Opencast coal mine muck pile lumpiness judgment method and system based on image segmentation

Abstract

The invention relates to the technical field of open pit mines, and provides an open pit coal mine muck pile lumpiness judgment method and system based on image segmentation. The judgment method comprises the following steps: performing muck pile image acquisition on a muck pile area in the open pit coal mine, converting an acquired first image into a gray image, and performing dust removal treatment to obtain a third image; based on a maximum between-class difference method, segmenting the third image to obtain a fourth image, and determining the muck pile rock particle size of the open pit coal mine according to a connected region of the fourth image; and according to the obtained muck pile rock particle size of the open pit coal mine, based on a preset muck pile rock lumpiness interval, the muck pile rock lumpiness distribution percentage of the open pit coal mine is obtained. Therefore, the judgment of the blasting muck pile lumpiness of the open pit coal mine is more convenient and efficient, the production of the mining, loading and transporting links after blasting is not influenced in the judgment process, the statistics of the boulder rate of the blasting muck pile rocks of the open pit coal mine is realized, and a reference is provided for the design optimization of blasting parameters of the open pit coal mine.

Description

Technical Field

[0001] The present application relates to the technical field of open-pit mines, and in particular to a method and system for judging the blockiness of open-pit coal mine blast piles based on image segmentation. Background Art

[0002] The blasting process is a key link in the production process of open-pit coal mines. The quality of blasting directly affects the safety and production efficiency of the subsequent mining, loading and transportation links. The rock splash distance, blast pile shape, explosive consumption, loose coefficient, rock block size, vibration speed, etc. can all be used as the basis for evaluating the blasting quality, and then guide the optimization of blasting parameter design. Among them, the rock block size of the blast pile is regarded as an important indicator for evaluating the blasting quality. If the rock block size of the blast pile is too large, the gaps between the rocks in the truck transportation link are not filled and utilized, thereby reducing the efficiency of mining, loading and transportation; on the contrary, if the rock block size is too small, it means that the amount of explosives used in the blasting is too large, which not only increases the blasting cost, but also easily generates dust and causes environmental problems. The ideal blast pile should have a reasonable gradation of rocks of different particle sizes, so that the rock blocks with small particle sizes and the rock blocks with large particle sizes reach a reasonable proportion. This not only saves blasting costs, but also can use small-size rocks to fill the gaps between large rocks during truck transportation, thereby improving transportation efficiency and generating higher economic benefits.

[0003] Therefore, the research on the size judgment of rock in open-pit coal mine blasting piles is of great significance for evaluating blasting effects, optimizing open-pit coal mine blasting design, reducing open-pit coal mine production costs, and meeting environmental protection requirements. Summary of the invention

[0004] The purpose of the present application is to provide a method and system for determining the blockiness of open-pit coal mine blast piles based on image segmentation, so as to solve or alleviate the problems existing in the above-mentioned prior art.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] The present application provides a method for determining the blockiness of blast piles in an open-pit coal mine based on image segmentation, comprising: collecting blast pile images of a blast pile area in an open-pit coal mine to obtain a first image; converting the first image into a grayscale image to obtain a second image, and performing dust removal processing on the second image to obtain a third image; segmenting the third image based on a maximum inter-class difference method to obtain a fourth image; performing particle size division according to a connected area of ​​the fourth image to determine the particle size of blast pile rocks in the open-pit coal mine, wherein the connected area is an area composed of pixels with the same pixel value and adjacent positions; calculating the number of the particle sizes of the blast pile rocks in the open-pit coal mine and the proportion of the number of the preset blast pile rock blockiness intervals to obtain the blockiness distribution percentage of the blast pile rocks in the open-pit coal mine, wherein the blast pile rock blockiness interval is an interval obtained by equidistantly dividing rock blocks of different particle sizes in the blast pile area.

[0007] Optionally, burst image acquisition is performed on a burst area in an open-pit coal mine to obtain a first image, including: before performing burst operations in the open-pit coal mine, respectively setting a plurality of image control points at the four corners of the estimated burst area; and using a drone to acquire burst image of burst rock blocks in the burst area of ​​the open-pit coal mine to obtain the first image, wherein the first image contains a plurality of the image control points, and each of the image control points is not less than 150 pixels away from an edge of the first image.

[0008] Optionally, the first image is converted into a grayscale image to obtain a second image, and the second image is dust-removed to obtain a third image, including: according to the formula: Y=0.299R+0.587G+0.114B, the first image is converted into a grayscale image to obtain the second image, wherein Y represents the grayscale value of the second image; R, G, and B represent the values ​​of the red, green, and blue color channels in the first image, respectively; based on the histogram equalization method, the second image is dust-removed to obtain the third image.

[0009] Optionally, based on a histogram equalization method, performing a dust removal operation on the second image to obtain the third image includes: obtaining a grayscale histogram of the second image; based on the grayscale histogram, determining a probability accumulation value of each grayscale level in the second image; according to the formula:

[0010] SS(k)=int(max(pix)-min(pix))×S(k)+0.5, performing dust removal operation on the second image to obtain the third image, wherein SS(k) represents the new grayscale level in the third image after the k-th grayscale level in the second image is equalized, pix represents the grayscale value in the second image, max(pix) and min(pix) represent the maximum grayscale value and the minimum grayscale value of all pixels in the second image respectively; S(k) represents the probability accumulated value of the k-th grayscale level in the second image, k∈(0~N), N=255, and k is an integer.

[0011] Optionally, determining the probability accumulation value of each gray level in the second image based on the gray histogram includes: according to the formula:

[0012]

[0013] Determine the pixel probability p(j) of gray level j in the gray level histogram corresponding to the second image, where n j represents the number of pixels of gray level j in the second image, N represents the total number of pixels in the second image, j∈(0~N), N=255, j and N are both integers; according to the formula:

[0014]

[0015] Calculate the probability cumulative value S(k) of the kth gray level in the gray histogram corresponding to the second image, where k∈(0-N) is a positive integer.

[0016] Optionally, segmenting the third image based on the maximum inter-class difference method to obtain the fourth image includes: obtaining the number of pixels in each gray level from 0 to 255 in the third image, and obtaining the proportion of each gray level in the third image; dividing each gray level from 0 to 255 of the third image into two gray levels; according to the formula:

[0017]

[0018] Calculate the maximum inter-class variance σ between the two gray levels divided by each gray level from 0 to 255 of the third image 2 , where p1 and p2 are the pixel probabilities of the two grayscale categories corresponding to the i-th grayscale; m1 and m2 are the pixel means of the two grayscale categories corresponding to the i-th grayscale; m g is the global pixel mean of the third image, and i is an integer; the third image is segmented according to the gray level corresponding to the largest maximum inter-class variance to obtain the fourth image.

[0019] Optionally, particle size division is performed according to the connected areas of the fourth image to determine the particle size of the blast rock in the open-pit coal mine, including: fitting the connected areas of the fourth image to obtain a minimum fitting ellipse that includes all pixels in the connected areas of the fourth image, wherein the major axis of the minimum fitting ellipse is the maximum particle size of the blast rock formed in the connected areas of the fourth image.

[0020] Optionally, the proportion of the number of the blast rock particle sizes in the open-pit coal mine in the total number of blast rock particle sizes in a preset blast rock particle size range is calculated to obtain the blast rock particle size distribution percentage of the open-pit coal mine, including: determining the blast rock particle size range of the open-pit coal mine based on the principle of equidistant division according to the maximum blast rock particle size of the open-pit coal mine, wherein the maximum blast rock particle size is the maximum blast rock particle size or the minimum blast rock particle size; dividing the blast rock of the open-pit coal mine based on the blast rock particle size range according to the number of the maximum particle sizes of the blast rock, calculating the proportion of the number of the blast rock particle sizes in the total number of the preset blast rock particle size range to obtain the blast rock particle size distribution percentage of the open-pit coal mine.

[0021] Optionally, before determining the particle size range of the blast pile rock of the open-pit coal mine based on the principle of equidistant division according to the limit blast pile rock particle size of the open-pit coal mine, the method further includes: according to the formula: Determine the limit blast rock particle size of the open-pit coal mine, wherein l exceeds limit and represents the limit blast rock particle size of the open-pit coal mine, and V represents the limit mining volume of the excavation equipment bucket of the open-pit coal mine, wherein the limit mining volume is the maximum mining volume or the minimum mining volume.

[0022] The embodiment of the present application also provides an open-pit coal mine blast pile block size judgment system based on image segmentation, comprising: an image acquisition unit, used to acquire blast pile images of a blast pile area in an open-pit coal mine to obtain a first image; an image preprocessing unit, used to convert the first image into a grayscale image to obtain a second image, and perform dust removal processing on the second image to obtain a third image; an image segmentation unit, used to segment the third image based on the maximum inter-class difference method to obtain a fourth image; a blast pile particle size unit, used to divide the particle size according to the connected area of ​​the fourth image to determine the blast pile rock particle size of the open-pit coal mine, wherein the connected area is an area composed of pixels with the same pixel value and adjacent positions; a blast pile block size distribution unit, used to calculate the number of the blast pile rock particle sizes of the open-pit coal mine and the proportion of the total number of blast pile rock block size intervals in a preset blast pile rock block size interval to obtain the blast pile rock block size distribution percentage of the open-pit coal mine, wherein the blast pile rock block size interval is an interval obtained by equidistantly dividing rock blocks of different particle sizes in the blast pile area.

[0023] Beneficial effects:

[0024] The method for judging the blockiness of open-pit coal mine blast pile based on image segmentation provided in the embodiment of the present application firstly collects the blast pile image of the blast pile area in the open-pit coal mine, and converts the collected first image into a grayscale image, and then performs dust removal processing to obtain a third image; then, based on the maximum inter-class difference method, the third image is segmented to obtain a fourth image, and the particle size of the blast pile rock in the open-pit coal mine is determined according to the connected area of ​​the fourth image; finally, the particle size of the blast pile rock in the open-pit coal mine is obtained, based on the preset blast pile rock blockiness interval, to obtain the blockiness distribution percentage of the blast pile rock in the open-pit coal mine. Thus, the judgment of the blockiness of the blast pile in the open-pit coal mine is made more convenient and efficient, and in the judgment process, the production of the mining, loading and transportation links after blasting is not affected, and the statistics of the large block rate of the blast pile rock in the open-pit coal mine blasting is realized, which provides a reference for the optimization of the design of blasting parameters in the open-pit coal mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 A hardware structure block diagram of a mobile terminal for executing an open-pit mine blast pile blockiness determination method based on image segmentation provided in an embodiment of the present application is shown;

[0027] Figure 2 A schematic flow chart of a method for determining the blockiness of an open-pit mine blast pile based on image segmentation according to an embodiment of the present application;

[0028] Figure 3 A schematic diagram showing the comparison of a local image of a pile explosion before and after segmentation according to an embodiment of the present application;

[0029] Figure 4 The present invention is a schematic diagram of the structure of an open-pit mine blast pile block size determination system based on image segmentation provided according to an embodiment of the present application.

[0030] The above drawings include the following reference numerals:

[0031] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0032] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for judging the blockiness of open-pit mine blast piles based on image segmentation according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0036] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] At present, there are two main methods for measuring the distribution of rock fragmentation after blasting: direct measurement and indirect calculation. Among them, direct measurement methods include visual inspection and screening. The visual inspection method mainly relies on the experience and judgment of blasting production technicians and has a certain degree of subjectivity; while the screening method can provide more accurate results, it has a large workload and low efficiency, and is not suitable for large-scale use.

[0039] Indirect measurement methods include 3D laser point cloud technology and image processing technology. Although 3D laser point cloud technology has high data accuracy and can obtain more information about the blast pile, it has a certain blind spot due to the shooting position and cannot fully measure the blast pile as a whole. In addition, the equipment cost is high and the surveying and mapping operation is difficult. UAV image acquisition technology has low cost, high efficiency, simple operation and good safety. It is suitable for complex working environments that are difficult to enter. However, its acquisition ability for the detailed features of the blast pile is weak and is greatly affected by the flight environment conditions.

[0040] Based on this, this application proposes a method for judging the blockiness of open-pit coal mine blast piles based on image segmentation. The blast pile images are collected by drones, and the collected blast pile images are pre-processed by dust removal using histogram equalization. The image segmentation is achieved by the maximum inter-class difference method, and the area and maximum diameter of the blast pile rocks after segmentation are accurately counted, thereby obtaining the particle size distribution of the blast pile rocks. Thus, by using simple equipment to collect data in a short time, accurate blast pile rock blockiness judgment results are provided without affecting the production links of mining, loading and transportation after the blast pile, which is used for rapid and efficient evaluation of the quality of open-pit mine blast piles, and provides an important reference basis for the design of open-pit coal mine blasting parameters.

[0041] like Figure 2 As shown, the method for judging the blockiness of open-pit coal mine blast pile based on image segmentation includes:

[0042] Step S201: collecting an image of a coal blasting area in an open-pit coal mine to obtain a first image.

[0043] Specifically, before the blasting operation is carried out in the above-mentioned open-pit coal mine, a plurality of image control points are arranged at the four corners of the estimated blasting area; blasting images of the blasting rocks in the above-mentioned blasting area of ​​the above-mentioned open-pit coal mine are collected by using a drone to obtain the above-mentioned first image, wherein the above-mentioned first image contains a plurality of the above-mentioned image control points, and each of the above-mentioned image control points is not less than 150 pixels away from the edge of the above-mentioned first image.

[0044] In this application, before the drone performs the image acquisition task, the drone route is planned in advance, the GPS signal is accurately calibrated, and the drone's automatic obstacle avoidance function is activated to effectively ensure that the drone can maintain a sufficient safe distance from the production equipment during flight.

[0045] In the image captured by the drone, the position of the image control point is not less than 150 pixels from the edge of the film so that it can be effectively included in the image range collected by the drone aerial survey. Since the explosive pile is generally a relatively regular rectangle with a small area, image control points are arranged at the positions of the four corners of the estimated explosive pile area. Among them, the target image of the image control point is clear, which is easy to judge (image control) and stereo measurement. In this application, the image control point is set at the one with small elevation fluctuation, relatively fixed all year round and easy to accurately locate and measure, while the image control points are avoided in the position of arc-shaped objects and shadows. In the process of laying out the image control points, the position of the image control points is accurately measured and its coordinate values ​​are recorded by total station, GPS, etc.

[0046] By deploying multiple image control points (pixel control points) at the four corners of the estimated explosion area, accurate actual geographic location information is provided for the points on the UAV aerial survey image, so as to effectively correct the problem of excessive height difference of the barometer caused by changes in environmental factors, the problem of limited positioning of the aircraft, magnetic field interference, excessive high-altitude difference generated by the barometer, and low accuracy of position offset coordinates.

[0047] In this application, 30 minutes after the open-pit coal mine blasting operation, when the dust dissipates and visibility is good, image acquisition is carried out, and during the image acquisition process, fixed-distance shooting is adopted, the aerial photography height is 60 meters, the lateral overlap rate is 70%, and the heading overlap rate is 80%. During the shooting process, the rock blocks in the blast pile area are photographed, and the areas with poor shooting effects are supplemented by multi-angle shooting to obtain the original blast pile pictures.

[0048] Step S202: convert the first image into a grayscale image to obtain a second image, and perform dust removal on the second image to obtain a third image.

[0049] In this application, first, the color image collected by the drone needs to be converted into a grayscale image to prepare for subsequent image segmentation. Specifically, according to the formula: Y = 0.299R + 0.587G + 0.114B, the first image is converted into a grayscale image to obtain the second image, where Y represents the grayscale value of the second image; R, G, and B represent the values ​​of the red, green, and blue color channels in the first image, respectively.

[0050] Due to the complex production environment of open-pit coal mines and the fact that drone images are collected in the time period after the blasting process with more dust particles, there are inevitably different degrees of dust particles in the image, which has a negative impact on the subsequent image segmentation operation. In this application, based on the histogram equalization method, the above-mentioned second image is dusted to obtain the above-mentioned third image. Since the dust is distributed more evenly in the entire image, the histogram equalization method is used to perform dust removal on the second image to increase the image contrast and retain the image details, thereby improving the image quality and image segmentation effect.

[0051] In the process of performing dust removal on the second image, first, the grayscale levels of the second image are listed, and the number of grayscale pixels of the image is counted to obtain the grayscale histogram of the second image. In this process, according to the formula:

[0052]

[0053] Determine the pixel probability p(j) of gray level j in the gray level histogram corresponding to the second image, where n j represents the number of pixels of gray level j in the above second image, N represents the total number of pixels in the above second image, j∈(0~N), N=255, j and N are both integers.

[0054] Then, based on the grayscale histogram, the probability accumulation value of each grayscale level in the second image is determined. Specifically, according to the formula:

[0055]

[0056] Calculate the probability cumulative value S(k) of the kth gray level in the gray histogram corresponding to the second image, where k∈(0-N), k is a positive integer;

[0057] Then, according to the formula: SS(k)=int(max(pix)-min(pix))×S(k)+0.5,

[0058] The second image is subjected to dust removal operation to obtain the third image, wherein SS(k) represents the new gray level of the k-th gray level in the second image after the equalization operation is performed, pix represents the gray value in the second image, max(pix) and min(pix) represent the maximum gray value and the minimum gray value of all pixels in the second image respectively; S(k) represents the probability accumulation value of the k-th gray level in the second image, k∈(0~N), N=255, and k is an integer.

[0059] Step S203: segment the third image based on the maximum inter-class difference method to obtain a fourth image.

[0060] In the present application, the number of pixels in each gray level from 0 to 255 in the third image is obtained, and the proportion of each gray level in the third image is obtained; each gray level from 0 to 255 in the third image is divided into two gray levels; according to the formula:

[0061]

[0062] Calculate the maximum inter-class variance σ between the two gray levels divided by each gray level from 0 to 255 of the third image above2 , where p1 and p2 are the pixel probabilities of the two grayscale categories corresponding to the i-th grayscale; m1 and m2 are the pixel means of the two grayscale categories corresponding to the i-th grayscale; m g is the global pixel mean of the third image, and i is an integer; the third image is segmented according to the gray level corresponding to the largest maximum inter-class variance to obtain the fourth image.

[0063] That is to say, there is a segmentation threshold t that divides all pixels of the third image into a grayscale class with a grayscale class smaller than the segmentation threshold t and a grayscale class larger than the segmentation threshold t. The pixel means of the two grayscale classes are m1 and m2 respectively. The pixel probabilities of a grayscale class smaller than the segmentation threshold t and a grayscale class larger than the segmentation threshold t are p1 and p2 respectively. There is p1+p2=1. The global pixel mean m of the third image is g =p1×m1+p2×m2. Calculate the inter-class variance σ when the segmentation threshold t=0, 1, ..., 255 one by one 2 The calculated segmentation threshold t that maximizes the inter-class variance is the optimal segmentation threshold. According to the optimal segmentation threshold, the third image is segmented into two categories: less than the optimal segmentation threshold and greater than the optimal segmentation threshold. Each pixel in the third image whose grayscale value is less than or equal to the optimal segmentation threshold is classified into one category, and the pixel is processed as black. Conversely, the pixel whose grayscale value is greater than the optimal segmentation threshold is classified into another category, and the pixel is processed as white. Then, a binary image after segmentation of the third image is obtained, that is, the fourth image.

[0064] Specifically, Figure 3 As shown, Figure 3 The left side in the middle is the local image of the explosion pile before segmentation. Figure 3 The middle right side is a local image of the explosion pile after segmentation.

[0065] Step S204, performing particle size division according to the connected areas of the fourth image to determine the particle size of the blasted rock in the open-pit coal mine, wherein the connected areas are areas composed of pixels having the same pixel value and adjacent positions.

[0066] Specifically, the connected area of ​​the fourth image is fitted to obtain a minimum fitting ellipse including all pixels in the connected area of ​​the fourth image, wherein the major axis of the minimum fitting ellipse is the maximum particle size of the explosive rock formed in the connected area of ​​the fourth image.

[0067] After image segmentation, the maximum diameter of each rock block is analyzed and counted. The rock diameter obtained by image segmentation is not the actual size of the rock block. The diameter unit of each small rock image obtained by blast pile image segmentation is pixel (px), while the actual size unit of the rock is meter (m), so it is necessary to determine a standard ratio coefficient to convert the image size into the actual size.

[0068] In this application, after the drone collects the image, a detailed three-dimensional model of the explosion pile is obtained through modeling software. In the three-dimensional model of the explosion pile, the distance between any two points can be calculated according to the difference in longitude and latitude. Here, the rock diameter in the three-dimensional model of the explosion pile is represented by the spatial distance between two points of the maximum diameter line segment of the rock, and the ratio of the pixel diameter (px) of the image of the rock in the fourth image segmentation to the actual diameter of the rock in the three-dimensional model of the explosion pile is defined as the standard proportional coefficient for converting the image size into the actual size.

[0069] Step S205, calculate the number of the above-mentioned blast rock particle sizes in the above-mentioned open-pit coal mine, and its proportion in the total number of the preset blast rock block size ranges, to obtain the blast rock block size distribution percentage of the above-mentioned open-pit coal mine, wherein the above-mentioned blast rock block size range is an interval obtained by equidistantly dividing the rock blocks of different particle sizes in the above-mentioned blast area.

[0070] Specifically, according to the ultimate blast rock particle size of the above-mentioned open-pit coal mine, based on the principle of equidistant division, the above-mentioned blast rock fragmentation range of the above-mentioned open-pit coal mine is determined, wherein the above-mentioned ultimate blast rock particle size is the maximum blast rock particle size or the minimum blast rock particle size; based on the above-mentioned blast rock fragmentation range, according to the number of the maximum particle sizes of the above-mentioned blast rock, the blast rock of the above-mentioned open-pit coal mine is divided, and the number of the above-mentioned blast rock particle sizes in the above-mentioned open-pit coal mine is calculated, and the proportion of the total number of the preset blast rock fragmentation range to obtain the blast rock fragmentation distribution percentage of the above-mentioned open-pit coal mine.

[0071] In order to obtain the distribution law of the particle size of the blast pile rock and evaluate the blasting quality of the open-pit coal mine, in this application, the particle size of the blast pile rock is divided based on the maximum mining and loading capacity of the bucket of the open-pit coal mine mining equipment. Specifically,

[0072] According to the formula: Determine the above-mentioned limit blasting rock particle size of the above-mentioned open-pit coal mine, wherein l exceeds limit and represents the above-mentioned limit blasting rock particle size of the above-mentioned open-pit coal mine, and V represents the limit mining volume of the bucket of the mining equipment of the above-mentioned open-pit coal mine, wherein the above-mentioned limit mining volume is the maximum mining volume or the minimum mining volume.

[0073] Then, according to the maximum particle size of the blast rock in the open-pit coal mine, based on the principle of equidistant division, the block size range of the blast rock in the open-pit coal mine is determined; then, based on the block size range of the blast rock and the maximum particle size of the blast rock, the blast rock in the open-pit coal mine is divided to obtain the block size distribution percentage of the blast rock.

[0074] That is to say, [0, l over limit) is divided into multiple intervals according to the equidistant division principle as the blast pile rock fragmentation intervals of the open-pit coal mine. Then, the maximum particle size of the blast pile rock obtained from the connected area in the fourth image is divided according to the intervals to obtain the proportion of the blast pile rock in each blast pile rock fragmentation interval and the particle size distribution law of the blast pile rock fragmentation is obtained.

[0075] In this way, it is possible to provide accurate results of rock block size judgment of blast piles without affecting the mining, loading and transportation production links after blast piles, making the judgment of blast pile block size in open-pit coal mines more convenient and efficient, which is conducive to the rapid and efficient evaluation of the blast pile quality of open-pit mines and provides an important reference basis for the design of blasting parameters in open-pit coal mines.

[0076] The embodiment of the present application also provides an open-pit coal mine blast pile block size judgment system based on image segmentation. It should be noted that the open-pit coal mine blast pile block size judgment system based on image segmentation in the embodiment of the present application can be used to execute the open-pit coal mine blast pile block size judgment method for image segmentation provided in the embodiment of the present application. The open-pit coal mine blast pile block size judgment system based on image segmentation is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been explained will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0077] The following is an introduction to the open-pit coal mine blasting block size determination system based on image segmentation provided in an embodiment of the present application.

[0078] like Figure 4 As shown, the embodiment of the present application also provides an open-pit coal mine blasting block size judgment system based on image segmentation, comprising:

[0079] An image acquisition unit 401 is used to acquire an image of a blast pile in a blast pile area in an open-pit coal mine to obtain a first image; an image preprocessing unit 402 is used to convert the first image into a grayscale image to obtain a second image, and to perform dust removal on the second image to obtain a third image; an image segmentation unit 403 is used to segment the third image based on a maximum inter-class difference method to obtain a fourth image; an blast pile particle size unit 404 is used to divide the particle size according to the connected area of ​​the fourth image to determine the particle size of the blast pile rock in the open-pit coal mine, wherein the connected area is an area composed of pixels having the same pixel value and adjacent positions; an blast pile block size distribution unit 405 is used to calculate the number of the blast pile rock particle sizes in the open-pit coal mine and the proportion of the number of the preset blast pile rock block size intervals to obtain the blast pile rock block size distribution percentage of the open-pit coal mine, wherein the blast pile rock block size interval is an interval obtained by equidistantly dividing rock blocks of different particle sizes in the blast pile area.

[0080] The open-pit coal mine blast pile fragmentation judgment system based on image segmentation provided in the embodiment of the present application can implement the steps and processes of any of the above-mentioned open-pit coal mine blast pile fragmentation judgment methods based on image segmentation, and achieve the same technical effects, which will not be described one by one here.

[0081] The above-mentioned open-pit coal mine blast pile block size judgment system based on image segmentation includes a processor and a memory. The above-mentioned image acquisition unit, image preprocessing unit, image segmentation unit, blast pile particle size unit and blast pile block size distribution unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in the form of any combination.

[0082] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and accurate results of determining the size of the blasted rock can be provided by adjusting kernel parameters.

[0083] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0084] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is running, the device where the computer-readable storage medium is located is controlled to execute the method for determining the blockiness of open-pit coal mine blast piles based on image segmentation.

[0085] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the program executes the method for determining the blockiness of open-pit coal mine blast piles based on image segmentation when running.

[0086] An embodiment of the present invention provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the steps of a method for determining the blockiness of an open-pit coal mine blast pile based on image segmentation are implemented. The device in this article may be a server, a PC, a PAD, a mobile phone, etc.

[0087] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for determining the blockiness of open-pit coal mine blast piles based on image segmentation in each embodiment of the present application are implemented.

[0088] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0089] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0094] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0095] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0097] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for judging the blockiness of open-pit coal mine blast piles based on image segmentation, characterized in that: include: Acquiring an image of a blast pile in a blast pile area in an open-pit coal mine to obtain a first image; Converting the first image into a grayscale image to obtain a second image, and performing dust removal processing on the second image to obtain a third image; Based on the maximum inter-class difference method, segment the third image to obtain a fourth image; Performing particle size division according to the connected area of ​​the fourth image to determine the particle size of the blast pile rock in the open-pit coal mine, wherein the connected area is an area composed of pixels having the same pixel value and adjacent positions; Calculate the proportion of the particle size of the blast pile rocks in the open-pit coal mine in the total number of blast pile rock fragmentation intervals, and obtain the blast pile rock fragmentation distribution percentage of the open-pit coal mine, wherein the blast pile rock fragmentation interval is an interval obtained by equidistantly dividing the rock blocks of different particle sizes in the blast pile area.

2. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 1 is characterized in that: The explosion pile image is collected in the explosion pile area in the open-pit coal mine to obtain a first image, including: Before the blasting operation is carried out in the open-pit coal mine, a plurality of image control points are arranged at the four corners of the estimated blasting area; The first image is obtained by collecting blast pile images of blast pile blocks in the blast pile area of ​​the open-pit coal mine using a drone, wherein the first image contains a plurality of image control points, and each of the image control points is not less than 150 pixels away from the edge of the first image.

3. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 1 is characterized in that: The first image is converted into a grayscale image to obtain a second image, and the second image is subjected to dust removal processing to obtain a third image, including: According to the formula: Y=0.299R+0.587G+0.114B, the first image is converted into a grayscale image to obtain the second image, wherein Y represents the grayscale value of the second image; R, G, and B represent the values ​​of the red, green, and blue color channels in the first image, respectively; Based on a histogram equalization method, a dust removal operation is performed on the second image to obtain the third image.

4. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 3 is characterized in that: Based on a histogram equalization method, performing a dust removal operation on the second image to obtain the third image includes: Acquire a grayscale histogram of the second image; Based on the grayscale histogram, determining a probability accumulation value of each grayscale level in the second image; According to the formula: SS(k)=int(max(pix)-min(pix))×S(k)+0.5, the dust removal operation is performed on the second image to obtain the third image, wherein SS(k) represents the new grayscale of the kth grayscale in the second image after the equalization operation is performed on the third image, pix represents the grayscale value in the second image, max(pix) and min(pix) represent the maximum grayscale value and the minimum grayscale value of all pixels in the second image respectively; S(k) represents the probability accumulation value of the kth grayscale in the second image, k∈(0~N), N=255, k is an integer.

5. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 4 is characterized in that: Determining a probability accumulation value of each gray level in the second image based on the gray level histogram includes: According to the formula: Determine the pixel probability p(j) of gray level j in the gray level histogram corresponding to the second image, where n j represents the number of pixels of gray level j in the second image, N represents the total number of pixels in the second image, j∈(0~N), N=255, j and N are both integers; According to the formula: Calculate the probability cumulative value S(k) of the kth gray level in the gray histogram corresponding to the second image, where k∈(0-N) is a positive integer.

6. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 1 is characterized in that: Based on the maximum inter-class difference method, the third image is segmented to obtain a fourth image, including: Obtaining the number of pixels in each gray level from 0 to 255 in the third image, and obtaining the proportion of each gray level in the third image; Dividing each grayscale level of the third image from 0 to 255 into two grayscale levels; According to the formula: Calculate the maximum inter-class variance σ between the two gray levels divided by each gray level from 0 to 255 of the third image 2 , where p1 and p2 are the pixel probabilities of the two grayscale categories corresponding to the i-th grayscale; m1 and m2 are the pixel means of the two grayscale categories corresponding to the i-th grayscale; m g is the global pixel mean of the third image, and i is an integer; The third image is segmented according to the gray level corresponding to the largest maximum between-class variance to obtain the fourth image.

7. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 1 is characterized in that: The particle size division is performed according to the connected area of ​​the fourth image to determine the particle size of the blast pile rock of the open-pit coal mine, including: The connected area of ​​the fourth image is fitted to obtain a minimum fitting ellipse including all pixels in the connected area of ​​the fourth image, wherein the major axis of the minimum fitting ellipse is the maximum particle size of the explosive rock formed in the connected area of ​​the fourth image.

8. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 7 is characterized in that: Calculating the proportion of the particle size of the blast pile rock in the open-pit coal mine to the total number of the blast pile rock fragmentation range in the preset blast pile rock fragmentation range, and obtaining the blast pile rock fragmentation distribution percentage of the open-pit coal mine, including: According to the limit blast pile rock particle size of the open-pit coal mine, based on the equidistant division principle, determine the blast pile rock block size range of the open-pit coal mine, wherein the limit blast pile rock particle size is the maximum blast pile rock particle size or the minimum blast pile rock particle size; Based on the blast rock fragmentation range, the blast rock of the open-pit coal mine is divided according to the number of maximum particle sizes of the blast rock, and the number of particle sizes of the blast rock in the open-pit coal mine is calculated, and the proportion of the particle size of the blast rock in the total number of the preset blast rock fragmentation range is calculated to obtain the blast rock fragmentation distribution percentage of the open-pit coal mine.

9. The method for determining the blockiness of open-pit coal mine blast piles based on image segmentation according to claim 8, characterized in that: Before determining the particle size range of the blast pile rock of the open-pit coal mine based on the principle of equidistant division according to the limit blast pile rock particle size of the open-pit coal mine, the method further includes: According to the formula: Determine the limit blast rock particle size of the open-pit coal mine, wherein l exceeds limit and represents the limit blast rock particle size of the open-pit coal mine, and V represents the limit mining volume of the excavation equipment bucket of the open-pit coal mine, wherein the limit mining volume is the maximum mining volume or the minimum mining volume.

10. A system for judging the blockiness of open-pit coal mine blast piles based on image segmentation, characterized in that: include: An image acquisition unit is used to acquire an image of a blast pile in a blast pile area in an open-pit coal mine to obtain a first image; An image preprocessing unit, configured to convert the first image into a grayscale image to obtain a second image, and perform dust removal processing on the second image to obtain a third image; An image segmentation unit, configured to segment the third image based on a maximum inter-class difference method to obtain a fourth image; A blast pile particle size unit, used to perform particle size division according to the connected area of ​​the fourth image to determine the particle size of the blast pile rock of the open-pit coal mine, wherein the connected area is an area composed of pixels having the same pixel value and adjacent positions; The blast pile fragmentation distribution unit is used to calculate the proportion of the number of blast pile rock particle sizes in the open-pit coal mine in the total number of blast pile rock fragmentation intervals, and obtain the blast pile rock fragmentation distribution percentage of the open-pit coal mine, wherein the blast pile rock fragmentation interval is an interval obtained by equidistantly dividing the rock blocks of different particle sizes in the blast pile area.

Images