Coal mine power disaster perception and alarm method based on visible light image

Abstract

The present invention discloses a coal mine dynamic disaster perception and alarm method based on visible light images. The main steps include: installing a visible light camera at a monitoring point in a coal mine, using equipment in the coal mine that has a distinct color difference from coal and rock thrown out by disasters as background equipment, monitoring and identifying whether the visible light video image shows a change in the color of the background equipment; when the color of the background equipment changes, the average brightness of the visible light video image is identified; when the average brightness is less than a set brightness threshold, the visible light camera is used to monitor the moving speed of the object that causes the color change of the background equipment in the monitoring area; when the moving speed is greater than the set speed threshold, the methane concentration data of the nearby area is obtained; when the methane concentration in the nearby area of ​​the visible light camera is normal, an impact ground pressure alarm signal is issued; when the methane concentration in the nearby area of ​​the visible light camera increases rapidly or reaches the alarm value, a coal and gas outburst alarm signal is issued.

Description

Technical Field

[0001] The present invention relates to a coal mine dynamic disaster perception and alarm method based on visible light images, in particular to an image-based target detection technology, a visual speed measurement technology, a coal mine rock burst recognition technology, and a coal and gas outburst recognition technology. Background Art

[0002] Coal is the main energy source in my country, and it will not change for a long time. It is the ballast of my country's energy. The coal industry is a high-risk industry. Accidents such as rock burst, coal and gas outburst, fire, flood, gas and coal dust explosion seriously threaten the safe production of coal mines. Therefore, timely identification of accidents such as rock burst, coal and gas outburst, fire, flood, gas and coal dust explosion in the coal mine production process, so as to start the disaster emergency plan and emergency rescue, plays an important role in ensuring the safe production of coal mines.

[0003] Rock burst, coal and gas outburst are typical coal mine power disasters, once they occur, they may cause severe damage and casualties. At present, it is possible to use thermal infrared images to identify coal mine power disasters, but the thermal infrared images formed by infrared thermal imagers have low information richness except temperature information, and are currently expensive and have relatively low image resolution. Visible light images are rich in information, and visible light cameras are relatively cheap and have high resolution compared to infrared thermal imagers. In addition, the cantilever tunneling machine, continuous coal mining machine, hydraulic anchor drilling vehicle, crawler transfer crusher, anchor transfer unit, digging anchor machine, shuttle car, belt conveyor, wind tube in the underground coal mine excavation working face, coal mining machine, hydraulic support, scraper conveyor, transfer machine, switch machine, crusher in the coal mining working face, and mobile substation in the horizontal tunnel all have a distinct color difference from the coal and rock thrown out by the disaster, and the above equipment can be used as the background to identify the characteristics of the coal and rock thrown out by the disaster.

[0004] In view of the problems existing in the existing monitoring of rock burst, coal and gas outburst disasters and the characteristics of the underground coal mine environment, the present invention realizes a coal mine dynamic disaster perception and alarm method based on visible light images. In the process of using visible light images to perceive coal mine dynamic disasters, the color, brightness and speed characteristics of a large amount of coal and rock thrown into the tunnel space are perceived by monitoring the visible light video images in the surveillance area, providing simple and clear information on a large amount of thrown coal and rock, which has the advantages of low cost, non-contact, wide monitoring range, rich information, fast processing speed and stable and reliable. Summary of the invention

[0005] The technical problem to be solved by the present invention is to use the equipment with distinct color difference from the coal rock thrown out by the disaster in the coal mine as the background, and use the visible light camera to monitor the color change, brightness characteristics and speed characteristics of the monitored area, so as to realize the perception and alarm of rock burst, coal and gas outburst disasters based on visible light images.

[0006] The present invention specifically adopts the following technical solutions to solve the above technical problems:

[0007] A coal mine power disaster perception and alarm method based on visible light images, characterized in that: coal mine power disasters include rock burst, coal and gas outburst, and the perception and alarm method includes the following steps:

[0008] Step 1: Install visible light cameras and methane sensors at monitoring points underground in coal mines;

[0009] Step 2: Collect visible light video images in the monitoring area, use the equipment in the coal mine that has a distinct color difference from the coal and rock thrown out by the disaster as the background equipment, and monitor and identify whether the visible light video images show any color changes in the background equipment;

[0010] Step 3: loop step 2, and when the background device color changes, perform average brightness recognition of the visible light video image;

[0011] Step 4: When the average brightness of the visible light video image is less than the set brightness threshold, the visible light camera is used to monitor the moving speed of the object that causes the background device color to change in the monitoring area;

[0012] Step 5: When the visible light camera detects that the moving speed of the object causing the background device color to change in the monitoring area is greater than the set speed threshold, the methane concentration data of the area near the visible light camera is obtained;

[0013] Step 6: When the methane concentration in the area near the visible light camera is normal, an impact rock pressure alarm signal is issued; when the methane concentration in the area near the visible light camera increases rapidly or reaches the alarm value, a coal and gas outburst alarm signal is issued.

[0014] Furthermore, the monitoring points for installing visible light cameras include on the hydraulic support of the coal mining face, on the coal mining machine, in the air intake tunnel of the coal mining face, in the return air tunnel of the coal mining face, in the excavation tunnel of the tunneling face, on the tunneling machine, and on one or both sides of the fork in the excavation tunnel.

[0015] Furthermore, the visible light camera is installed at the top of the tunnel, or close to the top of the tunnel, or at a height greater than 2 meters; the focal length and exposure value of the visible light camera are manually set, and the auto focus and auto white balance functions of the visible light camera are turned off.

[0016] Furthermore, the locations for installing visible light cameras include the top plate of the excavation tunnel, the two sides of the excavation tunnel close to the top plate, the top of the hydraulic support of the coal mining face, the hydraulic column side of the hydraulic support of the coal mining face close to the top plate, the top plate of the tunnel of the horizontal tunnel, and the two sides of the tunnel of the horizontal tunnel close to the top plate.

[0017] Furthermore, the background equipment includes: cantilever tunneling machines, continuous coal mining machines, hydraulic anchor drilling vehicles, crawler transfer crushers, anchor transfer units, anchor digging machines, shuttle cars, belt conveyors, and air ducts at the excavation working face; coal mining machines, hydraulic supports, scraper conveyors, transfer machines, switch machines, and crushers at the coal mining working face; and mobile substations in the level tunnels.

[0018] Furthermore, the black area in the visible light camera monitoring area is segmented based on the HSV color model; by monitoring whether the black area in the visible light camera monitoring area increases, it is monitored to identify whether the background device color changes in the visible light video image; by monitoring the average brightness in the HSV color model of the visible light video image in the monitoring area, it is monitored to identify whether the average brightness of the visible light video image is less than the set brightness threshold; by monitoring the moving speed of the center point of the outline of the black increase area in the previous and next frames of the visible light video image in the monitoring area, it is used as the moving speed of the object that causes the background device color change; the speed threshold is set to 13m / s.

[0019] Furthermore, in order to maximize the monitoring range of a single visible light camera while not affecting the speed measurement effect of the single visible light camera, the optimal inclination angle of the visible light camera is the maximum value that satisfies the following conditions:

[0020] (1) The visible light camera monitoring area only covers the bottom and sides of the tunnel;

[0021] (2) The actual moving speed of the farthest object in the monitoring area of ​​the visible light camera when it moves one pixel length in the monitoring image in one frame time is 1 / n times the set speed threshold (n is a positive integer).

[0022] Furthermore, the optimal tilt angle of the visible light camera is the maximum value of the following constraints:

[0023]

[0024] Where α is the tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the optical axis of the camera; H is the height of the visible light camera installation position from the tunnel floor; f is the focal length of the visible light camera; v is the actual moving speed of the object at the farthest end of the monitoring area when it moves one pixel length Δs in the monitoring image after one frame of time Δt1; v T is the set speed threshold.

[0025] Furthermore, when the visible light camera has an inclination relative to the vertical downward direction, the length of the same object in the tunnel monitored in different monitoring directions is different, and according to the speed ratio equal to the distance ratio in the same time, then:

[0026]

[0027] Wherein, v1 is the real moving speed of the object; v2 is the moving speed of the object recognized by the visible light camera; α is the forward tilt angle of the visible light camera relative to the vertical downward; θ2 is the angle formed by the projection point of the initial moving position of the object found in the image on the tunnel floor projection line of the visible light camera optical axis and the line connecting the visible light camera position, and the tunnel floor projection line of the visible light camera optical axis.

[0028] Furthermore, according to the mathematical relationship between the visible light image captured by the visible light camera and the object movement in the lane space that causes the background equipment color to change, the actual moving speed of the object can be obtained as:

[0029]

[0030] Among them, v b is the moving speed of the object detected by the visible light camera when it is at an angle; H is the height of the visible light camera installation position from the bottom plate of the tunnel; α b is the forward tilt angle of the visible light camera to perceive coal mine disasters relative to the vertical downward; Δs is the length of one pixel; f is the focal length of the visible light camera; x1, y1 are the horizontal and vertical coordinates of the initial point of the object moving in the imaging plane; x2, y2 are the horizontal and vertical coordinates of the end point of the object moving in the imaging plane after a period of time Δt; L c is the imaging pixel size of the visible light camera along the optical axis of the camera in the imaging plane.

[0031] Furthermore, in order to identify higher coal and rock ejection velocities, it is necessary to conduct a comprehensive analysis based on the visible light camera's field of view, forward tilt angle, acquisition frame rate, and the height of the visible light camera installation position from the tunnel floor. The method for estimating the maximum velocity that can be identified when the visible light camera has a tilt angle is as follows:

[0032]

[0033] Where V max is the maximum speed that the visible light camera can identify; H is the height of the visible light camera installation position from the tunnel floor; Δt1 is the time it takes to pass a frame; α is the forward tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the camera optical axis. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Flow chart of the coal mine power disaster perception and alarm method based on visible light images of the present invention;

[0035] Figure 2 A schematic diagram of the position of the visible light camera placed on the tunnel roof of the excavation working face of the present invention;

[0036] Figure 3 A schematic diagram of the visible light camera of the excavation working face of the present invention being placed on both sides of the tunnel close to the top plate;

[0037] Figure 4 A schematic diagram of the position of the visible light camera placed on the top of the hydraulic support of the coal mining face of the present invention;

[0038] Figure 5 A schematic diagram of the position of the visible light camera of the coal mining face of the present invention placed on the hydraulic support hydraulic column side close to the top plate;

[0039] Figure 6 Schematic diagram of a method for monitoring color change characteristics of background equipment using a visible light camera of the present invention;

[0040] Figure 7 Schematic diagram of the method for identifying the speed of coal and rock thrown out of disasters using a visible light camera of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail and completely below in conjunction with the accompanying drawings and specific implementation methods. The embodiments should not be construed as limiting the scope of use of the present invention.

[0042] like Figure 1 The process of the coal mine power disaster perception and alarm method based on visible light images shown in the figure includes:

[0043] 1. Initialization (101): Install visible light cameras in key monitoring areas in the mine, including on the hydraulic support of the coal mining face, on the coal mining machine, in the air intake tunnel of the coal mining face, in the return air tunnel of the coal mining face, in the heading tunnel of the excavation face, on the heading machine, and on one or both sides of the fork of the heading tunnel.

[0044] 2. Monitoring area setting (102): The monitoring area of ​​the visible light camera is set with the equipment in the coal mine and the coal and rock thrown out by the disaster having a distinct color difference as the main background.

[0045] 3. Visible light image monitoring of the color of the background equipment in the monitoring area (103): collect visible light video images in the monitoring area, use the equipment in the coal mine that has a distinct color difference from the coal and rock thrown out by the disaster as the background equipment, and monitor and identify whether the visible light video image shows any changes in the color of the background equipment.

[0046] 4. Has the background device color changed? (104): When the background device color of the monitored area changes, it indicates that there may be an abnormal background device color when rock burst, coal and gas outburst disasters occur. Then execute (105), otherwise return to execute (103).

[0047] 5. Statistics of average brightness value of visible light image (105): When the background device color changes, the average brightness of the visible light video image is identified and the average brightness value of the visible light image is counted.

[0048] 6. Is the average brightness less than the set threshold? (106): When the average brightness of the visible light video image is less than the set brightness threshold, it means that the average brightness of the color change area is less than the average brightness of the fire, gas and coal dust explosion, and there is no abnormal brightness. The interference of fire, gas and coal dust explosion on the perception of impact ground pressure and coal and gas outburst disasters is eliminated, then execute (107), otherwise return to execute (103).

[0049] 7. Visible light image monitoring of the moving speed of objects in the surveillance area that causes the background device color to change (107): When the average brightness of the visible light video image is less than the set brightness threshold, the visible light image monitoring of the surveillance area causes the moving speed of objects in the background device color to change.

[0050] 8. Moving speed is greater than the set threshold (108): When the visible light image is used to monitor the monitored area and the moving speed of the object that causes the background device color to change is greater than the set speed threshold, it indicates that an abnormal speed characteristic occurs when rock burst and coal and gas outburst disasters occur, then execute (109), otherwise return to execute (103).

[0051] 9. Is the methane concentration increasing rapidly or reaching the alarm value? (109): Obtain methane concentration data in the area near the visible light camera to identify whether it is rock burst or coal and gas outburst.

[0052] 10. Coal and gas outburst alarm (110): When the visible light camera detects that the background equipment color in the monitoring area has changed, and the average brightness of the visible light video image is less than the set brightness threshold, and the visible light image detects that the moving speed of the object that causes the background equipment color change in the monitoring area is greater than the set threshold, and at the same time, the methane concentration in the nearby area is monitored to increase rapidly or reach the alarm value, then a coal and gas outburst alarm is issued.

[0053] 11. Rock burst alarm (111): When the visible light camera detects that the background equipment in the monitoring area has changed in color, and the average brightness of the visible light video image is less than the set brightness threshold, and the visible light image detects that the moving speed of the object causing the background equipment color change in the monitoring area is greater than the set threshold, and at the same time, the methane concentration in the nearby area is monitored to be normal, then a rock burst alarm is issued.

[0054] like Figure 2 The schematic diagram of the location of the visible light camera on the tunnel roof of the excavation working face shown in the figure includes:

[0055] The visible light camera O is placed on the central axis of the tunnel roof, the camera faces the direction of the excavation end, and in order to better monitor disasters, the visible light camera is tilted downward relative to the vertical. The visible light camera monitoring area is the tunnel floor monitoring area (area ABCD) and the two sides of the tunnel.

[0056] like Figure 3 The schematic diagram of the visible light cameras placed on both sides of the tunnel near the roof is shown, including:

[0057] The visible light camera O is placed on both sides of the tunnel near the top plate. The visible light camera faces the direction of the excavation end, and in order to better monitor disasters, the visible light camera is tilted downward relative to the vertical. The monitoring area of ​​the visible light camera is the tunnel bottom plate monitoring area (area ABCD) and both sides of the tunnel.

[0058] like Figure 4 The schematic diagram of the position of the visible light camera placed on the top of the hydraulic support in the coal mining face shown in the figure includes:

[0059] The visible light camera O is placed at the top of the hydraulic support, and in order to better monitor disasters, the visible light camera is tilted downward relative to the vertical. The visible light camera monitoring area is the tunnel floor monitoring area (area ABCD) and the two sides of the tunnel (including the coal mining face and the hydraulic support).

[0060] like Figure 5 The schematic diagram of the visible light camera placed on the coal mining face on the hydraulic support hydraulic column side close to the roof position includes:

[0061] The visible light camera O is placed on the hydraulic column side of the hydraulic support close to the top plate, and in order to better monitor disasters, the visible light camera is tilted downward relative to the vertical. The visible light camera monitoring area is the tunnel floor monitoring area (area ABCD) and the two sides of the tunnel (including the coal mining face and the hydraulic support).

[0062] like Figure 6 The schematic diagram of the method for monitoring the color change characteristics of background equipment by a visible light camera shown in the figure includes:

[0063] When a disaster occurs, a large amount of coal rock (black) is thrown out, which will cause the background equipment with a distinct color difference from the coal rock within the monitoring range of the visible light camera to be blocked, covered or buried by the thrown coal rock. In addition to the original black area within the monitoring range, the color of the background equipment area will partially or completely change to the coal rock color (black). By setting the corresponding parameter range of the HSV color model, the black (coal rock color) area within the monitoring range can be segmented in a targeted manner. Then, the Vibe algorithm is used to count whether the number of pixels of the foreground point has changed. If there is a change, the black increase area within the monitoring range is identified, indicating that the black area within the monitoring range has changed, that is, the color change characteristics caused by the suspected disaster throwing coal rock have been identified.

[0064] like Figure 7 The schematic diagram of the method for identifying the speed of coal and rock thrown out by a visible light camera shown in the figure includes:

[0065] When rock burst and coal and gas outburst disasters occur, the shapes of the thrown coal and rocks are irregular and unpredictable, and the original black areas in the visible light image are exposed coal and rocks and black objects in the tunnel space. Therefore, we can use the center points P and Q of the maximum contour of the black change area in the previous and next frames in the visible light monitoring area as the characteristic points of the thrown coal and rocks when the disaster occurs. Then the moving speed of the center point of the maximum contour of the black change area in the previous and next frames can be approximately regarded as the speed of the coal and rocks thrown by the disaster.

[0066] In order to maximize the monitoring range of a single camera while not affecting the speed measurement effect of a single camera, the optimal inclination angle of the visible light camera is the maximum value that meets the following conditions:

[0067] (1) The visible light camera monitoring area only covers the bottom and sides of the tunnel;

[0068] (2) The actual moving speed of the farthest object in the monitoring area of ​​the visible light camera when it moves one pixel length in the monitoring image in one frame time is 1 / n times the set speed threshold (n is a positive integer).

[0069] That is, the optimal tilt angle of the visible light camera is the maximum value of the following constraints:

[0070]

[0071] Where α is the tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the optical axis of the camera; H is the height of the visible light camera installation position from the tunnel floor; f is the focal length of the visible light camera; v is the actual moving speed of the object at the farthest end of the monitoring area when it moves one pixel length Δs in the monitoring image after one frame of time Δt1; v Tis the set speed threshold.

[0072] When the visible light camera has an inclination relative to the vertical downward direction, the length of the same object in the tunnel monitored in different monitoring directions is different, and according to the speed ratio equal to the distance ratio in the same time, then:

[0073]

[0074] Wherein, v1 is the real moving speed of the object; v2 is the moving speed of the object recognized by the visible light camera; α is the forward tilt angle of the visible light camera relative to the vertical downward; θ2 is the angle formed by the projection point of the initial moving position of the object found in the image on the tunnel floor projection line of the visible light camera optical axis and the line connecting the visible light camera position, and the tunnel floor projection line of the visible light camera optical axis.

[0075] Then, according to the mathematical relationship between the visible light image collected by the visible light camera and the object movement in the lane space that causes the background equipment color to change, the actual moving speed of the object can be obtained as:

[0076]

[0077] Among them, v b is the moving speed of the object detected by the visible light camera when it is at an angle; H is the height of the visible light camera installation position from the bottom plate of the tunnel; α b is the forward tilt angle of the visible light camera to perceive coal mine disasters relative to the vertical downward; Δs is the length of one pixel; f is the focal length of the visible light camera; x1, y1 are the horizontal and vertical coordinates of the initial point of the object moving in the imaging plane; x2, y2 are the horizontal and vertical coordinates of the end point of the object moving in the imaging plane after a period of time Δt; L c is the imaging pixel size of the visible light camera along the optical axis of the camera in the imaging plane.

[0078] In order to identify higher coal and rock ejection velocities, it is necessary to conduct a comprehensive analysis based on the visible light camera's field of view, forward tilt angle, acquisition frame rate, and the height of the visible light camera installation position from the tunnel floor. The method for estimating the maximum velocity that can be identified when the visible light camera has a tilt angle is as follows:

[0079]

[0080] Where V max is the maximum speed that the visible light camera can identify; H is the height of the visible light camera installation position from the tunnel floor; Δt1 is the time it takes to pass a frame; α is the forward tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the camera optical axis.

Claims

1. A coal mine power disaster perception and alarm method based on visible light images, characterized in that: Coal mine dynamic disasters include rock burst, coal and gas outburst, and the sensing and alarming method includes the following steps: Step 1: Install visible light cameras and methane sensors at monitoring points underground in coal mines; Step 2: Collect visible light video images in the monitoring area, use the equipment in the coal mine that has a distinct color difference from the coal and rock thrown out by the disaster as the background equipment, and monitor and identify whether the visible light video images show any color changes in the background equipment; Step 3: loop step 2, and when the background device color changes, perform average brightness recognition of the visible light video image; Step 4: When the average brightness of the visible light video image is less than the set brightness threshold, the visible light camera is used to monitor the moving speed of the object that causes the background device color to change in the monitoring area; Step 5: When the visible light camera detects that the moving speed of the object causing the background device color to change in the monitoring area is greater than the set speed threshold, the methane concentration data of the area near the visible light camera is obtained; Step 6: When the methane concentration in the area near the visible light camera is normal, an impact rock pressure alarm signal is issued; when the methane concentration in the area near the visible light camera increases rapidly or reaches the alarm value, a coal and gas outburst alarm signal is issued.

2. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: The monitoring points for installing visible light cameras include the hydraulic supports of the coal mining face, the coal mining machines, the air intake tunnels of the coal mining face, the return air tunnels of the coal mining face, the excavation tunnels of the heading face, the excavation machines, and one or both sides of the fork in the heading tunnels.

3. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: The visible light camera is installed at the top of the tunnel, or close to the top of the tunnel, or at a height greater than 2 meters; the focal length and exposure value of the visible light camera are manually set, and the auto focus and auto white balance functions of the visible light camera are turned off.

4. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: The locations for installing visible light cameras include the top plate of the excavation tunnel, the two sides of the excavation tunnel close to the top plate, the top of the hydraulic support of the coal mining face, the hydraulic column side of the hydraulic support of the coal mining face close to the top plate, the top plate of the tunnel of the horizontal tunnel, and the two sides of the tunnel of the horizontal tunnel close to the top plate.

5. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: The background equipment includes: cantilever tunneling machines, continuous coal mining machines, hydraulic anchor drilling vehicles, crawler transfer crushers, anchor transfer units, anchor digging machines, shuttle cars, belt conveyors, and air ducts at the excavation face; coal mining machines, hydraulic supports, scraper conveyors, transfer machines, switch machines, and crushers at the coal mining face; and mobile substations in the level tunnels.

6. The method for coal mine power disaster perception and alarm based on visible light images according to claim 1, characterized in that: Based on the HSV color model, the image is segmented to identify the black area in the visible light camera monitoring area; by monitoring whether the black area in the visible light camera monitoring area increases, it is monitored to identify whether the background device color changes in the visible light video image; by monitoring the average brightness of the HSV color model of the visible light video image in the monitoring area, it is monitored to identify whether the average brightness of the visible light video image is less than the set brightness threshold; by monitoring the moving speed of the center point of the black increase area contour in the previous and next frames of the visible light video image in the monitoring area, it is used as the moving speed of the object that causes the background device color change; the speed threshold is set to 13m / s.

7. The method for coal mine power disaster perception and alarm based on visible light images according to claim 1, characterized in that: In order to maximize the monitoring range of a single visible light camera while not affecting the speed measurement effect of a single visible light camera, the optimal inclination angle of the visible light camera is the maximum value that satisfies the following conditions: (1) The visible light camera monitoring area only covers the bottom and sides of the tunnel; (2) The actual moving speed of the farthest object in the monitoring area of ​​the visible light camera when it moves one pixel length in the monitoring image in one frame time is 1 / n times the set speed threshold (n is a positive integer).

8. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: The optimal tilt angle of the visible light camera is the maximum value of the following constraints: Where α is the tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the optical axis of the camera; H is the height of the visible light camera installation position from the tunnel floor; f is the focal length of the visible light camera; v is the actual moving speed of the object at the farthest end of the monitoring area when it moves one pixel length Δs in the monitoring image after one frame of time Δt1; v T is the set speed threshold.

9. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: When the visible light camera has an inclination relative to the vertical downward direction, the length of the same object in the tunnel monitored in different monitoring directions is different, and according to the speed ratio equal to the distance ratio in the same time, then: Wherein, v1 is the real moving speed of the object; v2 is the moving speed of the object recognized by the visible light camera; α is the forward tilt angle of the visible light camera relative to the vertical downward; θ2 is the angle formed by the projection point of the initial moving position of the object found in the image on the tunnel floor projection line of the visible light camera optical axis and the line connecting the visible light camera position, and the tunnel floor projection line of the visible light camera optical axis.

10. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: According to the mathematical relationship between the visible light image collected by the visible light camera and the object movement in the lane space that causes the background equipment color to change, the actual moving speed of the object can be obtained as: Among them, v b is the moving speed of the object detected by the visible light camera when it is at an angle; H is the height of the visible light camera installation position from the bottom plate of the tunnel; α b is the forward tilt angle of the visible light camera relative to the vertical downward when sensing coal mine disasters; Δs is the length of one pixel; f is the focal length of the visible light camera; x1, y1 are the horizontal and vertical coordinates of the initial point of the object moving in the imaging plane; x2, y2 are the horizontal and vertical coordinates of the end point of the object moving in the imaging plane after a period of time Δt; L c is the imaging pixel size of the visible light camera along the optical axis of the camera in the imaging plane.

11. The method for sensing and alarming coal mine power disasters based on visible light images according to claim 1, characterized in that: In order to identify higher coal and rock ejection velocities, it is necessary to conduct a comprehensive analysis based on the visible light camera's field of view, forward tilt angle, acquisition frame rate, and the height of the visible light camera installation position from the tunnel floor. The maximum velocity estimation method that can be identified when the visible light camera has a tilt angle is as follows: Where V max is the maximum speed that the visible light camera can identify; H is the height of the visible light camera installation position from the tunnel floor; Δt1 is the time it takes to pass a frame; α is the forward tilt angle of the visible light camera relative to the vertical downward direction; 2θ L is the field of view of the visible light camera along the camera optical axis.

Images