Tunnel dust concentration real-time detection method and system based on video monitoring

Abstract

The invention belongs to the real-time monitoring technology of dust concentration, and particularly provides a tunnel dust concentration real-time detection method and system based on video monitoring, and the method comprises the steps: conveying a monitoring vehicle into different tunnel sections in a tunnel; the monitoring camera collects a dust video; monitoring images are intercepted from the monitored video once every unit time, images of different positions and different angles of the detected tunnel section in the tunnel are obtained, and according to the obtained image information and the position information of the monitoring vehicle, the view field images of all angles shot by the camera are spliced and integrated to obtain a three-dimensional view field in the monitoring range; performing gridding processing on an image intercepted by the video to obtain an average gray value of each monitoring unit; and fitting by adopting an experimental calibration method to obtain a function relationship between the average gray value of the image and the dust concentration value, and converting the average gray value of each monitoring unit into the dust concentration value. The method and system can monitor the dynamic change of the dust concentration in the cavern construction process in real time, and the workload of a construction site is reduced.

Description

Technical Field

[0001] The present invention relates to a real-time monitoring technology for dust concentration, and in particular to a real-time detection method and system for tunnel dust concentration based on video monitoring. Background Art

[0002] The drilling and blasting method has always been the main method for tunnel excavation due to its low excavation cost and strong adaptability to geological conditions. During the construction process of drilling and blasting, the rock will produce a large number of small-sized dust particles under the impact of drilling equipment and blasting loads. A large amount of dust not only reduces visibility in the tunnel and thus affects the progress and safety of on-site construction, but also increases the risk of workers suffering from pneumoconiosis to a certain extent. In addition, dust particles will increase the friction loss of construction machinery during use, greatly shorten its service life, and increase construction costs.

[0003] At present, most common dust concentration detection devices are dust sensors, and their detection principles include weighing method, β-ray method, charge induction method, light scattering method, etc. However, all kinds of commonly used concentration measurement methods have some problems, such as low accuracy, inability to monitor in real time, cumbersome operation, low sensitivity, etc. In addition, if the dust concentration at different positions in the tunnel is to be obtained, dust sensors need to be installed in multiple places in the tunnel, which consumes more manpower, material resources and financial resources. Due to the limitations of sensor installation conditions, although the sensor can obtain the dust concentration at the installation location more accurately, it is difficult to monitor the distribution of dust concentration in the tunnel. With the progress of tunnel excavation, the excavation working face gradually advances along the axis of the tunnel, and it is necessary to re-deploy sensors to monitor the dust concentration near the face, which increases the workload of the construction site and reduces the construction efficiency. In order to ensure the rapid and accurate judgment of the dust concentration and its distribution in the tunnel during the construction process, and adjust the relevant construction organization design plans such as tunnel ventilation in real time accordingly, to ensure the safe and efficient construction work, the dust concentration monitoring equipment needs to have high accuracy, real-time, safety and convenience. Therefore, it is necessary to adopt a new monitoring method to accurately and efficiently obtain the real-time dust concentration and its distribution in the tunnel during the construction process, to provide data support for the adjustment of on-site construction plans and the scheduling of construction personnel, etc. In addition, the monitoring device needs to be simple to operate, portable, and not require multiple installations, and not affect normal construction operations after blasting. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a real-time detection method and system for tunnel dust concentration based on video monitoring, which can monitor the dynamic changes of dust concentration during the construction process of the cavern in real time and reduce the workload on the construction site.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a real-time detection method of tunnel dust concentration based on video monitoring, comprising the following steps: S1. After a blasting operation is completed in the tunnel, a number of monitoring vehicles equipped with monitoring cameras and built-in positioning systems are sent into different sections of the tunnel through remote control; S2. The monitoring camera collects dust videos at different locations in different tunnel sections within the measurement range as the monitoring vehicle moves, and transmits the collected video data to the terminal in real time; S3, capturing a monitoring image from the monitored video every unit time, obtaining images at different positions and angles of the tunnel section being measured, and stitching and integrating the field of view images at various angles taken by the camera to obtain a three-dimensional field of view within the monitoring range based on the obtained image information and the position information of the monitoring vehicle; S4, using image processing technology to grid the image captured by the video, each grid unit is used as a monitoring unit, and the average gray value of each monitoring unit is obtained. Multiple monitoring units are integrated through the system to obtain the average gray value of each micro unit in the three-dimensional field of view; S5. The functional relationship between the average grayscale value of the image and the dust concentration value is fitted by using the experimental calibration method. According to the functional relationship between the average grayscale value of the image and the dust concentration value, the average grayscale value of each monitoring unit is converted into a dust concentration value.

[0006] The preferred solution further includes step S6, drawing a dust concentration distribution cloud map of each monitoring area according to the dust concentration value of each monitoring unit in the three-dimensional field of view, and obtaining the dust concentration distribution map of the monitoring area every unit time. In a preferred solution, in step S2, the collected video data is transmitted to the terminal wirelessly via WIFI.

[0007] In a preferred solution, the operation steps of step S4 are: S41, performing grid processing on the images captured by the video; S42: taking each grid of the gridded image as a monitoring unit, and obtaining the average grayscale value of each image monitoring unit by using a component method, a maximum value method, an average value method, or a weighted average method; S43: Obtaining an average grayscale value of each micro-unit in the three-dimensional field of view by calculating the average grayscale value of the monitoring images of different angles of each three-dimensional monitoring unit in the three-dimensional field of view.

[0008] In the preferred solution, in step S41, the gridding process step is: gridding the image captured by the video, the number of blocks of each image is m×n, each grid is a sub-image block, and a five-dimensional tensor is created to store each divided sub-image block, wherein the first two dimensions represent the position of the sub-image block in the original image, and the second dimension represents the position of the sub-image block in the original image. i Line jThe columns are divided into blocks, and the following three dimensions represent the R, G, and B values ​​of each sub-image block.

[0009] In a preferred solution, in step S42, a weighted average method is used to obtain the average grayscale value of each image monitoring unit, and the calculation formula is: Gray(i,j)=0.299*R(i,j)+0.578*G(i,j)+0.114*B(i,j) ; in, Gray(i, j) Indicates i Line j The average gray value of the image monitoring unit in the column block, R(i, j) Indicates i Line j The intensity value of the R component of the image monitoring unit of the column block; G(i, j) Indicates i Line j The G component intensity value of the image monitoring unit of the column block; B(i, j) Indicates i Line j The B component intensity value of the image monitoring unit of the column block.

[0010] In a preferred solution, in step S5, the operation steps of fitting the functional relationship between the gray value and the dust concentration value using the experimental calibration method are as follows: S501, injecting the dust to be tested into the experimental box, which is a transparent box, and obtaining a cross-sectional image of the experimental box through an image acquisition device. At the same time, a dust concentration sensor in the experimental box monitors the dust concentration in the experimental box in real time; S502, graying the obtained cross-sectional image of the experimental box to obtain an average gray value of the image; S503 , plotting a scatter plot of grayscale value and dust concentration based on the obtained image average grayscale value and dust concentration, performing formula fitting based on the scatter plot, and obtaining a functional relationship between the image average grayscale value and the dust concentration value.

[0011] In a preferred solution, the functional relationship between the average gray value of the image and the dust concentration value is: ; Where: c is the dust concentration, g is the average gray value of the image.

[0012] The present invention also provides a real-time monitoring system for tunnel dust concentration based on video monitoring. The above-mentioned real-time detection method for tunnel dust concentration based on video monitoring adopts the real-time monitoring system to perform real-time monitoring of tunnel dust concentration, including a video monitoring module, which is used to collect dust videos at different positions in different tunnel sections. The video monitoring module includes a monitoring vehicle, which is equipped with a monitoring camera, and a positioning system and a lighting lamp are arranged on the monitoring vehicle; a data transmission module, which transmits the monitoring image obtained by the video monitoring module to a terminal for processing by WIFI wireless method; a terminal, which has an image processing module, a data processing module and a result display module built in the terminal, the image processing module is used to perform image processing on the collected video data, the data processing module converts the average gray value of each monitoring unit into a dust concentration value based on the functional relationship between the average gray value of the image and the dust concentration value, and the result display module is used to display the dust concentration value.

[0013] In a preferred solution, the monitoring vehicle is provided with a lifting rod, and the monitoring camera is installed on the lifting rod.

[0014] A real-time detection method and system for tunnel dust concentration based on video monitoring has the following beneficial effects: 1. As the excavation working face gradually advances along the tunnel axis, the dust concentration monitoring method based on video monitoring does not need to redeploy sensors to monitor the dust concentration near the face, which reduces the workload at the construction site and improves construction efficiency.

[0015] 2. The system uses artificial intelligence technology to monitor real-time dust concentration, reduce subjective factors, untimely supervision and waste of human resources, and improve the real-time monitoring and data accuracy; 3. The real-time dust concentration monitoring system based on video surveillance can overcome the limitations of underground caverns such as tunnels and underground factories in terms of space, traffic, visibility and installation conditions, and monitor the dynamic changes of dust concentration during the cavern construction process in real time. It can be applied to the construction of all underground projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 It is a flow chart of the real-time monitoring method of tunnel dust concentration based on video monitoring of the present invention; Figure 2 This is a diagram of the experimental device for calibrating the functional relationship between dust concentration and image gray value of the present invention; Figure 3 This is a functional relationship diagram of dust concentration and image gray value of the present invention; Figure 4 This is a schematic diagram of the dust concentration real-time monitoring system; Figure 5This is a schematic diagram of the dust concentration monitoring vehicle of the present invention; In the figure: a monitoring vehicle 1, a lifting rod 2, a monitoring camera 3, a lighting lamp 4, an experimental box 5, a dust inlet 501 to be tested, dust particles 6, and an image acquisition device 7. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] Embodiment 1: The present invention provides a real-time monitoring system for tunnel dust concentration based on video monitoring, which can realize real-time monitoring of the dynamic changes of dust concentration at the construction site of underground caverns. Figure 4 and 5 As shown, it includes a video monitoring module for collecting dust videos at different positions in different tunnel sections. The video monitoring module includes a monitoring vehicle, which is equipped with a monitoring camera, and a positioning system and a lighting lamp are arranged on the monitoring vehicle; a data transmission module, which transmits the monitoring image obtained by the video monitoring module to the terminal for processing by WIFI wireless method; a terminal, which has an image processing module, a data processing module and a result display module built in the terminal. The image processing module is used to perform image processing on the collected video data. The data processing module converts the average gray value of each monitoring unit into a dust concentration value based on the functional relationship between the average gray value of the image and the dust concentration value. The result display module is used to display the dust concentration value.

[0019] like Figure 5 As shown, the monitoring vehicle is a remote-controlled vehicle, which includes a vehicle body and wheels. The vehicle body is between 60 cm and 80 cm long, and the width is between 40 cm and 60 cm.

[0020] The monitoring vehicle is equipped with a monitoring camera, which is a high frame rate camera used to collect dust videos at different locations in different tunnel sections. The monitoring camera collects video information at different locations within the measurement range as the monitoring vehicle moves, and captures an image every unit time and transmits it to the terminal wirelessly via WIFI. The monitoring camera can rotate to collect image data at different angles and locations.

[0021] The monitoring vehicle is equipped with a positioning system and lighting. Since the monitoring vehicle is used in the construction site of the underground cavern, the light is weak, so the front end of the monitoring vehicle needs to be equipped with a lighting. The monitoring vehicle is equipped with an odometer and an inertial navigation system, which can autonomously plan paths for different monitoring areas and accurately reach the designated location. The inertial navigation system includes an inertial measurement unit, which can continuously measure the acceleration in the coordinate system based on the initial position, that is, the position and initial posture in the three-dimensional world coordinate system, and obtain the driving trajectory and current position by quadratic integration of time. The odometer calculates the change in the distance the wheel moves relative to the ground based on the change in the pulse of the photoelectric encoder during the sampling period. The combination of the two can perform autonomous positioning and path planning according to the target location, so as to accurately reach the designated monitoring area in the tunnel.

[0022] Preferably, the monitoring vehicle is provided with a lifting rod, and the monitoring camera is installed on the lifting rod. By setting the lifting rod, the height of the monitoring camera can be adjusted, and the image acquisition height can be adjusted.

[0023] The monitoring vehicle and the monitoring camera serve as a video monitoring module.

[0024] It includes a terminal, which can be a computer or a mobile phone. The terminal has built-in image processing module, data processing module and result display module. The image processing module is used to perform image processing on the collected video data. The data processing module converts the average gray value of each monitoring unit into a dust concentration value based on the functional relationship between the average gray value of the image and the dust concentration value.

[0025] The result display module is a display screen used to display the dust concentration value obtained by detection.

[0026] During specific use, a monitoring vehicle equipped with a monitoring camera reaches the designated monitoring area of ​​the tunnel through remote control. The monitoring camera collects video information at different positions within the measurement range as the monitoring vehicle moves, and captures an image every unit time and transmits it to the terminal via WIFI. The terminal uses image processing technology to integrate a large number of monitoring images to construct a three-dimensional field of view of the monitoring area, and grids the images captured by the video, while obtaining the average grayscale value of each grid unit. A large number of grid units are integrated through the system to obtain the average grayscale value of each tiny unit in the three-dimensional field of view, and the grayscale value of each grid unit obtained is converted into a dust concentration value by combining the functional relationship between the image grayscale value and the dust concentration set in the terminal. Finally, the dust concentration distribution cloud map of the detection area and the change of dust concentration over time are obtained according to the calculated values ​​of each unit grid and the built-in positioning system of the monitoring vehicle.

[0027] Embodiment 2: like Figure 1 As shown, a real-time detection method for tunnel dust concentration based on video monitoring includes the following steps: S1. After a blasting operation is completed in the tunnel, a number of monitoring vehicles equipped with monitoring cameras and built-in positioning systems are sent into different sections of the tunnel through remote control to monitor the dust concentration within a certain range of the section. At least two monitoring vehicles are deployed within the monitoring range of each section.

[0028] S2. The monitoring camera collects dust videos at different locations in different tunnel sections within the measurement range as the monitoring vehicle moves, and transmits the collected video data to the terminal in real time. Specifically, the collected video data is transmitted to the terminal wirelessly via WIFI.

[0029] S3. A monitoring image is captured from the monitoring video every unit time to obtain images of different positions and angles of the measured tunnel section in the tunnel. Based on the obtained image information and the position information of the monitoring vehicle, the field of view images of each angle taken by the camera are stitched and integrated to obtain the three-dimensional field of view within the monitoring range.

[0030] S4. Use image processing technology to grid the images captured by the video. Each grid unit is used as a monitoring unit to obtain the average grayscale value of each monitoring unit. Multiple monitoring units are integrated through the system to obtain the average grayscale value of each micro unit in the three-dimensional field of view.

[0031] The specific steps are: S41, performing grid processing on the images captured from the video.

[0032] The gridding process is as follows: gridding the images captured by the video, the number of blocks for each image is m×n, each grid is a sub-image block, Python creates a five-dimensional tensor to store each divided sub-image block, where the first two dimensions represent the position of the sub-image block in the original image, and the second dimension represents the position of the sub-image block in the original image. i Line j The last three dimensions represent the R, G, and B values ​​of each sub-image block. The slicing function of numpy is directly used to write the pixels of the image block determined by the coordinate values ​​of the upper left corner and lower right corner of each grid directly into the five-dimensional tensor, and the grid boundary pixels are processed by rounding to complete the gridding of the image.

[0033] S42: each grid of the gridded image is taken as a monitoring unit, and the average grayscale value of each image monitoring unit is obtained by using a component method, a maximum value method, an average value method, or a weighted average method.

[0034] Specifically, in this embodiment, a weighted average method is used to obtain the average grayscale value of each image monitoring unit. Since the human visual system has different perceptual characteristics for different colors, the human eye is most sensitive to green and least sensitive to blue, and the sensitivity is ranked as green>red>blue. Therefore, a more reasonable grayscale image can be obtained by weighted averaging the three components of RGB according to the following formula: Gray(i,j)=0.299*R(i,j)+0.578*G(i,j)+0.114*B(i,j) ; in, Gray(i, j) Indicates i Line j The average gray value of the image monitoring unit in the column block, R(i, j) Indicates i Line j The intensity value of the R component of the image monitoring unit of the column block; G(i, j) Indicates i Line j The G component intensity value of the image monitoring unit of the column block; B(i, j) Indicates i Line j The B component intensity value of the image monitoring unit of the column block.

[0035] S43: The average gray value of each micro-unit in the three-dimensional field of view is obtained by calculating the average gray value of the monitoring images of different angles of each three-dimensional monitoring unit in the three-dimensional field of view.

[0036] S5. The functional relationship between the average grayscale value of the image and the dust concentration value is fitted by using the experimental calibration method. According to the functional relationship between the average grayscale value of the image and the dust concentration value, the average grayscale value of each monitoring unit is converted into a dust concentration value.

[0037] Due to the occlusion effect of dust on light, it will affect the brightness of different pixels in the tunnel image, thereby affecting the grayscale value of the image. Different concentrations of dust have different occlusion effects on light. The grayscale values ​​of images obtained at the same position and angle under the same light source are naturally different. In addition, the main light source inside the tunnel is the lighting lamp, and the proportion of natural light is negligible. Its brightness, light angle, etc. basically remain stable, and the grayscale value of the image is less affected by the global atmospheric light changes and the atmospheric light scattering effect. Therefore, combining image monitoring and sensor monitoring, the functional relationship between the image grayscale value and the dust concentration value is calibrated to obtain a more accurate mathematical relationship between the two.

[0038] The steps for fitting the functional relationship between grayscale value and dust concentration value using the experimental calibration method are as follows: S501. Inject the dust to be tested into the test box. Figure 2As shown, the experimental box is a transparent box with incident light on the top. The cross-sectional image of the experimental box is obtained through the image acquisition device. At the same time, the dust concentration sensor in the experimental box monitors the dust concentration in the experimental box in real time.

[0039] S502: grayscale the obtained cross-sectional image of the experimental box to obtain an average grayscale value of the image. The method for obtaining the average grayscale value of the image is the same as step 4.

[0040] S503, draw a scatter plot of gray value and dust concentration with the obtained average gray value of the image and the dust concentration. Specifically, the acquired data is processed by Matlab, and a scatter plot of gray value and dust concentration is drawn with dust mass concentration c as the ordinate and image gray mean g as the ordinate. The obtained scatter plot is as follows: Figure 3 shown.

[0041] Through image analysis, the two are approximately in a linear relationship, so a first-order fitting can be performed to obtain a mathematical model and proportional parameters. According to the scatter plot, a formula fitting is performed to obtain the functional relationship between the image average gray value and the dust concentration value. The expression is: ; Where: c is the dust concentration, g is the average gray value of the image.

[0042] S6. Draw a dust concentration distribution cloud map of each monitoring area according to the dust concentration value of each monitoring unit in the three-dimensional field of view, and obtain a dust concentration distribution map of the monitoring area every unit time. It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time detection method for tunnel dust concentration based on video monitoring, characterized in that: The following steps are involved: S1. After a blasting operation is completed in the tunnel, a number of monitoring vehicles equipped with monitoring cameras and built-in positioning systems are sent into different sections of the tunnel through remote control; S2. The monitoring camera collects dust videos at different locations in different tunnel sections within the measurement range as the monitoring vehicle moves, and transmits the collected video data to the terminal in real time; S3, capturing a monitoring image from the monitored video every unit time, obtaining images at different positions and angles of the tunnel section being measured, and stitching and integrating the field of view images at various angles taken by the camera to obtain a three-dimensional field of view within the monitoring range based on the obtained image information and the position information of the monitoring vehicle; S4, using image processing technology to grid the image captured by the video, each grid unit is used as a monitoring unit, and the average gray value of each monitoring unit is obtained. Multiple monitoring units are integrated through the system to obtain the average gray value of each micro unit in the three-dimensional field of view; S5. The functional relationship between the average grayscale value of the image and the dust concentration value is fitted by using the experimental calibration method. According to the functional relationship between the average grayscale value of the image and the dust concentration value, the average grayscale value of each monitoring unit is converted into a dust concentration value.

2. A real-time detection method for tunnel dust concentration based on video monitoring according to claim 1, characterized in that: The method further includes step S6, drawing a dust concentration distribution cloud map of each monitoring area according to the dust concentration value of each monitoring unit in the three-dimensional field of view, and obtaining a dust concentration distribution map of the monitoring area every unit time.

3. The real-time detection method of tunnel dust concentration based on video monitoring according to claim 1 is characterized in that: In step S2, the collected video data is transmitted to the terminal via WIFI wirelessly.

4. The real-time detection method of tunnel dust concentration based on video monitoring according to claim 1 is characterized in that: The operation steps of step S4 are: S41, performing grid processing on the images captured by the video; S42: taking each grid of the gridded image as a monitoring unit, and obtaining the average grayscale value of each image monitoring unit by using a component method, a maximum value method, an average value method, or a weighted average method; S43: Obtaining an average grayscale value of each micro-unit in the three-dimensional field of view by calculating the average grayscale value of the monitoring images of different angles of each three-dimensional monitoring unit in the three-dimensional field of view.

5. The real-time detection method of tunnel dust concentration based on video monitoring according to claim 4 is characterized in that: In step S41, the gridding process is as follows: gridding is performed on the images captured from the video, the number of blocks of each image is m×n, each grid is a sub-image block, and a five-dimensional tensor is created to store each divided sub-image block, wherein the first two dimensions represent the position of the sub-image block in the original image, and the second dimensions represent the position of the sub-image block in the original image. i Line j The columns are divided into blocks, and the following three dimensions represent the R, G, and B values ​​of each sub-image block.

6. A real-time detection method for tunnel dust concentration based on video monitoring according to claim 4, characterized in that: In step S42, the weighted average method is used to obtain the average grayscale value of each image monitoring unit, and the calculation formula is: Gray(i,j)=0.299*R(i,j)+0.578*G(i,j)+0.114*B(i,j) ； in, Gray(i, j) Indicates i Line j The average gray value of the image monitoring unit in the column block, R(i, j) Indicates i Line j The intensity value of the R component of the image monitoring unit of the column block; G(i, j) Indicates i Line j The G component intensity value of the image monitoring unit of the column block; B(i, j) Indicates i Line j The B component intensity value of the image monitoring unit of the column block.

7. The real-time detection method of tunnel dust concentration based on video monitoring according to claim 1 is characterized in that: In step S5, the operation steps of fitting the functional relationship between the gray value and the dust concentration value by using the experimental calibration method are as follows: S501, injecting the dust to be tested into the experimental box, which is a transparent box, and obtaining a cross-sectional image of the experimental box through an image acquisition device. At the same time, a dust concentration sensor in the experimental box monitors the dust concentration in the experimental box in real time; S502, graying the obtained cross-sectional image of the experimental box to obtain an average gray value of the image; S503 , plotting a scatter plot of grayscale value and dust concentration based on the obtained image average grayscale value and dust concentration, performing formula fitting based on the scatter plot, and obtaining a functional relationship between the image average grayscale value and the dust concentration value.

8. A real-time detection method for tunnel dust concentration based on video monitoring according to claim 7, characterized in that: The functional relationship between the image average gray value and the dust concentration value is: ； Where: c is the dust concentration, g is the average gray value of the image.

9. A real-time monitoring system for tunnel dust concentration based on video monitoring, characterized in that: The real-time detection method of tunnel dust concentration based on video monitoring as described in any one of claims 1 to 8 adopts the real-time monitoring system to perform real-time monitoring of tunnel dust concentration, including a video monitoring module for collecting dust videos at different locations in different tunnel sections, the video monitoring module including a monitoring vehicle, a monitoring camera mounted on the monitoring vehicle, and a positioning system and a lighting lamp arranged on the monitoring vehicle; Data transmission module, which transmits the monitoring images acquired by the video monitoring module to the terminal for processing via WIFI wireless mode; The terminal has built-in image processing module, data processing module and result display module. The image processing module is used to perform image processing on the collected video data. The data processing module converts the average gray value of each monitoring unit into a dust concentration value based on the functional relationship between the average gray value of the image and the dust concentration value. The result display module is used to display the dust concentration value.

10. A real-time monitoring system for tunnel dust concentration based on video monitoring according to claim 9, characterized in that: The monitoring vehicle is provided with a lifting rod, and the monitoring camera is installed on the lifting rod.

Images