CN116612441B - Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification - Google Patents
Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification Download PDFInfo
- Publication number
- CN116612441B CN116612441B CN202310896874.9A CN202310896874A CN116612441B CN 116612441 B CN116612441 B CN 116612441B CN 202310896874 A CN202310896874 A CN 202310896874A CN 116612441 B CN116612441 B CN 116612441B
- Authority
- CN
- China
- Prior art keywords
- image
- powder discharge
- pulverized coal
- coal
- drilling
- 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
- 239000000843 powder Substances 0.000 title claims abstract description 174
- 238000005553 drilling Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000003245 coal Substances 0.000 claims abstract description 167
- 239000002817 coal dust Substances 0.000 claims abstract description 76
- 230000008859 change Effects 0.000 claims abstract description 58
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 15
- 239000000428 dust Substances 0.000 claims description 14
- 238000013519 translation Methods 0.000 claims description 7
- 238000000265 homogenisation Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 239000011800 void material Substances 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 6
- 238000010276 construction Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000007599 discharging Methods 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 239000003818 cinder Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Machine Tool Sensing Apparatuses (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application discloses a drilling anti-jamming method, equipment and medium based on mine powder discharge image identification. Belonging to the technical field of image data processing. The problem of among the prior art reduce the efficiency of construction because of drilling card boring is solved. The method comprises the steps of obtaining a powder discharge image uploaded by a camera device group arranged on an anti-blocking device; grid division is carried out on the powder discharge image, and based on the quantity of coal dust in each grid, coal dust digital information corresponding to the powder discharge image is determined; based on the coal dust digital information, eliminating the target images which do not meet the preset similarity condition to obtain a second target image set; performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points; and determining the drilling jamming rate based on the reference powder discharge image and a preset pulverized coal volume change rate function so as to start different anti-jamming measures based on the drilling jamming rate.
Description
Technical Field
The application relates to the technical field of image data processing, in particular to a drilling anti-blocking method, device and medium based on mine powder discharge image recognition.
Background
The gas pre-extraction is a technology of drilling holes at the appointed position of the coal wall by adopting a mine drilling machine so as to gradually discharge the gas and perform the pre-extraction.
In the process of drilling, the prior art is difficult to match with the output power of a drilling machine in time due to the coupling effect of complex and changeable mining stress, lithology, cinder, compressed air multiphase flow field and other complex load in the drilling construction process, and cinder in the drilling cannot be discharged in time, so that the problem of drilling jam is extremely easy to cause even broken drilling accidents.
The problem of sticking the drill greatly reduces the construction efficiency, brings non-negligible potential safety hazard to constructors, and if the problem of sticking the drill is not treated in time, the spark generated by breaking the drill is extremely easy to cause serious safety accidents of the coal mine, thereby causing huge economic loss.
Disclosure of Invention
The embodiment of the application provides a drilling anti-seize method, equipment and medium based on mine powder discharge image identification, which are used for solving the following technical problems: the problem of drill sticking greatly reduces the construction efficiency, if the problem of drill sticking is not treated in time, the spark generated by broken drill is very easy to cause major safety accidents of coal mines, and thus huge economic loss is caused.
The embodiment of the application adopts the following technical scheme:
the embodiment of the application provides a drilling anti-seize method based on mine dust discharge image identification. The method comprises the steps of obtaining a powder discharge image uploaded by a camera device group arranged on an anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set; grid division is carried out on the powder discharge image, and based on the quantity of coal dust in each grid, coal dust digital information corresponding to the powder discharge image is determined; based on the coal dust digital information, eliminating the target images which do not meet the preset similarity condition to obtain a second target image set; performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points; and determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
According to the embodiment of the application, the powder discharging speed and the quantity are obtained through the powder discharging images uploaded by the camera device group on the anti-blocking device, so that the change of the powder discharging volume is obtained, and further the actual running state information of the drill rod is obtained. Secondly, the embodiment of the application realizes efficient and accurate image identification and registration by carrying out grid division on the powder discharge image and carrying out edge description through a coarse registration HOG feature detection algorithm, so that the accuracy of the image information for finally carrying out the drilling sticking rate calculation is higher. In addition, the embodiment of the application calculates the probability of drill sticking of the drill hole according to the volume change rate of the pulverized coal, and starts different anti-sticking measures based on different drill sticking probabilities, so that the drill sticking problem is rapidly and efficiently treated under the condition of maintaining the normal work of the drilling machine.
In one implementation of the application, the coal powder volume change rate is determined based on a reference powder discharge image and a preset coal powder volume change rate function, and the method specifically comprises the following steps: determining coal dust information based on a reference dust discharge image; based on the pulverized coal information and a preset pulverized coal volume change rate function:
；
determining the volume change rate of the pulverized coal; wherein, is the volume change rate of pulverized coal>Is the volume change of pulverized coal>Is a correction factor, +.>Representing the position between two camera devicesHorizontal distance (I)>The movement time of the two camera devices in the coal powder path is represented,for the feed rate of the drill,nfor the amount of coal dust identified by the camera, +.>Is the void ratio of coal powder->The cross section area of the single coal dust in the radial direction of the drill rod is S, and the cross section area of the coal dust deposit in the radial direction of the drill rod is the cross section area of the coal dust deposit in the powder discharge port.
In one implementation of the application, the drill sticking rate of the drill hole is determined based on the volume change rate of the pulverized coal, and the method specifically comprises the following steps: based on the function:
；
determining the drilling sticking rate of the drilling; wherein, Pthe drilling rate is the drilling rate;is the volume change rate of the pulverized coal; the drilling sticking rate is inversely related to the volume change rate of the pulverized coal.
In one implementation mode of the application, the powder discharge image is subjected to grid division, and based on the quantity of the coal dust in each grid, the coal dust digital information corresponding to the powder discharge image is determined, and the method specifically comprises the following steps: calculating a threshold value when the variance is maximum through an inter-class variance formula, and dividing the powder discharge image into an optimal binarization image; adopting a quadtree homogenization method to grid-divide the powder discharge image; determining coal dust characteristic points at grid junctions, and distributing according to the duty ratio of the coal dust characteristic points in different grids; based on the quantity of the pulverized coal in each grid, the pulverized coal in each grid is quantized to determine the digital information of the pulverized coal corresponding to the powder discharge image.
In one implementation manner of the present application, based on the digital information of pulverized coal, the target image which does not meet the preset similarity condition is removed, so as to obtain a second target image set, which specifically includes: determining the unit cells at the same position in the coal powder source image and the first target image, and respectively corresponding coal powder digital information; based on the coal dust digital information respectively corresponding to the unit cells at the same position, determining the similarity respectively corresponding to each grid between the coal dust source image and the first target image; summing the similarity corresponding to each grid respectively to obtain the similarity between the pulverized coal source image and the first target image; and eliminating the first target image which does not meet the preset similarity condition to obtain a second target image set.
In one implementation manner of the present application, edge description is performed on the powder discharge image in the second target image set by using a HOG feature detection algorithm of coarse registration, which specifically includes: selecting a plurality of random data points from the pulverized coal source image, and constructing a first data point set; selecting the random data points with the same quantity from the images of the second target image set, and constructing a second data point set; based on a least square method, a first data point set and a second data point set, calculating a rotation translation transformation matrix between images of the pulverized coal source image and a second target image set; determining data points with the distance smaller than a preset distance threshold value based on the rotation translation transformation matrix and the second data point set to construct a consistency point set, and determining a corresponding transformation matrix through the consistency point set; and selecting a plurality of pairs of coal dust characteristic points from the images of the coal dust source image and the second target image set, and carrying out edge description on the powder discharge images in the second target image set based on the size and the direction of the pixel gradient of the coal dust characteristic points.
In one implementation manner of the present application, edge description is performed on the powder discharge image in the second target image set based on the size and the direction of the pixel gradient of the coal dust feature point, which specifically includes: based on a preset pulverized coal detection unit, performing image detection on the pulverized coal characteristic points to determine the magnitude and the direction of pixel gradients corresponding to characteristic pixels in the preset pulverized coal detection unit respectively; the preset pulverized coal detection unit is a rule unit for presetting the number of pixels; constructing a histogram corresponding to each preset pulverized coal detection unit based on the size and the direction of the pixel gradient, and collecting the histogram into the HOG descriptor; training an SVM through the HOG descriptor to detect coal dust edge information of the powder discharge image, and determining the similarity of the powder discharge image according to the edge similarity of the coal dust characteristic points.
In one implementation of the present application, different anti-seize measures are initiated based on the drill sticking rate of the drill hole, specifically including: comparing the drilling jamming rate with a preset anti-jamming measure starting table; under the condition that the drilling sticking rate is at a preset first-level alarm level, a first-level alarm is sent out, and the feeding speed of the drilling machine is reduced; under the condition that the drilling sticking rate is in a preset secondary alarm level, a secondary alarm is sent out, and the rotation speed and the feeding speed of the drilling machine are reduced simultaneously; and under the condition that the drilling sticking rate is in a preset three-level alarm level, sending out three-level alarm, and controlling the drill rod to reversely rotate and withdraw from the drill rod.
The embodiment of the application provides drilling anti-blocking equipment based on powder discharge image identification, which comprises the following components: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to: acquiring a powder discharge image uploaded by a camera device group arranged on the anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set; grid division is carried out on the powder discharge image, and based on the quantity of coal dust in each grid, coal dust digital information corresponding to the powder discharge image is determined; based on the coal dust digital information, eliminating the target images which do not meet the preset similarity condition to obtain a second target image set; performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points; and determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
The non-volatile computer storage medium provided by the embodiment of the application stores computer executable instructions, and the computer executable instructions are set as follows: acquiring a powder discharge image uploaded by a camera device group arranged on the anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set; grid division is carried out on the powder discharge image, and based on the quantity of coal dust in each grid, coal dust digital information corresponding to the powder discharge image is determined; based on the coal dust digital information, eliminating the target images which do not meet the preset similarity condition to obtain a second target image set; performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points; and determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
The above at least one technical scheme adopted by the embodiment of the application can achieve the following beneficial effects: according to the embodiment of the application, the powder discharging speed and the quantity are obtained through the powder discharging images uploaded by the camera device group on the anti-blocking device, so that the change of the powder discharging volume is obtained, and further the actual running state information of the drill rod is obtained. Secondly, the application realizes efficient and accurate image identification and registration by carrying out grid division on the powder discharge image and carrying out edge description by a coarse registration HOG feature detection algorithm, so that the accuracy of the image information for finally carrying out the drilling sticking rate calculation is higher. In addition, the embodiment of the application calculates the probability of drill sticking of the drill hole according to the volume change rate of the pulverized coal, and starts different anti-sticking measures based on different drill sticking probabilities, so that the drill sticking problem is rapidly and efficiently treated under the condition of maintaining the normal work of the drilling machine.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic diagram of an anti-blocking device according to an embodiment of the present application;
FIG. 2 is a flow chart of a drilling anti-sticking method based on mine dust discharge image recognition provided by the embodiment of the application;
FIG. 3 is a flowchart of an image processing according to an embodiment of the present application;
fig. 4 is a schematic diagram of a powder discharge image digitizing algorithm according to an embodiment of the present application;
fig. 5 is a flowchart of a HOG feature detection algorithm based on coarse registration according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a drilling anti-seize device based on mine dust discharge image recognition according to an embodiment of the present application.
Reference numerals:
1 camera 1,2 camera 2,3 camera 3,4 camera 4,5 camera 5,6 camera 6,7 coal wall, 8 bracket, 9 drill rod, 10 drilling machine;
200 drilling anti-seize equipment based on mine dust discharge image recognition, 201 a processor and 202 a memory.
Detailed Description
The embodiment of the application provides a drilling anti-jamming method, equipment and medium based on mine powder discharge image identification.
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
The following describes the technical scheme provided by the embodiment of the application in detail through the attached drawings.
Fig. 1 is a schematic diagram of an anti-blocking device according to an embodiment of the present application. As shown in fig. 1, an anti-blocking device in an embodiment of the present application includes: three sets of image pick-up devices (camera 1, camera 2, camera 3, camera 4, camera 5 and camera 6) installed at the powder discharge outlet, a coal wall 7, a drilling machine 10, a drill rod 9 and a bracket 8. The three sets of camera devices are respectively arranged in 2 sets and 1 set along the horizontal and vertical directions of the powder discharge port, the distance between two phases of each set of camera device is preset to be 40cm, and in application, the camera devices can be adjusted according to the actual operation space.
In one embodiment of the application, when the coal mine drilling machine drills and discharges gas, coal dust is only acted by gravity after being discharged from a dust discharge port, and at the moment, the movement speed can be decomposed into horizontal speed and vertical speed and is transmitted through three sets of camera devices, namely, the coal dust is photographed by two cameras of each set of camera devices in sequence. According to the basic theory of object motion, the vertical speed of the pulverized coal is negligible in a very short time. Thus, the coal dust moving speedApproximately equal to horizontal speed>I.e. +.>While the horizontal movement speed +.>Wherein->Represents the horizontal distance of the two cameras, < >>The movement time of the two cameras along the coal dust path is represented. The change rate of the pulverized coal volume can be determined according to the pulverized coal quantity, the pulverized coal movement time, the camera distance and the feeding speed of the drilling machine>。
Further, taking an image capturing method of any one of the image capturing devices, such as the camera 1 and the camera 2, as an example. If the camera 1 collects the powder discharge image, the powder discharge image is used as a coal dust source image. After a set distance between the two cameras, the camera 2 continuously shoots to obtain powder discharge images, and the powder discharge images obtained by the continuous shooting of the camera 2 are used as a first target image set. According to the formulaCalculating to obtain average coal powder speed, wherein +.>Represents the horizontal distance of the two cameras, < >>The movement time of the two cameras in the coal powder path is shown, and the movement time is short according to the actual working condition, so that the average speed can be used as the instantaneous speed of the coal powder. According to the feeding speed of the drilling machine and combining the movement speed of the pulverized coal and the quantity of the pulverized coal in the powder discharge image, the volume change rate of the discharged powder can be calculated. Therefore, the real-time working condition of drilling and powder discharge can be obtained, and further anti-jamming control is realized.
Fig. 2 is a flowchart of a drilling anti-jamming method based on mine dust discharge image recognition provided by an embodiment of the application. As shown in fig. 2, the drilling anti-sticking method based on mine dust discharge image identification comprises the following steps:
step 101, acquiring a powder discharge image uploaded by an image pickup device group arranged on an anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set.
In one embodiment of the present application, an image capturing method of any one of the imaging devices, such as the camera 1 and the camera 2, is taken as an example. Taking the powder discharge image acquired by the camera 1 as a coal dust source image, and taking a plurality of powder discharge images continuously acquired by the camera 2 as a first target image set. And preprocessing the powder discharge image acquired by each camera.
Specifically, since the individual volume of the pulverized coal is small and the individual characteristic points are not obvious, a certain amount of pulverized coal and the position distribution thereof are taken as characteristic identification elements. In addition, the image quality affects the quality of the recognition effect, so that the nearest neighbor interpolation method is adopted to map the pixels of the output image onto the coordinates of the input image so as to improve the image quality. In addition, because the mine working condition is special and the visibility is low, the image enhancement technology is adopted to enhance the useful information in the image, and the application adopts the frequency domain method to perform coal dust characteristic identification so as to determine the quantity and the position of coal dust. It should be noted that, the method adopted in the process of preprocessing the powder discharge image is the prior art, and the embodiments of the present application are not described in detail.
Fig. 3 is a flowchart of an image processing according to an embodiment of the present application, as shown in fig. 3, after a powder discharge image is obtained, the powder discharge image is first preprocessed. Based on an image digitizing algorithm, converting image information of the powder discharge image into digital information, and based on a hamming distance before the image, performing similarity evaluation on the powder discharge image so as to reject images which do not meet the similarity requirement in the first target image set. And secondly, preserving the powder discharge image with higher similarity, carrying out image edge description based on a coarse registration HOG feature detection algorithm to improve image recognition accuracy, judging based on edge similarity, determining the similarity of the powder discharge image, and eliminating the powder discharge image with low similarity to obtain the powder discharge image meeting the requirement. The specific process of the powder discharge image processing in the embodiment of the present application is described in detail by steps 102 to 104.
Step 102, carrying out grid division on the powder discharge image, and determining the digital information of the coal powder corresponding to the powder discharge image based on the quantity of the coal powder in each grid.
In one embodiment of the application, the threshold value when the variance is maximum is calculated through an inter-class variance formula, and the powder discharge image is divided into optimal binarized images. And adopting a quadtree homogenization method to grid-divide the powder discharge image. And determining coal powder characteristic points at grid junctions, and distributing according to the duty ratio of the coal powder characteristic points in different grids. Based on the quantity of the pulverized coal in each grid, the pulverized coal in each grid is quantized to determine the digital information of the pulverized coal corresponding to the powder discharge image.
Specifically, the embodiment of the application provides a quadtree homogenization method based on a maximum inter-class variance method, which is used for carrying out gridding expansion on a powder discharge image, extracting coal dust characteristic point information and converting the coal dust characteristic point information into digital information. The specific process is as follows:
(1) The first step, a threshold k when the variance is maximum is calculated by adopting an inter-class variance formula, and the powder discharge image is divided into an optimal binarization image. The maximum inter-class variance method is to divide all image pixels into two classes, target and background, with a threshold k. And then, enabling the threshold k to change in the interval [0,1], and calculating the inter-class variance value of each gray level image to obtain the k value when the inter-class variance is maximum, wherein the k value is the threshold of the optimal binarized image.
(2) And secondly, carrying out grid division on the powder discharge image after image recognition. Dividing the image into n rows and n columns of grids by adopting a quadtree homogenization method, and enabling the powder discharge image to fall into each grid unit.
(3) Thirdly, quantifying the pulverized coal in each grid. Aiming at the coal powder characteristic points at the junctions of the grid units, dividing the coal powder characteristic points into grids with large duty ratio according to the duty ratio of the coal powder characteristic points at the boundaries in different grids.
(4) And fourthly, obtaining a new digital gridding partition after image processing, thereby converting the powder discharge image information into coal dust digital information.
Fig. 4 is a schematic diagram of a powder discharge image digitizing algorithm according to an embodiment of the application. As shown in fig. 4, the image with the reference number (1) from the left is the powder discharge image to be processed, and the image with the reference number (2) is the powder discharge image subjected to grid division. The image with the reference number (3) is the distribution condition of coal dust in each grid after the grid division of the powder discharge image. The image labeled (4) is to quantize the pulverized coal in each grid, thereby converting the image information into digital information.
According to the embodiment of the application, the image information is converted into the digital information, so that the information in each powder discharge image can be displayed more clearly and intuitively. The similarity comparison is carried out on the images through specific digital information, and the comparison process is more efficient and accurate.
And 103, removing the target images which do not meet the preset similarity condition based on the coal dust digital information to obtain a second target image set.
In one embodiment of the application, the coal dust digital information corresponding to the unit cells at the same position in the coal dust source image and the first target image is determined. And determining the similarity of the respective grid correspondence between the pulverized coal source image and the first target image based on the digital information of the pulverized coal respectively corresponding to the unit grids at the same position. And summing the similarity corresponding to each grid respectively to obtain the similarity between the pulverized coal source image and the first target image. And eliminating the first target image which does not meet the preset similarity condition to obtain a second target image set.
Specifically, the identified image is converted into numerical value information, and the similarity of the images is calculated by using a hamming distance method. If the calculated value is greater than the preset similarity threshold, the two images are considered to be two different images, and if the calculated value is not greater than the preset similarity threshold, the images are saved and the next step is carried out.
Specifically, the coal dust digital information of the same grid position in the coal dust source image and the first target image is determined. For example, the digital information of the first grid of the pulverized coal source image is compared with the digital information of the first grid in the first target image, and the digital information of the second grid of the pulverized coal source image is compared with the digital information of the second grid in the first target image. Determining the distance between the pulverized coal source image and each image in the first target set by a Hamming distance method, if the distance is larger than a preset similarity threshold, rejecting the image in the current first target set, if the distance is not larger than the preset similarity threshold, storing the image in the current first target set, and obtaining a second target image set through the stored image.
And 104, performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points.
In one embodiment of the application, the condition that pulverized coal is overlapped and overlapped in the powder discharge process is considered, so that an HOG feature detection algorithm based on coarse registration is adopted for image edge description to improve the image recognition accuracy. Firstly, a coarse registration method is adopted to enable two groups of images to obtain reasonable transformation matrix and point distribution relation, and then an HOG feature detection algorithm is adopted to carry out edge description on the powder discharge image.
Fig. 5 is a flowchart of a HOG feature detection algorithm based on coarse registration according to an embodiment of the present application. As shown in fig. 5, a plurality of data points are selected from the input source image and the second target image set, respectively, a transformation matrix is calculated from the selected data points, and a consistency point set is extracted. Under the condition that a consistency point set is obtained, a transformation matrix is determined, a plurality of pairs of coal dust characteristic points are randomly selected, the size and the direction of each characteristic pixel gradient are calculated, and a histogram is created. And training an SVM learning algorithm through the descriptors, judging the similarity of the powder discharge images, and determining the powder discharge images meeting the requirements based on the similarity.
In one embodiment of the application, a first data point set is constructed by selecting a plurality of random data points from the pulverized coal source image. And selecting the random data points with the same number from the images of the second target image set, and constructing a second data point set. And calculating a rotation translation transformation matrix between the images of the pulverized coal source image and the second target image set based on the least square method, the first data point set and the second data point set. And determining data points with the distance smaller than a preset distance threshold value based on the rotation translation transformation matrix and the second data point set to construct a consistency point set, and determining a corresponding transformation matrix through the consistency point set. And selecting a plurality of pairs of coal dust characteristic points from the images of the coal dust source image and the second target image set, and carrying out edge description on the powder discharge images in the second target image set based on the size and the direction of the pixel gradient of the coal dust characteristic points.
In one embodiment of the application, based on a preset pulverized coal detection unit, image detection is performed on the pulverized coal characteristic points to determine the magnitude and the direction of pixel gradients corresponding to characteristic pixels in the preset pulverized coal detection unit respectively; the preset pulverized coal detection unit is a rule unit for presetting the number of pixels. Based on the size and the direction of the pixel gradient, a histogram corresponding to each preset pulverized coal detection unit is constructed, and the histogram is collected into the HOG descriptor. Training an SVM through the HOG descriptor to detect coal dust edge information of the powder discharge image, and determining the similarity of the powder discharge image according to the edge similarity of the coal dust characteristic points.
Specifically, (1) first, a plurality of data points are randomly selected from the source image and the target image, for example, three points may be randomly selected, respectively, that is, a data point set { is selected from the pulverized coal source image PSelecting corresponding data point set from target image Q { + }>}。
(2) A transformation matrix is calculated. Combining the least square method with the data point set {Sum {>The rotation translation transformation matrix P' is calculated.
(3) A set of consistency points is extracted. All points with the P' and Q distances smaller than a threshold T (approaching 0 and preset to 0.1) are extracted to form a consistency point set.
(4) And judging whether to acquire the consistency point set. If the consistency point set is not obtained, returning to the first step to select the random points again until the consistency point set is obtained, and using the consistency point set to determine a corresponding transformation matrix.
(5) And randomly selecting a plurality of pairs of characteristic points. Several pairs of characteristic points of P and Q are randomly selected, a detection window covering the whole image is set, and a square unit (preset as 16 pixels) is set to detect a single powder discharge image.
(6) The feature pixel gradient magnitude and direction are calculated. The gradient magnitude and direction of each pixel in the pulverized coal detection unit are calculated.
(7) A histogram is created. The size and direction of the pixel image in each of the pulverized coal detecting units are calculated, and a histogram is created for each of the pulverized coal detecting units. The number of directions is preset, pixels in each direction are added, and the histogram in the detection unit is collected into the HOG descriptor.
(8) Finally, the descriptors train an SVM (support vector machine) learning algorithm. The SVM is trained by HOG descriptors to detect the coal dust edge information of the image. And judging according to the edge similarity of the coal powder characteristic points, so as to determine the similarity of the powder discharge images.
And 105, determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
In one embodiment of the application, the pulverized coal information is determined based on the reference pulverized coal discharge image, and the pulverized coal information and the preset pulverized coal volume change rate function are based on the pulverized coal information:
；
and determining the volume change rate of the pulverized coal. Wherein, is the volume change rate of pulverized coal>Is the volume change of pulverized coal>Is a correction factor, +.>Represents the horizontal distance between the two camera devices, < >>Indicating the way of coal dustThe movement time of the two camera devices is equal to the movement time of the two camera devices,for the feed rate of the drill,nfor the amount of coal dust identified by the camera, +.>Is the void ratio of coal powder->Is the cross-sectional area of a single coal powder,Sis the cross-sectional area of the pulverized coal deposit at the powder discharge port.
In one embodiment of the application, the function is based on:
；
and determining the drilling sticking rate of the drilling. Wherein, Pthe drilling rate is the drilling rate;is the volume change rate of the pulverized coal; the drilling sticking rate is inversely related to the volume change rate of the pulverized coal.
In particular, considering that the front view and the left view of the toner image have a certain correlation, it is assumed that the recognized front view and left view of the toner image are approximately the same,is the volume change rate of pulverized coal>Is the volume change of pulverized coal>Is a correction coefficient which is used to correct the image,represents the horizontal distance of the two cameras, < >>Representing the movement time of two cameras of the pulverized coal path, +.>For the feed rate of the drill,nfor the amount of coal fines identified by the camera, +.>Is the void ratio of coal powder->Is the cross-sectional area of single coal dust in the radial direction of the drill rod,Sis the cross-sectional area of the pulverized coal deposit at the radial powder discharge port of the drill rod.
According to the actual working condition, the drill sticking ratePRate of change with pulverized coal volumeQIn inverse relationship. Establishing a drill sticking rate expression asDetecting according to the pulverized coal volume change rate calculation method to obtain the pulverized coal volume change rateQThereby determining the drill sticking rateP。
In one embodiment of the application, the drill sticking rate is compared with a preset anti-sticking measure start table. And under the condition that the drilling sticking rate is at a preset first-level alarm level, sending out a first-level alarm, and reducing the feeding speed of the drilling machine. And under the condition that the drilling sticking rate is in a preset secondary alarm level, sending out a secondary alarm, and reducing the rotation speed and the feeding speed of the drilling machine simultaneously. And under the condition that the drilling sticking rate is in a preset three-level alarm level, sending out three-level alarm, and controlling the drill rod to reversely rotate and withdraw from the drill rod.
Specifically, the specific anti-blocking control measures are as follows: when the stuck drilling rate P is more than or equal to 30%, the stuck drilling alarm level is yellow, and the feeding speed of the drilling machine is reduced by 20%. When the stuck rate P is greater than or equal to 50%, the stuck alarm level is orange, and the rotation speed and the feeding speed of the drilling machine are reduced by 50% at the same time. When the stuck drill rate P is more than or equal to 70%, the stuck drill alarm level is red, and the drill rod is controlled to reversely rotate and withdraw from the drill rod.
It should be noted that, in the embodiment of the present application, the speed of the drilling machine may be adjusted according to the actual application, which is not limited in the embodiment of the present application.
Fig. 6 is a schematic structural diagram of a drilling anti-seize device based on mine dust discharge image recognition according to an embodiment of the present application. As shown in fig. 6, the borehole anti-sticking apparatus 200 based on mine dust discharge image recognition includes: at least one processor 201; and a memory 202 communicatively coupled to the at least one processor 201; wherein the memory 202 stores instructions executable by the at least one processor 201, the instructions being executable by the at least one processor 201 to enable the at least one processor 201 to: acquiring a powder discharge image uploaded by a camera device group arranged on the anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set. And carrying out grid division on the powder discharge image, and determining the digital information of the coal powder corresponding to the powder discharge image based on the quantity of the coal powder in each grid. And removing the target images which do not meet the preset similarity condition based on the coal dust digital information to obtain a second target image set. And performing edge description on the powder discharge images in the second target image set by using a coarse registration HOG feature detection algorithm so as to determine a reference powder discharge image based on the edge similarity of the coal powder feature points. And determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
The embodiment of the application also provides a nonvolatile computer storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to: acquiring a powder discharge image uploaded by a camera device group arranged on the anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set. And carrying out grid division on the powder discharge image, and determining the digital information of the coal powder corresponding to the powder discharge image based on the quantity of the coal powder in each grid. And removing the target images which do not meet the preset similarity condition based on the coal dust digital information to obtain a second target image set. And performing edge description on the powder discharge images in the second target image set by using a coarse registration HOG feature detection algorithm so as to determine a reference powder discharge image based on the edge similarity of the coal powder feature points. And determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the embodiments of the application by those skilled in the art. Such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (7)
1. Drilling anti-seize method based on mine dust discharge image identification, which is characterized by comprising the following steps:
acquiring a powder discharge image uploaded by a camera device group arranged on the anti-blocking device; the powder discharge image comprises a pulverized coal source image and a first target image set;
grid division is carried out on the powder discharge image, and based on the quantity of coal dust in each grid, coal dust digital information corresponding to the powder discharge image is determined;
based on the coal dust digital information, eliminating target images which do not meet preset similarity conditions to obtain a second target image set;
performing edge description on the powder discharge images in the second target image set through a coarse registration HOG feature detection algorithm to determine a reference powder discharge image based on the edge similarity of the coal powder feature points;
determining the pulverized coal volume change rate based on the reference powder discharge image and a preset pulverized coal volume change rate function, and determining the drilling sticking rate based on the pulverized coal volume change rate so as to start different anti-sticking measures based on the drilling sticking rate;
the method for determining the pulverized coal volume change rate based on the reference pulverized coal discharge image and a preset pulverized coal volume change rate function specifically comprises the following steps:
determining coal dust information based on the reference powder discharge image;
based on the pulverized coal information and a preset pulverized coal volume change rate function
Determining the volume change rate of the pulverized coal; wherein, is the volume change rate of pulverized coal>Is the volume change of pulverized coal>Is a correction factor, +.>Represents the horizontal distance between the two camera devices, < >>Indicates the movement time of the two photographing devices of the pulverized coal path, < + >>For the feed rate of the drill,nfor the amount of coal dust identified by the camera, +.>Is the void ratio of coal powder->Is the cross-sectional area of single coal dust in the radial direction of the drill rod,Sthe cross section area of the pulverized coal deposit is the radial powder discharge port of the drill rod;
the method comprises the steps of carrying out grid division on the powder discharge image, and determining the digital information of the coal powder corresponding to the powder discharge image based on the quantity of the coal powder in each grid, wherein the method specifically comprises the following steps:
calculating a threshold value when the variance is maximum through an inter-class variance formula, and dividing the powder discharge image into an optimal binarization image;
adopting a quadtree homogenization method to carry out grid division on the powder discharge image;
determining coal dust characteristic points at grid junctions, and distributing according to the occupation ratios of the coal dust characteristic points in different grids;
quantizing the pulverized coal in each grid based on the amount of the pulverized coal in each grid to determine the digital information of the pulverized coal corresponding to the powder discharge image;
based on the coal dust digital information, rejecting target images which do not meet a preset similarity condition to obtain a second target image set, wherein the method specifically comprises the following steps of:
determining the coal dust digital information corresponding to the unit cells at the same position in the coal dust source image and the first target image respectively;
based on the coal dust digital information respectively corresponding to the unit grids at the same position, determining the similarity respectively corresponding to each grid between the coal dust source image and the first target image;
summing the similarity corresponding to each grid respectively to obtain the similarity between the pulverized coal source image and the first target image;
and eliminating the first target image which does not meet the preset similarity condition to obtain a second target image set.
2. The method for preventing jamming of a drill hole based on mine drainage powder image recognition according to claim 1, wherein the determining the rate of jamming of the drill hole based on the rate of change of the pulverized coal volume comprises the following steps:
function-based
Determining the drilling sticking rate of the drilling;
wherein, Pthe drilling rate is the drilling rate;is the volume change rate of the pulverized coal; the drill sticking rate of the drill hole is inversely related to the volume change rate of the pulverized coal.
3. The drilling anti-seizing method based on mine powder discharge image recognition according to claim 1, wherein the edge description is carried out on the powder discharge image in the second target image set by a HOG feature detection algorithm of coarse registration, specifically comprising:
selecting a plurality of random data points from the pulverized coal source image, and constructing a first data point set;
selecting the random data points with the same quantity from the images of the second target image set, and constructing a second data point set;
based on a least square method, the first data point set and the second data point set, calculating a rotation translation transformation matrix between the images of the pulverized coal source image and the second target image set;
determining data points with the distance smaller than a preset distance threshold value based on the rotation translation transformation matrix and the second data point set to construct a consistency point set, and determining a corresponding transformation matrix through the consistency point set;
and selecting a plurality of pairs of coal dust characteristic points from the images of the coal dust source image and the second target image set, and carrying out edge description on the powder discharge images in the second target image set based on the size and the direction of the pixel gradient of the coal dust characteristic points.
4. The drilling anti-seize method based on mine dust discharge image recognition according to claim 3, wherein the edge description of the dust discharge image in the second target image set based on the magnitude and direction of the pixel gradient of the coal dust feature point specifically comprises:
based on a preset pulverized coal detection unit, performing image detection on pulverized coal characteristic points to determine the magnitude and direction of pixel gradients corresponding to characteristic pixels in the preset pulverized coal detection unit respectively; wherein the preset pulverized coal detection unit is a rule unit for presetting the number of pixels;
constructing a histogram corresponding to each preset pulverized coal detection unit based on the size and the direction of the pixel gradient, and collecting the histogram into an HOG descriptor;
training an SVM through the HOG descriptor to detect coal dust edge information of the powder discharge image, and determining the similarity of the powder discharge image according to the edge similarity of the coal dust characteristic points.
5. The method for preventing jamming of a drill hole based on mine drainage powder image recognition according to claim 1, wherein the method for starting different anti-jamming measures based on the drill jamming rate of the drill hole specifically comprises the following steps:
comparing the drilling sticking rate with a preset anti-sticking measure starting table;
under the condition that the drilling sticking rate is at a preset first-level alarm level, a first-level alarm is sent out, and the feeding speed of the drilling machine is reduced;
under the condition that the drilling sticking rate is at a preset secondary alarm level, a secondary alarm is sent out, and the rotation speed and the feeding speed of the drilling machine are reduced simultaneously;
and under the condition that the drilling sticking rate is in a preset three-level alarm level, sending out three-level alarm, and controlling the drill rod to reversely rotate and withdraw from the drill rod.
6. A drill hole anti-seize device based on mine dust discharge image identification, characterized in that the device comprises a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the device to perform the method of any of claims 1-5.
7. A non-transitory computer storage medium storing computer executable instructions, wherein the computer executable instructions are capable of performing the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896874.9A CN116612441B (en) | 2023-07-21 | 2023-07-21 | Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896874.9A CN116612441B (en) | 2023-07-21 | 2023-07-21 | Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612441A CN116612441A (en) | 2023-08-18 |
| CN116612441B true CN116612441B (en) | 2023-09-22 |
Family
ID=87680477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310896874.9A Active CN116612441B (en) | 2023-07-21 | 2023-07-21 | Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612441B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664875A (en) * | 2018-02-14 | 2018-10-16 | 北京广天夏科技有限公司 | Underground belt-conveying monitoring method based on image recognition |
| CN112541932A (en) * | 2020-11-30 | 2021-03-23 | 西安电子科技大学昆山创新研究院 | Multi-source image registration method based on different focal length transformation parameters of dual-optical camera |
| CN113673515A (en) * | 2021-08-20 | 2021-11-19 | 国网上海市电力公司 | Computer vision target detection algorithm |
| CN115690803A (en) * | 2022-10-31 | 2023-02-03 | 中电金信软件(上海)有限公司 | Digital image recognition method and device, electronic equipment and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10262190B2 (en) * | 2015-03-26 | 2019-04-16 | Beijing Kuangshi Technology Co., Ltd. | Method, system, and computer program product for recognizing face |
-
2023
- 2023-07-21 CN CN202310896874.9A patent/CN116612441B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664875A (en) * | 2018-02-14 | 2018-10-16 | 北京广天夏科技有限公司 | Underground belt-conveying monitoring method based on image recognition |
| CN112541932A (en) * | 2020-11-30 | 2021-03-23 | 西安电子科技大学昆山创新研究院 | Multi-source image registration method based on different focal length transformation parameters of dual-optical camera |
| CN113673515A (en) * | 2021-08-20 | 2021-11-19 | 国网上海市电力公司 | Computer vision target detection algorithm |
| CN115690803A (en) * | 2022-10-31 | 2023-02-03 | 中电金信软件(上海)有限公司 | Digital image recognition method and device, electronic equipment and readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 智能机器人技术在燃煤智慧电厂的功能设计与应用;赵俊杰;冯树臣;孙同敏;杨如意;张二祥;张越;于大鹏;唐剑;;能源科技(04);全文 * |
| 铁路场景下的红外与可见光图像自动配准算法;周杏芳;刘修扬;;电子测量技术(08);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612441A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiao et al. | A target detection model based on improved tiny-yolov3 under the environment of mining truck | |
| CN110472467A (en) | The detection method for transport hub critical object based on YOLO v3 | |
| Duan et al. | Coarse-grained density map guided object detection in aerial images | |
| Cao et al. | Region-based convolutional neural networks for object detection in very high resolution remote sensing images | |
| CN105469105A (en) | Cigarette smoke detection method based on video monitoring | |
| EP3151160B1 (en) | Visual attention detector and visual attention detection method | |
| CN102542289A (en) | Pedestrian volume statistical method based on plurality of Gaussian counting models | |
| CN103208008A (en) | Fast adaptation method for traffic video monitoring target detection based on machine vision | |
| CN110569843B (en) | Intelligent detection and identification method for mine target | |
| CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
| CN103927553B (en) | Coal and rock recognition method based on multi-scale micro-lamination and contrast ratio joint distribution | |
| CN111523527B (en) | Special transport vehicle monitoring method and device, medium and electronic equipment | |
| CN111429476B (en) | Method and device for determining action track of target person | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN104616006A (en) | Surveillance video oriented bearded face detection method | |
| CN111383455A (en) | Traffic intersection object flow statistical method, device, computer equipment and medium | |
| KR102140606B1 (en) | Image based steep slope monitoring method using virtual area | |
| CN116343436A (en) | Landslide detection method, landslide detection device, landslide detection equipment and landslide detection medium | |
| CN104615974A (en) | Continuous supporting pole number plate image recognizing method based on tracking algorithm | |
| Yang et al. | A method of pedestrians counting based on deep learning | |
| CN116612441B (en) | Drilling anti-seizing method, equipment and medium based on mine powder discharge image identification | |
| CN109359530B (en) | Intelligent video monitoring method and device | |
| CN104166836A (en) | Partitioning multi-scale engineering vehicle identification method and system based on multi-feature modeling | |
| CN102054278B (en) | Object tracking method based on grid contraction | |
| CN112581489A (en) | Video compression method, device 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 |