CN115487959A - Intelligent spraying control method for coal mine drilling machine - Google Patents
Intelligent spraying control method for coal mine drilling machine Download PDFInfo
- Publication number
- CN115487959A CN115487959A CN202211429971.9A CN202211429971A CN115487959A CN 115487959 A CN115487959 A CN 115487959A CN 202211429971 A CN202211429971 A CN 202211429971A CN 115487959 A CN115487959 A CN 115487959A
- Authority
- CN
- China
- Prior art keywords
- pixel point
- point
- motion
- dust
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005507 spraying Methods 0.000 title claims abstract description 61
- 239000003245 coal Substances 0.000 title claims abstract description 43
- 238000005553 drilling Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000000428 dust Substances 0.000 claims abstract description 314
- 239000002245 particle Substances 0.000 claims abstract description 203
- 238000004062 sedimentation Methods 0.000 claims abstract description 52
- 239000007921 spray Substances 0.000 claims abstract description 31
- 230000033001 locomotion Effects 0.000 claims description 267
- 230000001788 irregular Effects 0.000 claims description 16
- 239000000126 substance Substances 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003915 air pollution Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000008187 granular material Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000013618 particulate matter Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 206010035653 pneumoconiosis Diseases 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/12—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B21/00—Methods or apparatus for flushing boreholes, e.g. by use of exhaust air from motor
- E21B21/01—Arrangements for handling drilling fluids or cuttings outside the borehole, e.g. mud boxes
- E21B21/011—Dust eliminating or dust removing while drilling
- E21B21/013—Dust eliminating or dust removing while drilling by liquids
-
- 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
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
Abstract
The invention relates to the technical field of coal mine drilling, in particular to an intelligent spray control method for a coal mine drilling machine. The method comprises the following steps: acquiring continuous n frames of gray level images under the coal mine in the current time period, and acquiring a dust particle area based on the continuous n frames of gray level images; correcting the initial shape size value based on the shape similarity of every two dust particle areas to obtain a corrected shape size value, and further obtaining the sedimentation easiness; clustering the dust particle area, and recording the cluster with the maximum density as a dust dense area; and calculating the overall sedimentation easiness based on the sedimentation easiness of each dust particle area in the dust dense area and the Euclidean distance between the central point of each dust particle area and the central point of the dust dense area, further obtaining the target spraying amount, and adjusting the spraying amount of a spraying device of the drilling machine to the target spraying amount. The invention can realize the accurate regulation and control of the spraying device of the coal mine drilling rig.
Description
Technical Field
The invention relates to the technical field of coal mine drilling, in particular to an intelligent spray control method for a coal mine drilling machine.
Background
When a coal mine underground drilling machine performs drilling work, a large amount of dust is generated, the dust can harm the health of workers, particularly, fine dust particles are easily sucked into the lung by a human body to cause pneumoconiosis, the fine dust particles have adverse effects on safety production, and the fine dust suspended in the air can fly to a farther place along with the flowing of the air in a roadway to cause air pollution and harm in a wider range, so that the fine dust particles must be effectively settled. In the special working environment of the underground coal mine, wet spraying dust reduction is an economical and simple method, but the actual application situation is not ideal. Because the theoretical research in the aspect is less, blindness exists in practical application, a large amount of water resources are wasted, the dust falling efficiency is low, a large amount of accumulated water is generated in a production field, and the method is very unfavorable for the body health of operating personnel and safe and civilized production. Therefore, how to accurately evaluate the sedimentation condition of the dust particles in the underground coal mine to realize the accurate regulation and control of the spraying amount of the spraying device of the underground coal mine drilling rig is an important problem.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent spray control method for a coal mine drilling machine, which adopts the following technical scheme:
the invention provides an intelligent spray control method for a coal mine drilling machine, which comprises the following steps:
acquiring continuous n frames of gray level images under a coal mine in a current time period, wherein the continuous n frames of gray level images are composed of historical frame gray level images and current frame gray level images, and n is more than or equal to 2;
obtaining a moving pixel point in the gray image of the current frame based on the gray value of each pixel point in the gray image of each historical frame and the gray value of each pixel point in the gray image of the current frame; acquiring matching points of the motion pixel points in the gray level images of the historical frames based on the gray level values of the pixel points in the gray level images of the historical frames, and constructing associated data sequences of the motion pixel points; screening dust pixel points from all moving pixel points in the gray level image of the current frame based on the associated data sequence, the wind speed at the current moment and the wind direction angle at the current moment;
obtaining dust particle areas based on dust pixel points in the current frame gray level image, and calculating the circularity of each dust particle area; acquiring the area of each dust particle area as the initial shape and size value of each dust particle area; correcting the initial shape size value based on the shape similarity of every two dust particle areas in the current frame gray level image to obtain the corrected shape size value of each dust particle area; taking the product of the corrected shape size value and the circularity as the sedimentation easiness of the corresponding dust particle area;
clustering the dust particle areas in the gray level image of the current frame, and recording the cluster with the maximum density as a dust dense area; calculating the integral sedimentation easiness of the dust dense area based on the sedimentation easiness of each dust particle area in the dust dense area and the Euclidean distance between the central point of each dust particle area and the central point of the dust dense area; and obtaining a target spraying amount corresponding to the current moment based on the integral settlement easiness, and adjusting the spraying amount of a spraying device of the drilling machine to the target spraying amount.
Preferably, the obtaining the moving pixel point in the current frame gray image based on the gray value of each pixel point in each historical frame gray image and the gray value of each pixel point in the current frame gray image includes:
for any pixel point in the gray image of the current frame:
acquiring pixel points with the same positions as the pixel points in the gray level images of the historical frames, and recording the pixel points as the characteristic points corresponding to the pixel points;
respectively calculating the absolute value of the difference value of the gray values of the pixel point and each characteristic point corresponding to the pixel point; if the absolute value of the difference value of the gray value of the pixel point and the gray value of each corresponding characteristic point is 0, the pixel point is judged to be a background pixel point; and if at least one of the absolute values of the difference values of the gray values of the pixel point and the corresponding characteristic points is not 0, judging that the pixel point is a moving pixel point.
Preferably, the obtaining a matching point of each moving pixel point in each historical frame gray image based on the gray value of the pixel point in each historical frame gray image includes:
recording a historical frame gray image adjacent to a current frame gray image as a first frame target image, recording a historical frame gray image adjacent to the first frame target image as a second frame target image, and so on to obtain an n-1 frame target image;
for any moving pixel point in the gray image of the current frame:
calculating the matching degree between the motion pixel point and each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in each frame of target image according to the gray value of the motion pixel point, the gray value of each pixel point in the preset first neighborhood of the corresponding feature point of each frame of target image, the gray value of each pixel point in the preset second neighborhood of each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in each frame of target image; and taking the pixel point with the maximum matching degree with the motion pixel point in the preset first neighborhood of the corresponding characteristic point of each frame of target image as the matching point of the motion pixel point in the corresponding historical frame gray level image.
Preferably, the following formula is adopted to calculate the matching degree between the motion pixel point and each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in the first frame target image:
wherein, the first and the second end of the pipe are connected with each other,
is the first moving pixel point and the second
The matching degree of the w pixel point of the corresponding characteristic point in the first frame target image in the w pixel point in the preset first neighborhood,
is as follows
The gray value of each of the moving pixels,
is a first
The gray value of the w-th pixel point of the corresponding characteristic point of the motion pixel point in the first frame target image is preset in a first neighborhood,
is as follows
The number of pixels in a predetermined second neighborhood of the individual motion pixels,
is as follows
The gray value of the ith pixel point in the second neighborhood is preset for each moving pixel point,
is as follows
The gray value of the ith pixel point in the preset second neighborhood of the w pixel point of the corresponding feature point of the motion pixel point in the first frame target image is the gray value of the w pixel point in the preset first neighborhood, and e is a natural constant.
Preferably, the screening of the dust pixel points from all the moving pixel points in the current frame gray image based on the associated data sequence, the current wind speed and the current wind direction angle includes:
for any moving pixel point in the gray image of the current frame:
obtaining the motion direction angle and the motion speed of the motion pixel point in each time period according to the position information of any two adjacent pixel points in the matching data sequence corresponding to the motion pixel point and the acquisition time of the corresponding image; the motion direction angle and the motion speed of the motion pixel point in each time period form motion data of the motion pixel point in each time period, and a motion data sequence corresponding to the motion pixel point is constructed according to the motion data;
when the normalized wind speed at the current moment is smaller than a speed threshold value, obtaining an irregular index of the moving pixel point according to the moving data sequence corresponding to the moving pixel point; if the irregularity index is larger than the irregularity index threshold value, the moving pixel point is judged to be a dust pixel point;
when the normalized wind speed at the current moment is greater than or equal to a speed threshold, calculating the corresponding convergence of the motion pixel point according to the motion data sequence corresponding to the motion pixel point, the wind speed at the current moment and the wind direction angle at the current moment; and if the convergence is greater than the convergence threshold, judging that the moving pixel is a dust pixel.
Preferably, obtaining the irregularity index of the moving pixel point according to the moving data sequence corresponding to the moving pixel point includes:
calculating the absolute value of the difference value of the angles corresponding to any two adjacent elements in the motion data sequence corresponding to the motion pixel point, and recording the absolute value as a first absolute value; judging whether the first absolute value is larger than an angle threshold value or not, and if so, judging that the motion direction of the motion pixel point in the corresponding time period is changed; if the motion direction of the motion pixel point in the corresponding time period is not changed, judging that the motion direction of the motion pixel point in the corresponding time period is not changed;
counting the times of the change of the motion direction of the motion pixel point; taking the ratio of the number of times of change of the motion direction of the motion pixel point to the total judgment number of times of change of the motion direction as an irregularity index of the motion pixel point;
calculating the corresponding similarity of the motion pixel points by adopting the following formula:
wherein the content of the first and second substances,
is the first in the gray scale image of the current frame
The degree of congruence of each motion pixel point,
is the first in the gray scale image of the current frame
The motion direction angle in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the first in the gray scale image of the current frame
The wind speed in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the wind direction angle at the current moment,
is the wind speed at the present moment,
is the first in the gray scale image of the current frame
The number of the motion data in the motion data sequence corresponding to each motion pixel point, and e is a natural constant.
Preferably, the modifying the initial shape size value based on the shape similarity between every two dust particle areas in the current frame gray image to obtain a modified shape size value of each dust particle area includes:
for any two dust particle areas in the gray image of the current frame, respectively carrying out corner point detection on edge pixel points of the two dust particle areas, marking the area with the smaller number of corner points in the two dust particle areas as a first dust particle area, and marking the area with the larger number of corner points in the two dust particle areas as a second dust particle area;
selecting any corner in the first dust particle area as a first corner, and acquiring a clockwise included angle between a straight line formed by the first corner and the center point of the first dust particle area and a horizontal line, and recording the clockwise included angle as a first included angle; respectively acquiring clockwise included angles between straight lines formed by each corner point in the second dust particle area and the central point of the second dust particle area and a horizontal line, and recording the clockwise included angles as second included angles; taking an angular point in a second dust particle area corresponding to a second included angle corresponding to the minimum absolute value of the difference value of the first included angle as a matching point of the first angular point, wherein the matching point of the first angular point and the first angular point forms a matching point pair;
calculating the shape similarity of the first dust particle area and the second dust particle area based on a clockwise included angle between a straight line formed by two corner points in each matching point pair and the central point of the corresponding area and a horizontal line;
and if the shape similarity is larger than the similarity threshold, taking the initial shape size value of the dust particle area with the larger initial shape size value in the first dust particle area and the second dust particle area as the corrected shape size value of the dust particle area with the smaller initial shape size value.
Preferably, the similarity of the shapes of the first dust particle region and the second dust particle region is calculated using the following formula:
wherein, the first and the second end of the pipe are connected with each other,
the similarity in shape of the first dust particle region and the second dust particle region,
the number of corner points in the first dust particle region,
the number of corner points in the second dust particle region,
is the clockwise angle between the straight line formed by the first corner point in the jth matching point pair and the center point of the area where the first corner point is located and the horizontal line,
is the clockwise included angle between the straight line formed by the second corner point in the jth matching point pair and the center point of the area where the second corner point is located and the horizontal line,
to take the minimum function, e is a natural constant.
Preferably, the overall ease of settling of the dust-dense region is calculated using the following formula:
wherein, the first and the second end of the pipe are connected with each other,
the overall settling ease in the dust-dense area,
the ease of settling in the kth dust particle region in the dust dense region,
the maximum value of the Euclidean distance between the central point of each dust particle area in the dust dense area and the central point of the dust dense area,
is the Euclidean distance between the central point of the kth dust particle area in the dust-dense area and the central point of the dust-dense area,
is the number of dust particle areas within the dust dense area.
Preferably, the obtaining of the target spray usage amount corresponding to the current time based on the overall sedimentation easiness degree includes:
judging whether the integral sedimentation easiness degree is greater than a sedimentation easiness degree threshold value or not, and if so, taking the product of the initial spraying amount and the integral sedimentation easiness degree as a target spraying amount corresponding to the current moment; if the total sedimentation ease is less than or equal to the target spray amount, the sum of the constant 1 and the total sedimentation ease is recorded as a first index, and the product of the first index and the total sedimentation ease is used as the target spray amount corresponding to the current time.
The invention has at least the following beneficial effects:
firstly, preliminarily screening pixel points in a current frame gray image to obtain moving pixel points based on gray values of the pixel points in each historical frame gray image and gray values of the pixel points in the current frame gray image in the underground coal mine in the current time period; in consideration of the motion characteristics of dust particles and the relevance of dust in a plurality of gray level images, the method obtains the matching points of all motion pixel points in all historical frame gray level images, constructs the associated data sequence of all the motion pixel points, and then screens the dust pixel points from all the motion pixel points in the current frame gray level image based on the associated data sequence, the current-moment wind speed and the current-moment wind direction, so that the dust pixel points are accurately judged, and the dust pixel points are analyzed subsequently, so that the interference of complex environments under a coal mine is reduced; the invention also calculates the whole sedimentation easiness of the dust-dense region based on the sedimentation easiness of each dust particle region in the dust-dense region in the current frame gray image and the Euclidean distance between the central point of each dust particle region and the central point of the dust-dense region, further obtains the target spraying amount, adjusts the spraying amount of the spraying device of the drilling machine to the target spraying amount, ensures that the spraying of the nozzle of the spraying device of the drilling machine is more accurately applied to the dust-dense region, reduces the water resource waste, and improves the dust-settling efficiency and the accuracy of the regulation and control of the spraying device of the drilling machine.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an intelligent spray control method for a coal mine drilling machine provided by the invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined invention, the following detailed description is made with reference to the accompanying drawings and preferred embodiments for an intelligent spray control method for a coal mine drilling rig according to the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the intelligent spray control method for the coal mine drilling machine is described in detail below with reference to the accompanying drawings.
An embodiment of an intelligent spray control method for a coal mine drilling machine comprises the following steps:
the embodiment provides an intelligent spray control method for a coal mine drilling machine, and as shown in fig. 1, the intelligent spray control method for the coal mine drilling machine of the embodiment comprises the following steps:
the method comprises the following steps of S1, obtaining continuous n frames of gray level images under a coal mine in a current time period, wherein the continuous n frames of gray level images are composed of historical frame gray level images and current frame gray level images, and n is larger than or equal to 2.
The scenario addressed by the present embodiment is: when the colliery is bored the rig in the pit and is crept into, can produce a large amount of dust, in order to reduce air pollution, reduce the harm to the human body, need use atomizer on the rig to subside the dust, this embodiment gathers continuous multiframe colliery image in the pit when not using atomizer to subside, the motion characteristic through the dust is with the associativity of dust in the many images, get rid of the colliery down-hole complex environment's interference, the completion is to the accurate judgement of dust pixel, and then obtain the dust granule, through subsiding the evaluation of the ease factor to the dust granule, calculate the intensive regional whole of dust and subside the ease factor, and accomplish the control to rig atomizer according to whole settlement ease factor.
In the embodiment, a high-resolution camera and a fixed light source are utilized to collect n continuous frames of images of the underground coal mine when a spraying device is not used for sedimentation in the current time period, the collected images are RGB images, and graying processing is carried out on the RGB images by using a weighted graying method to obtain n continuous frames of grayscale images of the underground coal mine; the last frame gray image in the continuous n frames gray image is the gray image of the current frame, that is, the n frame gray image is the gray image of the current frame, and the n frame gray images are respectively marked as a Chinese book according to the time sequence
,
,…,
-means for, among other things,
is the 1 st frame gray-scale image,
is the 2 nd frame gray-scale image,
is the nth frame gray level image. Weighted graying is a well-known technique and will not be described in detail herein.
S2, obtaining a moving pixel point in the gray image of the current frame based on the gray value of each pixel point in the gray image of each historical frame and the gray value of each pixel point in the gray image of the current frame; acquiring matching points of the motion pixel points in the gray level images of the historical frames based on the gray level values of the pixel points in the gray level images of the historical frames, and constructing associated data sequences of the motion pixel points; and screening dust pixel points from all the moving pixel points in the gray level image of the current frame based on the associated data sequence, the wind speed at the current moment and the wind direction angle at the current moment.
Dust particles tend to move in the air, and when the air flow velocity is low, the movement of dust particles in the air is irregular; when the air flow velocity is large, the dust particles move in the air flow direction.
Acquiring underground wind speed of a coal mine by using a wind speed sensor, carrying out normalization processing on the wind speed, and setting a speed threshold value
And the normalized current wind speed
Less than a speed threshold
When the dust is detected, the influence of the wind speed on the dust is small, and the movement of the dust is judged to be irregular; otherwise, the wind speed has a large influence on the dust, so that the dust movement direction is close to the same as the wind speed direction. In the case of a particular application of the method,
the value of (c) can be set by the implementer.
Next, in this embodiment, the pixels in the gray image of the current frame are screened, the pixels in the gray image of the current frame are divided into two types, one type is a dust pixel, and the other type is a background pixel, and the dust pixels are subsequently analyzed, so that interference of irrelevant factors is eliminated, and the calculation amount is reduced.
For any pixel point in the gray image of the current frame: acquiring a pixel point which has the same position as the pixel point in the gray level image of the historical frame, and recording the pixel point as a characteristic point corresponding to the pixel point, wherein the pixel point corresponds to n-1 characteristic points; respectively calculating the absolute value of the difference value of the gray value of the pixel point and each characteristic point corresponding to the pixel point, and if the absolute value of the difference value of the gray value of the pixel point and each characteristic point corresponding to the pixel point is 0, judging that the pixel point in the gray image of the current frame is a background pixel point; and if at least one of the absolute values of the difference values of the gray values of the pixel point and the corresponding characteristic points is not 0, judging that the pixel point in the gray image of the current frame is a moving pixel point. By adopting the method, all the pixel points in the current frame gray image are judged, the pixel points in the current frame gray image are divided into two types, namely background pixel points and motion pixel points, and the probability that the motion pixel points are dust pixel points is higher. Because colliery is the environment complicacy in the pit, interference factor is more, leads to the initial judgement precision of dust pixel not high enough, so this embodiment will judge the motion pixel once more, obtains the dust pixel from the motion pixel, improves and judges the precision.
For the second in the gray image of the current frame
Individual moving pixel points:
in the embodiment, the matching point of the motion pixel point is respectively selected from the historical frame gray level images, the historical frame gray level image adjacent to the current frame gray level image is marked as a first frame target image, the historical frame gray level image adjacent to the first frame target image is marked as a second frame target image, and by analogy, the first frame historical frame gray level image is marked as an n-1 th frame target image, namely, each historical frame gray level image is marked in a reverse order mode; because the dust moves in the air, the position of the same dust in different gray level images is different, namely for any moving pixel point in the current frame gray level image, a matching point of the moving pixel point in each historical frame gray level image needs to be found, the characteristics of the moving pixel point and the matching point should be similar, namely the gray level difference between the moving pixel point and the matching point should be smaller, and the gray level difference between the neighborhood pixel point of the moving pixel point and the neighborhood pixel point of the matching point should also be smaller; because the acquisition time interval of two adjacent frames of images is small, even if dust moves in the air, the position difference of the same dust in the two adjacent frames of images is not too large, a neighborhood with a proper size is set according to the wind speed at the current moment, and a matching point of a moving pixel point can be found in the neighborhood of a feature point corresponding to the moving pixel point. Based on this, according to
Gray value of each moving pixel, number one
The gray value and the gray value of the w-th pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in the first frame target image
Each pixel point in the preset second neighborhood of each motion pixel pointGray value of
The gray value of each pixel point in a preset second neighborhood of a w-th pixel point in a preset first neighborhood of the corresponding feature point of each motion pixel point in the first frame target image is calculated
A motion pixel point and the second
The matching degree between the w pixel points in the preset first neighborhood of the corresponding characteristic point of each motion pixel point in the first frame target image is as follows:
wherein the content of the first and second substances,
is as follows
A motion pixel point and the second
The matching degree of the w-th pixel point of the corresponding characteristic point in the first frame target image of each moving pixel point in the preset first neighborhood,
is as follows
The gray value of each of the moving pixels,
is as follows
The gray value of the w pixel point in the preset first neighborhood of the corresponding characteristic point of each moving pixel point in the first frame target image,
is as follows
The number of pixels in a predetermined second neighborhood of the individual motion pixels,
is as follows
The gray value of the ith pixel point in the preset second neighborhood of the motion pixel point,
is a first
The gray value of the ith pixel point in a preset second neighborhood of a w pixel point in a preset first neighborhood of a corresponding feature point of each moving pixel point in the first frame target image is a natural constant; in this embodiment, the size of the first neighborhood is preset to be 5 × 5, and the size of the second neighborhood is preset to be 3 × 3, so that in this embodiment, the size of the first neighborhood is preset to be 5 × 5, and the size of the second neighborhood is preset to be 3 × 3
The value of (b) is 8, and in a specific application, an implementer can set the size of the first neighborhood and the size of the second neighborhood according to actual conditions, and if the current wind speed is too large, the sizes of the neighborhoods can be increased appropriately.
By adopting the method, the second image in the gray level image of the current frame can be obtained
A motion pixel point and a second motion pixel point
The matching degree of each pixel point in a preset first neighborhood of the corresponding characteristic point of each motion pixel point in the first frame target image is set as
The first and second motion pixel points are in the preset first neighborhood of the corresponding characteristic point in the first frame target image
Taking the pixel point with the maximum matching degree of the motion pixel points as the first
The matching point of each moving pixel point is obtained as the first point in the gray level image of the current frame
The matching point of each motion pixel point in the first frame target image is similar to the first frame target image
The matching point of each motion pixel point in the first frame target image can be obtained
The matching point of each motion pixel point in the first frame target image is the matching point in the second frame target image, namely the first frame target image is obtained
A moving pixelMatching points of the points in the second frame target image can be obtained by analogy, and the first frame gray level image in the current frame gray level image can be obtained
The matching point of each moving pixel point in each frame of target image is based on the first point in the gray scale image of the current frame
Matching points of the moving pixel points in each frame of target image, and constructing a matching data sequence Q = last CT corresponding to the moving pixel points
，
，
,…,
And (c) the step of (c) in which,
is the first in the gray scale image of the current frame
The number of the motion pixel points is equal to that of the motion pixel points,
is the first in the gray scale image of the current frame
The matching point of each motion pixel point in the 1 st frame target image,
is the first in the gray scale image of the current frame
The matching point of each moving pixel point in the 2 nd frame target image,
is the first in the gray scale image of the current frame
And matching points of the motion pixel points in the target image of the (n-1) th frame.
According to the gray level of the current frame
The position information of any two adjacent pixel points in the matching data sequence corresponding to each motion pixel point and the acquisition time of the corresponding image are obtained
The motion direction angle and motion speed of each motion pixel point in each time period, the first
The specific calculation formula of the motion direction angle and the motion speed of each motion pixel point in the 1 st time period is as follows:
wherein the content of the first and second substances,
is a first
The motion direction angle of each motion pixel point in the 1 st time period,
is as follows
The motion speed of each motion pixel point in the 1 st time period,
is a first
The abscissa of each of the moving pixel points,
is as follows
The ordinate of each of the moving pixels is,
is as follows
The abscissa of the 1 st matching point of each motion pixel point,
is as follows
The ordinate of the 1 st matching point of each moving pixel point,
at the time of acquiring the 1 st frame of the target image,
in order to capture the moment of the gray scale image of the current frame,
is an arctangent function; the 1 st time period is used for acquiring the 1 st frame targetAnd the time period is formed by all the time between the image and the acquisition of the gray scale image of the current frame. The calculation formula of the motion direction angle and the motion speed is the existing formula, and will not be described in detail herein.
In the same way, can obtain
The motion direction angle and motion speed of each motion pixel point in each time segment, i.e. based on the second
Obtaining a motion direction angle and a motion speed by the position information and the acquisition time of any two adjacent pixel points in the matching data sequence corresponding to each motion pixel point, wherein each motion direction angle and each motion speed form motion data, and
the plurality of moving pixel points correspond to a plurality of moving data; according to the first
Each motion data corresponding to each motion pixel point is obtained
Motion data sequences corresponding to individual motion pixel points, i.e.
Wherein, in the step (A),
is as follows
A sequence of motion data corresponding to each motion pixel point,
is as follows
The moving speed of each moving pixel point in the 1 st time period,
is a first
The motion direction angle of each motion pixel point in the 1 st time period,
is as follows
The motion speed of each motion pixel point in the 2 nd time period,
is as follows
The motion direction angle of each motion pixel point in the 2 nd time period,
is a first
The motion speed of the motion pixel point in the (n-1) th time period,
is as follows
And the motion direction angle of each motion pixel point in the (n-1) th time period.
When the normalized wind speed at the current moment is less than the speed threshold value
It is stated that the dust does a random movement in the air, and this embodiment will be based on the movementAnd (4) analyzing the motion pixel points by the irregular indexes of the pixel points, and screening out real dust pixel points from all the motion pixel points. Specifically, the motion direction angle in the motion data sequence is judged, the absolute value of the difference value of the angles corresponding to any two adjacent elements in the motion data sequence is calculated, and whether the absolute value is greater than the angle threshold value is judged
If it is greater than the above, it is judged that
The motion direction of each motion pixel point in the corresponding time period is changed once; if not, determining the first step
The motion direction of each motion pixel point in the corresponding time period is not changed; make statistics of
The number of times that the motion direction of each motion pixel point changes; this embodiment setup
In specific application, an implementer can set the method according to specific conditions; first, the
The more times the movement direction of each movement pixel point changes, the more unstable the movement direction of the movement pixel point in the air is, namely the more irregular the movement of the movement pixel point in the space is, therefore, the ratio of the times the movement direction of the movement pixel point changes to the total judgment times of whether the movement direction changes is taken as an irregular index of the movement pixel point, and the larger the irregular index is, the more irregular the movement of the movement pixel point in the space is, the more likely the movement is a dust pixel point; setting an irregular index threshold value, and judging the gray of the current frame when the irregular index is larger than the irregular index threshold valueIn the degree image
Each motion pixel point is a dust pixel point; when the irregularity index is less than or equal to the irregularity index threshold, determining the first place in the gray image of the current frame
Each motion pixel is an interference pixel. In this embodiment, the threshold value of the irregular index is 0.9, and in a specific application, an implementer can set the threshold value of the irregular index according to a specific situation.
When the normalized wind speed at the current moment is more than or equal to the speed threshold value
When the dust particles are influenced by wind speed in space, the movement direction of the dust particles tends to the wind speed direction, in order to accurately screen out dust pixel points from the movement pixel points, the movement of the dust needs to be analyzed, and when the movement of the dust needs to be analyzed, the convergence degree of the dust pixel points and the current wind direction and the current wind speed need to be analyzed from the two aspects of the movement direction and the movement speed, and the convergence degree corresponding to the movement pixel points can reflect the consistency condition of the movement direction of the movement pixel points and the current wind direction and the consistency condition of the speed of the movement pixel points and the current wind speed. Specifically, according to the gray level of the current frame
Calculating the first motion data sequence, the wind speed and the wind direction angle of the current moment corresponding to each motion pixel point, and calculating the second motion data sequence, the wind speed and the wind direction angle of the current moment corresponding to each motion pixel point
The corresponding degree of similarity of each motion pixel point is:
wherein, the first and the second end of the pipe are connected with each other,
is the first in the gray scale image of the current frame
The degree of congruence of each motion pixel point,
is the first in the gray scale image of the current frame
The motion direction angle in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the first in the gray scale image of the current frame
The wind speed in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the wind direction angle at the current moment,
the wind speed at the current moment.
The larger the approach degree corresponding to the motion pixel point is, the more likely the motion pixel point is to be a dust pixel point, an approach degree threshold value is set, and the second time in the gray level image of the current frame is judged
Whether the corresponding convergence of each moving pixel point is greater than a convergence threshold value or not is judged, and if so, the first pixel point in the gray level image of the current frame is judged
Each motion pixel point is a dust pixel point; if not, judging the first gray level image in the current frame
Each motion pixel point is an interference pixel point; in this embodiment, the threshold of the degree of convergence is set to 0.9, and in a specific application, an implementer may set the threshold according to a specific situation.
Similarly, by adopting the method, the categories of all the moving pixels in the current frame gray image are judged, and the moving pixels are divided into two categories, namely dust pixels and interference pixels.
S3, obtaining dust particle areas based on dust pixel points in the gray level image of the current frame, and calculating the circularity of each dust particle area; acquiring the area of each dust particle area as the initial shape and size value of each dust particle area; correcting the initial shape size value based on the shape similarity of every two dust particle areas in the current frame gray image to obtain the corrected shape size value of each dust particle area; and taking the product of the corrected shape size value and the circularity as the sedimentation easiness degree of the corresponding dust particle area.
In the step S2, dust pixel points in the gray image of the current frame are obtained, and adjacent dust pixel points which can form a closed area are connected to obtain a dust particle area; since the larger the particle size of the particulate matter is, the more likely the particulate matter is to settle in the settling process, the ease of settling in the dust particle region is calculated based on the shape and size values in the dust particle region, and the amount of the dust settling spray is adjusted based on the ease of settling.
Calculating the circularity of each dust particle area, wherein the calculation formula of the circularity is the existing formula and is not repeated herein; acquiring the area of each dust particle area as the initial shape and size value of the corresponding dust particle area; considering that the distances from the camera to different dust particles are different when the image is initially acquired, when the initial shape size value of the dust particle region is acquired, the large particles are determined to be small particles in the image when the distance is long, so that the embodiment needs to calculate the similarity of the shapes between the two dust particles, update the initial shape size value of the dust particle region, and prevent the occurrence of the above problems from interfering with the result.
Specifically, for any two dust particle areas in the current frame gray image, the central points of the two dust particle areas are firstly obtained, and the specific obtaining process is as follows: selecting a pixel point with the minimum sum of Euclidean distances from the pixel point to the edge pixel point in the dust particle area as a central point of the dust particle area; then, respectively carrying out corner point detection on the edge pixel points of the two dust particle areas to obtain a plurality of corner points of each dust particle area; if the shapes of the two dust particle areas are similar, the clockwise included angles between the straight lines formed by the two corner points and the central point of the corresponding positions of the two dust particle areas and the horizontal line are similar, so that the shape of the two dust particle areas is represented by the angle difference between the corner points and the central point in the embodimentSimilarity, firstly matching the corner points of the two dust particle areas, wherein the matching mode specifically comprises the following steps: recording a region with a smaller number of angular points in the two dust particle regions as a first dust particle region, recording a region with a larger number of angular points in the two dust particle regions as a second dust particle region, selecting any angular point in the first dust particle region as a first angular point, acquiring a clockwise included angle between a straight line formed by the first angular point and a central point of the first dust particle region and a horizontal line, and recording the clockwise included angle as a first included angle; respectively acquiring clockwise included angles between straight lines formed by each corner point in the second dust particle area and the central point of the second dust particle area and a horizontal line, and recording the clockwise included angles as second included angles; taking the corner point in the second dust particle area corresponding to the second included angle corresponding to the minimum absolute value of the difference value of the first included angle as a matching point of the first corner point, wherein the matching point of the first corner point and the first corner point forms a matching point pair; by the above method, can obtain
A plurality of pairs of matching points, wherein,
in order to take the function of the minimum value,
the number of corner points in the first dust particle region,
is the number of corner points in the second dust particle region. Calculating the shape similarity of the first dust particle area and the second dust particle area based on the clockwise included angle between the straight line formed by the two corner points in each matching point pair and the central point of the corresponding area and the horizontal line, namely:
wherein the content of the first and second substances,
the similarity in shape of the first dust particle region and the second dust particle region,
the number of corner points in the first dust particle region,
the number of corner points in the second dust particle region,
is the clockwise angle between the straight line formed by the first corner point in the jth matching point pair and the center point of the area where the first corner point is located and the horizontal line,
is the clockwise included angle between the straight line formed by the second corner point in the jth matching point pair and the center point of the area where the second corner point is located and the horizontal line,
is a function of taking the minimum value.
The greater the similarity of the shapes of the first dust particle region and the second dust particle region, the more similar the two regions are; and setting a similarity threshold, when the shape similarity of the first dust particle area and the second dust particle area is greater than the similarity threshold, judging that the two dust particle areas have the same size, and taking the initial shape size value of the dust particle area with the larger initial shape size value as the corrected shape size value of the dust particle area with the smaller initial shape size value, namely finishing updating the shape size value of the dust particle area with the smaller initial shape size value. The threshold of similarity in this embodiment is 0.95, which can be set by the implementer in specific applications. By adopting the method, the shape similarity of any two dust particle areas in the gray-scale image of the current frame can be calculated, the updating of the initial shape size value of the dust particle area is further completed, and the corrected shape size value of each dust particle area is obtained.
When the larger the circularity of a certain dust particle region is, the larger the corrected shape size value is, the more likely the dust particles settle; therefore, for any dust particle area, the product of the circularity of the dust particle area and the corrected shape size value of the dust particle area is taken as the sedimentation easiness of the dust particle area, and the larger the sedimentation easiness is, the more easily the dust particles are sedimented; by the above method, the ease of settling in each dust particle region can be obtained.
S4, clustering dust particle areas in the gray level image of the current frame, and marking the cluster with the maximum density as a dust dense area; calculating the integral sedimentation easiness of the dust dense area based on the sedimentation easiness of each dust particle area in the dust dense area and the Euclidean distance between the central point of each dust particle area and the central point of the dust dense area; and obtaining a target spraying amount corresponding to the current moment based on the integral settlement easiness, and adjusting the spraying amount of a spraying device of the drilling machine to the target spraying amount.
Clustering all dust particle areas in the gray level image of the current frame by adopting a DBSCAN density clustering algorithm to obtain a cluster with the highest density, and marking the cluster with the highest density as a dust dense area, wherein the DBSCAN density clustering algorithm is a known technology and is not repeated herein; the dust dense area is an area with the most dense dust particles in the current frame gray image, when fog drops are emitted under a coal mine by using a spraying device, the spraying device emits the fog drops towards the center of the dust dense area, and the more distant the spraying device is from the center point of the dust dense area, the greater the particle sedimentation difficulty is, so that a position weight is given based on the Euclidean distance between the center point of each dust particle area and the center point of the dust dense area, the sedimentation easiness of the edge particles is relatively reduced when the integral sedimentation easiness of the dust dense area is calculated, and the integral sedimentation easiness of the dust dense area is more accurately described; the calculation formula of the overall settlement easiness of the dust dense area is as follows:
wherein the content of the first and second substances,
the overall settling ease in the dust-dense area,
to ease the settling of the kth dust particle region in the dust-dense region,
the maximum value of the Euclidean distance between the central point of each dust particle area in the dust dense area and the central point of the dust dense area,
is the Euclidean distance between the central point of the kth dust particle area in the dust-dense area and the central point of the dust-dense area,
is the number of dust particle areas within the dust dense area.
Introduction of
The method aims to normalize the Euclidean distance between the central point of each dust particle area and the central point of the dust dense area, and facilitates the setting of a subsequent threshold value. The Euclidean distance between the central point of each dust particle area and the central point of the dust dense area is in inverse proportion to the overall sedimentation easiness of the dust dense area, and the sedimentation easiness of each dust particle area is in direct proportion to the overall sedimentation easiness of the dust dense area; when the Euclidean distance between the central points of all dust particle areas in the dust-dense area to the central point of the dust-dense area is smaller and the sedimentation easiness of all dust particle areas in the dust-dense area is higher, the atomizing device is utilized to emit fog drops to the center of the dust-dense area, and all dust particles in the dust-dense area are easier to sediment, namely the integral sedimentation easiness of the dust-dense area is higher; when the Euclidean distance between the central points of all the dust particle areas in the dust dense area to the central point of the dust dense area is larger and the sedimentation easiness of all the dust particle areas in the dust dense area is smaller, the atomizing device is utilized to emit fog drops to the center of the dust dense area, and all the dust particles in the dust dense area are less prone to sedimentation, namely the integral sedimentation easiness of the dust dense area is smaller.
The overall settlement easiness of the dust-dense area is obtained according to the steps, and the greater the overall settlement easiness of the dust-dense area is, the more easily each dust particle in the dust-dense area settles; the smaller the overall sedimentation easiness of the dust-dense area is, the less the sedimentation of each dust particle in the dust-dense area is; when the overall sedimentation ease of the dust-dense area is low, in order to make dust particles in the space settle more quickly, the set initial spraying amount needs to be adjusted, the spraying amount is increased, and the target spraying amount corresponding to the current moment is obtained; the specific expression of the target spray dosage is as follows:
wherein the content of the first and second substances,
is the target spray dosage corresponding to the current moment,
the amount of the initial spray is the amount of the initial spray,
is the threshold for ease of sedimentation. The initial spray dosage is set by the worker as the case may be.
When the whole sedimentation easiness of the dust-dense area is larger, that is, the whole sedimentation easiness of the dust-dense area is larger than that of the dust-dense area
During the process, the coal mine underground dust is easy to settle, so that the target spraying amount corresponding to the current moment is obtained based on the overall settling easiness and the initial spraying amount of the dust dense region, and the spraying amount of a spraying device of a drilling machine is adjusted to the target spraying amount; when the whole settling easiness of the dust-dense region is small, that is, the whole settling easiness of the dust-dense region is not more than
When, explain the coal mine undergroundThe sedimentation difficulty of the dust is high, in order to make the dust particles quickly sedimentate, the spraying dosage needs to be increased, the target spraying dosage corresponding to the current moment is obtained by adopting the formula, and the spraying dosage of a spraying device of the drilling machine is adjusted to the target spraying dosage; the spraying amount of a spraying device of the drilling machine is used as the target spraying amount to carry out dust settling work, so that a better and faster dust settling effect is achieved. In this example
The value of (b) is 0.6, which can be set by the practitioner in a particular application, as the case may be.
In the embodiment, firstly, based on the gray value of each pixel point in each historical frame gray image of the underground coal mine in the current time period and the gray value of each pixel point in the current frame gray image, preliminarily screening the pixel points in the current frame gray image to obtain moving pixel points; in consideration of the motion characteristics of dust particles and the relevance of dust in a plurality of gray level images, the embodiment acquires the matching points of all the motion pixel points in all the historical frame gray level images, constructs the associated data sequence of all the motion pixel points, and then screens the dust pixel points from all the motion pixel points in the current frame gray level image based on the associated data sequence, the current-moment wind speed and the current-moment wind direction, so that the accurate judgment of the dust pixel points is completed, the dust pixel points are analyzed subsequently, and the interference of the complex environment under a coal mine is reduced; the embodiment calculates the whole sedimentation easiness degree of the dust-dense region based on the sedimentation easiness degree of each dust particle region in the dust-dense region in the current frame gray image and the Euclidean distance between the central point of each dust particle region and the central point of the dust-dense region, further obtains the target spraying amount, adjusts the spraying amount of the spraying device of the drilling machine to the target spraying amount, enables the spraying of the nozzle of the spraying device of the drilling machine to be more accurately applied to the dust-dense region, reduces the water resource waste, and improves the dust-settling efficiency and the accuracy of regulation and control of the spraying device of the drilling machine.
It should be noted that: the above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit of the present invention.
Claims (10)
1. An intelligent spray control method for a coal mine drilling machine is characterized by comprising the following steps:
acquiring continuous n frames of gray images under a coal mine in the current time period, wherein the continuous n frames of gray images are composed of historical frame gray images and current frame gray images, and n is more than or equal to 2;
obtaining a moving pixel point in the gray image of the current frame based on the gray value of each pixel point in the gray image of each historical frame and the gray value of each pixel point in the gray image of the current frame; acquiring matching points of the motion pixel points in the gray level images of the historical frames based on the gray level values of the pixel points in the gray level images of the historical frames, and constructing associated data sequences of the motion pixel points; screening dust pixel points from all moving pixel points in the gray level image of the current frame based on the associated data sequence, the wind speed at the current moment and the wind direction angle at the current moment;
obtaining dust particle areas based on dust pixel points in the current frame gray level image, and calculating the circularity of each dust particle area; acquiring the area of each dust particle area as the initial shape and size value of each dust particle area; correcting the initial shape size value based on the shape similarity of every two dust particle areas in the current frame gray level image to obtain the corrected shape size value of each dust particle area; taking the product of the corrected shape size value and the circularity as the sedimentation easiness of the corresponding dust particle area;
clustering dust particle areas in the gray level image of the current frame, and recording the cluster with the highest density as a dust dense area; calculating the overall sedimentation easiness of the dust dense region based on the sedimentation easiness of each dust particle region in the dust dense region and the Euclidean distance from the central point of each dust particle region to the central point of the dust dense region; and obtaining a target spraying amount corresponding to the current moment based on the integral settlement easiness, and adjusting the spraying amount of a spraying device of the drilling machine to the target spraying amount.
2. The intelligent spray control method for the coal mine drilling rig according to claim 1, wherein the obtaining of the moving pixel point in the current frame gray image based on the gray value of each pixel point in each historical frame gray image and the gray value of each pixel point in the current frame gray image comprises:
for any pixel point in the gray image of the current frame:
acquiring pixel points with the same positions as the pixel points in the gray level images of the historical frames, and recording the pixel points as the characteristic points corresponding to the pixel points;
respectively calculating the absolute value of the difference value of the gray value of the pixel point and the gray value of each characteristic point corresponding to the pixel point; if the absolute value of the difference value between the gray value of the pixel point and the gray value of each corresponding characteristic point is 0, judging that the pixel point is a background pixel point; and if at least one of the absolute values of the difference values of the gray values of the pixel point and the corresponding characteristic points is not 0, judging that the pixel point is a moving pixel point.
3. The intelligent spray control method for the coal mine drilling rig according to claim 1, wherein the obtaining of the matching point of each moving pixel point in each historical frame gray image based on the gray value of the pixel point in each historical frame gray image comprises:
recording a historical frame gray image adjacent to the current frame gray image as a first frame target image, recording a historical frame gray image adjacent to the first frame target image as a second frame target image, and so on to obtain an n-1 frame target image;
for any moving pixel point in the gray image of the current frame:
calculating the matching degree between the motion pixel point and each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in each frame of target image according to the gray value of the motion pixel point, the gray value of each pixel point in the preset first neighborhood of the corresponding feature point of each frame of target image, the gray value of each pixel point in the preset second neighborhood of each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in each frame of target image; and taking the pixel point with the maximum matching degree with the moving pixel point in the preset first neighborhood of the corresponding characteristic point of the moving pixel point in each frame of target image as the matching point of the moving pixel point in the corresponding historical frame gray level image.
4. The intelligent spraying control method for the coal mine drilling machine as claimed in claim 3, wherein the matching degree between the motion pixel point and each pixel point in the preset first neighborhood of the corresponding feature point of the motion pixel point in the first frame target image is calculated by adopting the following formula:
wherein, the first and the second end of the pipe are connected with each other,
is as follows
A motion pixel point and the second
The matching degree of the w pixel point of the corresponding characteristic point in the first frame target image in the w pixel point in the preset first neighborhood,
is as follows
The gray value of each of the moving pixels,
is as follows
The gray value of the w-th pixel point of the corresponding characteristic point of the motion pixel point in the first frame target image is preset in a first neighborhood,
is as follows
The number of pixels in a predetermined second neighborhood of the individual motion pixels,
is as follows
The gray value of the ith pixel point in the preset second neighborhood of the motion pixel point,
is as follows
The gray value of the ith pixel point in the preset second neighborhood of the w pixel point in the preset first neighborhood of the corresponding feature point of each motion pixel point in the first frame target image is the natural constant.
5. The intelligent spray control method for the coal mine drilling rig according to claim 1, wherein the screening of dust pixel points from all moving pixel points in a gray image of a current frame based on the associated data sequence, the wind speed at the current time and the wind direction angle at the current time comprises:
for any moving pixel point in the gray image of the current frame:
obtaining the motion direction angle and the motion speed of the motion pixel point in each time period according to the position information of any two adjacent pixel points in the matching data sequence corresponding to the motion pixel point and the acquisition time of the corresponding image; the motion direction angle and the motion speed of the motion pixel point in each time period form motion data of the motion pixel point in each time period, and a motion data sequence corresponding to the motion pixel point is constructed according to the motion data;
when the normalized wind speed at the current moment is smaller than a speed threshold value, obtaining an irregular index of the moving pixel point according to the moving data sequence corresponding to the moving pixel point; if the irregular index is larger than the irregular index threshold value, judging the moving pixel point as a dust pixel point;
when the normalized wind speed at the current moment is greater than or equal to the speed threshold, calculating the corresponding degree of convergence of the motion pixel point according to the motion data sequence corresponding to the motion pixel point, the wind speed at the current moment and the wind direction angle at the current moment; and if the convergence is greater than the convergence threshold, judging that the moving pixel is a dust pixel.
6. The intelligent spray control method for the coal mine drilling machine according to claim 5, wherein the obtaining of the irregularity index of the moving pixel point according to the moving data sequence corresponding to the moving pixel point comprises:
calculating the absolute value of the difference value of the angles corresponding to any two adjacent elements in the motion data sequence corresponding to the motion pixel point, and recording the absolute value as a first absolute value; judging whether the first absolute value is larger than an angle threshold value or not, and if so, judging that the motion direction of the motion pixel point in the corresponding time period is changed; if the motion direction of the motion pixel point in the corresponding time period is not changed, judging that the motion direction of the motion pixel point in the corresponding time period is not changed;
counting the times of the change of the motion direction of the motion pixel point; taking the ratio of the number of times of change of the motion direction of the motion pixel point to the total judgment number of times of change of the motion direction as an irregularity index of the motion pixel point;
calculating the corresponding degree of similarity of the motion pixel points by adopting the following formula:
wherein the content of the first and second substances,
is the first in the gray scale image of the current frame
The degree of convergence of each motion pixel point,
is the first in the gray scale image of the current frame
The motion direction angle in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the first in the gray scale image of the current frame
The wind speed in the ith motion data in the motion data sequence corresponding to each motion pixel point,
is the wind direction angle at the current moment,
is the wind speed at the present moment,
is the first in the gray scale image of the current frame
The number of the motion data in the motion data sequence corresponding to each motion pixel point, and e is a natural constant.
7. The intelligent spray control method for the coal mine drilling machine according to claim 1, wherein the step of correcting the initial shape size value based on the shape similarity of every two dust particle areas in the current frame gray scale image to obtain the corrected shape size value of each dust particle area comprises the steps of:
respectively detecting corner points of edge pixel points of any two dust particle areas in a current frame gray level image, marking the area with the smaller number of corner points in the two dust particle areas as a first dust particle area, and marking the area with the larger number of corner points in the two dust particle areas as a second dust particle area;
selecting any corner point in a first dust particle area to be marked as a first corner point, and acquiring a clockwise included angle between a straight line formed by the first corner point and the central point of the first dust particle area and a horizontal line, and marking as a first included angle; respectively acquiring clockwise included angles between straight lines formed by each corner point in the second dust particle area and the central point of the second dust particle area and a horizontal line, and recording the clockwise included angles as second included angles; taking an angular point in a second dust particle area corresponding to a second included angle corresponding to the minimum absolute value of the difference value of the first included angle as a matching point of the first angular point, wherein the matching point of the first angular point and the first angular point forms a matching point pair;
calculating the shape similarity of the first dust particle area and the second dust particle area based on a clockwise included angle between a straight line formed by two corner points in each matching point pair and the central point of the corresponding area and a horizontal line;
if the shape similarity is greater than the similarity threshold, the initial shape size value of the dust particle region having a larger initial shape size value in the first dust particle region and the second dust particle region is set as the corrected shape size value of the dust particle region having a smaller initial shape size value.
8. The intelligent spray control method for the coal mine drilling machine as claimed in claim 7, wherein the similarity of the shapes of the first dust particle area and the second dust particle area is calculated by the following formula:
wherein the content of the first and second substances,
the similarity in shape of the first dust particle region and the second dust particle region,
the number of corner points in the first dust particle region,
the number of corner points in the second dust particle region,
is the clockwise angle between the straight line formed by the first corner point in the jth matching point pair and the center point of the area where the first corner point is located and the horizontal line,
is the clockwise included angle between the straight line formed by the second corner point in the jth matching point pair and the center point of the area where the second corner point is located and the horizontal line,
to take the minimum function, e is a natural constant.
9. The intelligent spray control method for the coal mine drilling machine according to claim 1, characterized in that the following formula is adoptedCalculating the integral settlement easiness of the dust dense area by the formula:
wherein the content of the first and second substances,
the overall settling ease in the dust-dense area,
to ease the settling of the kth dust particle region in the dust-dense region,
the maximum value of the Euclidean distance between the central point of each dust particle area in the dust dense area and the central point of the dust dense area,
is the Euclidean distance between the central point of the kth dust particle area in the dust dense area and the central point of the dust dense area,
is the number of dust particle areas within the dust dense area.
10. The intelligent spray control method for the coal mine drilling machine according to claim 1, wherein the obtaining of the target spray amount corresponding to the current moment based on the overall settlement easiness comprises:
judging whether the integral sedimentation easiness is larger than a sedimentation easiness threshold value or not, and if so, taking the product of the initial spraying usage and the integral sedimentation easiness as a target spraying usage corresponding to the current moment; if the total sedimentation ease is less than or equal to the target spray amount, the sum of the constant 1 and the total sedimentation ease is recorded as a first index, and the product of the first index and the total sedimentation ease is used as the target spray amount corresponding to the current time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211429971.9A CN115487959B (en) | 2022-11-16 | 2022-11-16 | Intelligent spraying control method for coal mine drilling machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211429971.9A CN115487959B (en) | 2022-11-16 | 2022-11-16 | Intelligent spraying control method for coal mine drilling machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115487959A true CN115487959A (en) | 2022-12-20 |
| CN115487959B CN115487959B (en) | 2023-02-17 |
Family
ID=85115766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211429971.9A Active CN115487959B (en) | 2022-11-16 | 2022-11-16 | Intelligent spraying control method for coal mine drilling machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115487959B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485794A (en) * | 2023-06-19 | 2023-07-25 | 济南幼儿师范高等专科学校 | Face image analysis method for virtual vocal music teaching |
| CN116563799A (en) * | 2023-07-11 | 2023-08-08 | 山东昆仲信息科技有限公司 | Dust online monitoring method based on video monitoring |
| CN116933734A (en) * | 2023-09-15 | 2023-10-24 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Intelligent diagnosis method for cutter faults of shield machine |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020051776A1 (en) * | 2018-09-11 | 2020-03-19 | Intel Corporation | Method and system of deep supervision object detection for reducing resource usage |
| CN111530203A (en) * | 2020-07-08 | 2020-08-14 | 湖南九九智能环保股份有限公司 | Intelligent dust measurement and control system and dust suppression and dust fall method thereof |
| CN114005058A (en) * | 2021-10-28 | 2022-02-01 | 河北省科学院应用数学研究所 | Dust identification method and device and terminal equipment |
| CN114675695A (en) * | 2022-03-26 | 2022-06-28 | 太仓武港码头有限公司 | Control method, system, equipment and storage medium for dust suppression of storage yard |
| CN114985150A (en) * | 2022-08-02 | 2022-09-02 | 山东大拇指喷雾设备有限公司 | Visual perception-based control method for accurate spraying of spraying machine |
-
2022
- 2022-11-16 CN CN202211429971.9A patent/CN115487959B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020051776A1 (en) * | 2018-09-11 | 2020-03-19 | Intel Corporation | Method and system of deep supervision object detection for reducing resource usage |
| CN111530203A (en) * | 2020-07-08 | 2020-08-14 | 湖南九九智能环保股份有限公司 | Intelligent dust measurement and control system and dust suppression and dust fall method thereof |
| CN114005058A (en) * | 2021-10-28 | 2022-02-01 | 河北省科学院应用数学研究所 | Dust identification method and device and terminal equipment |
| CN114675695A (en) * | 2022-03-26 | 2022-06-28 | 太仓武港码头有限公司 | Control method, system, equipment and storage medium for dust suppression of storage yard |
| CN114985150A (en) * | 2022-08-02 | 2022-09-02 | 山东大拇指喷雾设备有限公司 | Visual perception-based control method for accurate spraying of spraying machine |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485794A (en) * | 2023-06-19 | 2023-07-25 | 济南幼儿师范高等专科学校 | Face image analysis method for virtual vocal music teaching |
| CN116485794B (en) * | 2023-06-19 | 2023-09-19 | 济南幼儿师范高等专科学校 | Face image analysis method for virtual vocal music teaching |
| CN116563799A (en) * | 2023-07-11 | 2023-08-08 | 山东昆仲信息科技有限公司 | Dust online monitoring method based on video monitoring |
| CN116563799B (en) * | 2023-07-11 | 2023-09-22 | 山东昆仲信息科技有限公司 | Dust online monitoring method based on video monitoring |
| CN116933734A (en) * | 2023-09-15 | 2023-10-24 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Intelligent diagnosis method for cutter faults of shield machine |
| CN116933734B (en) * | 2023-09-15 | 2023-12-19 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Intelligent diagnosis method for cutter faults of shield machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115487959B (en) | 2023-02-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115487959B (en) | Intelligent spraying control method for coal mine drilling machine | |
| CN111047555B (en) | Ore image granularity detection algorithm based on image processing technology | |
| CN108986064B (en) | People flow statistical method, equipment and system | |
| CN106447669B (en) | The adhesion particle image concave point dividing method differentiated based on round masking-out area ratio | |
| CN103049787B (en) | A kind of demographic method based on head shoulder feature and system | |
| CN111696123A (en) | Remote sensing image water area segmentation and extraction method based on super-pixel classification and identification | |
| CN104112269B (en) | A kind of solar battery laser groove parameter detection method and system based on machine vision | |
| CN106989683B (en) | A kind of shield tail clearance of shield machine vision measuring method | |
| CN100544446C (en) | The real time movement detection method that is used for video monitoring | |
| CN105139015B (en) | A kind of remote sensing images Clean water withdraw method | |
| CN114627140B (en) | Coal mine ventilator intelligent adjusting method based on high-voltage frequency converter | |
| CN106709938B (en) | Based on the multi-target tracking method for improving TLD | |
| CN107464256B (en) | A kind of target detection and possibility differentiate modified correlating method | |
| CN104239865A (en) | Pedestrian detecting and tracking method based on multi-stage detection | |
| CN109060836A (en) | High-pressure oil pipe joint external screw thread detection method based on machine vision | |
| CN111832536A (en) | Lane line detection method and device | |
| CN108470338B (en) | A kind of water level monitoring method | |
| CN108921076B (en) | Pavement crack disease self-adaptive constant false alarm detection method based on image | |
| CN109272482B (en) | Urban intersection vehicle queuing detection system based on sequence images | |
| CN106128121A (en) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis | |
| CN109708658B (en) | Visual odometer method based on convolutional neural network | |
| WO2023273011A1 (en) | Method, apparatus and device for detecting object thrown from height, and computer storage medium | |
| CN109146859A (en) | A kind of pavement crack detection system based on machine vision | |
| CN109978940A (en) | A kind of SAB air bag size vision measuring method | |
| CN109876569A (en) | A kind of bag filter purification gas index on-line measuring device, system and method |
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 |