CN113269705A - Video-based explosive feeding depth detection method and device - Google Patents
Video-based explosive feeding depth detection method and device Download PDFInfo
- Publication number
- CN113269705A CN113269705A CN202010092206.7A CN202010092206A CN113269705A CN 113269705 A CN113269705 A CN 113269705A CN 202010092206 A CN202010092206 A CN 202010092206A CN 113269705 A CN113269705 A CN 113269705A
- Authority
- CN
- China
- Prior art keywords
- video frame
- pipe
- length
- video
- frame picture
- 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.)
- Pending
Links
- 239000002360 explosive Substances 0.000 title claims abstract description 114
- 238000001514 detection method Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 abstract description 7
- 230000005284 excitation Effects 0.000 abstract description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 26
- 230000008569 process Effects 0.000 description 15
- 229910052742 iron Inorganic materials 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000005422 blasting Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 239000003814 drug Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000008141 laxative Substances 0.000 description 2
- 230000002475 laxative effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- PMVSDNDAUGGCCE-TYYBGVCCSA-L Ferrous fumarate Chemical compound [Fe+2].[O-]C(=O)\C=C\C([O-])=O PMVSDNDAUGGCCE-TYYBGVCCSA-L 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012377 drug delivery Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/22—Measuring arrangements characterised by the use of optical techniques for measuring depth
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a video-based explosive feeding depth detection method and device, wherein the method comprises the following steps: acquiring a plurality of video frame pictures in an explosive feeding video file at preset time intervals; detecting a pipe in the vertical direction in each video frame picture, and determining the length and position information of the pipe in each video frame picture with the pipe; analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes according to the analysis result; and obtaining the explosive feeding depth detection result according to the number of the tubes and the length information of the tubes. According to the technical scheme, the explosive loading depth detection is efficiently and accurately carried out, the efficiency and the accuracy of the explosive loading depth detection are improved, the explosive loading construction quality is ensured, and the explosive excitation quality is further ensured.
Description
Technical Field
The invention relates to the technical field of petroleum seismic exploration, in particular to a video-based explosive feeding depth detection method and device.
Background
In oil seismic exploration, explosive explosion (i.e. blasting) is used to generate seismic waves, and the condition of underground geological structures is deduced according to the seismic waves received by detectors. When blasting is carried out by using the explosive, firstly, drilling is carried out at a specified position for blasting explosive holes, then the explosive is placed in a certain stratum depth for blasting, the explosive feeding depth is different at different positions of different terrains, but the explosive is placed at a specified depth position in the design. In the process of lowering, a constructor needs to pull a line for binding the explosive and lowers the explosive to a specified position by gravity a little, but due to the reasons of narrow well wall, scratch and the like, if the explosive is lowered by gravity in the explosive lowering process, the explosive may be clamped in the middle part of the well and does not reach the preset explosive lowering depth, if the explosive is detonated at a non-specified position, most of seismic wave energy generated by explosion is absorbed by stratums such as shallow water level, earth surface and the like, seismic waves transmitted to a target layer are greatly reduced, and the imaging quality is directly influenced. In order to avoid the situation, in the actual production process, a metal iron pipe needs to be placed in a charge well to push explosives downwards to a designated position, the length of the iron pipe is generally fixed and limited, multiple sections of iron pipes need to be spliced in the pipe descending process, after one iron pipe is loaded, another iron pipe needs to be spliced, then the pipe is continuously connected to push the explosives downwards, and if the iron pipe cannot be pushed downwards, the situation that the explosives are loaded to the designated position is shown. The construction of well drilling, laxative and blasting is usually gone on in the place that has few people's cigarette in the field, in order to ensure the construction quality of the degree of depth of making a prescription, need carry out the video recording to whole laxative process, the construction is accomplished the back, needs the manual work to detect the video of collecting back, whether the pipe depth of transferring when making a prescription through the statistics judges the explosive that falls and reaches the predetermined degree of depth, this detection scheme has artifical visual inspection work load big, and is inefficient, and the precision is poor, problem with high costs.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a video-based explosive loading depth detection method, which is used for efficiently and accurately detecting the explosive loading depth and comprises the following steps:
acquiring a plurality of video frame pictures in an explosive feeding video file at preset time intervals;
detecting a pipe in the vertical direction in each video frame picture, and determining the length and position information of the pipe in each video frame picture with the pipe;
analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes according to the analysis result;
and obtaining the explosive feeding depth detection result according to the number of the tubes and the length information of the tubes.
The embodiment of the invention also provides a video-based explosive loading depth detection device, which is used for efficiently and accurately detecting the explosive loading depth and comprises the following components:
the explosive loading video file acquisition unit is used for reading a plurality of video frame pictures in the explosive loading video file at preset time intervals;
the detection unit is used for detecting the pipe in the vertical direction in each video frame picture and determining the length and position information of the pipe in each video frame picture with the pipe;
the determining unit is used for analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes to be arranged according to the analysis result;
and the processing unit is used for obtaining the detection result of the explosive loading depth according to the number of the pipes and the length information of the pipes.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the video-based explosive feeding depth detection method is realized.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program for executing the video-based explosive loading depth detection method.
The technical scheme provided by the embodiment of the invention comprises the following steps: acquiring a plurality of video frame pictures in an explosive feeding video file at preset time intervals; detecting a pipe in the vertical direction in each video frame picture, and determining the length and position information of the pipe in each video frame picture with the pipe; analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes according to the analysis result; according to the number of the pipes and the length information of the pipes, the explosive feeding depth detection result is obtained, the explosive feeding depth detection is efficiently and accurately carried out, the efficiency and the accuracy of the explosive feeding depth detection are improved, the explosive feeding construction quality is ensured, the explosive excitation quality is further ensured, and meanwhile, the cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a video-based explosive loading depth detection method in an embodiment of the invention;
FIG. 2 is a schematic diagram of the video-based explosive loading depth detection in an embodiment of the present invention;
FIG. 3 is a graphical representation of the effectiveness of video-based explosives dosing depth detection in an embodiment of the invention;
FIG. 4 is a schematic structural diagram of a video-based explosive loading depth detection device in an embodiment of the invention;
fig. 5 is a schematic structural diagram of a video-based explosive feeding depth detection device in another embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As the inventor finds technical problems in the explosive loading depth detection technology in the prior art, the video-based explosive loading depth detection scheme is provided, and the number and the length of loaded pipes are automatically detected and analyzed according to the video of the loaded pipes recorded on site, so that whether the explosive is placed to the specified depth is judged. The video-based explosive loading depth detection scheme is described in detail below.
Fig. 1 is a schematic flow chart of a video-based explosive loading depth detection method in an embodiment of the invention, and as shown in fig. 1, the method includes the following steps:
step 101: acquiring a plurality of video frame pictures in an explosive feeding video file at preset time intervals;
step 102: detecting a pipe in the vertical direction in each video frame picture, and determining the length and position information of the pipe in each video frame picture with the pipe;
step 103: analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes according to the analysis result;
step 104: and obtaining the explosive feeding depth detection result according to the number of the tubes and the length information of the tubes.
The video-based explosive feeding depth detection method provided by the embodiment of the invention realizes efficient and accurate explosive feeding depth detection, improves the efficiency and accuracy of explosive feeding depth detection, ensures the explosive feeding construction quality and further ensures the explosive excitation quality.
The following describes in detail a solution according to an embodiment of the present invention with reference to fig. 2 to 3.
First, the above step 101 is described.
In specific implementation, a recorded video file for drug delivery is opened, video frames (videos are all composed of still pictures, and these still pictures are referred to as frames) are read at specified time intervals Sn, and then subsequent analysis processing (including single frame detection and inter-frame detection below) is performed.
In specific implementation, the selection of the time interval Sn is considered as follows: generally, in a video, 1s includes 30 frames or twenty-few frames, a difference between two adjacent frames is not large, in order to improve efficiency of algorithm processing, each frame is not processed, but several frames are processed once, and an interval time may be: number of frames of interval/total number of frames per second (seconds).
Next, a step of preprocessing the video frame picture after the step 101 is described.
In one embodiment, the video-based explosive depth detection method may further include: after a plurality of video frame pictures in the explosive loading video file are read at preset time intervals, the following steps of preprocessing are carried out on each read video frame picture:
reducing each read video frame picture according to a preset proportion;
converting each video frame picture after the reduction processing into a gray level image to obtain a video frame gray level image;
and carrying out equalization processing on each video frame gray level image to obtain the video frame gray level image after equalization processing.
In specific implementation, the preprocessing part mainly converts a video frame (in video processing, a dynamic video is composed of a frame of static image, and a frame of image is an image) into a gray image, reduces the size of the image and performs equalization processing.
The details of the above pretreatment are described below.
1. Reducing each read video frame picture according to a preset proportion: due to the fact that the recorded video is high in resolution and large in data volume, in order to improve processing speed, the read video image is subjected to reduction processing, data processing amount is reduced, and further efficiency of explosive feeding depth detection based on the video is improved.
2. Converting each video frame picture after the reduction processing into a gray level image to obtain a video frame gray level image: the video frame to be detected is converted into a gray image from a color image, and the accuracy of the detection of the explosive loading depth based on the video is improved by the preprocessing step of converting the video frame into the gray image because the field environment changes greatly, the color of the tube is not fixed, the tube is influenced by conditions such as light, shooting and the like, and the tube is difficult to identify by using the color. The invention mainly carries out detection by analyzing the geometric shape, the color identification only carries out some auxiliary detections, the morphological analysis is carried out, and the gray level image is utilized, thus improving the efficiency of detection processing.
3. Carrying out equalization processing on each video frame gray level image to obtain a video frame gray level image after equalization processing: in order to reduce the influence of uneven light variation in the field environment on the image capturing effect, the image needs to be equalized.
In an embodiment, the equalizing the gray level map of each video frame to obtain the gray level map of the video frame after the equalizing process may include obtaining the gray level map of the video frame after the equalizing process according to the following formula:
wherein, PrIs the probability density of the gray scale, rkIs the kth gray level, k is 0,1,2, …, L-1, nkIs that the gray level in the image (picture) is rkN is the total number of pixels in the image.
SkPerforming histogram equalization to obtain r gray level in the input imagej(abscissa) mapping of a pixel to a grey level S in the output imagek(abscissa) corresponding pixel, where njIs that the gray level in the image (picture) is rjThe number of pixels.
In one embodiment, the step of preprocessing may further include:
extracting a boundary in the vertical direction on each video frame gray level image after equalization processing;
and carrying out binarization processing on each video frame gray map subjected to the equalization processing of the extracted boundary to obtain a video frame gray map subjected to binarization processing.
In specific implementation, the preprocessing may further include extracting boundary information in a vertical direction on the image and performing binarization processing on the image:
1. extracting boundary information in the vertical direction on the image, namely extracting the boundary in the vertical direction on each video frame gray level image after equalization processing:
in one embodiment, the extracting the boundary in the vertical direction on the gray scale map of each video frame after the equalization processing may include: the vertical boundary is extracted according to the following formula:
in particular, the boundary factor in the y direction can be used to extract the boundary in the vertical direction on the image.
Wherein, in the above formula (3), fiGrad for images to be boundary extractedyTo find the gradient in the y-direction, fgrdYThe boundary in the Y direction is obtained.
In specific implementation, the vertical boundary refers to an upper boundary and a lower boundary in the whole picture. Then, the boundary of the pipe is found according to the length, the position relation and the like of the pipe. The vertical boundary extraction is stable in feature extraction, the speed is high, and a good foundation is laid for the following linear detection by utilizing Hough transform.
2. Performing binarization processing on the image, namely performing binarization processing on each video frame gray map after the equalization processing of the extracted boundary to obtain a video frame gray map after binarization processing:
in an embodiment, performing binarization processing on each equalized video frame gray scale map with the extracted boundary to obtain a video frame gray scale map after binarization processing may include:
carrying out binarization processing on the image, wherein the calculation process is as follows:
(1) finding the minimum and maximum gray value g of the imageminAnd gmaxThe initial threshold is:
T0＝(gmin+gmax)×0.5； (4)
(2) using a threshold value T0Dividing the image into a foreground part and a background part, and calculating the average gray value of the two parts:
wherein: gbAverage gray of background, GfIs the average gray value of the foreground, g is the gray value of the pixel, and h (g) is the probability density of the gray value of the pixel.
(3) Let Tk＝(Gb+Gf)×0.5 (7)
If T isk＝Tk+1Then get TkIf not, go to (2) and continue iteration.
Where k is the number of iterations, TkIs a threshold value, T, obtained by the k-th iteration calculationk+1Is the threshold calculated by the (k + 1) th iteration.
In specific implementation, after the color picture is grayed, the obtained grayscale image is subjected to binarization processing. For binarization, the objective is to classify the target user context in preparation for subsequent lane identification. The most common method for the binarization of the gray level image is a threshold value method, the difference between a target and a background in the image is utilized, the image is respectively set to be in two different levels, and a proper threshold value is selected to determine whether a certain pixel is the target or the background, so that the binarized image is obtained, and the efficiency and the accuracy of the explosive loading depth detection based on the video are further improved.
Next, the above step 102, i.e., single frame inspection of the tube, is described.
In one embodiment, detecting a pipe in a vertical direction in each video frame picture and determining length and position information of the pipe in each video frame picture where the pipe exists may include:
finding a tube in each video frame picture in the vertical direction by using Hough transform;
detecting the length of the pipe in each video frame picture, determining that the pipe exists in the video frame pictures when the length of the pipe is larger than a preset length threshold value, and recording the length and position information of the pipe in each video frame picture in which the pipe exists.
This step 102 is described in detail below.
1. First, we will describe finding the tube in each video frame picture by using hough transform to find the straight line.
The Hough transform is a method for detecting straight lines by using a linear polar coordinate parameter space, the boundary detection in the last step is mainly used for detecting boundary lines in the vertical direction, the boundary lines displayed in an image are a series of pixel points with the value of 1, a point P is set as a point on a straight line in the image, and the point coordinate is P under a Cartesian coordinate system(x,y)The polar coordinate of the point is
The distance of the origin of the example image of the straight line is rho, which can be obtained under polar coordinates:
wherein the content of the first and second substances,
is the angle of rotation of the origin to the perpendicular to this line.
The polar equation of the straight line can be found:
ρ＝x×cos(θ)+y×sin(θ)； (10)
where r is the distance from the origin of the straight line in polar coordinates to the straight line, and θ is the angle of the straight line in polar coordinates.
That is, a straight line can be uniquely determined by using a set of parameters (ρ, θ), and the equation of the straight line is a point in a polar coordinate system, i.e., a graphA straight line in the image corresponds to a point in polar parameter space. For any point on the extracted boundary, all straight lines that may pass through the point correspond to a point in the polar parameter space, and an infinite number of straight lines that pass through the point form a curve in the polar parameter space. And a plurality of boundary points will generate a plurality of curves in the parameter space of polar coordinates. When these boundary points are on a straight line, the curves in polar parameter space will have intersection points of (ρ)i,θi) This is the polar parameter of this straight line.
Because the tube needs to be detected and is vertically placed, the value range of rho is limited within the height of the whole image in the calculation process of Hough parameter space, and theta is (90-theta)υ°,90°+θυ°]In this context, the tubes are considered to be vertically disposed, where θυThe angle is a deviation angle from the vertical direction, and is a set parameter, the parameter space is divided into m × n grids, m and n are the number of the grids divided in the horizontal direction and the vertical direction respectively, and a counter of a straight line determined by (rho, theta) is stored in the grids. For each boundary point (x, y) in the image, the value of ρ calculated with the θ argument using equation (10) is then incremented by 1 in the corresponding line counter in the grid. After all the points are calculated, the linear counters in the parameter space are counted, and the longest vertical straight lines can be found by finding the largest linear counters. And then processing the detected straight lines, deleting the straight lines with too short lengths, and combining the straight lines with similar distances to obtain a tube image in the vertical direction in the video frame picture.
The method for detecting the straight line by utilizing Hough transform is a problem of transferring the straight line on an image space to a midpoint detection point in a parameter space, is a parameter estimation method in a voting mode, and has the characteristics of strong anti-noise capability and insensitivity to edge discontinuity.
2. Next, the detection of the down tube region is described, whereby the length and position information of the tube is recorded in each video frame picture where the tube is present.
In particular toIn the implementation process, the position of the medicine well is fixed because the position of the camera is fixed in the shooting process. Detecting the vertical straight line of the sub-window with the width w, the height and the image equal height of the image to be detected, wherein the sliding step length of the time window is Ss(usually half the width of the window), detecting the total length of the vertical lines in the current sliding window, if the length is more than Th(Note: T)hThe method is used for judging whether the tube length is a tube length threshold of the tube, namely a preset length threshold, if the tube length is larger than the preset length threshold, the tube is considered to be present, otherwise, the vertical tube is not present), the region to be detected is considered to be a candidate tube region (as shown by a rectangular frame in fig. 3, a rectangular shape in fig. 3 represents the detected tube region, and an x coordinate corresponding to a circular shape represents the position of the tube), and the current window position and the detected length are recorded.
During specific implementation, candidate pipe regions in the video frame picture are determined, the comparison range is narrowed, and the efficiency of explosive loading depth detection based on the video is further improved.
Fourth, next, the above step 103, i.e., the inter-frame analysis of the tube, is introduced.
In one embodiment, analyzing the change of the pipe length in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the timing information of all the video frame pictures, and determining the number of the pipes to be arranged according to the analysis result may include:
and determining the preset times that the length of the pipe is continuously reduced according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and adding one to the number of the pipes.
In one embodiment, analyzing the change of the pipe length in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the timing information of all the video frame pictures, and determining the number of the pipes to be arranged according to the analysis result may include:
and when the length of the pipe is determined to be reduced to a preset minimum value and the length of the pipe is suddenly increased by the preset length according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, the number of the pipes to be dropped is increased by one.
In one embodiment, analyzing the change of the pipe length in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the timing information of all the video frame pictures, and determining the number of the pipes to be arranged according to the analysis result may include:
and when the length of the pipe is determined to be continuously unchanged within a preset time period according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, keeping the number of the lower pipes unchanged.
In specific implementation, after the detection of the candidate pipe region (the position information of the pipe) in the single frame is completed (i.e. after the step 102), the sampling time S is set to be givennAnd sampling and analyzing the video frames at intervals of seconds, and analyzing and comparing the continuously recorded detection results.
If no tube candidate is detected, SnAnd jumping to the 2 in the three for the interval of seconds to continue the detection.
If a tube candidate area is detected, the lengths of the candidate tubes in the detected tube candidate area are compared, if the lengths continuously decrease by NdSecond (N)dWhen detecting the region, the number of times of detecting the length of the detected pipe is reduced, namely the preset number of times, if the length of the detected pipe is reduced and is smaller than the given threshold value compared with the last detection, the counting is added with 1, and if N is continuously detecteddThe next descending is regarded as the descending of the pipe), the time interval of the height descending is regarded as the descending of the iron pipe, the number of the descending of the iron pipe is added with 1, and then the candidate pipe area is emptied.
If the line length in a certain tube region drops to a preset minimum value (preferably one tenth of the detected tube length), the length suddenly increases (the rate of increase in the length of the tube exceeds a preset increase) and then continues to drop again, indicating that the tube is being renewed.
If the length of the tube in the detected area is constant for a long time, other interference objects are possible, and the tube can be eliminated.
In specific implementation, the implementation mode of interframe analysis of the pipes can improve the detection accuracy of the number of the pipes, and further improve the accuracy of the explosive feeding depth detection based on the video.
Next, the above step 104 is described.
In specific implementation, after the whole video is detected, the number of the detected pipes is counted, and the total pipe descending length is obtained by multiplying the number by the pipe length, so that the explosive loading depth detection result can be obtained.
In order to more easily understand how the present invention may be carried out, the following description is given in its entirety.
1. Setting parameters: setting a medicine feeding video to be detected, and setting parameters such as tube feeding depth, default tube length, video frame scaling, time interval between detection frames and the like.
2. And detecting the number of the lower tubes.
(1) Data pre-processing
Converting a video frame to be detected from a color image into a gray image, and then scaling according to a specified proportion, reducing the data volume and improving the calculation speed; then, carrying out equalization processing on the image to remove the influence of light change on the image; extracting a boundary in a vertical direction on the image by using a boundary factor in a y direction; and then carrying out binarization processing on the result.
(2) Single frame based pipe candidate region detection
Detecting a pipe in a vertical direction
According to the direction characteristics and performance requirements of the lower tube, a plurality of candidate straight lines are found in the vertical direction by utilizing Hough transform, then the detected straight lines are processed, the too short straight lines are deleted, and adjacent straight lines are combined to obtain a tube image in the vertical direction.
Determining tube candidate area
The tube length in the candidate area is detected using a sliding window and the position and tube length are recorded.
(3) Interframe analysis of tubes
Because the position of the camera is relatively fixed, the position of the shot hole in the video is relatively fixed and does not change greatly.
And performing sampling inspection on the video frames according to a specified time interval, analyzing and comparing the recorded tube candidate area information on the tube length change in the recorded tube candidate area according to time sequence and space, namely performing sampling inspection analysis on the video frames by taking the given sampling inspection time as an interval, and analyzing and comparing the continuous detection results. If the length of the detected tube is not changed all the time, the tube is indicated to be a tube-like area, namely if the length of the detected tube is not changed, other interferents are possible, and the tube can be removed; if the detected tube length continuously decreases, namely if the tube length detected at the same position is continuously shortened, the tube is positioned; if the tube candidate area is blank for a period of time, then the length of the detected tube suddenly appears a large value, and then the length continuously drops, thus a new tube is indicated; if the line length in a certain pipe region drops to a minimum, the length suddenly increases and then continues to drop again, indicating that a new pipe is going on again.
3. And outputting a detection result.
And after the video detection is finished, outputting the detected number and depth of the iron pipes for feeding the medicine.
In summary, the technical scheme provided by the embodiment of the invention calculates the explosive loading depth by detecting the number of the iron pipes in the video. The video images are automatically detected and analyzed by computer processing, the quality monitoring level and the quality monitoring capability of the explosive loading depth are improved, the explosive loading construction and explosive excitation quality are ensured, the labor cost is saved, and the time of the process is saved.
Based on the same inventive concept, the embodiment of the invention also provides a video-based explosive feeding depth detection device, which is described in the following embodiment. The video-based explosive feeding depth detection device is similar to the video-based explosive feeding depth detection method in the problem solving principle, so that the implementation of the video-based explosive feeding depth detection device can refer to the implementation of the video-based explosive feeding depth detection method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 4 is a schematic structural diagram of a video-based explosive loading depth detection device in an embodiment of the present invention, and as shown in fig. 4, the device includes:
the explosive charging method comprises the following steps that an obtaining unit 01 is used for reading a plurality of video frame pictures in an explosive charging video file at preset time intervals;
the detection unit 03 is used for detecting a pipe in the vertical direction in each video frame picture and determining the length and position information of the pipe in each video frame picture with the pipe;
a determining unit 05, configured to analyze changes in the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the timing information of all the video frame pictures, and determine the number of the pipes according to an analysis result;
and the processing unit 07 is used for obtaining the detection result of the explosive loading depth according to the number of the pipes and the length information of the pipes.
In one embodiment, as shown in fig. 5, the video-based explosive loading depth detection device may further include: the preprocessing unit 02 is used for, after a plurality of video frame pictures in the explosive loading video file are read at preset time intervals, performing the following preprocessing steps on each read video frame picture:
reducing each read video frame picture according to a preset proportion;
converting each video frame picture after the reduction processing into a gray level image to obtain a video frame gray level image;
and carrying out equalization processing on each video frame gray level image to obtain the video frame gray level image after equalization processing.
In one embodiment, the preprocessing unit may be further configured to:
extracting a boundary in the vertical direction on each video frame gray level image after equalization processing;
and carrying out binarization processing on each video frame gray map subjected to the equalization processing of the extracted boundary to obtain a video frame gray map subjected to binarization processing.
In one embodiment, the detection unit may be specifically configured to:
finding a tube in each video frame picture in the vertical direction by using Hough transform;
detecting the length of the pipe in each video frame picture, determining that the pipe exists in the video frame pictures when the length of the pipe is larger than a preset length threshold value, and recording the length and position information of the pipe in each video frame picture in which the pipe exists.
In an embodiment, the number determining unit may be specifically configured to:
and determining the preset times that the length of the pipe is continuously reduced according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and adding one to the number of the pipes.
In an embodiment, the number determining unit may be specifically configured to:
and when the length of the pipe is determined to be reduced to a preset minimum value and the length of the pipe is suddenly increased by the preset length according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, the number of the pipes to be dropped is increased by one.
In an embodiment, the number determining unit may be specifically configured to:
and when the length of the pipe is determined to be continuously unchanged within a preset time period according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, keeping the number of the lower pipes unchanged.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the video-based explosive feeding depth detection method is realized.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program for executing the video-based explosive loading depth detection method.
The technical scheme provided by the embodiment of the invention has the beneficial technical effects that: according to the embodiment of the invention, the process of feeding the explosive downwards by using the iron pipe in the explosive feeding process is automatically analyzed according to the video of the explosive feeding process, the iron pipe is detected through Hough transform, and the length change of the iron pipe is monitored to judge the number of the iron pipes for explosive feeding, so that the monitoring efficiency of the link is greatly improved, the detectable video number is improved, the labor cost of the part is reduced, the quality control accuracy of the explosive feeding depth of the well gun is improved, and the final explosive discharging yield and the explosive discharging imaging effect are improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (16)
1. A video-based explosive feeding depth detection method is characterized by comprising the following steps:
acquiring a plurality of video frame pictures in an explosive feeding video file at preset time intervals;
detecting a pipe in the vertical direction in each video frame picture, and determining the length and position information of the pipe in each video frame picture with the pipe;
analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes according to the analysis result;
and obtaining the explosive feeding depth detection result according to the number of the tubes and the length information of the tubes.
2. The video-based explosive loading depth detection method of claim 1, further comprising: after a plurality of video frame pictures in the explosive loading video file are read at preset time intervals, the following steps of preprocessing are carried out on each read video frame picture:
reducing each read video frame picture according to a preset proportion;
converting each video frame picture after the reduction processing into a gray level image to obtain a video frame gray level image;
and carrying out equalization processing on each video frame gray level image to obtain the video frame gray level image after equalization processing.
3. The video-based explosive loading depth detection method of claim 2, wherein the preprocessing step further comprises:
extracting a boundary in the vertical direction on each video frame gray level image after equalization processing;
and carrying out binarization processing on each video frame gray map subjected to the equalization processing of the extracted boundary to obtain a video frame gray map subjected to binarization processing.
4. The video-based explosive loading depth detection method of claim 1, wherein detecting a pipe in a vertical direction in each video frame picture and determining length and position information of the pipe in each video frame picture where the pipe exists comprises:
finding a tube in each video frame picture in the vertical direction by using Hough transform;
detecting the length of the pipe in each video frame picture, determining that the pipe exists in the video frame pictures when the length of the pipe is larger than a preset length threshold value, and recording the length and position information of the pipe in each video frame picture in which the pipe exists.
5. The video-based explosive loading depth detection method according to claim 1, wherein the analyzing the change of the length of the pipe in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes to be loaded according to the analysis result comprises:
and determining the preset times that the length of the pipe is continuously reduced according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and adding one to the number of the pipes.
6. The video-based explosive loading depth detection method according to claim 1, wherein the analyzing the change of the length of the pipe in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes to be loaded according to the analysis result comprises:
and when the length of the pipe is determined to be reduced to a preset minimum value and the length of the pipe is suddenly increased by the preset length according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, the number of the pipes to be dropped is increased by one.
7. The video-based explosive loading depth detection method according to claim 1, wherein the analyzing the change of the length of the pipe in all the video frame pictures according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes to be loaded according to the analysis result comprises:
and when the length of the pipe is determined to be continuously unchanged within a preset time period according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, keeping the number of the lower pipes unchanged.
8. A video-based explosive feeding depth detection device is characterized by comprising:
the explosive loading video file acquisition unit is used for reading a plurality of video frame pictures in the explosive loading video file at preset time intervals;
the detection unit is used for detecting the pipe in the vertical direction in each video frame picture and determining the length and position information of the pipe in each video frame picture with the pipe;
the determining unit is used for analyzing the change of the lengths of the pipes in all the video frame pictures according to the length and position information of the pipes in each video frame picture and the time sequence information of all the video frame pictures, and determining the number of the pipes to be arranged according to the analysis result;
and the processing unit is used for obtaining the detection result of the explosive loading depth according to the number of the pipes and the length information of the pipes.
9. The video-based explosive loading depth detection device of claim 8, further comprising: the preprocessing unit is used for reading a plurality of video frame pictures in the explosive loading video file at preset time intervals, and then preprocessing each read video frame picture as follows:
reducing each read video frame picture according to a preset proportion;
converting each video frame picture after the reduction processing into a gray level image to obtain a video frame gray level image;
and carrying out equalization processing on each video frame gray level image to obtain the video frame gray level image after equalization processing.
10. The video-based explosive depth detection device of claim 9, wherein the preprocessing unit is further configured to:
extracting a boundary in the vertical direction on each video frame gray level image after equalization processing;
and carrying out binarization processing on each video frame gray map subjected to the equalization processing of the extracted boundary to obtain a video frame gray map subjected to binarization processing.
11. The video-based explosive loading depth detection device of claim 8, wherein the detection unit is specifically configured to:
finding a tube in each video frame picture in the vertical direction by using Hough transform;
detecting the length of the pipe in each video frame picture, determining that the pipe exists in the video frame pictures when the length of the pipe is larger than a preset length threshold value, and recording the length and position information of the pipe in each video frame picture in which the pipe exists.
12. The video-based explosive loading depth detection device of claim 8, wherein the number determination unit is specifically configured to:
and determining the preset times that the length of the pipe is continuously reduced according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, and adding one to the number of the pipes.
13. The video-based explosive loading depth detection device of claim 8, wherein the number determination unit is specifically configured to:
and when the length of the pipe is determined to be reduced to a preset minimum value and the length of the pipe is suddenly increased by the preset length according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, the number of the pipes to be dropped is increased by one.
14. The video-based explosive loading depth detection device of claim 8, wherein the number determination unit is specifically configured to:
and when the length of the pipe is determined to be continuously unchanged within a preset time period according to the length and position information of the pipe in each video frame picture and the time sequence information of all the video frame pictures, keeping the number of the lower pipes unchanged.
15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when executing the computer program.
16. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010092206.7A CN113269705A (en) | 2020-02-14 | 2020-02-14 | Video-based explosive feeding depth detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010092206.7A CN113269705A (en) | 2020-02-14 | 2020-02-14 | Video-based explosive feeding depth detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113269705A true CN113269705A (en) | 2021-08-17 |
Family
ID=77227351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010092206.7A Pending CN113269705A (en) | 2020-02-14 | 2020-02-14 | Video-based explosive feeding depth detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269705A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101666597A (en) * | 2009-09-18 | 2010-03-10 | 重庆大学 | Detecting device of control time sequence of non-contact initiating explosive device and method thereof |
| CN202836513U (en) * | 2012-09-13 | 2013-03-27 | 广州市天驰测绘技术有限公司 | Distance detector with video |
| CN104100256A (en) * | 2013-04-15 | 2014-10-15 | 西安科技大学 | Method for measuring coal mine underground drilling depth based on image processing technology |
| CN104318761A (en) * | 2014-08-29 | 2015-01-28 | 华南理工大学 | Highway-scene-based detection and vehicle detection tracking optimization method |
| CN110136172A (en) * | 2019-05-21 | 2019-08-16 | 中国矿业大学 | The detection method that safeguard is worn before a kind of miner goes into the well |
| CN110751678A (en) * | 2018-12-12 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Moving object detection method and device and electronic equipment |
-
2020
- 2020-02-14 CN CN202010092206.7A patent/CN113269705A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101666597A (en) * | 2009-09-18 | 2010-03-10 | 重庆大学 | Detecting device of control time sequence of non-contact initiating explosive device and method thereof |
| CN202836513U (en) * | 2012-09-13 | 2013-03-27 | 广州市天驰测绘技术有限公司 | Distance detector with video |
| CN104100256A (en) * | 2013-04-15 | 2014-10-15 | 西安科技大学 | Method for measuring coal mine underground drilling depth based on image processing technology |
| CN104318761A (en) * | 2014-08-29 | 2015-01-28 | 华南理工大学 | Highway-scene-based detection and vehicle detection tracking optimization method |
| CN110751678A (en) * | 2018-12-12 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Moving object detection method and device and electronic equipment |
| CN110136172A (en) * | 2019-05-21 | 2019-08-16 | 中国矿业大学 | The detection method that safeguard is worn before a kind of miner goes into the well |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210319561A1 (en) | Image segmentation method and system for pavement disease based on deep learning | |
| Huang et al. | A multidirectional and multiscale morphological index for automatic building extraction from multispectral GeoEye-1 imagery | |
| CN105389814A (en) | Air bubble detection method for air tightness test | |
| CN110992349A (en) | Underground pipeline abnormity automatic positioning and identification method based on deep learning | |
| Mohebbi et al. | Rock mass structural data analysis using image processing techniques (Case study: Choghart iron ore mine northern slopes) | |
| CN111141653B (en) | Tunnel leakage rate prediction method based on neural network | |
| CN104992429A (en) | Mountain crack detection method based on image local reinforcement | |
| CN103927553B (en) | Coal and rock recognition method based on multi-scale micro-lamination and contrast ratio joint distribution | |
| CN109934170B (en) | Mine resource statistical method based on computer vision | |
| CN111381275A (en) | First arrival picking method and device for seismic data | |
| CN115035182B (en) | Landslide hazard early warning method and system | |
| CN115797354A (en) | Method for detecting appearance defects of laser welding seam | |
| CN111191531A (en) | Rapid pedestrian detection method and system | |
| CN109165603A (en) | A kind of Ship Detection and device | |
| CN112580542A (en) | Steel bar counting method based on target detection | |
| CN113899349B (en) | Sea wave parameter detection method, equipment and storage medium | |
| CN103942576A (en) | Method for identifying coal and rock through airspace multiscale random characteristics | |
| CN117593601A (en) | Water gauge tide checking method based on deep learning | |
| CN117409541A (en) | Strip mine slope monitoring and early warning method and system | |
| CN117036399A (en) | Non-contact penetration or dynamic detection test data acquisition method and terminal equipment | |
| CN113269705A (en) | Video-based explosive feeding depth detection method and device | |
| CN116543308A (en) | Landslide detection early warning model and early warning method based on multi-model fusion | |
| CN107958226B (en) | Road curve detection method, device and terminal | |
| CN116343078A (en) | Target tracking method, system and equipment based on video SAR | |
| Wijaya et al. | Building crack due to lombok earthquake classification based on glcm features and svm classifier |
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 |