Coal mine underground safety monitoring semantic recognition method and system

Abstract

The invention provides an underground coal mine safety monitoring semantic recognition method and system. The underground coal mine safety monitoring semantic recognition method comprises the steps that in the technical scheme, video data are collected through a camera device installed in an underground coal mine; framing processing is carried out on the video data, image preprocessing is carried out, and an underground image is generated; extracting image features of the underground image; classifying pixels in the underground image according to the image features so as to determine a semantic recognition result corresponding to the underground image according to a pixel classification result; and feeding back the semantic recognition result to a security monitoring platform. Video data are captured in real time through the high-definition camera device, the system can intelligently recognize semantic content of underground images, and finally accurate semantic information is fed back to the safety monitoring platform in real time, so that managers can quickly master underground dynamic conditions, safety accidents are effectively prevented, and the safety and management efficiency of coal mine operation are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and system for semantic recognition of safety monitoring in underground coal mines. Background Art

[0002] my country is rich in coal resources, but the mining conditions are complex and natural disasters are serious. In order to ensure the safe production of coal mines, in addition to further strengthening the awareness of coal mine safety management, the key is to establish a coal mine underground safety monitoring system to form a reliable safety early warning mechanism and management decision-making information channel above and below the coal mine. In recent years, with the development of network technology, monitoring technology is constantly advancing in the direction of unmanned, intelligent and digital. Coal mine safety monitoring systems have been widely used, but there are still some limitations.

[0003] Existing systems mainly focus on monitoring and controlling the environmental parameters of coal mines and the working status of electromechanical equipment in the production and transportation of mines. However, these systems often lack semantic recognition capabilities and cannot intelligently identify and warn abnormal scenes in monitoring videos. In addition, the underground environment of coal mines is complex, and signal collection is often interfered by various factors, resulting in low efficiency and accuracy of semantic recognition for safety monitoring. Summary of the invention

[0004] The embodiments of the present application provide a method and system for semantic recognition of safety monitoring in underground coal mines, thereby at least to a certain extent solving the problem of low efficiency and accuracy of semantic recognition of safety monitoring.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] According to one aspect of the present application, a semantic recognition method for underground safety monitoring in a coal mine is provided, comprising: collecting video data by means of a camera installed in an underground coal mine; performing frame processing on the video data and image preprocessing to generate an underground image; extracting image features of the underground image; classifying pixels in the underground image according to the image features to determine a semantic recognition result corresponding to the underground image according to the pixel classification result; and feeding back the semantic recognition result to a safety monitoring platform.

[0007] In the present application, based on the aforementioned scheme, the video data is collected by means of a camera installed underground in a coal mine, including: installing a camera in advance underground in the coal mine; collecting video data by means of the camera, and transmitting the video data to a monitoring center by wire or wireless means.

[0008] In the present application, based on the aforementioned scheme, the video data is framed and image preprocessed to generate a downhole image, including: frame-processing the video data to generate a single-frame image; preprocessing the single-frame image to generate a downhole image.

[0009] In the present application, based on the aforementioned solution, the extracting of image features of the downhole image includes: performing convolution processing on the downhole image according to a deep convolutional neural network, and outputting image features.

[0010] In the present application, based on the aforementioned scheme, the pixels in the downhole image are classified according to the image features to determine the semantic recognition result corresponding to the downhole image according to the pixel classification result, including: classifying the pixels in the downhole image according to the fully connected layer of the deep convolutional neural network to generate a pixel classification result; determining the semantic recognition result corresponding to the downhole image according to the pixel classification result.

[0011] In the present application, based on the aforementioned solution, the feeding back of the semantic recognition result to the safety monitoring platform includes: marking the semantic recognition result at the corresponding position of the downhole image; and feeding back the downhole image to the safety monitoring platform.

[0012] In the present application, based on the aforementioned solution, it also includes: issuing an alarm based on the semantic recognition result.

[0013] According to one aspect of the present application, a semantic recognition system for underground safety monitoring in a coal mine is provided, comprising:

[0014] A collection unit, used for collecting video data through a camera installed in the coal mine;

[0015] An image unit, used for performing frame processing on the video data and image preprocessing to generate downhole images;

[0016] An extraction unit, used for extracting image features of the downhole image;

[0017] A recognition unit, used for classifying pixels in the downhole image according to the image features, so as to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result;

[0018] The feedback unit is used to feed back the semantic recognition result to the security monitoring platform.

[0019] In the present application, based on the aforementioned scheme, the video data is collected by means of a camera installed underground in a coal mine, including: installing a camera in advance underground in the coal mine; collecting video data by means of the camera, and transmitting the video data to a monitoring center by wire or wireless means.

[0020] In the present application, based on the aforementioned scheme, the video data is framed and image preprocessed to generate a downhole image, including: frame-processing the video data to generate a single-frame image; preprocessing the single-frame image to generate a downhole image.

[0021] In the present application, based on the aforementioned solution, the extracting of image features of the downhole image includes: performing convolution processing on the downhole image according to a deep convolutional neural network, and outputting image features.

[0022] In the present application, based on the aforementioned scheme, the pixels in the downhole image are classified according to the image features to determine the semantic recognition result corresponding to the downhole image according to the pixel classification result, including: classifying the pixels in the downhole image according to the fully connected layer of the deep convolutional neural network to generate a pixel classification result; determining the semantic recognition result corresponding to the downhole image according to the pixel classification result.

[0023] In the present application, based on the aforementioned solution, the feeding back of the semantic recognition result to the safety monitoring platform includes: marking the semantic recognition result at the corresponding position of the downhole image; and feeding back the downhole image to the safety monitoring platform.

[0024] In the present application, based on the aforementioned solution, it also includes: issuing an alarm based on the semantic recognition result.

[0025] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for semantic recognition of underground safety monitoring in coal mines as described in the above-mentioned embodiment is implemented.

[0026] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the semantic recognition method for underground safety monitoring in coal mines as described in the above-mentioned embodiments.

[0027] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the semantic recognition method for underground safety monitoring of coal mines provided in the above-mentioned various optional implementations.

[0028] In the technical solution of the present application, video data is collected by a camera installed in a coal mine; the video data is framed and image preprocessed to generate an underground image; the image features of the underground image are extracted; the pixels in the underground image are classified according to the image features to determine the semantic recognition results corresponding to the underground image according to the pixel classification results; and the semantic recognition results are fed back to the security monitoring platform. Video data is captured in real time by a high-definition camera, and these data are converted into clear and accurate underground images after frame division and image preprocessing. Advanced image processing technology is used to extract key features in the image, such as color, texture, etc., and then the various objects in the underground are accurately distinguished through a sophisticated pixel classification algorithm. Based on these classification results, the system can intelligently identify the semantic content of the underground image, and finally feed back the accurate semantic information to the security monitoring platform in real time, so that management personnel can quickly grasp the underground dynamics, effectively prevent safety accidents, and significantly improve the safety and management efficiency of coal mine operations.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 A flowchart of a method for semantic recognition of safety monitoring in underground coal mines in one embodiment of the present application is schematically shown.

[0032] Figure 2 A flowchart for determining semantic recognition results of downhole images in one embodiment of the present application is schematically shown.

[0033] Figure 3 A schematic diagram of a semantic recognition system for underground safety monitoring in a coal mine in an embodiment of the present application is schematically shown.

[0034] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0036] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0039] The implementation details of the technical solution of this application are described in detail below:

[0040] Figure 1 A flowchart of a method for semantic recognition of safety monitoring in underground coal mines according to an embodiment of the present application is shown. Figure 1 As shown, the semantic recognition method for underground safety monitoring of coal mines includes at least steps S110 to S150, which are described in detail as follows:

[0041] In step S110, video data is collected by a camera installed in the coal mine.

[0042] In one embodiment of the present application, video data is collected by a camera installed in a coal mine, including:

[0043] Install camera equipment in coal mines in advance;

[0044] Video data is collected by cameras and transmitted to the monitoring center via wired or wireless means.

[0045] In one embodiment of the present application, the camera device is installed in key areas, such as wellheads, tunnel intersections, working surfaces, etc., to comprehensively monitor the underground conditions. At the same time, ensure that the camera device can cover areas where potential safety hazards may exist. The camera device adopts continuous or timed acquisition to ensure real-time acquisition of underground conditions. At the same time, set a reasonable storage strategy to save important video data.

[0046] Optionally, the video data can be transmitted to the monitoring center via wired or wireless means. Wired transmission is stable and reliable, but laying the line is more complicated; wireless transmission is flexible and convenient, but signal coverage and interference issues need to be considered. When choosing a transmission method, make a trade-off based on the actual situation.

[0047] Optionally, encryption measures are taken during the transmission and storage of video data to ensure data security. At the same time, a corresponding access control mechanism is established to prevent unauthorized access and leakage.

[0048] The above solution can collect real-time video data from underground mines through the camera installed in the underground mines. These data are comprehensive and accurate, and can truly reflect the underground environment, equipment operation status and personnel activities. This is crucial for the safe production of coal mines, because real-time monitoring data helps to discover potential safety hazards in a timely manner.

[0049] In step S120, the video data is frame-processed and image preprocessed to generate a downhole image.

[0050] In one embodiment of the present application, the video data is framed and image preprocessed to generate a downhole image, including:

[0051] Performing frame processing on the video data to generate a single-frame image;

[0052] The single frame image is preprocessed to generate a downhole image.

[0053] In one embodiment of the present application, the video data is framed and processed to generate a single frame image. In the decoded video stream, each frame image is extracted at a set time interval. It can be set to extract all frames, or extract frames in a specific time period or under specific conditions according to requirements.

[0054] Specifically, in the process of performing frame processing on the video data, the image quality of the decoded video stream is evaluated to generate image quality parameters. Then, the frame frequency is determined according to the quality parameters, so as to decompose the image according to the frame frequency to generate a single frame image. The above process performs frame processing on the collected video data and converts a continuous video stream into a series of independent image frames.

[0055] The single frame image is preprocessed to generate an underground image. In this embodiment, the image frame is preprocessed, including steps such as denoising, enhancement, and restoration, to improve image quality and improve the accuracy of subsequent processing. For example, the degraded mine image can be enhanced by using a dark primary color prior and an atmospheric scattering model to reduce the impact of image reflection light and enhance the realism of the image.

[0056] Specifically, the single-frame image Z(x, y) is denoised by the following formula to generate a denoised image G(x, y):

[0057]

[0058] Among them, x, y represent the pixel coordinates of the image, and σ represents the variance of the pixel value.

[0059] After that, the contrast of the denoised image G(x,y) is adjusted to generate the downhole image G′(x,y):

[0060] G′(x,y)=α·G(x,y)+β

[0061] Through the above process, the image is denoised and contrast adjusted to adapt to the application scenario in the coal mine, reduce the impact and interference of the external environment on image acquisition, and improve the clarity of the image.

[0062] In step S130, image features of the downhole image are extracted.

[0063] In one embodiment of the present application, the downhole image is convolved according to a deep convolutional neural network, and the output image feature O(i, j) is:

[0064]

[0065] Among them, I(i,j) is the input image, K(m,n) is the convolution kernel, and m and n represent the sizes of the convolution kernel respectively.

[0066] In one embodiment of the present application, key features are extracted from the preprocessed image, including color, texture, shape, etc., which can be used for subsequent pixel classification and semantic recognition. The feature extraction process needs to ensure that the extracted features are representative, robust, and concise to facilitate subsequent processing.

[0067] In step S140, pixels in the downhole image are classified according to the image features, so as to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result.

[0068] like Figure 2As shown, in one embodiment of the present application, pixels in the downhole image are classified according to the image features to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result, including:

[0069] S210, classifying pixels in the downhole image according to a fully connected layer of a deep convolutional neural network to generate a pixel classification result;

[0070] S220, determining a semantic recognition result corresponding to the downhole image according to the pixel classification result.

[0071] In this embodiment, a fully connected layer or a convolutional layer is used to classify each pixel, and the classification score S(i,j) is generated as:

[0072] S(i,j)=W o O(i,j)+b o

[0073] Among them, W o 、b o are the weights and biases of the classifier, and O(i,j) is the pixel feature on the downhole image. The above process classifies the pixels in the downhole image according to the extracted image features. The classification result can reflect the type, location, size and other information of the downhole object.

[0074] Afterwards, the semantic recognition result corresponding to the downhole image is determined according to the pixel classification result, specifically, the probability distribution of the semantics of the downhole image is determined according to the classification score corresponding to each pixel:

[0075]

[0076] Among them, e represents the base of natural logarithm, n and m represent the number of pixels in the horizontal and vertical directions of the downhole image. Through the above calculation process, the semantic probability distribution of the downhole image can be obtained, and then the corresponding semantic recognition result can be determined according to the probability distribution. Specifically, it can be determined by the corresponding relationship between the probability distribution and the recognition result.

[0077] The above process performs semantic recognition on underground images based on the results of pixel classification to determine the categories and attributes of objects in the images. The results of semantic recognition can be used to judge the safety status of the underground mine, such as whether there are any illegal operations by personnel, equipment failures, or environmental parameters exceeding the standard.

[0078] In step S150, the semantic recognition result is fed back to the security monitoring platform.

[0079] In one embodiment of the present application, feeding back the semantic recognition result to the security monitoring platform includes:

[0080] Marking the semantic recognition result at the corresponding position of the downhole image;

[0081] The downhole image is fed back to the safety monitoring platform.

[0082] In one embodiment of the present application, different colors are assigned to different semantic categories, and then these colors are filled into the positions of corresponding pixels in the original image. In this way, the distribution of different semantic categories in the image can be intuitively seen through the color differences.

[0083] Optionally, for larger objects or regions, a bounding box can be drawn to mark its location. A bounding box usually uses a rectangle or polygon to approximate the outline of the object.

[0084] The annotated underground images are transmitted to the safety monitoring platform through the network. This can be achieved through a local area network, a wide area network, or the Internet, depending on the deployment and communication requirements of the system. During the transmission process, the size, format, and quality of the image may need to be considered to ensure the efficiency and reliability of data transmission.

[0085] Through the above steps, we can annotate the semantic recognition results of underground images on the original images in a visual way, and feed back the annotated images to the safety monitoring platform in a timely manner. This helps relevant personnel quickly understand the status of the underground environment, discover potential safety hazards in a timely manner, and take effective measures to ensure production safety.

[0086] In one embodiment of the present application, specific alarm information is generated based on the recognized semantic information and the set alarm conditions. The alarm information should include key information such as alarm type, location, time, severity, etc. Select the appropriate alarm method according to the actual situation, such as sound and light alarm, SMS alarm, email alarm, etc. Ensure that the alarm information can be conveyed to relevant personnel in a timely and accurate manner.

[0087] By setting reasonable alarm trigger conditions, selecting appropriate alarm methods, and responding and processing alarm information in a timely manner, the safety and efficiency of underground operations can be effectively improved.

[0088] In the technical solution of the present application, video data is collected by a camera installed in a coal mine; the video data is framed and image preprocessed to generate an underground image; the image features of the underground image are extracted; the pixels in the underground image are classified according to the image features to determine the semantic recognition results corresponding to the underground image according to the pixel classification results; and the semantic recognition results are fed back to the security monitoring platform. Video data is captured in real time by a high-definition camera, and these data are converted into clear and accurate underground images after frame division and image preprocessing. Advanced image processing technology is used to extract key features in the image, such as color, texture, etc., and then the various objects in the underground are accurately distinguished through a sophisticated pixel classification algorithm. Based on these classification results, the system can intelligently identify the semantic content of the underground image, and finally feed back the accurate semantic information to the security monitoring platform in real time, so that management personnel can quickly grasp the underground dynamics, effectively prevent safety accidents, and significantly improve the safety and management efficiency of coal mine operations.

[0089] The following introduces an embodiment of the device of the present application, which can be used to execute the semantic recognition method for underground safety monitoring in coal mines in the above-mentioned embodiment of the present application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the semantic recognition method for underground safety monitoring in coal mines in the above-mentioned embodiment of the present application.

[0090] Figure 3 A block diagram of a semantic recognition system for underground safety monitoring in a coal mine according to an embodiment of the present application is shown.

[0091] Reference Figure 3 As shown, according to an embodiment of the present application, a semantic recognition system for underground safety monitoring of coal mines includes:

[0092] A collection unit, used for collecting video data through a camera installed in the coal mine;

[0093] An image unit, used for performing frame processing on the video data and image preprocessing to generate downhole images;

[0094] An extraction unit, used for extracting image features of the downhole image;

[0095] A recognition unit, used for classifying pixels in the downhole image according to the image features, so as to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result;

[0096] The feedback unit is used to feed back the semantic recognition result to the security monitoring platform.

[0097] In the present application, based on the aforementioned scheme, the video data is collected by means of a camera installed underground in a coal mine, including: installing a camera in advance underground in the coal mine; collecting video data by means of the camera, and transmitting the video data to a monitoring center by wire or wireless means.

[0098] In the present application, based on the aforementioned scheme, the video data is framed and image preprocessed to generate a downhole image, including: frame-processing the video data to generate a single-frame image; preprocessing the single-frame image to generate a downhole image.

[0099] In the present application, based on the aforementioned solution, the extracting of image features of the downhole image includes: performing convolution processing on the downhole image according to a deep convolutional neural network, and outputting image features.

[0100] In the present application, based on the aforementioned scheme, the pixels in the downhole image are classified according to the image features to determine the semantic recognition result corresponding to the downhole image according to the pixel classification result, including: classifying the pixels in the downhole image according to the fully connected layer of the deep convolutional neural network to generate a pixel classification result; determining the semantic recognition result corresponding to the downhole image according to the pixel classification result.

[0101] In the present application, based on the aforementioned solution, the feeding back of the semantic recognition result to the safety monitoring platform includes: marking the semantic recognition result at the corresponding position of the downhole image; and feeding back the downhole image to the safety monitoring platform.

[0102] In the present application, based on the aforementioned solution, it also includes: issuing an alarm based on the semantic recognition result.

[0103] In the technical solution of the present application, video data is collected by a camera installed in a coal mine; the video data is framed and image preprocessed to generate an underground image; the image features of the underground image are extracted; the pixels in the underground image are classified according to the image features to determine the semantic recognition results corresponding to the underground image according to the pixel classification results; and the semantic recognition results are fed back to the security monitoring platform. Video data is captured in real time by a high-definition camera, and these data are converted into clear and accurate underground images after frame division and image preprocessing. Advanced image processing technology is used to extract key features in the image, such as color, texture, etc., and then the various objects in the underground are accurately distinguished through a sophisticated pixel classification algorithm. Based on these classification results, the system can intelligently identify the semantic content of the underground image, and finally feed back the accurate semantic information to the security monitoring platform in real time, so that management personnel can quickly grasp the underground dynamics, effectively prevent safety accidents, and significantly improve the safety and management efficiency of coal mine operations.

[0104] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0105] It should be noted that the computer system 400 of the electronic device shown in the figure is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0106] The computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, the ROM 402 and the RAM 403 are connected to each other through the bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0107] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0108] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 409, and / or installed from a removable medium 411. When the computer program is executed by a central processing unit (CPU) 401, various functions defined in the system of the present application are executed.

[0109] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a 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 above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0110] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0112] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0113] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0114] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0115] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0116] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0117] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A semantic recognition method for safety monitoring in underground coal mines, characterized in that: include: Video data is collected through a camera installed underground in a coal mine; Performing frame processing on the video data and image preprocessing to generate downhole images; extracting image features of the downhole image; Classifying pixels in the downhole image according to the image features, so as to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result; The semantic recognition result is fed back to the security monitoring platform.

2. The method according to claim 1, characterized in that Video data is collected through cameras installed in coal mines, including: Install camera equipment in coal mines in advance; Video data is collected by cameras and transmitted to the monitoring center via wired or wireless means.

3. The method according to claim 1, characterized in that: The video data is frame processed and image preprocessed to generate downhole images, including: Performing frame processing on the video data to generate a single-frame image; The single frame image is preprocessed to generate a downhole image.

4. The method according to claim 1, characterized in that Extracting image features of the downhole image includes: The downhole images are convolved according to the deep convolutional neural network to output image features.

5. The method according to claim 1, characterized in that Classifying pixels in the downhole image according to the image features to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result, including: Classifying pixels in the downhole image according to a fully connected layer of a deep convolutional neural network to generate a pixel classification result; A semantic recognition result corresponding to the downhole image is determined according to the pixel classification result.

6. The method according to claim 1, characterized in that Feeding back the semantic recognition result to the security monitoring platform includes: Marking the semantic recognition result at the corresponding position of the downhole image; The downhole image is fed back to the safety monitoring platform.

7. The method according to claim 1, characterized in that Also includes: An alarm is issued based on the semantic recognition result.

8. A semantic recognition system for underground coal mine safety monitoring, characterized in that: include: A collection unit, used for collecting video data through a camera installed in the coal mine; An image unit, used for performing frame processing on the video data and image preprocessing to generate downhole images; An extraction unit, used for extracting image features of the downhole image; A recognition unit, used for classifying pixels in the downhole image according to the image features, so as to determine a semantic recognition result corresponding to the downhole image according to the pixel classification result; The feedback unit is used to feed back the semantic recognition result to the security monitoring platform.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for semantic recognition of underground coal mine safety monitoring as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the semantic recognition method for underground safety monitoring in coal mines as described in any one of claims 1 to 7.

Images