CN111425256B - Coal mine tunnel monitoring method and device and computer storage medium - Google Patents
Coal mine tunnel monitoring method and device and computer storage medium Download PDFInfo
- Publication number
- CN111425256B CN111425256B CN202010121837.7A CN202010121837A CN111425256B CN 111425256 B CN111425256 B CN 111425256B CN 202010121837 A CN202010121837 A CN 202010121837A CN 111425256 B CN111425256 B CN 111425256B
- Authority
- CN
- China
- Prior art keywords
- monitoring image
- winch
- target
- coordinate
- image sequence
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 167
- 239000003245 coal Substances 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 230000033001 locomotion Effects 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 11
- 238000012806 monitoring device Methods 0.000 claims description 11
- 230000001174 ascending effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 241000195940 Bryophyta Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mining & Mineral Resources (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a coal mine tunnel monitoring method. The method comprises the following steps: acquiring a tunnel monitoring image sequence in a coal mine tunnel; identifying targets in the tunnel monitoring image sequence and classifying the targets; if the target comprises a person, generating a first alarm instruction; and if the target is the mine car, tracking and counting the mine car. Through the mode, the method and the device can monitor the violation behaviors of coal mine tunnel transportation operation.
Description
Technical Field
The application relates to the technical field of video monitoring, in particular to a coal mine tunnel monitoring method, a coal mine tunnel monitoring device and a computer storage medium.
Background
The safety production is the key of all the work and is easy to appear in the coal mining operation
The phenomenon of 'three violations' is particularly suitable for mine roadway transportation operation. A typical coal mine roadway is a horizontal or inclined passageway that serves underground coal mining and does not go through the ground. The transportation characteristics of the coal mine tunnel are: the transportation volume is large, the roadway route is complex, the roadway is narrow, and the transportation operation of the coal mine roadway must be strictly carried out according to related safety regulations. In the transportation operation of the coal mine tunnel, after a winch above the coal mine tunnel is started, illegal behaviors of operators such as vehicle taking, vehicle pedaling, vehicle jumping, pedestrian driving and the like in the lifting process of a mine car and casualties and property loss events caused by the phenomenon of over-trailer of the mine car are frequent.
Disclosure of Invention
The application provides a coal mine tunnel monitoring method, a coal mine tunnel monitoring device and a computer storage medium, which are used for solving the problems of complex monitoring means and inaccurate monitoring result in the related technology.
In order to solve the technical problem, the application provides a coal mine tunnel monitoring method. The method comprises the following steps: acquiring a tunnel monitoring image sequence in a coal mine tunnel; identifying targets in the tunnel monitoring image sequence and classifying the targets; if the target comprises a person, generating a first alarm instruction; and if the target is the mine car, tracking and counting the mine car.
In order to solve the technical problem, the application provides a coal mine tunnel monitoring device. The device comprises a communication circuit, a processor and a memory; the processor is coupled with the memory and the communication circuit, and executes the instruction when working so as to realize the coal mine tunnel monitoring method by matching with the memory and the communication circuit.
To solve the above technical problem, the present application provides a computer storage medium. The computer storage medium stores a computer program that is executed to implement the steps of the coal mine roadway monitoring method described above.
The method and the device can identify the targets in the tunnel monitoring image sequence in the coal mine tunnel and classify the targets, so that the possibility of misjudgment of the targets can be reduced. When the target is classified as a person, triggering an alarm; when the target classification is the mine car, count the mine car, can accurately discern illegal operations such as personnel take off the car in the coal mine tunnel, driving pedestrian or mine car super trailer. The coal mine tunnel monitoring method is simple in hardware composition, and monitoring cost can be reduced while illegal operations in the coal mine tunnel are accurately identified.
Drawings
Fig. 1 is a schematic flow chart of a first embodiment of a coal mine roadway monitoring method of the present application;
FIG. 2 is a schematic flow chart diagram illustrating one embodiment of tracking and counting mine cars as provided herein;
FIG. 3 is a schematic flow chart diagram of a second embodiment of a coal mine roadway monitoring method of the present application;
FIG. 4 is a schematic flow chart diagram illustrating one embodiment of the present application for obtaining the motion state of the drawworks;
fig. 5 is a schematic structural diagram of an embodiment of a coal mine roadway monitoring device provided by the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a computer storage medium provided in the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the coal mine roadway monitoring method, the coal mine roadway monitoring device, and the computer storage medium provided in the present application are further described in detail with reference to the accompanying drawings and the detailed description.
Referring to fig. 1, fig. 1 is a schematic flow chart of a coal mine roadway monitoring method according to a first embodiment of the present application. The embodiment comprises the following steps:
s110: and acquiring a tunnel monitoring image sequence in the coal mine tunnel.
In this embodiment, the tunnel monitoring image sequence is obtained from a monitoring camera installed in a coal mine tunnel, for example. The roadway monitoring image sequence is formed by multiple continuous roadway monitoring images of the mine car in a single ascending or single descending process.
The monitoring camera collects real-time monitoring images in the roadway. The monitoring camera can be a visible light monitoring camera, an infrared monitoring camera, a thermal imaging camera or a depth camera.
The number of the monitoring cameras installed in the coal mine tunnel can be one or more. The installation position of the monitoring camera can be the position at the outlet, the inlet or between the outlet and the inlet of the inclined channel of the coal mine tunnel. The number and the mounted position of surveillance camera head use actual demand as the standard, and this application does not do the restriction to this.
The installation angle of the monitoring camera is preferably that the running track of the mine car in the tunnel monitoring image sequence is parallel or approximately parallel to the upper edge and the lower edge of the tunnel monitoring image. Of course, the running track of the mine car in the roadway monitoring image sequence may also have an inclination angle with the upper and lower edges of the roadway monitoring image, which is not limited in this application.
S120: and identifying the targets in the tunnel monitoring image sequence and classifying the targets.
This step mainly performs two actions: and (4) identifying and classifying. Firstly, identifying and primarily classifying targets in the tunnel monitoring image sequence, and secondarily classifying the primarily classified targets. The target may refer to personnel and mine cars, among others.
In this embodiment, a human-vehicle detection algorithm may be used to identify the personnel and mine vehicles in the roadway monitoring image sequence. The human-vehicle detection algorithm can be a target detection algorithm such as R-CNN, R-FCN, SSD or YOLO.
The man-vehicle detection algorithm can accurately extract the target characteristics in the tunnel monitoring image sequence after training, and output the initial coordinates, the serial numbers and the primary classification results of the targets in the tunnel monitoring image sequence. In this embodiment, the initial coordinates of the target refer to coordinates in a tunnel monitoring image of a frame in which the target is recognized for the first time. For coordinates of persons or mine cars (class, x)1,y1,x2,y2) Wherein class represents the primary classification of the object, (x)1,y1) And (x)2,y2) The coordinates of the upper left corner and the lower right corner of the target are respectively. The number of the object may be the order of the objects identified in the sequence of the monitoring images of the roadway, the number being, for example, 0, 1, 2, …, k, one number uniquely corresponding to one object.
In order to make the classification of the target more accurate and reduce the possibility of false alarm caused by wrong classification of the target, the embodiment also performs secondary classification on the target output by the human-vehicle detection algorithm. And inputting the target output by the human-vehicle detection algorithm into a classifier, and outputting personnel, mine cars and backgrounds by the classifier. The classifier adopts algorithms including VGG, AlexNet, GoogLeNet, SqueezeNet or ResNet, etc.
When the target category output by the classifier is "person", S130 is performed.
When the target class output by the classifier is "background", S160 is performed.
When the target category output by the classifier is "mine car", S140 is executed.
S130: and generating a first alarm instruction.
And when the target category output by the classifier comprises personnel, generating a first alarm instruction to remind workers of illegal behaviors of pedestrians in the coal mine tunnel.
The first alarm command may trigger a corresponding alarm, for example, an alarm sound or a voice alarm through a speaker, or a text like "pedestrian or dangerous" may be displayed on the monitor screen, or a light alarm may be sent through an alarm lamp.
S140: and tracking and counting the mine cars, and comparing the tracking and counting with a threshold number.
And when the target category output by the classifier is the mine car, tracking and counting the mine cars in the tunnel monitoring image sequence.
Referring to FIG. 2, FIG. 2 is a schematic flow chart of one embodiment of the mine car tracking and counting provided herein. The implementation mode comprises the following steps:
s141: and acquiring initial coordinates of a target in an initial frame of the tunnel monitoring image sequence.
And acquiring initial coordinates of the mine car in the initial frame of the roadway monitoring image sequence in S120. The initial frame is a tunnel monitoring image of a frame of the mine car which is identified for the first time. When two or more mine cars exist in the roadway monitoring image sequence, the initial frames and initial coordinates of different mine cars may be different. This step therefore refers to the acquisition of the initial coordinates (x) of each object classified as a tram car, respectively1,y1,x2,y2) To track and count the mine car.
S142: and tracking the target of the tunnel monitoring image sequence by using a tracking algorithm, and acquiring the tracking coordinate of the target after the preset tracking time.
As the mine car moves towards a certain direction in the coal mine tunnel, a tracking algorithm can be adopted to track the track of the mine car in the tunnel monitoring image sequence. Acquiring a tracking frame after the initial frame is preset with tracking time, and calculating the tracking coordinate (x) of the target in the tracking frame by using a tracking algorithmt1,yt1,xt2,yt2). The preset tracking time can be 1 second, 2 seconds, 3 seconds or 5 seconds and the like, and the specific preset tracking time can be set according to the actual length of the coal mine tunnel in the tunnel monitoring image sequence and the running speed of the mine car, which is not limited in the application.
The tracking algorithm may be KCF, SiamMask, MOSSE, CSK or STC, etc.
In this embodiment, the coordinate systems adopted by the tunnel monitoring image sequence are all the same, so as to ensure that the initial coordinate and the tracking coordinate have comparability. The coordinate system adopted by the tunnel monitoring image sequence can be a pixel coordinate system, an image coordinate system and the like.
S143: and judging the coordinate relation between the initial coordinate and the tracking coordinate and a preset boundary so as to count the target in an uplink or downlink manner.
The preset boundary is a median line of the running track of the mine car in the roadway monitoring image sequence. When the running rail of the mine car is parallel to the upper edge and the lower edge of the tunnel monitoring image in the tunnel monitoring image sequence, the abscissa of the preset boundary is xTAnd w is the width of the tunnel monitoring video image as w/2. In this embodiment, the abscissa of the left pixel of the preset boundary is smaller than the abscissa of the right pixel of the preset boundary.
If the left side of the preset boundary is the uplink direction, the right side of the preset boundary is the downlink direction: the average of the two abscissas of the initial coordinate is smaller than the abscissa of the preset dividing line, i.e., (x)1+x2)/2<xT(ii) a The average of the two abscissas of the tracking coordinate is greater than the abscissa of the preset boundary line, i.e., (x)t1+xt2)/2>xTAnd adding 1 to the count of the mine car in the descending direction. If the average of the two abscissas of the initial coordinate is larger than the abscissa of the predetermined dividing line, i.e., (x)1+x2)/2>xT(ii) a The mean of the two abscissas of the tracking coordinates is smaller than the abscissa of the dividing line, i.e. (x)t1+xt2)/2<xTAnd adding 1 to the count of the mine car in the ascending direction. In the single ascending or descending process of the mine car group in the coal mine roadway, all mine cars in the mine car group can run towards the same direction, so that the counting of the mine cars can be accumulated in the single running direction, and the ascending or descending direction of the mine cars can be judged while the counting of the mine cars is carried out. The target classified as a mine car by the output of the classifier is tracked, and whether the classification of the classifier is correct can be further judged, for example, in S120, the background is identified and classified as the mine car by mistake, but because the background is relatively static in the roadway monitoring image sequence and does not appear on the other side of the preset boundary, the target identified and classified as the mine car by mistake is not counted, and the accuracy of counting the mine cars can be improved.
If the left side of the preset boundary is the downlink direction, the right side of the preset boundary is the uplink direction: if it is initialThe average of the two abscissas of the coordinates is smaller than the abscissa (x) of the preset boundary line1+x2)/2<xT(ii) a The mean of the two abscissas of the tracking coordinate is greater than the abscissa of the dividing line, i.e. (x)t1+xt2)/2>xTAnd adding 1 to the count of the mine car in the ascending direction. If the average of the two abscissas of the initial coordinate is larger than the abscissa of the predetermined dividing line, i.e., (x)1+x2)/2>xT(ii) a The average of the two abscissas of the tracking coordinates is smaller than the abscissa of the preset boundary line, i.e., (x)t1+xt2)/2<xTAnd adding 1 to the count of the mine car in the descending direction.
Based on the identification of the roadway surveillance image sequence as one or more targets of the mine car, tracking counting is performed according to the method of S140. When the accumulated tracking count is greater than the threshold number during the single ascending or descending of the mine car group, S150 is performed. And executing S160 when the accumulated tracking count in the ascending or descending process of the single mine car group is less than or equal to the threshold number.
The quantity threshold is a safety threshold for the quantity of mine cars lifted at a time determined by the winch performance parameters, the track parameters and other factors in the roadway operation.
S150: and generating a second alarm instruction.
The second warning command may trigger a corresponding warning, for example by emitting a warning sound or voice warning via a loudspeaker, or by displaying a text on the monitor screen like "existence of a supertrailer, danger", or by emitting a light warning via a warning lamp. The second alert command may be the same as or different from the first alert command.
S160: no alarm is given.
And (3) identifying and classifying the personnel in the tunnel monitoring image sequence, or when the tracking count of the mine car is less than or equal to the threshold number, indicating that no illegal action exists in the operation process of the mine car group in the coal mine tunnel, and at the moment, not giving an alarm.
This embodiment is through discerning, categorised and count tunnel monitoring image sequence, can count the mine car flow in the tunnel automatically to can automatic alarm to violations such as personnel take off the bus, the driving pedestrian, can improve the security of coal mine transportation in the coal mine tunnel. Further, the embodiment performs secondary classification on the targets in the tunnel monitoring image sequence, so that the accuracy of target detection can be improved, and the possibility of false alarm is reduced. The required hardware of this application coal mine tunnel monitoring method constitutes simply, need not to carry out discernment in advance and comparison to every mine car and every staff, perhaps sets up pressure sensor on the mine car track, perhaps sets up radio frequency identification label etc. on the mine car, can also reduce the control cost when accurately discerning the operation of violating the regulations.
In order to reduce the calculation of the tunnel monitoring image sequence, the embodiment can identify, classify and count the targets in the tunnel monitoring image sequence when the operation state of the winch is judged to be operation. Referring to fig. 3, fig. 3 is a schematic flow chart of a coal mine roadway monitoring method according to a second embodiment of the present application. This embodiment is based on the first embodiment of the coal mine tunnel monitoring method, and therefore, the same steps are not described herein again. The embodiment comprises the following steps:
s310: a sequence of winch monitoring images is acquired.
Wherein the winch is used for pulling the mine car in the coal mine tunnel. The winch monitoring image sequence is acquired in real time through a monitoring camera of the winch room, and the winch monitoring image comprises an image of a winding drum part of a winch. In order to improve the accuracy of determining the running state of the winch, in this embodiment, the winch monitoring image sequence may be obtained by extracting a reel portion in the original winch monitoring image sequence, and the extraction method of the reel portion image may be manual selection or extraction of coordinates of a reel area by using an image segmentation algorithm.
The winch monitoring image sequence can be a visible light monitoring image sequence, an infrared monitoring image sequence or a thermal imaging monitoring image sequence and the like.
S320: and detecting the winch monitoring image sequence by using a dynamic detection algorithm to acquire the motion state of the winch.
The embodiment can detect the speed characteristics of pixels in the winch monitoring image sequence by using a dynamic detection algorithm to acquire the motion state of the winch.
Referring to fig. 4, fig. 4 is a schematic flow chart illustrating an embodiment of obtaining the motion state of the winch according to the present application. The implementation mode comprises the following steps:
s321: and calculating the speed characteristic of each pixel point in the current frame winch monitoring image in the winch monitoring image sequence by using a dynamic detection algorithm.
The dynamic detection algorithm may be a Lucas-Kanade optical flow algorithm, a block matching algorithm, a GMM algorithm or a KNN algorithm, etc. In the embodiment, the speed characteristic of each pixel point in the winch monitoring image sequence is calculated by using a Lucas-Kanade optical flow algorithm as an example.
And calculating the current position of each pixel point in the current frame of winch monitoring image and the historical position of each pixel point in the previous frame of winch monitoring image by using a Lucas-Kanade optical flow algorithm, wherein a first time interval is formed between the current frame of winch monitoring image and the previous frame of winch monitoring image. And calculating the speed characteristic of each pixel point in the first number of pixel points in the winch monitoring image according to the first time interval, the current position of each pixel point and the historical position of each pixel point. The formula is expressed as follows:
I(xi,yi,ti)＝I(xi+δx,yi+δy,ti+δt) (1)
in the formula (1), the previous frame time is t, and the first time interval between the current frame winch monitoring image and the previous frame winch monitoring image is delta t, I (x)i+δt,yi+δt,ti+ deltat) represents the ith pixel point I (x) in the previous winch monitoring image after delta t timei,yi,ti) I is a positive integer.
In the formula (2), (v)xi,vyi) The speed characteristic v of the ith pixel point in the current frame winch monitoring imagexiVelocity characteristic of abscissa of i-th pixel point, vyiThe speed characteristic of the vertical coordinate of the ith pixel point is obtained.
S322: and counting the target number of pixel points with the speed characteristics of the target speed in the current frame winch monitoring image, and comparing the ratio of the target number to the number of the pixel points in the winch monitoring image with a proportional threshold value.
In this embodiment, a histogram statistical method may be used to calculate a histogram with pixel points as target speeds, and the formula is as follows:
wherein N iskRepresentative velocity vkM is the number of pixels in the length direction of the winch monitoring image, n is the number of pixels in the width direction of the winch monitoring image, m x n is the total number of pixels in the winch monitoring image, and P is the total number of pixels in the winch monitoring imagevAnd the ratio of the target number to the total number of pixel points in the winch monitoring image is expressed.
Since the winch monitoring image sequence is composed of a plurality of continuous winch monitoring images, the speed characteristics and the target number of pixels in the plurality of winch monitoring images at the first time interval are different. The method and the device adopt the ratio of the maximum target number in the multi-frame winch monitoring image to the pixel number in the winch monitoring image to compare with a proportional threshold. The proportional threshold value can be determined according to the area of the winch drum part in the winch monitoring image in the whole winch monitoring image.
If the ratio of the maximum target number in the winch monitoring image sequence to the number of pixel points in the winch monitoring image is greater than or equal to a proportional threshold value, namely | max (Pv)|≥VthThen, S323 is executed.
If the ratio of the maximum target number in the winch monitoring image sequence to the number of pixel points in the winch monitoring image is smaller than a proportional threshold value, namely | max (P)v)|<VthThen, S324 is executed.
S323: and determining the motion state of the winch as running.
When the target number of pixel points in the winch monitoring image move at the same speed, and the ratio of the target number to the number of the pixel points in the winch monitoring image is larger than or equal to a proportional threshold, the winch can be determined to be rolling, and therefore the movement state of the winch can be determined to be running.
If the motion state of the winch is running, the winch is indicated to pull the mine car to run in the coal mine tunnel, and at the moment, the alarm function is started to execute S330.
S324: the motion state of the winch is determined to be stopped.
And judging that the motion state of the winch is a stop state, not starting an alarm function at the moment, and not identifying, classifying and counting the targets in the tunnel monitoring image.
S330: and when the motion state of the winch is operation, acquiring a tunnel monitoring image sequence in the coal mine tunnel.
In this embodiment, the monitoring camera in the coal mine tunnel may be opened to acquire the tunnel monitoring image sequence when the motion state of the winch is determined to be running, and the monitoring camera in the coal mine tunnel may be closed when the motion state of the winch is determined to be stopped. Or the monitoring camera in the coal mine tunnel is in a state of continuously opening and acquiring the tunnel monitoring image sequence, and the tunnel monitoring image sequence in the coal mine tunnel at the same or similar time as the winch operation time is intercepted according to the time when the movement state of the winch is judged to be changed into operation, so as to be used for identifying, classifying and counting targets in the tunnel monitoring image sequence; and the tunnel monitoring image sequence during the period of judging the motion state of the winch to be static is not used for identifying, classifying and counting the targets in the tunnel monitoring image sequence.
S340: and identifying the targets in the tunnel monitoring image sequence and classifying the targets.
When the object is classified as "person", S350 is performed.
When the object is classified as "background", S380 is performed.
When the object is classified as a "mine car", S360 is executed.
S350: and generating a first alarm instruction.
S360: and tracking and counting the mine cars, and comparing the tracking and counting with a threshold number.
When the accumulated tracking count is greater than the threshold number during the single ascending or descending of the mine car group, S370 is performed. And executing S380 when the accumulated tracking count in the ascending or descending process of the single mine car group is less than or equal to the threshold number.
S370: generating a second alarm instruction
S380: no alarm is given.
This embodiment is through discerning, categorised and count tunnel monitoring image sequence, can count the mine car flow in the tunnel automatically to can automatic alarm to violations such as personnel take off the bus, the driving pedestrian, can improve the security of coal mine transportation in the coal mine tunnel. And when the running state of the winch is static, the operation of identifying, classifying and counting the targets in the roadway monitoring image sequence is not performed, so that the operation on the roadway monitoring image sequence can be reduced. Further, the embodiment performs secondary classification on the targets in the tunnel monitoring image sequence, so that the accuracy of target detection can be improved, and the possibility of false alarm is reduced. The required hardware of this application coal mine tunnel monitoring method constitutes simply, need not to carry out discernment in advance and comparison to every mine car and every staff, perhaps sets up pressure sensor on the mine car track, perhaps sets up radio frequency identification label etc. on the mine car, can also reduce the control cost when accurately discerning the operation of violating the regulations.
The embodiment of the coal mine tunnel monitoring method is implemented by a coal mine tunnel monitoring device, so that the application also provides a coal mine tunnel monitoring device, please refer to fig. 5, and fig. 5 is a schematic structural diagram of an embodiment of the coal mine tunnel monitoring device provided by the application. The coal mine tunnel monitoring device 100 of this embodiment may include a processor 101, a memory 102, and a communication circuit 103, which are connected to each other, and the coal mine tunnel monitoring device 100 of this embodiment may implement the above-described embodiment of the coal mine tunnel monitoring method. The communication circuit 103 is used for establishing communication connection with a monitoring camera in a coal mine tunnel or a winch house to obtain a tunnel monitoring image sequence or a winch monitoring image sequence, the memory 102 is used for storing the tunnel monitoring image sequence or the winch monitoring image sequence, and the processor 101 is used for processing the winch monitoring image sequence to calculate the running state of a winch or processing the tunnel monitoring image sequence to identify, classify and count targets in the tunnel monitoring image sequence.
The processor 101 may be an integrated circuit chip having signal processing capability. The processor 101 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
For the method of the above embodiment, it may exist in the form of a computer program, so that the present application provides a computer storage medium, please refer to fig. 6, and fig. 6 is a schematic structural diagram of an embodiment of the computer storage medium provided in the present application. The computer storage medium 200 of the present embodiment stores therein a computer program 201 that can be executed to implement the method in the above-described embodiments.
The computer storage medium 200 of this embodiment may be a medium that can store program instructions, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may also be a server that stores the program instructions, and the server may send the stored program instructions to other devices for operation, or may self-operate the stored program instructions.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A coal mine roadway monitoring method is characterized by comprising the following steps:
acquiring a tunnel monitoring image sequence in the coal mine tunnel;
identifying a target in the roadway monitoring image sequence by using a vehicle detection algorithm, and classifying the target by using a classifier, wherein the classifier is used for outputting personnel, mine cars and backgrounds;
if the target category output by the classifier is personnel, generating a first alarm instruction;
and if the target category output by the classifier is the mine car, tracking and counting the mine car.
2. The method of claim 1, further comprising:
acquiring a sequence of monitoring images of a winch, wherein the winch is used for pulling a mine car in the coal mine tunnel;
detecting the winch monitoring image sequence by using a dynamic detection algorithm to obtain the motion state of the winch;
and when the motion state of the winch is running, executing the steps of identifying the target in the roadway monitoring image sequence and classifying the target.
3. The method of claim 2, wherein said detecting a motion state of said drawworks in said drawworks monitoring image using a dynamic detection algorithm comprises:
calculating the speed characteristic of each pixel point in the current frame winch monitoring image in the winch monitoring image sequence by using a dynamic detection algorithm;
counting the target number of pixel points with the speed characteristics as the target speed in the current frame winch monitoring image;
if the ratio of the maximum target number in the winch monitoring image sequence to the number of pixel points in the winch monitoring image is larger than or equal to a proportional threshold, determining that the movement state of the winch is running;
and if the ratio of the maximum target number in the winch monitoring image sequence to the number of pixel points in the winch monitoring image is smaller than a proportional threshold, determining that the movement state of the winch is stopped.
4. The method as claimed in claim 3, wherein said calculating the speed characteristic of each pixel point in the current frame of winch monitor image in the sequence of winch monitor images using a dynamic detection algorithm comprises:
calculating the current position of each pixel point in the current frame of winch monitoring image and the historical position of each pixel point in the previous frame of winch monitoring image by using a dynamic detection algorithm, wherein a first time interval is formed between the current frame of winch monitoring image and the previous frame of winch monitoring image;
and calculating the speed characteristic of each pixel point in a first number of pixel points in the winch monitoring image according to the first time interval, the current position of each pixel point and the historical position of each pixel point.
5. The method of claim 1, wherein said tracking counting said mine cars comprises:
acquiring initial coordinates of the target in an initial frame of the tunnel monitoring image sequence;
tracking a target of the tunnel monitoring image sequence by using a tracking algorithm, and acquiring a tracking coordinate of the target after preset tracking time;
and judging the coordinate relation between the initial coordinate and the tracking coordinate and a preset boundary so as to count the target in an uplink or downlink manner.
6. The method according to claim 5, wherein the determining the coordinate relationship between the initial coordinate and the tracking coordinate and a preset boundary for counting the targets up or down comprises:
if the average value of the two abscissas of the initial coordinate is smaller than the abscissa of the preset boundary, and the average value of the two abscissas of the tracking coordinate is larger than the abscissa of the preset boundary, adding 1 to the count of the mine cars in the descending direction; the preset boundary is a median line of the running track of the mine car in the roadway monitoring image sequence, the left side of the preset boundary is an uplink direction, the right side of the preset boundary is the downlink direction, and the abscissa of the left pixel of the preset boundary is smaller than the abscissa of the right pixel of the preset boundary;
if the average value of the two horizontal coordinates of the initial coordinate is larger than the horizontal coordinate of the preset boundary and the average value of the two horizontal coordinates of the tracking coordinate is smaller than the horizontal coordinate of the preset boundary, adding 1 to the count of the ascending mine car; or
If the average value of the two horizontal coordinates of the initial coordinate is smaller than the horizontal coordinate of the preset boundary, and the average value of the two horizontal coordinates of the tracking coordinate is larger than the horizontal coordinate of the preset boundary, adding 1 to the count of the mine car in the uplink direction; the preset boundary is a median line of the running track of the mine car in the roadway monitoring image sequence, the left side of the preset boundary is in a downlink direction, the right side of the preset boundary is in an uplink direction, and the abscissa of the left pixel of the preset boundary is smaller than the abscissa of the right pixel of the preset boundary;
and if the average value of the two abscissas of the initial coordinate is larger than the abscissa of the preset boundary and the average value of the two abscissas of the tracking coordinate is smaller than the abscissa of the preset boundary, adding 1 to the count of the mine cars in the descending direction.
7. The method of claim 5, wherein the obtaining initial coordinates of the target in an initial frame of the sequence of roadway monitoring images comprises:
and acquiring coordinates of two vertexes of the target on a diagonal line of an area where the target is located in an initial frame of the tunnel monitoring image sequence as the initial coordinates.
8. The method of any of claims 1 to 7, further comprising:
generating a second alarm instruction when the tracking count is greater than a quantity threshold.
9. A coal mine tunnel monitoring device is characterized by comprising a communication circuit, a processor and a memory; the processor is coupled to the memory and the communication circuit, and in operation executes instructions to cooperate with the memory and the communication circuit to implement the coal mine roadway monitoring method of any one of claims 1 to 8.
10. A computer storage medium storing a computer program for execution to implement the steps of a coal mine roadway monitoring method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010121837.7A CN111425256B (en) | 2020-02-26 | 2020-02-26 | Coal mine tunnel monitoring method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010121837.7A CN111425256B (en) | 2020-02-26 | 2020-02-26 | Coal mine tunnel monitoring method and device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111425256A CN111425256A (en) | 2020-07-17 |
| CN111425256B true CN111425256B (en) | 2022-02-18 |
Family
ID=71547277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010121837.7A Active CN111425256B (en) | 2020-02-26 | 2020-02-26 | Coal mine tunnel monitoring method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111425256B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674311A (en) * | 2021-06-30 | 2021-11-19 | 浙江大华技术股份有限公司 | Abnormal behavior detection method and device, electronic equipment and storage medium |
| TWI790187B (en) * | 2021-09-22 | 2023-01-11 | 日商不二輸送機工業股份有限公司 | Counting device and counting method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09115088A (en) * | 1995-10-23 | 1997-05-02 | Shinko Electric Co Ltd | Monitor system for inside tunnel |
| CN101626496A (en) * | 2009-08-11 | 2010-01-13 | 孙晋欣 | Inclined lane track condition wireless mobile video monitoring system |
| CN201620916U (en) * | 2010-03-30 | 2010-11-03 | 陕西盛纳德矿山科技有限公司 | Intelligent safety monitoring system applied on inclined hoisting shafts of coal mines |
| CN109458941A (en) * | 2018-12-29 | 2019-03-12 | 天津市三特电子有限公司 | The automatic load measurement system of mine car and monitoring method |
| CN109492621A (en) * | 2018-12-18 | 2019-03-19 | 新乡市中誉鼎力软件科技股份有限公司 | Mine vehicle recognition methods, server and system |
-
2020
- 2020-02-26 CN CN202010121837.7A patent/CN111425256B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09115088A (en) * | 1995-10-23 | 1997-05-02 | Shinko Electric Co Ltd | Monitor system for inside tunnel |
| CN101626496A (en) * | 2009-08-11 | 2010-01-13 | 孙晋欣 | Inclined lane track condition wireless mobile video monitoring system |
| CN201620916U (en) * | 2010-03-30 | 2010-11-03 | 陕西盛纳德矿山科技有限公司 | Intelligent safety monitoring system applied on inclined hoisting shafts of coal mines |
| CN109492621A (en) * | 2018-12-18 | 2019-03-19 | 新乡市中誉鼎力软件科技股份有限公司 | Mine vehicle recognition methods, server and system |
| CN109458941A (en) * | 2018-12-29 | 2019-03-12 | 天津市三特电子有限公司 | The automatic load measurement system of mine car and monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111425256A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | A YOLO-based traffic counting system | |
| KR101735365B1 (en) | The robust object tracking method for environment change and detecting an object of interest in images based on learning | |
| CN101908141B (en) | Video smoke detection method based on mixed Gaussian model and morphological characteristics | |
| TWI452540B (en) | Image based detecting system and method for traffic parameters and computer program product thereof | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| US20080100473A1 (en) | Spatial-temporal Image Analysis in Vehicle Detection Systems | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN111425256B (en) | Coal mine tunnel monitoring method and device and computer storage medium | |
| CN105303191A (en) | Method and apparatus for counting pedestrians in foresight monitoring scene | |
| CN101908142A (en) | Feature analysis-based video flame detecting method | |
| CN111325048B (en) | Personnel gathering detection method and device | |
| KR20190046351A (en) | Method and Apparatus for Detecting Intruder | |
| CN103324910A (en) | Fire alarming method based on video detection | |
| CN111626170A (en) | Image identification method for railway slope rockfall invasion limit detection | |
| CN111696135A (en) | Intersection ratio-based forbidden parking detection method | |
| Kamijo et al. | A real-time traffic monitoring system by stochastic model combination | |
| Cheng et al. | A multiscale parametric background model for stationary foreground object detection | |
| CN113850995A (en) | Event detection method, device and system based on tunnel radar vision data fusion | |
| CN113055651A (en) | Artificial intelligence type vehicle security system and computer readable storage medium | |
| CN112083678A (en) | Gate security control method and device, electronic equipment and storage medium | |
| CN117037404A (en) | Electronic fence early warning method based on target detection and target tracking | |
| Tamersoy et al. | Counting vehicles in highway surveillance videos | |
| KR102407202B1 (en) | Apparatus and method for intelligently analyzing video | |
| KR101294498B1 (en) | Method of objects recognition for tunnel accident monitoring system | |
| CN113674311A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium |
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 |