CN117514352A - Colliery water damage early warning system based on video identification - Google Patents
Colliery water damage early warning system based on video identification Download PDFInfo
- Publication number
- CN117514352A CN117514352A CN202311537391.6A CN202311537391A CN117514352A CN 117514352 A CN117514352 A CN 117514352A CN 202311537391 A CN202311537391 A CN 202311537391A CN 117514352 A CN117514352 A CN 117514352A
- Authority
- CN
- China
- Prior art keywords
- image
- water
- video
- control center
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 150
- 238000012544 monitoring process Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 36
- 239000003245 coal Substances 0.000 claims abstract description 17
- 238000007726 management method Methods 0.000 claims abstract description 15
- 238000005553 drilling Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 7
- 238000013500 data storage Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 33
- 230000009466 transformation Effects 0.000 claims description 29
- 230000009172 bursting Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 230000033228 biological regulation Effects 0.000 claims description 3
- 230000009347 mechanical transmission Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 description 4
- 239000002817 coal dust Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 239000011435 rock Substances 0.000 description 4
- 230000001131 transforming effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000002243 precursor Substances 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000002706 hydrostatic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F11/00—Rescue devices or other safety devices, e.g. safety chambers or escape ways
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Pulmonology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a coal mine water disaster early warning system based on video identification, which comprises a plurality of cameras, wherein the cameras are connected with video acquisition cards, the video acquisition cards are connected with a water disaster processing unit, the water disaster processing unit is provided with a control center, the control center is connected with an alarm system, and the water disaster processing unit is also provided with an information management system; the control center is also connected with a water-bursting monitoring unit, the water-bursting monitoring unit comprises a backboard and a top plate which are arranged beside a drilling hole, a camera is arranged on the top plate, a laser module is arranged on one side of the camera, the laser module is connected with a motor, the motor drives the laser module, the control center is provided with a power supply module for supplying power, and the control center sends water-bursting data to a server end of the information management system through a set wireless communication module for data storage.
Description
Technical Field
The invention belongs to the technical field of coal mine water damage early warning, and particularly relates to a coal mine water damage early warning system based on video identification.
Background
Because the underground mining activity breaks the natural balance state of the underground rock mass, the water body around the mining working face enters the mining working face through faults, a water-resisting layer and weak parts of the rock stratum under the action of hydrostatic pressure and mine pressure to form mine water burst. This phenomenon occurs and develops as a gradual process, with some fast (one or two days or less) and some slow (half a month or several days after mining) depending on the specific location of the face, the geology of the stope, the water pressure and the mine pressure. During the period from the beginning of the development of the working surface to the water burst, some abnormal phenomena are shown on the working surface and the vicinity thereof, and these abnormal phenomena are collectively called water burst precursors. The precursors are identified and mastered, emergency measures can be timely taken, people in the dangerous area are evacuated, and accidents caused by hurting people are prevented.
In the mine construction and production process, a large amount of water is needed for underground dust removal and fire control; and constructing a large-caliber engineering hole in the horizontal tunnel downward from the upper horizontal tunnel of the mine, and using the large-caliber engineering hole as a coal chute well, a cable well or a pipeline well. When the mine exploitation working face is deeper and is closer to the aquifer, water is supplied by utilizing the underground large-caliber drilling holes of the mine, which is more economical than water supply by utilizing the ground water well, but water inrush or water inrush events tend to occur easily for the large-caliber drilling holes, potential safety hazards are brought to production, and accidents that the working face is submerged by water are seriously caused, so that the drilling holes are required to be monitored, the drilling hole water inrush events are timely processed, and the production safety is ensured.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a coal mine water damage early warning system based on video identification, which solves the problems in the background art.
The invention provides the following technical scheme:
the coal mine water disaster early warning system based on video identification comprises a plurality of cameras, wherein the cameras are connected with video acquisition cards, the video acquisition cards are connected with a water disaster processing unit, the water disaster processing unit is provided with a control center, the control center is connected with an alarm system, and the water disaster processing unit is also provided with an information management system;
the control center is also connected with a water-bursting monitoring unit, the water-bursting monitoring unit comprises a backboard and a top plate which are arranged beside a drilling hole, a camera is arranged on the top plate, a laser module is arranged on one side of the camera, the laser module is connected with a motor, the motor drives the laser module, the control center is provided with a power supply module for supplying power, and the control center sends water-bursting data to a server end of the information management system through a set wireless communication module for data storage.
Preferably, the water damage processing unit comprises image preprocessing, feature extraction and image recognition; the image preprocessing comprises image enhancement and image segmentation, wherein the image with low quality is enhanced, and a target is segmented to extract a target area; the feature extraction part is used for extracting dynamic and static features aiming at the characteristics of the water damage image on the basis of the segmentation of the previous image, the image recognition is used for carrying out water damage detection according to the extracted dynamic and static features and combining an algorithm, the water damage prediction and the interference object are classified and recognized according to the mode recognition method, and finally the processing result is output.
Preferably, the image enhancement method adopts mirror image transformation, rotation transformation and brightness contrast adjustment; the mirror image transformation of the image can be divided into a horizontal mirror image, a vertical mirror image and a diagonal mirror image; the horizontal mirror image refers to the exchange of the contents on the left and right sides of the image based on the vertical center line of the image; the vertical mirror image is to exchange the contents of the upper and lower parts of the image by taking the horizontal central axis as the center, and the diagonal mirror image is the combination of the horizontal mirror image and the vertical mirror image.
Preferably, the rotation transformation is to rotate the image by a specified angle according to a certain point, the rotated image is not deformed, but the vertical symmetry axis and the horizontal symmetry axis of the original image are changed, the coordinate of the rotated image is obtained through calculation with the original coordinate relation, and the width and the height of the rotated image and the origin of coordinates are changed; when the method is executed, the mirror image transformation and the rotation transformation are executed through a certain probability, and the transformation mode and the rotation angle are random within a certain range.
Preferably, the brightness and contrast adjustment is to increase or decrease the intensity of the pixels of the image, and the contrast adjustment is to make the difference between the pixel intensities at the bright and dark positions of the image larger so as to widen the display accuracy in a certain area.
Preferably, the control center mainly comprises a monitoring server, a monitoring client terminal and the like, is connected with the server and the computer through a network switch, can receive and store real-time video signals from different monitoring points and process results output by the image processing unit.
Preferably, the control center and each alarm system have linkage functions, namely when an alarm signal appears at a certain point of a certain alarm system, the related monitoring camera for video monitoring carries out real-time video recording acquisition on the sending point of the automatic steering alarm signal, and meanwhile, the host page of the ground monitoring safety management center jumps out of the video image of the alarm point and is accompanied with buzzing alarm sound, so that ground safety management personnel can find potential safety hazards and time report at the first time and underground staff can get rid of dangerous situations to avoid accidents.
Preferably, the information management center can display the processing result of the flood image processing unit and the video monitoring information on a computer and transmit the processing result and the video monitoring information to a database for storage, so as to observe and query historical information.
Preferably, the method for monitoring water burst by the water burst monitoring unit includes that S1, when water burst occurs in drilling, a camera starts recording, a laser module starts working at the moment, a laser head is started in a PWM voltage regulation starting mode, and a red laser spot is irradiated at the top end of a backboard;
s2, the control center controls the motor to be connected with the laser module through the mechanical transmission structure, so that the laser module rotates clockwise slowly, a laser point irradiated by the laser module on the backboard moves from the top end to the highest point of the water column of the water burst slowly, when the laser point moves to the set lowest point, the motor rotates reversely, the laser point is driven to return to the initial position of the top end of the backboard rapidly, and the video camera stops recording;
s3, transmitting the recorded video information to a control center, processing the acquired video, identifying the track of the laser point in the video image, and calculating to obtain the water level height; and finally, the water burst data and the water burst column image are sent to a server of the information management system in a wireless communication mode and are stored.
In addition, the horizontal mirror transformation of the image satisfies the formula,the inversion formula of the method is satisfied,vertical mirror transform formula satisfies +.>The inversion formula is that,in the above, w and h are the width and height of the image acquired by the camera, (x) 0 ,y 0 ) The method is characterized in that the coordinates (x, y) of the original image are transformed coordinates, and after mirror image transformation is carried out on some images with unfilled water, the direction of water flow is changed, so that the functions of diversifying water flow forms and enriching data sets can be achieved. In the rotation transformation process of the image, after transforming the coordinate system to an original point with the rotation center, the coordinates (x 1, y 1) rotate by an angle a clockwise to obtain rotated coordinates which are recorded as (x 2, y 2), and the coordinate value formulas of the two coordinates satisfy the following conditions:
the water outlet shape of the water burst is not fixed, and the rotation transformation is also used for diversifying the water flow shape, enriching the characteristics, improving the contrast between a target image and a background and enabling the visual effect and the identification characteristics of a target area to be more prominent.
Because the acquired image information cannot possibly contain illumination in all actual scenes, the richness of the data set can be increased by adjusting and transforming the brightness and the contrast of the original image, so that the generalization capability of the finally trained model is better, the requirements of more coal dust detection application scenes are met, and the brightness and the contrast are adjusted as follows: g (x) =a×f (x) +b; in the above formula, f (x) is an original image pixel, g (x) is an output image pixel, a is a gain for adjusting contrast, and a is more than 0; b is bias for adjusting the brightness of the image; (i, j) pixels of the ith row and the jth column can be expressed as g (i, j) =a×f (i, j) +b; in order to simulate coal dust images under different illumination as much as possible, the brightness contrast is adjusted within a certain range, namely, the brightness contrast of the image is reduced or increased by a certain probability, and the brightness and the contrast of the image are kept unchanged by a certain probability, and the adjustment range and the probability can be specified according to requirements.
In addition, the flood area image is segmented by using a threshold segmentation method, a video differential segmentation method and the like, hydrologic basic data are integrated, and according to different water bursting sources, the spreading trend is analyzed, and the water bursting areas are separated from background images such as coal rocks and the like; and according to the number of pixels of the binary image, performing water inrush area estimation and trend prediction, after flood area image segmentation, separating the video dynamic target area from the background image to obtain a binary image, if fk (x, y) is the k frame image of the video and the pixel resolution is MxN, after target segmentation, the target image gk (x, y) isAfter the k frame image is segmented, water bursting area estimation can be performed according to the pixel number of the binary image. n255 represents the number of pixels with a gray value of 255, the relative water burst area is available +.>Characterization, fitting to the actual area can be performed. For predicting the water bursting trend, the water bursting area can be estimated according to the image area proportion, and the water bursting area expansion speed can be usedCharacterization, where T is the time interval between the video kth frame acquisition image and the (k-1) th frame acquisition image. The flood area expansion speed can represent the water inrush trend, and the faster the flood area expansion speed is, the more fierce the water potential is, and the larger the water inrush amount is.
In addition, when water burst monitoring unit is in water burst, after the camera gathers the facula image of the laser module, carry on recognition of the target detection and calculation processing of the tracking algorithm, can get the quantity, size, shape, movement track information of facula extracted in the image sequence, because the quantity change situation of the light in the image sequence is not always a back plate facula and a water surface reflection facula, can cause the subsequent calculation to appear error because of the situation that the fluctuation of the water surface causes goal facula and moving facula at the same time, in order to avoid the above-mentioned situation to happen, distinguish the direct facula of back plate and water surface reflection facula accurately, analyze the image facula data after the target tracking of the light spot, in the first step, choose K pieces of objects as the cluster centroid at random in the whole picture, this method is in order to classify the image facula according to above the water line and below the water line, take K=2; secondly, respectively calculating Manhattan distances between the facula objects and the clustering centroid; thirdly, assuming that the number of the facula objects is N, for each object, finding the centroid nearest to the facula object as a label, if N=1, directly classifying the facula object into one type, and ending classification; fourth, for the class of the same label, updating the centroid; fifth, repeating the third step and the fourth step, continuously dividing new clusters, calculating new centroids until the new centroids are the same as the last calculated centroids or the difference is smaller than a set threshold value, finishing classification, and recording the centroid positions of the two types of light spots at the moment; the moving tracks of the direct laser points and the reflecting laser points can be obtained after the light spot images are classified, and the moving tracks of the centers of mass of the direct laser points and the reflecting laser points are used as the moving track coordinates of the direct light spots and the reflecting light spots.
In the process of calculating the height of the water burst column, a geometric relation diagram is constructed, the position of the water level in the image obtained by the image water level distinguishing method is Y, and the pixel value is the length of the AC. The image acquired by the camera is 640 x 480 pixels in size, the longitudinal length AD of the image is 480 pixels, the wide angle of the camera is 41.41 degrees, and the angle AEC of the part above the water level in the image, namely the size of alpha, meets the following conditions: α= (AC/AD) ·41.41 °; the position of the camera is E, EA, ED is the wide angle of the camera, the highest point of the visual field of the camera is A, and the corner of the bracket is Q. And if the length of AQ and EQ is measured by the scale, the following condition AEQ is beta: beta = arctan (AQ/EQ); in the triangle EQY, the height QY of the back plate above the water column, qy=eq·tan (α+β) can be obtained according to the tangent theorem; according to the height QX of the backboard, the bottom end of the backboard and the well drilling are positioned on the same plane, so that the height of the water column of the water burst can be obtained, namely XY, XY=QX-QY; the control center sets a fixed value as a safe water burst height threshold value of the drill hole, and the alarm system gives an alarm once the actual water burst height exceeds the set threshold value.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a coal mine water disaster early warning system based on video identification, which is characterized in that water inrush information in a mine is acquired through video identification and analyzed and processed, and a control center and each alarm system have a linkage function, namely when an alarm signal appears at a certain point of one alarm system, a related monitoring camera for video monitoring carries out real-time video recording acquisition on an automatic steering alarm signal sending point, and meanwhile, a host page of a ground monitoring safety management center jumps out of a video image of the alarm point and is accompanied with buzzing alarm sound, so that ground safety management personnel can find potential safety hazards and time report and underground staff can exclude dangerous situations for avoiding accidents at the first time.
The water burst detection unit can monitor the water burst height of the underground drilling hole, and the alarm system gives an alarm once the actual water burst height exceeds a set threshold value; meanwhile, the condition that the target light spot and the moving light spot exist simultaneously due to water surface fluctuation is avoided through the setting method, errors in subsequent calculation are reduced, and accuracy of monitoring the water burst height is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system block diagram of the present invention.
FIG. 2 is a block diagram of a water inrush monitoring unit control system of the present invention.
Fig. 3 is a graph of the geometry of the water burst height calculation of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, of the embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Embodiment one:
1-2, a coal mine water disaster early warning system based on video identification comprises a plurality of cameras, wherein the cameras are connected with video acquisition cards, the video acquisition cards are connected with a water disaster processing unit, the water disaster processing unit is provided with a control center, the control center is connected with an alarm system, and the water disaster processing unit is also provided with an information management system;
the water damage processing unit comprises image preprocessing, feature extraction and image recognition; the image preprocessing comprises image enhancement and image segmentation, wherein the image with low quality is enhanced, and a target is segmented to extract a target area; the feature extraction part is used for extracting dynamic and static features aiming at the characteristics of the water damage image on the basis of the segmentation of the previous image, the image recognition is used for carrying out water damage detection according to the extracted dynamic and static features and combining an algorithm, the water damage prediction and the interference object are classified and recognized according to the mode recognition method, and finally the processing result is output.
The image enhancement method adopts mirror image transformation, rotation transformation and brightness contrast adjustment; the mirror image transformation of the image can be divided into a horizontal mirror image, a vertical mirror image and a diagonal mirror image; the horizontal mirror image refers to the exchange of the contents on the left and right sides of the image based on the vertical center line of the image; the vertical mirror image is to exchange the contents of the upper and lower parts of the image by taking the horizontal central axis as the center, and the diagonal mirror image is the combination of the horizontal mirror image and the vertical mirror image.
The rotation transformation is to rotate the image according to a certain point by a designated angle, the rotated image is not deformed, but the vertical symmetry axis and the horizontal symmetry axis of the original image are changed, the coordinate of the rotated image is obtained through calculation with the original coordinate relation, and the width and the height of the rotated image and the origin of the coordinate are changed; when the method is executed, the mirror image transformation and the rotation transformation are executed through a certain probability, and the transformation mode and the rotation angle are random within a certain range.
The brightness and contrast adjustment is to increase or decrease the intensity of the image pixels, and the contrast adjustment is to make the pixel intensity difference between the bright and dark positions of the image larger so as to widen the display accuracy in a certain area.
The control center is mainly composed of a monitoring server, a monitoring client terminal and the like, is connected with the server and the computer through a network switch, can receive and store real-time video signals from different monitoring points and process results output by the image processing unit.
The control center and each alarm system have linkage functions, namely when an alarm signal appears at a certain point of one alarm system, the related monitoring camera for video monitoring carries out real-time video recording acquisition on the point from which the alarm signal is sent, and meanwhile, the host page of the ground monitoring safety management center jumps out of the video image of the alarm point and is accompanied with buzzing alarm sound, so that ground safety management personnel can find potential safety hazards and time report for the first time and underground personnel can exclude dangerous situations to avoid accidents.
The information management center can display the processing result of the flood image processing unit and the video monitoring information on the computer and transmit the processing result and the video monitoring information to the database for storage, and the processing result and the video monitoring information are used for observation and historical information inquiry.
The horizontal mirror transformation of the image satisfies the formula,the inversion formula of the method is satisfied,vertical mirror transform formula satisfies +.>The inversion formula is that,in the above, w and h are the width and height of the image acquired by the camera, (x) 0 ,y 0 ) The method is characterized in that the coordinates (x, y) of the original image are transformed coordinates, and after mirror image transformation is carried out on some images with unfilled water, the direction of water flow is changed, so that the functions of diversifying water flow forms and enriching data sets can be achieved. In the rotation transformation process of the image, after transforming the coordinate system to an original point with the rotation center, the coordinates (x 1, y 1) rotate by an angle a clockwise to obtain rotated coordinates which are recorded as (x 2, y 2), and the coordinate value formulas of the two coordinates satisfy the following conditions:
the water outlet shape of the water burst is not fixed, and the rotation transformation is also used for diversifying the water flow shape, enriching the characteristics, improving the contrast between a target image and a background and enabling the visual effect and the identification characteristics of a target area to be more prominent.
Because the acquired image information cannot possibly contain illumination in all actual scenes, the richness of the data set can be increased by adjusting and transforming the brightness and the contrast of the original image, so that the generalization capability of the finally trained model is better, the requirements of more coal dust detection application scenes are met, and the brightness and the contrast are adjusted as follows: g (x) =a×f (x) +b; in the above formula, f (x) is an original image pixel, g (x) is an output image pixel, a is a gain for adjusting contrast, and a is more than 0; b is bias for adjusting the brightness of the image; (i, j) pixels of the ith row and the jth column can be expressed as g (i, j) =a×f (i, j) +b; in order to simulate coal dust images under different illumination as much as possible, the brightness contrast is adjusted within a certain range, namely, the brightness contrast of the image is reduced or increased by a certain probability, and the brightness and the contrast of the image are kept unchanged by a certain probability, and the adjustment range and the probability can be specified according to requirements.
Dividing flood area images by using a threshold segmentation method, a video differential segmentation method and the like, integrating hydrologic basic data, analyzing spreading trend according to different water bursting sources, and separating the water bursting areas from background images such as coal rocks and the like; and according to the number of pixels of the binary image, performing water inrush area estimation and trend prediction, after flood area image segmentation, separating the video dynamic target area from the background image to obtain a binary image, if fk (x, y) is the k frame image of the video and the pixel resolution is MxN, after target segmentation, the target image gk (x, y) isAfter the k frame image is segmented, water bursting area estimation can be performed according to the pixel number of the binary image. n255 represents the number of pixels with a gray value of 255, the relative water burst area is available +.>Characterization, fitting to the actual area can be performed. For predicting the water bursting trend, the water bursting area can be estimated according to the image area proportion, and the water bursting area expansion speed can be usedCharacterization, where T is the time interval between the video kth frame acquisition image and the (k-1) th frame acquisition image. The flood area expansion speed can represent the water inrush trend, and the faster the flood area expansion speed is, the more fierce the water potential is, and the larger the water inrush amount is.
Embodiment two:
referring to fig. 3, on the basis of the first embodiment, the control center is further connected with a water-bursting monitoring unit, the water-bursting monitoring unit includes a back plate and a top plate which are arranged beside the drill hole, a camera is arranged on the top plate, a laser module is arranged on one side of the camera, the laser module is connected with a motor, the motor drives the laser module, the control center is provided with a power supply module for supplying power, and the control center sends water-bursting data to a server end of the information management system through a set wireless communication module for data storage.
The method for monitoring water burst by the water burst monitoring unit comprises the following steps that S1, when drilling water burst occurs, a camera starts recording, a laser module starts working at the moment, a laser head is started in a PWM voltage regulation starting mode, and a red laser spot is irradiated at the top end of a backboard;
s2, the control center controls the motor to be connected with the laser module through the mechanical transmission structure, so that the laser module rotates clockwise slowly, a laser point irradiated by the laser module on the backboard moves from the top end to the highest point of the water column of the water burst slowly, when the laser point moves to the set lowest point, the motor rotates reversely, the laser point is driven to return to the initial position of the top end of the backboard rapidly, and the video camera stops recording;
s3, transmitting the recorded video information to a control center, processing the acquired video, identifying the track of the laser point in the video image, and calculating to obtain the water level height; and finally, the water burst data and the water burst column image are sent to a server of the information management system in a wireless communication mode and are stored.
When water burst monitoring unit is in water burst, after the camera collects the facula image of the laser module, carries on recognition of the target detection and calculation processing of the tracking algorithm, can get the quantity, size, shape, movement track information of facula extracted in the image sequence, because the quantity change situation of the facula in the image sequence is not always a back plate facula and a water surface reflection facula, also can cause the subsequent calculation to appear error because of the situation that the fluctuation of the water surface causes the simultaneous existence of the target facula and the moving facula, in order to avoid the above-mentioned situation to happen, distinguish the back plate facula and the water surface reflection facula accurately, analyze the image facula data after the target tracking of the light spot, in the first step, choose K objects as the cluster centroid at random in the whole picture, this method is in order to classify the image facula according to above the water line and below the water line, take K=2; secondly, respectively calculating Manhattan distances between the facula objects and the clustering centroid; thirdly, assuming that the number of the facula objects is N, for each object, finding the centroid nearest to the facula object as a label, if N=1, directly classifying the facula object into one type, and ending classification; fourth, for the class of the same label, updating the centroid; fifth, repeating the third step and the fourth step, continuously dividing new clusters, calculating new centroids until the new centroids are the same as the last calculated centroids or the difference is smaller than a set threshold value, finishing classification, and recording the centroid positions of the two types of light spots at the moment; the moving tracks of the direct laser points and the reflecting laser points can be obtained after the light spot images are classified, and the moving tracks of the centers of mass of the direct laser points and the reflecting laser points are used as the moving track coordinates of the direct light spots and the reflecting light spots.
In the process of calculating the height of the water burst column, a geometric relation diagram is constructed, the position of the water level in the image obtained by the image water level distinguishing method is Y, and the pixel value is the length of the AC. The image acquired by the camera is 640 x 480 pixels in size, the longitudinal length AD of the image is 480 pixels, the wide angle of the camera is 41.41 degrees, and the angle AEC of the part above the water level in the image, namely the size of alpha, meets the following conditions: α= (AC/AD) ·41.41 °; the position of the camera is E, EA, ED is the wide angle of the camera, the highest point of the visual field of the camera is A, and the corner of the bracket is Q. And if the length of AQ and EQ is measured by the scale, the following condition AEQ is beta: beta = arctan (AQ/EQ); in the triangle EQY, the height QY of the back plate above the water column, qy=eq·tan (α+β) can be obtained according to the tangent theorem; according to the height QX of the backboard, the bottom end of the backboard and the well drilling are positioned on the same plane, so that the height of the water column of the water burst can be obtained, namely XY, XY=QX-QY; the control center sets a fixed value as a safe water burst height threshold value of the drill hole, and the alarm system gives an alarm once the actual water burst height exceeds the set threshold value.
Other technical solutions not described in detail in the present invention are all prior art in the field, and are not described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations of the present invention will be apparent to those skilled in the art; any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The coal mine water disaster early warning system based on video identification is characterized by comprising a plurality of cameras, wherein the cameras are connected with video acquisition cards, the video acquisition cards are connected with a water disaster processing unit, the water disaster processing unit is provided with a control center, the control center is connected with an alarm system, and the water disaster processing unit is also provided with an information management system; the control center is also connected with a water-bursting monitoring unit, the water-bursting monitoring unit comprises a backboard and a top plate which are arranged beside a drilling hole, a camera is arranged on the top plate, a laser module is arranged on one side of the camera, the laser module is connected with a motor, the motor drives the laser module, the control center is provided with a power supply module for supplying power, and the control center sends water-bursting data to a server end of the information management system through a set wireless communication module for data storage.
2. The coal mine water damage early warning system based on video identification according to claim 1, wherein the water damage processing unit comprises image preprocessing, feature extraction and image identification; the image preprocessing comprises image enhancement and image segmentation, wherein the image with low quality is enhanced, and a target is segmented to extract a target area; the feature extraction part is used for extracting dynamic and static features aiming at the characteristics of the water damage image on the basis of the segmentation of the previous image, the image recognition is used for carrying out water damage detection according to the extracted dynamic and static features and combining an algorithm, the water damage prediction and the interference object are classified and recognized according to the mode recognition method, and finally the processing result is output.
3. The coal mine water damage early warning system based on video identification according to claim 2, wherein the image enhancement method adopts mirror image transformation, rotation transformation and brightness contrast adjustment; the mirror image transformation of the image can be divided into a horizontal mirror image, a vertical mirror image and a diagonal mirror image; the horizontal mirror image refers to the exchange of the contents on the left and right sides of the image based on the vertical center line of the image; the vertical mirror image is to exchange the contents of the upper and lower parts of the image by taking the horizontal central axis as the center, and the diagonal mirror image is the combination of the horizontal mirror image and the vertical mirror image.
4. The coal mine water damage early warning system based on video identification according to claim 3, wherein the rotation transformation is to rotate an image by a specified angle according to a certain point, the rotated image is not deformed, but the vertical symmetry axis and the horizontal symmetry axis of an original image are changed, the coordinate of the rotated image is obtained through calculation with the original coordinate relation, and the width and the height of the rotated image and the origin of coordinates are changed; when the method is executed, the mirror image transformation and the rotation transformation are executed through a certain probability, and the transformation mode and the rotation angle are random within a certain range.
5. The system of claim 3, wherein the brightness and contrast adjustment is to increase or decrease the intensity of the pixels of the image, and the contrast adjustment is to increase the difference between the intensities of the pixels at the bright and dark positions of the image so as to widen the display accuracy in a certain area.
6. The system of claim 1, wherein the control center is mainly composed of a monitoring server, a monitoring client terminal, etc., and is connected with the server and the computer through a network switch, and can receive, store, etc. real-time video signals from different monitoring points, and process the results output by the image processing unit.
7. The coal mine water disaster early warning system based on video identification according to claim 1, wherein the control center and each alarm system have linkage functions, namely when an alarm signal appears at a certain point of a certain alarm system, a video monitoring related monitoring camera carries out real-time video recording acquisition on an automatic steering alarm signal sending point, and meanwhile, a host page of a ground monitoring safety management center jumps out of a video image of the alarm point and is accompanied with buzzing alarm sound, so that ground safety management personnel can find potential safety hazards and time information for the first time and underground personnel can exclude dangerous situations to avoid accidents.
8. The coal mine water disaster early warning system based on video identification according to claim 1, wherein the information management center can display the processing result of the flood image processing unit and the video monitoring information on a computer and transmit the processing result and the video monitoring information to a database for storage for observation and historical information inquiry.
9. The coal mine water disaster early warning system based on video identification according to claim 1, wherein the method for monitoring water bursting by the water bursting monitoring unit comprises the following steps that S1, when water bursting occurs in drilling, a camera starts to record, a laser module starts to work at the moment, a laser head is started in a PWM voltage regulation starting mode, and a red laser spot is irradiated at the top end position of a backboard;
s2, the control center controls the motor to be connected with the laser module through the mechanical transmission structure, so that the laser module rotates clockwise slowly, a laser point irradiated by the laser module on the backboard moves from the top end to the highest point of the water column of the water burst slowly, when the laser point moves to the set lowest point, the motor rotates reversely, the laser point is driven to return to the initial position of the top end of the backboard rapidly, and the video camera stops recording;
s3, transmitting the recorded video information to a control center, processing the acquired video, identifying the track of the laser point in the video image, and calculating to obtain the water level height; and finally, the water burst data and the water burst column image are sent to a server of the information management system in a wireless communication mode and are stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311537391.6A CN117514352B (en) | 2023-11-17 | 2023-11-17 | Colliery water damage early warning system based on video identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311537391.6A CN117514352B (en) | 2023-11-17 | 2023-11-17 | Colliery water damage early warning system based on video identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117514352A true CN117514352A (en) | 2024-02-06 |
| CN117514352B CN117514352B (en) | 2024-05-07 |
Family
ID=89756410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311537391.6A Active CN117514352B (en) | 2023-11-17 | 2023-11-17 | Colliery water damage early warning system based on video identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117514352B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2109560A (en) * | 1981-09-26 | 1983-06-02 | Hill J And R | Fluid flow alarm device |
| CN105422180A (en) * | 2016-01-04 | 2016-03-23 | 中国矿业大学(北京) | Underground flood alarm system based on image and water inflow monitoring device |
| CN205638554U (en) * | 2016-01-04 | 2016-10-12 | 中国矿业大学(北京) | Colliery floods alarm system based on image and hydrologic data monitoring |
| CN107882593A (en) * | 2017-11-09 | 2018-04-06 | 河南理工大学 | Mine water disaster the condition of a disaster UAV Intelligent detection system and detection method |
| CN208734382U (en) * | 2018-07-21 | 2019-04-12 | 中铁十八局集团有限公司 | A kind of prominent mud calamity emergency processing system of tunnel gushing water |
| CN110111322A (en) * | 2019-05-13 | 2019-08-09 | 招商局重庆交通科研设计院有限公司 | A kind of tunnel defect identifying system based on image |
| CN114241720A (en) * | 2021-12-24 | 2022-03-25 | 北京市市政工程研究院 | Tunnel construction intelligent forecasting and early warning system and method based on digital twins |
-
2023
- 2023-11-17 CN CN202311537391.6A patent/CN117514352B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2109560A (en) * | 1981-09-26 | 1983-06-02 | Hill J And R | Fluid flow alarm device |
| CN105422180A (en) * | 2016-01-04 | 2016-03-23 | 中国矿业大学(北京) | Underground flood alarm system based on image and water inflow monitoring device |
| CN205638554U (en) * | 2016-01-04 | 2016-10-12 | 中国矿业大学(北京) | Colliery floods alarm system based on image and hydrologic data monitoring |
| CN107882593A (en) * | 2017-11-09 | 2018-04-06 | 河南理工大学 | Mine water disaster the condition of a disaster UAV Intelligent detection system and detection method |
| CN208734382U (en) * | 2018-07-21 | 2019-04-12 | 中铁十八局集团有限公司 | A kind of prominent mud calamity emergency processing system of tunnel gushing water |
| CN110111322A (en) * | 2019-05-13 | 2019-08-09 | 招商局重庆交通科研设计院有限公司 | A kind of tunnel defect identifying system based on image |
| CN114241720A (en) * | 2021-12-24 | 2022-03-25 | 北京市市政工程研究院 | Tunnel construction intelligent forecasting and early warning system and method based on digital twins |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117514352B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106128053A (en) | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device | |
| CN109448326B (en) | Geological disaster intelligent group defense monitoring system based on rapid image recognition | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN105405150A (en) | Abnormal behavior detection method and abnormal behavior detection device based fused characteristics | |
| US20220292278A1 (en) | Model-based image change quantification | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| CN106210633A (en) | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification | |
| CN113362374A (en) | High-altitude parabolic detection method and system based on target tracking network | |
| CN109086682A (en) | A kind of intelligent video black smoke vehicle detection method based on multi-feature fusion | |
| CN114267155A (en) | Geological disaster monitoring and early warning system based on video recognition technology | |
| Joshi et al. | Damage identification and assessment using image processing on post-disaster satellite imagery | |
| CN117514352B (en) | Colliery water damage early warning system based on video identification | |
| CN113344882A (en) | Method for counting drill rods of underground drilling machine based on computer vision | |
| KR20210133827A (en) | Apparatus for learning deep learning model and method thereof | |
| CN106156747B (en) | The method of the monitor video extracting semantic objects of Behavior-based control feature | |
| Zhang et al. | Deep learning‐based automatic detection of muck types for earth pressure balance shield tunneling in soft ground | |
| CN111553305A (en) | Violation video identification system and method | |
| CN117423157A (en) | Mine abnormal video action understanding method combining migration learning and regional invasion | |
| CN115909094A (en) | Underground pile foundation construction progress identification method based on 2D image and video fusion | |
| CN113450385B (en) | Night work engineering machine vision tracking method, device and storage medium | |
| Chen et al. | An image restoration and detection method for picking robot based on convolutional auto-encoder | |
| CN112668535A (en) | YOLOv3 model-based coal mine monkey vehicle violation detection and early warning method | |
| CN112883889A (en) | Method suitable for detecting violation behaviors in power construction scene | |
| Shin et al. | Anomaly detection algorithm based on global object map for video surveillance system | |
| CN115439511B (en) | Excavator motion monitoring method, system and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |