can also be one or more; if the server receives multiple flame alarm information, the server can determine the area corresponding to the multiple flame detectors that send the multiple flame alarm information (which can be one area or multiple areas) as the to-be-detected area.

[0119] In this embodiment, the server sets the flame detector in each area, which can preliminarily detect whether there is a flame in each area, and when receiving the flame alarm information sent by the flame detector, determines the to-be-detected area where there is a flame based on the flame detector that sends the flame alarm information.

[0120] In an example embodiment, as shown in Figure 6 Another flame smoke concentration detection method is provided, which is applied to the server as an example and includes the following steps:

[0121] Step S601, when receiving the flame alarm information, determining the flame detector that sends the flame alarm information.

[0122] Step S602, determining the area associated with the flame detector as the to-be-detected area where there is a flame.

[0123] Step S603, starting the visible light camera device in multiple directions in the to-be-detected area.

[0124] In step S604, the visible light images of the to-be-detected region in the presence of the flame and the smoke concentration represented by each visible light image are obtained by the visible light camera devices arranged at multiple positions in the to-be-detected region.

[0125] In step S605, the area information of the smoke of the flame in the visible light image collected by the visible light camera device and the camera pixels of the visible light camera device are determined for each visible light camera device.

[0126] In step S606, the weight corresponding to the visible light camera device is determined according to the distance ratio relationship between the actual distance and the distance threshold, the area information, and the pixel ratio relationship between the camera pixels and the camera pixel threshold.

[0127] In step S607, the initial smoke concentration represented by the initial visible light image collected by each visible light camera device is obtained.

[0128] In step S608, the smoke concentration difference information between the initial smoke concentration and the smoke concentration corresponding to each visible light camera device is determined as the target smoke concentration corresponding to each visible light camera device.

[0129] In step S609, the target smoke concentration corresponding to each visible light camera device is fused based on the weight corresponding to each visible light camera device to obtain the actual smoke concentration of the flame in the to-be-detected region.

[0130] In this embodiment, first, the server can obtain the actual distance, the area information, and the camera pixels corresponding to each visible light camera device based on the visible light image collected by each visible light camera device, so as to determine the weight corresponding to the visible light camera device based on the actual distance, the area information, and the camera pixels, that is, the influence degree of the actual smoke concentration of the flame in the to-be-detected region, so as to fuse the smoke concentrations corresponding to the visible light camera devices into the actual smoke concentration based on the weight; second, the server can detect the smoke concentration of each region in the absence of the flame by starting the visible light camera device in the absence of the flame, so as to realize the zero clearing processing of the visible light camera device for detecting the smoke concentration, avoid the influence of the originally existing smoke particles in the air on the smoke concentration detection, and further improve the detection accuracy of the flame smoke concentration. The above flame smoke concentration detection method can improve the detection accuracy of the flame smoke concentration by comprehensively determining the actual smoke concentration of the flame in the to-be-detected region based on the smoke concentrations detected by the visible light camera devices in the to-be-detected region, and is not easily affected by the external environment.

[0131] In order to more clearly illustrate the flame smoke concentration detection method provided by the embodiments of the present application, the flame smoke concentration detection method will be specifically described below with one specific embodiment, but it should be understood that the embodiments of the present application are not limited to this. As shown in Figure 7 The present application also provides a real-time observation method of flame smoke concentration, which specifically comprises the following steps:

[0132] S1: Visible light camera devices are installed at the top of each power tower in the forest.

[0133] S2: If a fire occurs in the forest, all visible light camera devices within the fire occurrence range can be started according to the degree of increase in smoke concentration within a certain time to collect visible light images of flame smoke; after the visible light camera devices collect the visible light images, the visible light images are sent to the server.

[0134] S3: The server extracts the visible light images collected by all visible light camera devices, and determines the smoke concentration weight of each visible light camera device according to the distance between the visible light camera device and the flame smoke, the camera pixels of the camera device, and the percentage of the flame smoke area in the visible light image area.

[0135] S4: The server extracts the smoke concentration in the visible light images collected by the visible light camera devices according to the visible light images collected by the visible light camera devices.

[0136] S5: The actual smoke concentration of the flame is calculated according to the smoke concentration corresponding to each visible light camera device and the weight of the visible light camera device.

[0137] In the embodiment, multiple visible light camera devices are used as the detection standard of smoke concentration, which can eliminate as much as possible the interference caused by temperature and environment and other factors on a single smoke detector or visible light camera device, and improve the anti-interference ability of the flame smoke concentration detection in the mountain fire environment. At the same time, the smoke concentration of each visible light camera device is calculated by using the weight, which can make the actual smoke concentration calculated more accurate and reliable. The distribution position of the visible light camera device can also be flexibly arranged according to the local mountain fire occurrence situation, so as to better analyze the size of the smoke concentration in the vegetation environment and provide a reference for the smoke concentration detection in the mountain fire condition.

[0138] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0139] Based on the same inventive concept, the embodiments of the present application also provide a flame smoke concentration detection device for implementing the flame smoke concentration detection method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more flame smoke concentration detection device embodiments provided below can refer to the limitations of the flame smoke concentration detection method described above, which will not be repeated here.

[0140] In an exemplary embodiment, as shown in Figure 8 A flame smoke concentration detection device is provided, comprising: a first smoke concentration determination module 802, a camera device weight determination module 804, and a second smoke concentration determination module 806, wherein:

[0141] The first smoke concentration determination module 802 is configured to acquire multiple visible light images of the detection area in the presence of flame and the smoke concentration represented by each visible light image through multiple visible light cameras arranged in multiple positions in the detection area.

[0142] The camera device weight determination module 804 is configured to determine the weight corresponding to each visible light camera based on the actual distance between each visible light camera and the flame in the detection area.

[0143] The second smoke concentration determination module 806 is configured to perform fusion processing on the smoke concentration represented by the visible light images collected by each visible light camera based on the weight corresponding to each visible light camera, to obtain the actual smoke concentration of the flame in the detection area.

[0144] In an example embodiment, the camera weight determination module 804 is further configured to determine, for each visible light camera, area information of the smoke of the flame in a visible light image captured by the visible light camera and a camera pixel of the visible light camera; determine a weight corresponding to the visible light camera according to a distance ratio relationship between an actual distance and a distance threshold, the area information, and a pixel ratio relationship between the camera pixel and a camera pixel threshold; the distance threshold is an actual distance corresponding to each visible light camera, and a value of the actual distance corresponding to the visible light camera is greater than values of the remaining actual distances; the camera pixel threshold is a camera pixel corresponding to each visible light camera, and a value of the camera pixel corresponding to the visible light camera is greater than values of the remaining camera pixels.

[0145] In an example embodiment, the camera weight determination module 804 is further configured to identify a smoke image of the flame from the visible light image captured by the visible light camera; and determine an area ratio relationship between an area of the smoke image and an area of the visible light image as the area information of the smoke of the flame in the visible light image captured by the visible light camera.

[0146] In an example embodiment, each visible light camera is installed on a top of a power tower pole in the detection area.

[0147] The flame smoke concentration detection device further comprises an actual distance determination module configured to identify, for each visible light camera, a power tower pole image of the power tower pole and a smoke image of the flame from a visible light image captured by the visible light camera; determine, based on the power tower pole image and an actual height of the power tower pole, scale information of the visible light image, and determine, based on the smoke image, an image distance between the visible light camera and the smoke of the flame; the image distance is used to represent a distance between the smoke of the flame in the visible light image and the visible light camera; and determine, based on the scale information and the image distance, an actual distance between the visible light camera and the smoke of the flame in the detection area.

[0148] In an example embodiment, the second smoke concentration determination module 806 is further configured to obtain an initial smoke concentration represented by an initial visible light image captured by each visible light camera; the initial smoke concentration is obtained by each visible light camera in the absence of the flame in the detection area; determine, for each visible light camera, smoke concentration difference information between the initial smoke concentration corresponding to the visible light camera and the smoke concentration, as a target smoke concentration corresponding to the visible light camera; and perform fusion processing on the target smoke concentration corresponding to each visible light camera based on the weight corresponding to each visible light camera to obtain an actual smoke concentration of the flame in the detection area.

[0149] In an example embodiment, a flame detector is arranged in each area.

[0150] The flame smoke concentration detection device further comprises a flame detection module configured to, in a case where the flame alarm information is received, determine a flame detector that sends the flame alarm information; determine a region associated with the flame detector as a to-be-detected region where the flame exists; and start the visible light camera device in multiple orientations in the to-be-detected region.

[0151] The modules in the flame smoke concentration detection device can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in a hardware form, or stored in a memory in the computer device in a software form, so as to be called and executed by the processor to perform operations corresponding to the modules.

[0152] In an example embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 9 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store a first smoke concentration corresponding to each visible light camera device. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with a terminal through a network connection. The computer program is executed by the processor to implement a flame smoke concentration detection method.

[0153] Those skilled in the art can understand that Figure 9 The structure shown in the above

[0154] In an example embodiment, a computer device is also provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0155] In an example embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0156] In an example embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0157] A person of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the computer program can include the processes of the above method embodiments. Any reference to a memory, a database or other medium in the embodiments provided in the present application can include at least one of a non-volatile memory and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., and is not limited thereto. The processor involved in the embodiments provided in the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., and is not limited thereto.

[0158] Any combination of the technical features in the above embodiments can be made. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0159] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of flame smoke concentration detection, characterized by, The method comprises: acquiring multiple visible light images of the to-be-detected area in the presence of a flame and smoke concentration represented by each visible light image through multiple visible light camera devices arranged at multiple positions in the to-be-detected area; determining a weight corresponding to each visible light camera device based on an actual distance between the visible light camera device and the flame in the to-be-detected area; fusing smoke concentration represented by visible light images collected by each visible light camera device based on the weight corresponding to the visible light camera device to obtain actual smoke concentration of the flame in the to-be-detected area; wherein the weight corresponding to each visible light camera device is obtained based on the following formula: wherein λ n represents the weight corresponding to the nth visible light camera device; L n represents the actual distance between the nth visible light camera device and the flame in the region to be detected, L MAX represents the maximum actual distance among the actual distances corresponding to the respective visible light camera devices; the actual distance corresponding to each visible light camera device is determined according to the image distance between the visible light camera device and the flame on the visible light image collected by the visible light camera device, and the scale of the visible light image collected by the visible light camera device; PI n represents the imaging pixels of the nth visible light camera device, PI MAX represents the maximum imaging pixel among the imaging pixels of the respective visible light camera devices; S n represents the area ratio between the smoke image in the visible light image collected by the nth visible light camera device and the visible light image collected by the nth visible light camera device.

2. The method of claim 1, wherein, The method further comprises: For each visible light camera device, identifying a smoke image of the flame from the visible light image collected by the visible light camera device.

3. The method of claim 1, wherein, Each visible light camera device is installed at the top of a power tower pole in the to-be-detected area; The actual distance between each visible light camera device and the flame in the to-be-detected area is determined in the following manner: For each visible light camera device, identifying a power tower pole image of the power tower pole and a smoke image of the flame from the visible light image collected by the visible light camera device; Based on the power tower pole image and the actual height of the power tower pole, determining scale information of the visible light image, and based on the smoke image, determining an image distance between the visible light camera device and the smoke of the flame; the image distance is used to represent the distance between the smoke of the flame and the visible light camera device in the visible light image; Based on the scale information and the image distance, determining the actual distance between the visible light camera device and the smoke of the flame in the to-be-detected area.

4. The method of claim 1, wherein, The fusing smoke concentration represented by visible light images collected by each visible light camera device based on the weight corresponding to the visible light camera device to obtain actual smoke concentration of the flame in the to-be-detected area comprises: acquiring initial smoke concentration represented by an initial visible light image collected by each visible light camera device; the initial smoke concentration is obtained by each visible light camera device in the absence of a flame in the to-be-detected area; determining smoke concentration difference information between the initial smoke concentration and the smoke concentration corresponding to each visible light camera device as target smoke concentration corresponding to the visible light camera device; fusing target smoke concentration corresponding to each visible light camera device based on the weight corresponding to the visible light camera device to obtain actual smoke concentration of the flame in the to-be-detected area.

5. The method according to any one of claims 1 to 4, characterized in that, Each area is provided with a flame detector; Before acquiring multiple visible light images of the to-be-detected area in the presence of a flame and smoke concentration represented by each visible light image through multiple visible light camera devices arranged at multiple positions in the to-be-detected area, the method further comprises: Upon receiving a flame alarm information, determining a flame detector that sends the flame alarm information; The area associated with the flame detector is determined as a to-be-detected area where a flame exists; Visible light camera devices in multiple directions in the to-be-detected area are started.

6. A flame smoke concentration detection device, characterized by, The device comprises: A first smoke concentration determination module is configured to acquire multiple visible light images of the to-be-detected area in the presence of a flame and smoke concentration represented by each visible light image through visible light camera devices arranged in multiple directions in the to-be-detected area; A camera device weight determination module is configured to determine a weight corresponding to each visible light camera device based on an actual distance between the visible light camera device and the flame in the to-be-detected area; A second smoke concentration determination module is configured to perform fusion processing on smoke concentration represented by visible light images collected by each visible light camera device based on the weight corresponding to the visible light camera device to obtain an actual smoke concentration of the flame in the to-be-detected area; The weight corresponding to each visible light camera device is obtained based on the following formula: wherein λ n represents the weight corresponding to the nth visible light camera device; L n represents the actual distance between the nth visible light camera device and the flame in the region to be detected, L MAX represents the maximum actual distance among the actual distances corresponding to the respective visible light camera devices; the actual distance corresponding to each visible light camera device is determined according to the image distance between the visible light camera device and the flame on the visible light image collected by the visible light camera device, and the scale of the visible light image collected by the visible light camera device; PI n represents the imaging pixels of the nth visible light camera device, PI MAX represents the maximum imaging pixel among the imaging pixels of the respective visible light camera devices; S n represents the area ratio between the smoke image in the visible light image collected by the nth visible light camera device and the visible light image collected by the nth visible light camera device.

7. The apparatus of claim 6, wherein, The camera device weight determination module is further configured to identify a smoke image of the flame from the visible light image collected by each visible light camera device.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images