CN109951687B - Machine vision implementation system for underground coal mine environment - Google Patents
Machine vision implementation system for underground coal mine environment Download PDFInfo
- Publication number
- CN109951687B CN109951687B CN201910218626.2A CN201910218626A CN109951687B CN 109951687 B CN109951687 B CN 109951687B CN 201910218626 A CN201910218626 A CN 201910218626A CN 109951687 B CN109951687 B CN 109951687B
- Authority
- CN
- China
- Prior art keywords
- coal mine
- image
- image acquisition
- fog
- underground
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention discloses a machine vision implementation system for an underground coal mine environment, which comprises: the system comprises a plurality of first image acquisition terminals, a plurality of second image acquisition terminals, a data transmission line, a power line and a display unit; the first image acquisition terminals are uniformly distributed and fixed from the coal mine port to the coal mine shaft bottom area and are used for acquiring environmental image data of a preset area under the coal mine; the first image acquisition terminal and the second image acquisition terminal are both connected with a ground power supply through power lines; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the first image acquisition terminal and the second image acquisition terminal transmit acquired data to a display unit on the ground through a data transmission line for display; the technical effect of tracking and shooting the moving target in the coal mine can be provided while monitoring the video image in the coal mine.
Description
Technical Field
The invention relates to the field of coal mine monitoring, in particular to a machine vision implementation system for an underground environment of a coal mine.
Background
Coal mines are areas where humans mine coal resources in coal-rich mining areas, and are generally divided into underground coal mines and opencast coal mines. Although many safety regulations are established for coal mining, coal mine accidents still occur, and the coal mine accidents can cause serious casualties and economic losses.
Therefore, the coal mine site needs to be monitored in real time to guarantee coal mine safety, particularly, the coal mine with a complex environment is underground, the underground space of the coal mine is narrow, light is insufficient, and machine vision of the underground environment of the coal mine is difficult to realize.
Disclosure of Invention
The invention provides a machine vision implementation system for an underground environment of a coal mine, which solves the technical problems that the existing underground video monitoring system of the coal mine can only provide images in a certain area and cannot track and shoot underground moving targets, realizes reasonable system design, and can provide the technical effect of tracking and shooting the underground moving targets of the coal mine while monitoring the video images of the coal mine.
In order to achieve the above object, the present application provides a system for implementing machine vision in an underground environment of a coal mine, the system comprising:
the system comprises a plurality of first image acquisition terminals, a plurality of second image acquisition terminals, a data transmission line, a power line and a display unit; a plurality of first image acquisition terminals are uniformly distributed and fixed in a region from a coal mine port to a coal mine shaft bottom area, and the first image acquisition terminals
The system is used for collecting environmental image data of a preset area under a coal mine; the first image acquisition terminal and the second image acquisition terminal are both connected with a ground power supply through power lines; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the first image acquisition terminal and the second image acquisition terminal transmit acquired data to a display unit on the ground through a data transmission line for display.
The principle of the method is that a plurality of first image acquisition terminals are uniformly distributed and fixed in a region from a coal mine port to a coal mine shaft bottom, namely, all regions under the coal mine can be subjected to image acquisition; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the method can provide the underground monitoring video image of the coal mine and can track and shoot the underground moving target of the coal mine.
Furthermore, a plurality of second image acquisition terminals are uniformly distributed from the coal mine port to the coal mine shaft bottom area, each second image acquisition terminal is arranged on the coal mine shaft wall through a movable mounting structure and can move on the movable mounting structure, each second image acquisition terminal is provided with a corresponding preset image acquisition area, when a preset moving object enters a preset image acquisition area corresponding to a certain second image acquisition terminal, the second image capturing terminal captures an image of the moving object, and when the moving object leaves the image capturing area, and stopping image acquisition of the moving target by the second image acquisition terminal, and simultaneously acquiring images of a plurality of moving targets by the second image acquisition terminal when the plurality of moving targets simultaneously enter a preset image acquisition area corresponding to the same second image acquisition terminal.
Further, the movable mounting structure specifically includes: the device comprises a flexible guide rail, an electric trolley, a controller and a detection module; the second image acquisition terminal is fixedly installed on a body of the electric trolley, the electric trolley is installed on the flexible guide rail and is in sliding connection with the flexible guide rail, the flexible guide rail is fixed on a coal mine well wall, the detection module is fixed on the body of the electric trolley, and the detection module is connected with the controller; the preset moving target is provided with a matching signal sending module, when the detection module detects that a matching signal exists in a preset image acquisition area, the received matching signal is sent to the controller, the controller matches the matching signal, and after the matching is successful, the controller controls the second image acquisition to acquire an image of the preset moving target and controls the electric trolley to track and move the preset moving target; when the preset moving target moves out of the preset image acquisition area, the electric trolley stops tracking and resets to the initial position. After the moving target enters the preset image acquisition area, the detection module can receive the matching signal, then the controller controls the electric trolley to track the moving target, the tracking technology is a target tracking technology in the prior art, and the repeated description is omitted in the application.
Further, the first image acquisition terminal and the second image acquisition terminal are internally provided with an image defogging processing module, and the image defogging processing module specifically comprises:
the acquisition unit is used for acquiring an underground coal mine environment image; the judging unit is used for judging whether fog exists in the underground environment image of the coal mine; the analysis unit is used for analyzing the fog of the image in the underground environment of the coal mine and judging the type of the fog in the image in the underground environment of the coal mine if the fog exists in the image in the underground environment of the coal mine, wherein the type of the fog comprises: fog in the underground environment of the coal mine of a first monitoring object is collected in a second collection unit;
the defogging unit is used for defogging the underground environment image of the coal mine, and if the type of the fog is the first type, the defogging unit is used for defogging the underground environment image of the coal mine based on a defogging algorithm; if the type of the fog is the second type, automatically wiping the lens of the acquisition equipment in the acquisition unit; if both the first and second species are present, both treatments are performed simultaneously.
The method comprises the steps of judging whether fog exists in a coal mine monitoring image or not, analyzing the fog in the coal mine underground environment image, judging the type of the fog in the coal mine underground environment image, fully considering various reasons of the fog generation of the coal mine underground environment image, carrying out defogging treatment on the coal mine underground environment image, and carrying out defogging treatment on the coal mine underground environment image based on a defogging algorithm if the type of the fog is the first type; if the type of the fog is the second type, automatically wiping the lens of the acquisition equipment in the acquisition unit; if the first type and the second type are both available, the two types of treatment are carried out simultaneously, so that the final underground coal mine environment defogging treatment effect is better.
Further, the determining unit specifically includes: the establishing module is used for carrying out deep learning on the basis of the coal mine underground environment image with historical fog and establishing a fog judging model of the coal mine underground environment image; the judging module is used for judging whether fog exists in the coal mine monitoring image or not based on the coal mine underground environment image fog judging model; the analysis unit specifically includes: the first analysis module is used for carrying out deep learning based on the underground coal mine environment image with fog in the underground coal mine environment of the monitored object and establishing a fog type judgment model of the first underground coal mine environment image; the second analysis module is used for carrying out deep learning on the basis of the underground coal mine environment image with fog on the lens of the acquisition equipment and establishing a fog type judgment model of the second underground coal mine environment image; and the third analysis module is used for judging the type of fog in the underground coal mine environment image based on the first underground coal mine environment image fog type judgment model and the second underground coal mine environment image fog type judgment model. Adopt current degree of depth learning algorithm in this application, study through the colliery environmental image that has the fog to the history, establish colliery environmental image fog and judge the model, judge whether there is the fog in the image through the characteristic that obtains corresponding image that has the fog, this mode is for realizing through prior art, and this application is no longer repeated.
Further, the defogging processing is carried out on the underground coal mine environment image based on the defogging algorithm, and the method specifically comprises the following steps: the method comprises the following steps of describing the influence of fog on an image by using a fog image degradation model, wherein the fog image degradation model is expressed as follows:
I(x)=J(x)e−rd(x)+A(1−e−rd(x)) (1)
wherein x is the spatial coordinate of the image pixel, r represents the atmospheric scattering coefficient, d represents the scene depth, and A is the global atmospheric light component;
based on the above model, using t (x) to represent transmittance, a fog map model describing fog image formation is established:
I(x)=J(x)t(x)+A(1−t(x))； （2）
x is the space coordinate of the image pixel, I (x) is the image to be defogged, J (x) is the image without fog, A is the global atmospheric light component, and t is the refractive index, namely the atmospheric transmission coefficient;
estimated transmittance t (x):
obtaining the global atmospheric light a, and then according to equation (2):
t(x)=(A−I(x))/(A−J(x)) (3)
t (x) ranges from [0, 1], I (x) ranges from [0,255], J (x) ranges from [0,255 ]; a and I (x) are known, and the range of t (x) is determined from the range of J (x):
0≤J(x)≤255,0≤I(x)≤A,0≤J(x)≤A,0≤t(x)≤1 (4)
t(x)≥A−I(x)A−0=A−I(x)A=1−I(x)A (5)
the combination of formula (4) and formula (5) gives:
1−I(x)A≤t(x)≤1 (6)
therefore, the formula for calculating the initial estimated transmittance is:
t(x)=1−I(x)A (7)
to ensure the naturalness of the picture, a parameter w is added to adjust the transmittance:
t(x)=1−wI(x)A (8)
the iterative idea estimates the transmittance:
transforming equation (2) to obtain:
J(x)=(I(x)-A)/ t(x)+A (9)
after the global atmospheric light A and the transmissivity t (x) are estimated, calculating by using a formula (9) to obtain a defogged image; the image is processed using automatic contrast enhancement or brightness enhancement or gamma correction image processing methods after the defogging operation. After the defogging operation, the brightness of the obtained fog-free image is darker, and the fog-free image can be processed by using image processing methods such as automatic contrast enhancement, brightness enhancement, gamma correction and the like so as to obtain a fog-free image with better effect.
Further, the acquisition unit specifically is video monitor system, utilizes clean structure to wipe the processing automatically to the collection equipment camera lens in the acquisition unit, clean structure includes:
the device comprises a fixing plate, a controller, a mechanical arm, an installation plate, a motor, a cleaning shaft and a circular disc; the fixed plate is fixed on the upper surface of the shell of the video monitoring camera, the controller is installed and fixed on the fixed plate, one end of the mechanical arm is fixedly connected with the fixed plate, the other end of the mechanical arm can extend to a lens of the video monitoring camera under the control of the controller, the other end of the mechanical arm is fixedly connected with the back surface of the installation disc, the motor is fixed in the middle of the front surface of the installation disc, one end of the cleaning shaft is connected with a rotating shaft of the motor, the other end of the cleaning shaft is connected with the back surface of the disc, and; the motor is used for rotating under the control of the controller, drives the disc to rotate, and the sponge layer on the front surface of the disc is in contact with the lens of the video monitoring camera to rotate so as to clear away fog on the surface of the lens of the video monitoring camera.
Wherein, control arm and motor through the controller, the arm drives the camera lens that the disc is close to the video surveillance camera head, and the motor drives the disc and rotates, utilizes the sponge to clean and absorb water, carries out the defogging to the camera lens of video surveillance camera head, and the controller controls the arm of machinery after accomplishing to withdraw clean the structure.
Furthermore, a control program is preset in the controller and used for controlling the displacement and the displacement of the mechanical arm, so that the sponge layer on the front surface of the disc is in contact with a lens of the video monitoring camera during cleaning; after cleaning is finished, the cleaning structure is retracted, so that the cleaning structure does not appear in the monitoring sight range of the video monitoring camera; the controller controls the displacement and the displacement amount to accurately clean.
Be equipped with pressure sensor in the sponge layer, when pressure sensor detected the positive sponge layer of disc and the camera lens contact of video surveillance camera head, transmitted the pressure that detects for the controller, controller control motor rotates and predetermines the number of turns, utilizes the arm to withdraw clean structure after accomplishing to rotate.
Further, be equipped with humidity transducer in the sponge layer, humidity transducer transmits the in-situ humidity information of sponge that detects for the controller, and when the in-situ humidity of sponge that detects was greater than the threshold value, the controller controlled the arm drive disc and removed for the disc removes to the first shell of video surveillance camera, utilizes the first shell of video surveillance camera to extrude the sponge layer, stops the extrusion when in-situ humidity of sponge is less than the threshold value, and utilizes the controller to control the arm and withdraw clean structure. When the moisture is more in the sponge layer, can lead to clear effect relatively poor, consequently, when sponge layer moisture was too much, the controller controlled arm to drive the disc and removed for the disc removes to the first shell of video surveillance camera, utilizes the first shell of video surveillance camera to extrude the sponge layer, extrudes unnecessary moisture then cleans, ensures clear effect.
Furthermore, a plurality of infrared alignment transmitting modules are arranged on a shell at the position of the video monitoring camera lens, a plurality of infrared alignment receiving modules are arranged on a disc at the edge of the sponge layer, the front size of the disc is matched with the front size of the video monitoring camera lens, the infrared alignment transmitting modules correspond to the infrared alignment receiving modules one by one, the infrared alignment transmitting modules and the infrared alignment receiving modules are both connected with a controller, when the controller receives the cleaning instruction, the controller simultaneously starts an infrared alignment transmitting module and an infrared alignment receiving module, the infrared alignment transmitting module is used for transmitting alignment infrared information, the infrared alignment receiving module is used for receiving the alignment infrared information, when all the infrared alignment receiving modules receive the alignment infrared information sent by the corresponding infrared alignment transmitting modules, the controller controls the motor to clean, and if the alignment is unsuccessful, the motor is not cleaned. The technical problem that the image defogging processing effect obtained by the existing coal mine video monitoring system is incomplete is solved, computer image defogging is respectively carried out according to different conditions generated by fog in the image, and the defogging processing is carried out by wiping the lens of the monitoring camera, so that the technical effect of the defogging processing effect of the monitoring image is guaranteed.
One or more technical solutions provided by the present application have at least the following technical effects or advantages: the technical problem that the existing underground coal mine video monitoring system can only provide images in a certain area and cannot track and shoot underground moving targets is solved, the system is reasonable in design, and the technical effect that the underground coal mine moving targets can be tracked and shot while underground coal mine monitoring video images are provided is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention;
FIG. 1 is a schematic composition diagram of a machine vision implementation system for a coal mine underground environment in the application;
FIG. 2 is a schematic structural view of a movable mounting structure of the present application;
FIG. 3 is a schematic diagram of the image defogging module according to the present application;
fig. 4 is a schematic view of the structure of the cleaning structure of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described and thus the scope of the present invention is not limited by the specific embodiments disclosed below.
Referring to fig. 1, the present application provides a system for implementing machine vision in an underground coal mine environment, the system including: the system comprises a plurality of first image acquisition terminals a, a plurality of second image acquisition terminals b, a data transmission line c, a power line and a display unit d; the first image acquisition terminals are uniformly distributed and fixed from the coal mine port to the coal mine shaft bottom area and are used for acquiring environmental image data of a preset area under the coal mine; the first image acquisition terminal and the second image acquisition terminal are both connected with a ground power supply through power lines; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the first image acquisition terminal and the second image acquisition terminal transmit acquired data to a display unit on the ground through a data transmission line for display.
The principle of the method is that a plurality of first image acquisition terminals are uniformly distributed and fixed in a region from a coal mine port to a coal mine shaft bottom, namely, all regions under the coal mine can be subjected to image acquisition; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the method can provide the underground monitoring video image of the coal mine and can track and shoot the underground moving target of the coal mine.
In the embodiment of the application, a plurality of second image acquisition terminals are uniformly distributed from a coal mine port to a coal mine shaft bottom area, each second image acquisition terminal is arranged on a coal mine shaft wall through a movable mounting structure, the second image acquisition terminals can move on the movable mounting structure, each second image acquisition terminal is provided with a corresponding preset image acquisition area, when a preset moving object enters a preset image acquisition area corresponding to a certain second image acquisition terminal, the second image capturing terminal captures an image of the moving object, and when the moving object leaves the image capturing area, and stopping image acquisition of the moving target by the second image acquisition terminal, and simultaneously acquiring images of a plurality of moving targets by the second image acquisition terminal when the plurality of moving targets simultaneously enter a preset image acquisition area corresponding to the same second image acquisition terminal.
In the embodiment of the present application, please refer to fig. 2, the movable mounting structure specifically includes: the device comprises a flexible guide rail 9, an electric trolley 10, a controller 11 and a detection module 12; the second image acquisition terminal 13 is fixedly installed on the body of the electric trolley, the electric trolley is installed on a flexible guide rail and is in sliding connection with the flexible guide rail, the flexible guide rail is fixed on the wall of a coal mine well, the detection module is fixed on the body of the electric trolley and is connected with the controller; a matching signal sending module 14 is arranged on the preset moving target 15, when the detection module detects that a matching signal exists in the preset image acquisition area, the received matching signal is sent to the controller, the controller matches the matching signal, and after the matching is successful, the controller controls the second image acquisition to acquire an image of the preset moving target and controls the electric trolley to track and move the preset moving target; when the preset moving target moves out of the preset image acquisition area, the electric trolley stops tracking and resets to the initial position. After the moving target enters the preset image acquisition area, the detection module can receive the matching signal, then the controller controls the electric trolley to track the moving target, the tracking technology is a target tracking technology in the prior art, and the repeated description is omitted in the application. In an embodiment of the present application, image defogging processing modules are respectively disposed in the first image acquisition terminal and the second image acquisition terminal, please refer to fig. 3, where the image defogging processing modules specifically include: the acquisition unit is used for acquiring an underground coal mine environment image; the judging unit is used for judging whether fog exists in the underground environment image of the coal mine; the analysis unit is used for analyzing the fog of the image in the underground environment of the coal mine and judging the type of the fog in the image in the underground environment of the coal mine if the fog exists in the image in the underground environment of the coal mine, wherein the type of the fog comprises: fog in the underground environment of the coal mine of a first monitoring object is collected in a second collection unit; the defogging unit is used for defogging the underground environment image of the coal mine, and if the type of the fog is the first type, the defogging unit is used for defogging the underground environment image of the coal mine based on a defogging algorithm; if the type of the fog is the second type, automatically wiping the lens of the acquisition equipment in the acquisition unit; if both the first and second species are present, both treatments are performed simultaneously.
The method comprises the steps of judging whether fog exists in a coal mine monitoring image or not, analyzing the fog in the coal mine underground environment image, judging the type of the fog in the coal mine underground environment image, fully considering various reasons of the fog generation of the coal mine underground environment image, carrying out defogging treatment on the coal mine underground environment image, and carrying out defogging treatment on the coal mine underground environment image based on a defogging algorithm if the type of the fog is the first type; if the type of the fog is the second type, automatically wiping the lens of the acquisition equipment in the acquisition unit; if the first type and the second type are both available, the two types of treatment are carried out simultaneously, so that the final underground coal mine environment defogging treatment effect is better.
In an embodiment of the present application, the determining unit specifically includes: the establishing module is used for carrying out deep learning based on the coal mine underground environment image with the historical fog and establishing the coal mine underground environment
Judging a model of image fog; the judging module is used for judging whether fog exists in the coal mine monitoring image or not based on the coal mine underground environment image fog judging model; the analysis unit specifically includes: the first analysis module is used for carrying out deep learning based on the underground coal mine environment image with fog in the underground coal mine environment of the monitored object and establishing a fog type judgment model of the first underground coal mine environment image; the second analysis module is used for carrying out deep learning on the basis of the underground coal mine environment image with fog on the lens of the acquisition equipment and establishing a fog type judgment model of the second underground coal mine environment image; and the third analysis module is used for judging the type of fog in the underground coal mine environment image based on the first underground coal mine environment image fog type judgment model and the second underground coal mine environment image fog type judgment model. Adopt current degree of depth learning algorithm in this application, study through the colliery environmental image that has the fog to the history, establish colliery environmental image fog and judge the model, judge whether there is the fog in the image through the characteristic that obtains corresponding image that has the fog, this mode is for realizing through prior art, and this application is no longer repeated. Further, the defogging processing is carried out on the underground coal mine environment image based on the defogging algorithm, and the method specifically comprises the following steps: the method comprises the following steps of describing the influence of fog on an image by using a fog image degradation model, wherein the fog image degradation model is expressed as follows:
I(x)=J(x)e−rd(x)+A(1−e−rd(x)) (1)
wherein x is the spatial coordinate of the image pixel, r represents the atmospheric scattering coefficient, d represents the scene depth, and A is the global atmospheric light component;
based on the above model, using t (x) to represent transmittance, a fog map model describing fog image formation is established:
I(x)=J(x)t(x)+A(1−t(x))； （2）
x is the space coordinate of the image pixel, I (x) is the image to be defogged, J (x) is the image without fog, A is the global atmospheric light component, and t is the refractive index, namely the atmospheric transmission coefficient;
estimated transmittance t (x):
obtaining the global atmospheric light a, and then according to equation (2):
t(x)=(A−I(x))/(A−J(x)) (3)
t (x) ranges from [0, 1], I (x) ranges from [0,255], J (x) ranges from [0,255 ]; a and I (x) are known, and the range of t (x) is determined from the range of J (x):
0≤J(x)≤255,0≤I(x)≤A,0≤J(x)≤A,0≤t(x)≤1 (4)
t(x)≥A−I(x)A−0=A−I(x)A=1−I(x)A (5)
the combination of formula (4) and formula (5) gives:
1−I(x)A≤t(x)≤1 (6)
therefore, the formula for calculating the initial estimated transmittance is:
t(x)=1−I(x)A (7)
to ensure the naturalness of the picture, a parameter w is added to adjust the transmittance:
t(x)=1−wI(x)A (8)
the iterative idea estimates the transmittance:
transforming equation (2) to obtain:
J(x)=(I(x)-A)/ t(x)+A (9)
after the global atmospheric light A and the transmissivity t (x) are estimated, calculating by using a formula (9) to obtain a defogged image; the image is processed using automatic contrast enhancement or brightness enhancement or gamma correction image processing methods after the defogging operation. After the defogging operation, the brightness of the obtained fog-free image is darker, and the fog-free image can be processed by using image processing methods such as automatic contrast enhancement, brightness enhancement, gamma correction and the like so as to obtain a fog-free image with better effect.
In an embodiment of the present application, the acquisition unit is specifically a video monitoring system, and a cleaning structure is used to automatically wipe a lens of an acquisition device in the acquisition unit, please refer to fig. 4, where the cleaning structure includes:
the device comprises a fixed plate 2, a controller 3, a mechanical arm 4, an installation plate 5, a motor 6, a cleaning shaft 7 and a circular disc 8; the fixed plate is fixed on the upper surface of the shell of the video monitoring camera, the controller is installed and fixed on the fixed plate, one end of the mechanical arm is fixedly connected with the fixed plate, the other end of the mechanical arm can extend to a lens of the video monitoring camera under the control of the controller, the other end of the mechanical arm is fixedly connected with the back surface of the installation disc, the motor is fixed in the middle of the front surface of the installation disc, one end of the cleaning shaft is connected with a rotating shaft of the motor, the other end of the cleaning shaft is connected with the back surface of the disc, and; the motor is used for rotating under the control of the controller, drives the disc to rotate, and the sponge layer on the front surface of the disc is in contact with the lens of the video monitoring camera to rotate so as to clear away fog on the surface of the lens of the video monitoring camera.
Wherein, control arm and motor through the controller, the arm drives the camera lens that the disc is close to the video surveillance camera head, and the motor drives the disc and rotates, utilizes the sponge to clean and absorb water, carries out the defogging to the camera lens of video surveillance camera head, and the controller controls the arm of machinery after accomplishing to withdraw clean the structure.
In the embodiment of the application, a control program is preset in the controller and used for controlling the displacement and the displacement of the mechanical arm, so that the sponge layer on the front surface of the disc is in contact with a lens of the video monitoring camera during cleaning; after cleaning is finished, the cleaning structure is retracted, so that the cleaning structure does not appear in the monitoring sight range of the video monitoring camera; the controller controls the displacement and the displacement amount to accurately clean.
Be equipped with pressure sensor in the sponge layer, when pressure sensor detected the positive sponge layer of disc and the camera lens contact of video surveillance camera head, transmitted the pressure that detects for the controller, controller control motor rotates and predetermines the number of turns, utilizes the arm to withdraw clean structure after accomplishing to rotate.
Wherein, in this application embodiment, be equipped with humidity transducer in the sponge layer, humidity transducer transmits the in-sponge layer humidity information who detects for the controller, and when the in-sponge layer humidity that detects was greater than the threshold value, the controller controlled arm to drive the disc and removes for the disc removes to the first shell of video surveillance camera, utilizes the first shell extrusion sponge layer of video surveillance camera, stops the extrusion when in-sponge layer humidity is less than the threshold value, and utilizes the controller to control the arm to withdraw clean structure. When the moisture is more in the sponge layer, can lead to clear effect relatively poor, consequently, when sponge layer moisture was too much, the controller controlled arm to drive the disc and removed for the disc removes to the first shell of video surveillance camera, utilizes the first shell of video surveillance camera to extrude the sponge layer, extrudes unnecessary moisture then cleans, ensures clear effect.
Wherein, in this application embodiment, be equipped with a plurality of infrared alignment emission modules on the shell of video surveillance camera head camera lens department, be equipped with a plurality of infrared alignment receiving module on the disc at sponge layer edge, disc front size matches with video surveillance camera head camera lens front size, infrared alignment emission module and infrared alignment receiving module one-to-one, infrared alignment emission module and infrared alignment receiving module all are connected with the controller, when the controller received clean instruction, infrared alignment emission module and infrared alignment receiving module were opened simultaneously to the controller, infrared alignment emission module is used for the emission to aim at infrared information, infrared alignment receiving module
The controller is used for receiving alignment infrared information, when all the infrared alignment receiving modules receive the alignment infrared information sent by the corresponding infrared alignment transmitting module, the controller controls the motor to clean, and if the alignment is unsuccessful, the motor is not cleaned. The technical problem that the image defogging processing effect obtained by the existing coal mine video monitoring system is incomplete is solved, computer image defogging is respectively carried out according to different conditions generated by fog in the image, and the defogging processing is carried out by wiping the lens of the monitoring camera, so that the technical effect of the defogging processing effect of the monitoring image is guaranteed.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (4)
1. The utility model provides a colliery is environmental machine vision in pit and realizes system which characterized in that, the system includes: the system comprises a plurality of first image acquisition terminals, a plurality of second image acquisition terminals, a data transmission line, a power line and a display unit; the first image acquisition terminals are uniformly distributed and fixed from the coal mine port to the coal mine shaft bottom area and are used for acquiring environmental image data of a preset area under the coal mine; the first image acquisition terminal and the second image acquisition terminal are both connected with a ground power supply through power lines; the second image acquisition terminal is used for acquiring images corresponding to a movable target preset under the coal mine and carrying out moving tracking shooting on the movable target; the first image acquisition terminal and the second image acquisition terminal transmit acquired data to a display unit on the ground through a data transmission line for display;
first image acquisition terminal with all be equipped with image defogging processing module in the second image acquisition terminal, image defogging processing module specifically includes:
the acquisition unit is used for acquiring an underground coal mine environment image; the judging unit is used for judging whether fog exists in the underground environment image of the coal mine; the analysis unit is used for analyzing the fog of the image in the underground environment of the coal mine and judging the type of the fog in the image in the underground environment of the coal mine if the fog exists in the image in the underground environment of the coal mine, wherein the type of the fog comprises: fog in the underground environment of the coal mine of a first monitoring object is collected in a second collection unit; the defogging unit is used for defogging the underground environment image of the coal mine, and if the type of the fog is the first type, the defogging unit is used for defogging the underground environment image of the coal mine based on a defogging algorithm; if the type of the fog is the second type, automatically wiping the lens of the acquisition equipment in the acquisition unit; if the first and the second are both present, carrying out two treatments simultaneously;
the plurality of second image acquisition terminals are uniformly distributed from the coal mine port to the coal mine shaft bottom area, each second image acquisition terminal is arranged on the coal mine shaft wall through a movable mounting structure and can move on the movable mounting structure, each second image acquisition terminal is provided with a corresponding preset image acquisition area, when a preset moving object enters a preset image acquisition area corresponding to a certain second image acquisition terminal, the second image capturing terminal captures an image of the moving object, and when the moving object leaves the image capturing area, the second image acquisition terminal stops image acquisition of the moving target, and when a plurality of moving targets simultaneously enter a preset image acquisition area corresponding to the same second image acquisition terminal, the second image acquisition terminal simultaneously acquires images of the plurality of moving targets;
the acquisition unit specifically is video monitor system, utilizes clean structure to automatic processing of wiping of collection equipment camera lens in the acquisition unit, clean structure includes:
the device comprises a fixing plate, a controller, a mechanical arm, an installation plate, a motor, a cleaning shaft and a circular disc; the fixed plate is fixed on the upper surface of the shell of the video monitoring camera, the controller is installed and fixed on the fixed plate, one end of the mechanical arm is fixedly connected with the fixed plate, the other end of the mechanical arm can extend to a lens of the video monitoring camera under the control of the controller, the other end of the mechanical arm is fixedly connected with the back surface of the installation disc, the motor is fixed in the middle of the front surface of the installation disc, one end of the cleaning shaft is connected with a rotating shaft of the motor, the other end of the cleaning shaft is connected with the back surface of the disc, and; the motor is used for rotating under the control of the controller to drive the disc to rotate, and the sponge layer on the front surface of the disc is in contact with the lens of the video monitoring camera to rotate so as to remove fog on the surface of the lens of the video monitoring camera;
a control program is preset in the controller and used for controlling the displacement and the displacement of the mechanical arm so that the sponge layer on the front surface of the disc is in contact with a lens of the video monitoring camera during cleaning; after cleaning is finished, the cleaning structure is retracted, so that the cleaning structure does not appear in the monitoring sight range of the video monitoring camera; a pressure sensor is arranged in the sponge layer, when the pressure sensor detects that the sponge layer on the front side of the disc is in contact with a lens of the video monitoring camera, the detected pressure is transmitted to the controller, the controller controls the motor to rotate for a preset number of turns, and the mechanical arm is used for withdrawing the cleaning structure after the rotation is finished;
the sponge layer is internally provided with a humidity sensor, the humidity sensor transmits detected humidity information in the sponge layer to the controller, when the detected humidity in the sponge layer is larger than a threshold value, the controller controls the mechanical arm to drive the disc to move, so that the disc moves towards the video monitoring camera shell, the video monitoring camera shell is used for extruding the sponge layer, when the humidity in the sponge layer is lower than the threshold value, the extrusion is stopped, and the controller is used for controlling the mechanical arm to withdraw the cleaning structure.
2. The system of claim 1, wherein the moveable mounting structure comprises:
the device comprises a flexible guide rail, an electric trolley, a controller and a detection module; the second image acquisition terminal is fixedly installed on a body of the electric trolley, the electric trolley is installed on the flexible guide rail and is in sliding connection with the flexible guide rail, the flexible guide rail is fixed on a coal mine well wall, the detection module is fixed on the body of the electric trolley, and the detection module is connected with the controller; the preset moving target is provided with a matching signal sending module, when the detection module detects that a matching signal exists in a preset image acquisition area, the received matching signal is sent to the controller, the controller matches the matching signal, and after the matching is successful, the controller controls the second image acquisition to acquire an image of the preset moving target and controls the electric trolley to track and move the preset moving target; when the preset moving target moves out of the preset image acquisition area, the electric trolley stops tracking and resets to the initial position.
3. The system for implementing machine vision in an underground coal mine environment according to claim 1, wherein the judging unit specifically comprises:
the establishing module is used for carrying out deep learning on the basis of the coal mine underground environment image with historical fog and establishing a fog judging model of the coal mine underground environment image;
the judging module is used for judging whether fog exists in the coal mine monitoring image or not based on the coal mine underground environment image fog judging model; the analysis unit specifically includes: the first analysis module is used for carrying out deep learning based on the underground coal mine environment image with fog in the underground coal mine environment of the monitored object and establishing a fog type judgment model of the first underground coal mine environment image; the second analysis module is used for carrying out deep learning on the basis of the underground coal mine environment image with fog on the lens of the acquisition equipment and establishing a fog type judgment model of the second underground coal mine environment image; and the third analysis module is used for judging the type of fog in the underground coal mine environment image based on the first underground coal mine environment image fog type judgment model and the second underground coal mine environment image fog type judgment model.
4. The system for implementing machine vision in an underground coal mine environment according to claim 1, wherein a plurality of infrared alignment transmitting modules are arranged on a shell at the position of the lens of the video monitoring camera, a plurality of infrared alignment receiving modules are arranged on a disc at the edge of the sponge layer, the front size of the disc is matched with the front size of the lens of the video monitoring camera, the infrared alignment transmitting modules and the infrared alignment receiving modules are in one-to-one correspondence, the infrared alignment transmitting modules and the infrared alignment receiving modules are both connected with the controller, when the controller receives a cleaning instruction, the controller simultaneously starts the infrared alignment transmitting modules and the infrared alignment receiving modules, the infrared alignment transmitting modules are used for transmitting alignment infrared information, the infrared alignment receiving modules are used for receiving the alignment infrared information, when all the infrared alignment receiving modules receive the alignment infrared information transmitted by the corresponding infrared alignment transmitting modules, the controller controls the motor to perform cleaning, and if the alignment is unsuccessful, the cleaning is not performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910218626.2A CN109951687B (en) | 2019-03-21 | 2019-03-21 | Machine vision implementation system for underground coal mine environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910218626.2A CN109951687B (en) | 2019-03-21 | 2019-03-21 | Machine vision implementation system for underground coal mine environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109951687A CN109951687A (en) | 2019-06-28 |
| CN109951687B true CN109951687B (en) | 2021-04-23 |
Family
ID=67011181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910218626.2A Expired - Fee Related CN109951687B (en) | 2019-03-21 | 2019-03-21 | Machine vision implementation system for underground coal mine environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109951687B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110430402A (en) * | 2019-08-20 | 2019-11-08 | 福州市协成智慧科技有限公司 | A kind of Internet of Things vision optimization monitoring device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201581930U (en) * | 2009-12-30 | 2010-09-15 | 扬州三鑫矿山成套设备有限公司 | Mining circulating robot |
| CN204442554U (en) * | 2015-03-09 | 2015-07-01 | 石家庄学院 | A kind of real-time tracking system based on monopod video camera |
| CN106851210A (en) * | 2017-03-01 | 2017-06-13 | 中国矿业大学(北京) | Development machine abnormal work and calamity forecast system based on image |
| CN206668325U (en) * | 2017-03-21 | 2017-11-24 | 中国矿业大学(北京) | A kind of mine movable object real-time tracking and Precise Position System |
| CN107958233A (en) * | 2017-12-26 | 2018-04-24 | 重庆轩腾科技有限公司 | Intelligent face recognition system |
| CN108124089A (en) * | 2017-12-26 | 2018-06-05 | 重庆轩腾科技有限公司 | Intelligent monitor system based on monitoring camera-shooting |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6990406B2 (en) * | 2002-07-22 | 2006-01-24 | California Institute Of Technology | Multi-agent autonomous system |
-
2019
- 2019-03-21 CN CN201910218626.2A patent/CN109951687B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201581930U (en) * | 2009-12-30 | 2010-09-15 | 扬州三鑫矿山成套设备有限公司 | Mining circulating robot |
| CN204442554U (en) * | 2015-03-09 | 2015-07-01 | 石家庄学院 | A kind of real-time tracking system based on monopod video camera |
| CN106851210A (en) * | 2017-03-01 | 2017-06-13 | 中国矿业大学(北京) | Development machine abnormal work and calamity forecast system based on image |
| CN206668325U (en) * | 2017-03-21 | 2017-11-24 | 中国矿业大学(北京) | A kind of mine movable object real-time tracking and Precise Position System |
| CN107958233A (en) * | 2017-12-26 | 2018-04-24 | 重庆轩腾科技有限公司 | Intelligent face recognition system |
| CN108124089A (en) * | 2017-12-26 | 2018-06-05 | 重庆轩腾科技有限公司 | Intelligent monitor system based on monitoring camera-shooting |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109951687A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109905678B (en) | Coal mine monitoring image defogging processing system | |
| CN101789177B (en) | Device and method for detecting and tracking vehicles crossing and pressing the yellow line and for capturing vehicle information | |
| CN104077773A (en) | Image edge detection method, and image target identification method and device | |
| CN112248835B (en) | Charging mechanical arm control method and system | |
| CN102168947A (en) | System for monitoring wear of pantograph sliding plate | |
| CN109951687B (en) | Machine vision implementation system for underground coal mine environment | |
| CN105141824A (en) | Image acquisition method and image acquisition device | |
| CN109895116B (en) | Power pipe gallery track robot patrol inspection method and device | |
| CN112598701A (en) | Automatic tracking and monitoring video acquisition system and method for farm targets | |
| CN102785719A (en) | Wall-climbing robot, system and method for shooting water gage images of ship | |
| CN110689728A (en) | Parking stall monitoring device and parking charging system | |
| CN110411533A (en) | A kind of railway ponding monitoring alarm and method based on machine vision | |
| CN105120209A (en) | Mining camera following shooting method and system for fully mechanized coal mining face | |
| CN114047197A (en) | Cable surface defect detection device based on machine vision and operation method | |
| CN111698476B (en) | Intelligent dustproof pan-tilt camera for fully mechanized coal mining face and control method thereof | |
| CN205545533U (en) | Two mesh cloud platforms of visible light camera and thermal infrared imaging camera | |
| CN112211145A (en) | Semi-automatic road sweeping method and device for road sweeper | |
| CN111345277A (en) | Transformer substation intelligent inspection robot with bird repelling function | |
| CN112964180A (en) | Urban rail vehicle collector shoe detection system | |
| CN110867094A (en) | Parking stall monitoring device and parking charging system | |
| CN205356515U (en) | Formation of image control system of intelligence digital camera | |
| CN110126930A (en) | A kind of formula cruiser that tracks with cleaning function suitable for cell | |
| CN111807003A (en) | Non-metal foreign matter detection system for belt conveyor | |
| CN110084177B (en) | Positioning system, method, control system, air conditioner and storage medium | |
| CN110827317B (en) | Four-eye moving object detection and identification equipment and method based on FPGA |
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 | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210423 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |