Robot-based mine fire monitoring method, device, equipment and storage medium

Through robots collecting environmental and smoke-sensitive gas information in the mine, and determining the fire with the processing results, the problem of indefinite fire detection in the prior art is solved, and efficient and accurate fire monitoring is achieved.

CN113361420BActive Publication Date: 2024-11-26CCTEG CHINA COAL RES INST
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202110648237.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-10
Publication Date
2024-11-26
Estimated Expiration
2041-06-10

AI Technical Summary

Technical Problem

Existing mine fire detection methods are susceptible to environmental impacts, and the fiber distributed temperature measurement method has problems such as monitoring blind spots and equipment being easily damaged, resulting in unreliable and accurate detection.

Method used

The robot-based fire monitoring method is adopted to collect environmental information through the first device and the second device to collect smoke and sensitive gas information, and to determine whether the fire exists or not, thereby improving the reliability and accuracy of identification.

Benefits of technology

It realizes efficient and reliable fire monitoring in different areas of the mine, reduces blind spots, improves the accuracy and reliability of fire identification, and can detect fires in a short period of time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113361420B_ABST
    Figure CN113361420B_ABST
Patent Text Reader

Abstract

The present disclosure discloses a mine fire monitoring method, device, equipment and storage medium based on a robot, which relates to the field of computer technology. The specific implementation scheme is: obtaining first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of the current location of the robot; obtaining second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at the current location of the robot; processing the first monitoring information to obtain a first recognition result; processing the second monitoring information to obtain a second recognition result; determining whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Thus, the features of the environment, smoke and sensitive gas information at the current location of the robot are integrated, which can improve the reliability and accuracy of coal mine fire identification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a robot-based mine fire monitoring method, device, equipment and storage medium. Background Art

[0002] The frequent occurrence of coal mine fires poses a serious threat to the safe production of mines. Once a fire occurs, it will have serious consequences for the safe production of mines. In related technologies, the fire detection method is single and easily affected by the environment. For example, in actual detection, the optical fiber distributed temperature measurement method is prone to monitoring blind spots, and the optical fiber is difficult to install and easily damaged. Therefore, how to find a reliable, effective and highly accurate mine fire monitoring method is an urgent problem to be solved in the current mine safety. Summary of the invention

[0003] The present disclosure provides a robot-based mine fire monitoring method, device, computer equipment and storage medium.

[0004] According to a first aspect of the present disclosure, a robot-based mine fire monitoring method is provided, comprising:

[0005] Acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of a current location of the robot;

[0006] Acquire second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at a current location of the robot;

[0007] Processing the first monitoring information to obtain a first identification result;

[0008] Processing the second monitoring information to obtain a second identification result;

[0009] It is determined whether there is a fire at a current location of the robot according to the first recognition result and the second recognition result.

[0010] According to a second aspect of the present disclosure, a robot-based mine fire monitoring device is provided, comprising:

[0011] A first acquisition module, used to acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of a current location of the robot;

[0012] A second acquisition module, used to acquire second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at a current location of the robot;

[0013] A first processing module, used for processing the first monitoring information to obtain a first identification result;

[0014] A second processing module, used for processing the second monitoring information to obtain a second identification result;

[0015] A determination module is used to determine whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result.

[0016] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the above-mentioned embodiment.

[0020] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program is stored, wherein the computer instructions are used to cause the computer to execute the method described in the above-mentioned first embodiment.

[0021] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the method described in the above-mentioned first embodiment when executed by a processor.

[0022] The robot-based mine fire monitoring method, device, equipment and storage medium provided by the present disclosure have at least the following beneficial effects:

[0023] The device of the disclosed embodiment first obtains the first monitoring information collected by the first device in the robot, wherein the first device is used to collect the environment of the current location of the robot, obtains the second monitoring information collected by the second device in the robot, wherein the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then processes the first monitoring information to obtain the first recognition result, and processes the second monitoring information to obtain the second recognition result, and finally determines whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Therefore, since the first recognition result and the second recognition result are combined, the characteristics of the environment, smoke and sensitive gas information of the current location of the robot are integrated, the reliability and accuracy of coal mine fire identification can be improved, and since the method is based on a robot, fire monitoring in different areas can be achieved.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0026] Figure 1 A schematic diagram of a flow chart of a robot-based mine fire monitoring method provided by the present disclosure;

[0027] Figure 2 A schematic flow chart of another robot-based mine fire monitoring method provided by the present disclosure;

[0028] Figure 3 A schematic flow chart of another robot-based mine fire monitoring method provided by the present disclosure;

[0029] Figure 4 A structural block diagram of a robot-based mine fire monitoring device provided by the present disclosure;

[0030] Figure 5 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] The robot-based mine fire monitoring method provided by the present disclosure can be executed by the robot-based mine fire monitoring device provided by the present disclosure, and can also be executed by the robot provided by the present disclosure. The present disclosure is explained below by taking the robot-based mine fire monitoring device provided by the present disclosure to execute the robot-based mine fire monitoring method provided by the present disclosure as an example, which cannot be used as a limitation of the present disclosure and is hereinafter referred to as "device".

[0033] A robot-based mine fire monitoring method provided by the present disclosure is described in detail below with reference to the accompanying drawings.

[0034] Figure 1 A schematic flow chart of a robot-based mine fire monitoring method provided for one embodiment of the present disclosure.

[0035] like Figure 1 As shown, the robot-based mine fire monitoring method may include the following steps:

[0036] Step 101: Acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of the current location of the robot.

[0037] The first device may be a camera, such as a high-definition camera, an infrared camera, a night vision camera, etc., without limitation. It is understandable that the first device may be used to collect a video of the environment where the robot is located to obtain the first monitoring information.

[0038] Among them, the first monitoring information can be video image information. It can be understood that the device can use the first monitoring information to monitor the environment of the mine where the robot is located. For example, the first monitoring information can be used to identify whether there is flame, smoke, etc. in the environment, which can indicate characteristic information that the mine is in danger of fire. There is no limitation on this.

[0039] It should be noted that when the robot is conducting inspections or performing other operations, the device can collect information about the environment of the robot's current location. For example, the device can capture the robot's surrounding environment through a camera to obtain video information of the environment of the robot's current location. The device can then analyze the video information to monitor whether a fire has occurred at the robot's location.

[0040] Since the robot can continuously change its position when patrolling or performing other operations in the mine, the device can obtain first monitoring information at different locations in the mine to realize fire monitoring at various locations in the mine, thereby reducing blind spots.

[0041] Step 102, obtaining second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at the current location of the robot.

[0042] The second device may be a sensor, such as a photoelectric smoke sensor, a gas-sensitive smoke sensor, etc., or may be any component that has a certain measurement capability for smoke and sensitive gases, which is not limited in the present disclosure.

[0043] The second monitoring information may be the concentration of smoke or the concentration of sensitive gas, which is not limited.

[0044] It is understandable that when a fire occurs, it is usually accompanied by smoke. When the fire is serious, the smoke concentration at the location where the fire occurs is relatively high. Therefore, the device can use the smoke sensor to perform photoelectric monitoring of the smoke at the current location of the robot, and then determine whether there is a fire at the current location of the robot.

[0045] In addition, some sensitive gases usually appear in mines, such as carbon monoxide, sulfur dioxide, methane and other compounds. When a fire occurs in a mine, a large amount of carbon monoxide or other sensitive gases usually appear. Therefore, the device can collect sensitive gases in the air through the second device, so that the occurrence of the fire can be determined based on the change in the amount or concentration of the sensitive gas, and there is no limitation on this.

[0046] It should be noted that, since a variety of sensitive gases may appear when a fire occurs in a mine, and the characteristics of different types of sensitive gases may also be different, the present disclosure does not limit the second device and the second monitoring information.

[0047] Step 103: Process the first monitoring information to obtain a first identification result.

[0048] The first recognition result is the result of processing the first monitoring information. In order to more accurately identify the fire that may occur in the mine, the device can process the first monitoring information in different ways to obtain recognition results of different angles of the fire, such as smoke recognition results, flame recognition results, etc., without limitation. Smoke and flame are both characteristics of fire. The device can process the first monitoring information to determine whether flame or smoke appears in the environment where the robot is located.

[0049] For example, if the device wants to determine whether a flame appears in the environment where the robot is currently located, the device can pre-process the first monitoring information, that is, the video image, for example, the video image can be grayed, binarized, and filtered for denoising, and then the area of ​​the flame in each frame of the video is calculated. If the area of ​​the flame is less than a preset area threshold, it can be determined that no flame appears in the current video image. If the area of ​​the flame is greater than the preset area threshold, it can be considered that there is a high possibility that a flame appears in the current video. The device can then further analyze the video image containing the flame to determine whether a real flame appears in the video image, for example, by color analysis, gray gradient analysis, and other methods, which are not limited in the present disclosure.

[0050] Alternatively, if the device wants to determine whether smoke appears in the environment of the current location, the device can preprocess the first monitoring information, that is, the video image, wherein the preprocessing here may be different from the preprocessing performed by the device when determining whether flames appear in the environment of the current location of the robot. For example, the video image can be grayscaled, the image smoothed, etc., and then the smoke movement area in the video image can be segmented, and then the smoke area can be determined through the trained neural network, and there is no limitation on this.

[0051] Step 104: Process the second monitoring information to obtain a second identification result.

[0052] The second recognition result may be a recognition result of the device on smoke and sensitive gas information at the current location of the robot.

[0053] For example, after collecting the smoke information and temperature information of the robot's current location, the second device can determine the smoke concentration and sensitive gas concentration generated by the fire. If the smoke concentration and / or the concentration of sensitive gas is greater than the specified threshold, the second recognition result can be determined as the presence of smoke. If the smoke concentration and / or the concentration of sensitive gas is less than the specified threshold, the second recognition result can be determined as the absence of smoke. There is no limitation on this.

[0054] Step 105: Determine whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result.

[0055] It should be noted that in the present disclosure, the first recognition result and the second recognition result can be combined to achieve composite monitoring of fires, thereby improving the reliability, effectiveness and accuracy of mine fire monitoring, so that when a fire occurs in a mine, the fire can be discovered in a short time.

[0056] Specifically, the first recognition result can be divided into a smoke recognition result and a flame recognition result. If the flame recognition result is that there is flame, the device can determine that a fire has occurred in the current mine. The second recognition result is also the recognition result of smoke, and when the device determines whether a fire has occurred in the mine through smoke, it is necessary to combine the first recognition result and the second recognition result. That is, only when the smoke recognition result in the first recognition result is that there is smoke, and the second recognition result is also that there is smoke, can it be said that a fire has occurred in the current mine.

[0057] It can be understood that if the device detects either smoke or flame, it can be determined that there is a fire at the robot's current location, or if smoke and flame exist at the same time, it can be determined that there is a fire at the robot's current location.

[0058] It should be noted that after determining that there is a fire at the current location of the robot, the device can warn of the fire through an alarm device that can issue any type of alarm information, and the present disclosure is not limited here.

[0059] The device of the disclosed embodiment first obtains the first monitoring information collected by the first device in the robot, wherein the first device is used to collect the environment of the current location of the robot, obtains the second monitoring information collected by the second device in the robot, wherein the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then processes the first monitoring information to obtain the first recognition result, and processes the second monitoring information to obtain the second recognition result, and finally determines whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Therefore, since the first recognition result and the second recognition result are combined, the characteristics of the environment, smoke and sensitive gas information of the current location of the robot are integrated, the reliability and accuracy of coal mine fire identification can be improved, and since the method is based on a robot, fire monitoring in different areas can be achieved.

[0060] Figure 2 A schematic flow chart of another robot-based mine fire monitoring method provided in yet another embodiment of the present disclosure.

[0061] like Figure 2 As shown, the robot-based mine fire monitoring method may include the following steps:

[0062] Step 201: Acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of the current location of the robot.

[0063] Step 202, obtaining second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at the current location of the robot.

[0064] It should be noted that steps 201 and 202 may refer to the specific implementation process of the above-mentioned embodiment and will not be described in detail here.

[0065] Step 203: Perform motion recognition on the first monitoring information to determine each frame image containing a suspected smoke area.

[0066] The first monitoring information may be video information, that is, a video taken by the device at the current location of the robot, and the video may include environmental information around the robot.

[0067] It should be noted that the device can use motion recognition to obtain the area where smoke changes appear in the first monitoring information, so that the changed area can be extracted from the image in real time for further processing, thereby greatly improving the monitoring efficiency and accuracy.

[0068] Specifically, the device can process each frame image in the video to determine each frame image in the video containing suspected smoke areas. For example, each frame image in the video can be pre-processed, such as grayscale, image smoothing, etc., and then each frame image obtained after the pre-processing can be segmented, such as mean background modeling and motion area extraction, so as to obtain each frame image containing suspected smoke areas.

[0069] Step 204: input each frame image containing the suspected smoke area into the trained neural network model to determine the smoke area contained in the first monitoring information.

[0070] It should be noted that in order to better distinguish between suspected smoke areas and smoke areas, the device can input each frame image containing the suspected smoke area into a trained neural network model, such as a feature extractor, without limitation, so that the smoke area can be extracted using the trained neural network model.

[0071] In order to improve the reliability of smoke area monitoring, the neural network model can combine smoke motion features, smoke texture features and smoke blur model features to extract the smoke area in each frame image containing suspected smoke areas. Thus, the smoke area with better confidence in the image is determined through the rich detail features of the smoke, thereby reducing the possibility of false detection caused by targets similar to smoke such as water mist, so as to realize smoke monitoring in complex environments.

[0072] Step 205: Determine a first recognition result according to the area of ​​the smoke region.

[0073] Specifically, if an image with a smoke region area larger than a specified area threshold appears in each frame image containing a suspected smoke region, it means that smoke appears in the environment where the current robot is located. If the area of ​​the smoke region is larger than the specified area threshold, the first recognition result is that there is smoke, and if the area of ​​the smoke region is smaller than the specified area threshold, the first recognition result is that there is no smoke.

[0074] Step 206: Process the second monitoring information to obtain a second identification result.

[0075] Optionally, the device can determine the smoke concentration and the concentration of sensitive gas at the current location of the inspection robot based on the second monitoring information, and then determine whether there is smoke at the current location of the robot based on the concentration of the smoke and the sensitive gas.

[0076] Specifically, the device can determine the smoke concentration and the concentration of sensitive gas in the air through a smoke sensor and a photoelectric monitoring device, which is not limited.

[0077] Specifically, the smoke concentration threshold and the sensitive gas concentration threshold can be pre-set. If the concentration of smoke and / or sensitive gas is greater than the specified threshold, it means that there is smoke at the current location of the robot. If the concentration of smoke and / or sensitive gas is less than the specified threshold, it means that there is no smoke at the current location of the robot.

[0078] Step 207: Determine whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result.

[0079] Specifically, if the first recognition result and the second recognition result both show that there is smoke, it means that there is a fire at the robot's current location. If only one of the first recognition result and the second recognition result shows that there is smoke, it means that there may be a fire at the robot's current location. If the first recognition result and the second recognition result both show that there is no smoke, it means that there is no fire at the robot's current location. This disclosure is not limited here.

[0080] In the disclosed embodiment, the device first obtains the first monitoring information collected by the first device in the robot, the first device is used to collect the environmental information of the current location of the robot, and then obtains the second monitoring information collected by the second device in the robot, the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then performs motion recognition on the first monitoring information to determine each frame image containing a suspected smoke area, and inputs each frame image containing a suspected smoke area into the trained neural network model to determine the smoke area contained in the first monitoring information, and finally determines whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Therefore, due to the combination of the first recognition result and the second recognition result, the device can determine whether a fire has occurred in the mine where the current robot is located from different angles of the smoke, which effectively improves the accuracy and reliability of monitoring.

[0081] Figure 3 A schematic flow chart of another robot-based mine fire monitoring method provided in an embodiment of the present disclosure.

[0082] like Figure 3 As shown, the robot-based mine fire monitoring method may include the following steps:

[0083] Step 301: Acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of the current location of the robot.

[0084] Step 302, obtaining second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at the current location of the robot.

[0085] It should be noted that steps 301 and 302 may refer to the specific implementation process of the above-mentioned embodiment, which will not be described in detail here.

[0086] Step 303: pre-process the first monitoring information to determine the flame area contained in the video information.

[0087] Specifically, the device may first pre-process the first monitoring information, that is, the video image information, such as grayscale, binarization, and denoising, and then calculate the area of ​​the flame region in the video image, which is not limited in the present disclosure.

[0088] Step 304: Determine a first flame judgment result according to the area of ​​the flame region.

[0089] Specifically, the device can compare the area of ​​the flame region with a specified area threshold to obtain a first flame judgment result. In the present disclosure, the area of ​​the flame region greater than the specified threshold is taken as the first specified result, and if the area of ​​the flame region is less than or equal to the specified threshold, the first flame judgment result is not the first specified result.

[0090] Optionally, when the first judgment result is not the first specified result, the device may determine that the first recognition result is that there is no flame at the current position of the robot.

[0091] Optionally, when the first judgment result is the first designated result, the device may further process the video image to determine whether there is a flame at the current location of the robot.

[0092] Step 305 , when the first flame judgment result is the first designated result, a first color analysis is performed on the flame area to determine a second flame judgment result.

[0093] Specifically, if the current first flame judgment result is the first specified result, it means that the area of ​​the flame region is greater than the specified threshold, and then the device can perform a first color analysis on the flame region, for example, RGB color analysis (R represents red, G represents green, and B represents blue), that is, using RGB color as a criterion to perform color analysis on the image of the flame region.

[0094] It is understandable that the device can also use the HSV color space or the HLS color space to analyze the flame area, which is not limited here.

[0095] In the present disclosure, the result that the RGB color threshold is greater than the preset RGB color threshold can be used as the second specified result. When the image RGB color threshold of the flame area is greater than the preset RGB color threshold, the device can further process the image of the flame area.

[0096] Optionally, when the first flame judgment result is not the second specified result, the device may determine that the first recognition result is that there is no flame at the current position of the robot.

[0097] Step 306: When the second flame judgment result is the second designated result, a second color analysis is performed on the flame area to determine a third flame judgment result.

[0098] Specifically, if the current second flame judgment result is the second specified result, it means that the image RGB color threshold of the flame area is greater than the preset RGB color threshold, and then the device can perform a second color analysis on the flame area, for example, YCbCr flame color analysis (Y is the brightness signal, Cb is the blue component color difference, and Cr is the red component color difference), that is, using YCbCr color as a criterion to perform color analysis on the image of the flame area.

[0099] In the present disclosure, the result that the YCbCr color threshold is greater than the preset YCbCr color threshold can be used as the second specified result. If the YCbCr color threshold is greater than the preset YCbCr color threshold, the device can further process the image of the flame area.

[0100] Optionally, when the second flame judgment result is not the second specified result, the device may determine that the first recognition result is that there is no flame at the current position of the robot.

[0101] Step 307: When the third flame judgment result is the third designated result, flame tip angle analysis is performed on the flame area to determine the first recognition result.

[0102] Specifically, if the third flame judgment result is the third specified result, that is, the YCbCr color threshold is greater than the preset YCbCr color threshold, the device can perform flame graph grayscale gradient analysis and flame tip angle analysis on the flame area image, which is not limited.

[0103] Among them, the sharp corner refers to the protrusion on the edge of the flame shape. The fixed point of the sharp corner is the local extreme point of the flame image. The flame sharp corner has a narrow and long feature. When a mine fire occurs, the number of sharp corners shows irregular jumps. Therefore, the device can determine whether a fire has occurred by identifying the number of sharp corners.

[0104] Thus, the device can determine that the first recognition result is that there is flame at the current position of the robot when the number of sharp corners in the flame area reaches a specified threshold, and determine that the first recognition result is that there is no flame at the current position of the robot when the number of sharp corners in the flame area is less than the specified threshold.

[0105] Step 308: Process the second monitoring information to obtain a second identification result.

[0106] Step 309: Determine whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result.

[0107] It should be noted that the specific implementation process of steps 308 and 309 can refer to the above-mentioned embodiments 104 and 105, and will not be repeated here.

[0108] In the disclosed embodiment, the device first obtains the first monitoring information collected by the first device in the robot, wherein the first device is used to collect the environmental information of the current location of the robot, and then obtains the second monitoring information collected by the second device in the robot, wherein the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then determines the first flame judgment result according to the area of ​​the flame area, and when the first flame judgment result is the first specified result, the flame area is subjected to a first color analysis to determine the second flame judgment result, and when the second flame judgment result is the second specified result, the flame area is subjected to a second color analysis to determine the third flame judgment result, and when the third flame judgment result is the third specified result, the flame area is subjected to a flame sharp angle analysis, and when the flame area has a sharp angle, it is determined that the first recognition result is that there is a flame at the current location of the robot, and then the second monitoring information is processed to obtain the second recognition result, and finally, according to the first recognition result and the second recognition result, it is determined whether there is a fire at the current location of the robot. Thus, due to the combination of the first recognition result and the second recognition result, the device can determine whether there is a fire in the mine where the current robot is located from the perspective of smoke and flame, which effectively improves the accuracy and reliability of monitoring.

[0109] In order to implement the above embodiment, the embodiment of the present disclosure also proposes a robot-based mine fire monitoring device. Figure 4 A schematic structural diagram of a robot-based mine fire monitoring device provided in an embodiment of the present disclosure.

[0110] like Figure 4 As shown, the robot-based mine fire monitoring device includes: a first acquisition module 410 , a second acquisition module 420 , a first processing module 430 , a second processing module 440 and a determination module 450 .

[0111] A first acquisition module 410 is used to acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of the current location of the robot;

[0112] A second acquisition module 420, used to acquire second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at the current location of the robot;

[0113] A first processing module 430 is used to process the first monitoring information to obtain a first identification result;

[0114] A second processing module 440 is used to process the second monitoring information to obtain a second identification result;

[0115] The determination module 450 is used to determine whether there is a fire at the current location of the robot according to the first recognition result and the second recognition result.

[0116] Optionally, the first monitoring information is video information, and the first processing module is specifically used to:

[0117] Performing motion recognition on the first monitoring information to determine each frame image containing a suspected smoke area;

[0118] Inputting each frame image containing the suspected smoke area into the trained neural network model to determine the smoke area contained in the first monitoring information;

[0119] A first recognition result is determined according to the area of ​​the smoke region.

[0120] Optionally, the first monitoring information is video information, and the first processing module includes:

[0121] A first determining unit, configured to pre-process the first monitoring information to determine a flame area included in the video information;

[0122] A second determination unit, used to determine the first flame judgment result according to the area of ​​the flame region;

[0123] a third determination unit, configured to perform a first color analysis on the flame area to determine a second flame determination result when the first flame determination result is a first specified result;

[0124] a fourth determination unit, configured to perform a second color analysis on the flame area to determine a third flame determination result when the second flame determination result is a second specified result;

[0125] The fifth determination unit is used to perform flame tip angle analysis on the flame area to determine the first recognition result when the third flame judgment result is the third designated result.

[0126] Optionally, the third determining unit is further configured to:

[0127] When the first judgment result is not the first designated result, it is determined that the first recognition result is that there is no flame at the current position of the robot.

[0128] Optionally, the fourth determining unit is further configured to:

[0129] When the second judgment result is not the second designated result, the first recognition result is determined to be no flame.

[0130] Optionally, the fifth determining unit is further configured to:

[0131] In a case where the third judgment result of flame is not the third designated result, the first recognition result is determined to be no flame.

[0132] Optionally, the second processing module is specifically used for:

[0133] Determine the smoke concentration and the concentration of sensitive gas at the current location of the inspection robot according to the second monitoring information;

[0134] According to the concentration of smoke and sensitive gases, determine whether there is smoke at the current location of the robot.

[0135] The device of the disclosed embodiment first obtains the first monitoring information collected by the first device in the robot, wherein the first device is used to collect the environment of the current location of the robot, obtains the second monitoring information collected by the second device in the robot, wherein the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then processes the first monitoring information to obtain the first recognition result, and processes the second monitoring information to obtain the second recognition result, and finally determines whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Therefore, since the first recognition result and the second recognition result are combined, the characteristics of the environment, smoke and sensitive gas information of the current location of the robot are integrated, the reliability and accuracy of coal mine fire identification can be improved, and since the method is based on a robot, fire monitoring in different areas can be achieved.

[0136] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0137] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0138] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0139] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a robot-based mine fire monitoring method. For example, in some embodiments, the robot-based mine fire monitoring method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the robot-based mine fire monitoring method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the robot-based mine fire monitoring method in any other appropriate manner (eg, by means of firmware).

[0141] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0143] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0146] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0147] The device of the disclosed embodiment first obtains the first monitoring information collected by the first device in the robot, wherein the first device is used to collect the environment of the current location of the robot, obtains the second monitoring information collected by the second device in the robot, wherein the second device is used to collect the smoke and sensitive gas information of the current location of the robot, and then processes the first monitoring information to obtain the first recognition result, and processes the second monitoring information to obtain the second recognition result, and finally determines whether there is a fire at the current location of the robot based on the first recognition result and the second recognition result. Therefore, since the first recognition result and the second recognition result are combined, the characteristics of the environment, smoke and sensitive gas information of the current location of the robot are integrated, the reliability and accuracy of coal mine fire identification can be improved, and since the method is based on a robot, fire monitoring in different areas can be achieved.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A robot-based mine fire monitoring method, characterized in that: include: Acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of a current location of the robot; Acquire second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at a current location of the robot; Processing the first monitoring information to obtain a first identification result; Processing the second monitoring information to obtain a second identification result; Determining whether there is a fire at a current location of the robot according to the first recognition result and the second recognition result; The first monitoring information is video information, and the processing of the first monitoring information to obtain a first recognition result includes: Preprocessing the first monitoring information to determine a flame area contained in the video information; Determine a first flame judgment result according to the area of ​​the flame region, and take the area of ​​the flame region being greater than a specified threshold as the first specified result; When the first flame judgment result is the first designated result, performing a first color analysis on the flame area to determine a second flame judgment result, and taking a result where the image RGB color threshold of the flame area is greater than a preset RGB color threshold as the second designated result; When the second flame judgment result is the second designated result, performing a second color analysis on the flame area to determine a third flame judgment result, and taking a result where the YCbCr color threshold is greater than a preset YCbCr color threshold as the third designated result; When the third flame judgment result is the third designated result, performing flame tip angle analysis on the flame area to determine the first recognition result, the flame tip angle refers to a protrusion on the edge of the flame shape; The processing of the second monitoring information to obtain a second identification result includes: Determine the smoke concentration and the concentration of sensitive gas at the current location of the inspection robot according to the second monitoring information; Determine whether there is smoke at the current location of the robot according to the smoke concentration and the concentration of the sensitive gas, wherein if the smoke concentration and the concentration of the sensitive gas are greater than a specified threshold, determine that the second recognition result is smoke, and if the smoke concentration and the concentration of the sensitive gas are less than the specified threshold, determine that the second recognition result is no smoke; Among them, the first recognition result is divided into a smoke recognition result and a flame recognition result. If the flame recognition result is that there is flame, it is determined that a fire has occurred in the current mine. Among them, only when the smoke recognition result in the first recognition result is that there is smoke and the second recognition result is also that there is smoke, it is determined that a fire has occurred in the current mine.

2. The method according to claim 1, characterized in that The first monitoring information is video information, and the processing of the first monitoring information to obtain a first recognition result includes: Performing motion recognition on the first monitoring information to determine each frame image containing a suspected smoke area; Inputting each frame image containing the suspected smoke area into the trained neural network model to determine the smoke area contained in the first monitoring information; A first recognition result is determined according to the area of ​​the smoke region.

3. The method according to claim 1, characterized in that After determining the first flame judgment result according to the area of ​​the flame region, the method further includes: When the first flame judgment result is not the first designated result, the first recognition result is determined to be that there is no flame at the current position of the robot.

4. The method according to claim 1, characterized in that: After performing the first color analysis on the flame area to determine the second flame judgment result, the method further includes: When the second flame determination result is not the second designated result, the first recognition result is determined to be no flame.

5. The method according to claim 1, characterized in that After performing a second color analysis on the flame area to determine a third flame breaking result, the method further includes: In a case where the third flame judgment result of the flame is not the third designated result, the first recognition result is determined to be no flame.

6. A robot-based mine fire monitoring device, characterized in that: include: A first acquisition module, used to acquire first monitoring information collected by a first device in the robot, wherein the first device is used to collect environmental information of a current location of the robot; A second acquisition module, used to acquire second monitoring information collected by a second device in the robot, wherein the second device is used to collect smoke and sensitive gas information at a current location of the robot; A first processing module, used for processing the first monitoring information to obtain a first identification result; A second processing module, used for processing the second monitoring information to obtain a second identification result; a determination module, configured to determine whether there is a fire at a current location of the robot according to the first recognition result and the second recognition result; The first monitoring information is video information, and the first processing module includes: A first determining unit, configured to pre-process the first monitoring information to determine a flame area included in the video information; A second determination unit is used to determine a first flame judgment result according to the area of ​​the flame region, and to take the area of ​​the flame region being greater than a specified threshold as a first specified result; a third determination unit, configured to, when the first flame judgment result is the first designated result, perform a first color analysis on the flame area to determine a second flame judgment result, and take a result where the image RGB color threshold of the flame area is greater than a preset RGB color threshold as the second designated result; a fourth determination unit, configured to, when the second flame judgment result is a second designated result, perform a second color analysis on the flame area to determine a third flame judgment result, and take a result in which the YCbCr color threshold is greater than a preset YCbCr color threshold as the third designated result; A fifth determining unit is used for, when the third flame judgment result is a third designated result, performing flame tip angle analysis on the flame region to determine the first recognition result, wherein the flame tip angle refers to a protrusion on the edge of the flame shape; The second processing module is specifically used for: Determine the smoke concentration and the concentration of sensitive gas at the current location of the inspection robot according to the second monitoring information; Determine whether there is smoke at the current location of the robot according to the smoke concentration and the concentration of the sensitive gas, wherein if the smoke concentration and the concentration of the sensitive gas are greater than a specified threshold, determine that the second recognition result is smoke, and if the smoke concentration and the concentration of the sensitive gas are less than the specified threshold, determine that the second recognition result is no smoke; Among them, the first recognition result is divided into a smoke recognition result and a flame recognition result. If the flame recognition result is that there is flame, it is determined that a fire has occurred in the current mine. Among them, only when the smoke recognition result in the first recognition result is that there is smoke and the second recognition result is also that there is smoke, it is determined that a fire has occurred in the current mine.

7. The device according to claim 6, characterized in that The first monitoring information is video information, and the first processing module is specifically used to: Performing motion recognition on the first monitoring information to determine each frame image containing a suspected smoke area; Inputting each frame image containing the suspected smoke area into the trained neural network model to determine the smoke area contained in the first monitoring information; A first recognition result is determined according to the area of ​​the smoke region.

8. The device according to claim 6, characterized in that The third determining unit is further configured to: When the first flame judgment result is not the first designated result, the first recognition result is determined to be that there is no flame at the current position of the robot.

9. The device according to claim 6, characterized in that The fourth determining unit is further configured to: When the second flame determination result is not the second designated result, the first recognition result is determined to be no flame.

10. The device according to claim 6, characterized in that The fifth determining unit is further configured to: In a case where the third flame judgment result of the flame is not the third designated result, the first recognition result is determined to be no flame.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Robot cable gallery field fire early warning and fire extinguishment method, device and system

    CN108295407A

  • Robot Fire Detection Method

    CN109145689A

  • Fire-extinguishing scheduling method and system for fire-fighting robots of electric tunnel

    CN111111074A

  • Robot positioning method and apparatus, intelligent robot, and storage medium

    US20220362939A1