A drilling depth statistics method and system based on target detection

Abstract

The present invention relates to a drilling depth statistics method and system based on target detection. The method comprises: inputting an image frame of a drilling rig into a pre-trained target detection model, identifying the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtaining a first recognition result; calculating the pixel distance between the plug and the tail of the drill rod according to the first recognition result; if the difference between the pixel distance between the plug and the tail of the drill rod in the image frame and the previous frame is greater than a preset threshold, the number of drill rods is increased by 1; and the drilling depth is calculated according to the known length of the drill rod and the number of drill rods. The scheme provided by the present invention can realize real-time, efficient and accurate drilling statistics, and has the advantages of strong pertinence, high recognition rate and strong generalization ability. Compared with traditional methods, the real-time performance of drilling depth statistics can be greatly improved, the statistical accuracy can be improved, and the labor cost can be reduced. In addition, the scheme does not require hardware changes to the existing drilling rig equipment, thereby reducing the transformation cost.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and mining and excavation, and in particular to a drilling depth statistics method and system based on target detection. Background Art

[0002] With the development of artificial intelligence and 5G technologies, artificial intelligence is increasingly being used in the energy sector. my country is a major energy country, and energy mining safety is an issue that the industry attaches great importance to. Water exploration and release operations are an important means to ensure the safety of energy mining. By developing a statistical algorithm for the depth of water exploration and release drilling, we can improve statistical accuracy, improve underground construction standards, and reduce labor costs. This will help reduce labor costs while improving safety.

[0003] At present, the statistical methods of water exploration and release drilling depth are mainly divided into traditional statistical methods, external auxiliary statistics and front-up rod water exploration and release statistical methods. Among them, the traditional statistical method is mainly to complete the statistics of water exploration and release drilling depth through manual counting and reporting by underground workers, and then through historical video verification by workers on the well. This method has the disadvantages of workers' misreporting, concealment, long statistical time, and high labor costs. The external auxiliary statistical method mainly achieves water exploration and release statistics by adjusting the drilling rig structure and installing sensors, but this type of method has the disadvantages of high construction difficulty, non-compliance with the safety certification of auxiliary equipment, and high transformation cost. The front-up rod water exploration and release statistical method realizes drilling rod statistics by switching the state of the statistical probe rod, but this method is suitable for scenes with fixed front-up rod features. The camera angle of the rear-up rod drilling rig changes greatly, and the feature gap is obvious. This method has problems such as insufficient recognition rate. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present invention provides a drilling depth statistics method and system based on target detection.

[0005] According to a first aspect of an embodiment of the present invention, a drilling depth statistics method based on target detection is provided, comprising:

[0006] Inputting the image frame of the drilling rig into a pre-trained target detection model, identifying the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtaining a first recognition result;

[0007] Calculate the pixel distance between the plug and the tail of the drill pipe according to the first recognition result;

[0008] If the difference between the pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold, the number of drill rods is increased by 1;

[0009] The drilling depth is calculated based on the known drill rod length and the number of drill rods.

[0010] Furthermore, before determining the pixel distance between the plug and the tail of the drill pipe according to the first recognition result, the method further includes:

[0011] Calculating an average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame;

[0012] Determining the pixel distance between the plug and the tail of the drill pipe according to the first recognition result specifically includes:

[0013] The pixel distance between the plug and the tail of the drill rod is calculated according to the average value of the coordinates of the drill plug and the coordinates of the tail of the drill rod.

[0014] Furthermore, before calculating the pixel distance between the plug and the tail of the drill pipe according to the first recognition result, the method further includes:

[0015] Identify the coordinates of the drill pipe tail of the drilling rig and the main machine in the image frame and the previous image frame separated by a preset number of frames to obtain a second identification result;

[0016] Determining whether the coordinates of the drill pipe tail in the first recognition result are valid according to the second recognition result;

[0017] If it is valid, the step of calculating the pixel distance between the plug and the tail of the drill rod according to the first recognition result is executed; otherwise, it is not executed.

[0018] Further, judging whether the coordinates of the drill pipe tail in the first recognition result are valid according to the second recognition result specifically includes:

[0019] Calculate the motion vectors of the drill rod tail and the main machine according to the coordinates of the drill rod tail and the main machine in the image frame and the previous image frames separated by a preset number of frames;

[0020] Whether the coordinates of the drill rod tail in the first recognition result are valid is determined according to the angle between the motion vectors of the drill rod tail and the host.

[0021] According to a second aspect of an embodiment of the present invention, a drilling depth statistics system based on target detection is provided, comprising:

[0022] An object recognition module, used to input the image frame of the drilling rig into a pre-trained object detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result;

[0023] A distance calculation module, used for calculating the pixel distance between the plug and the tail of the drill pipe according to the first recognition result;

[0024] A drill rod technology module, for increasing the number of drill rods by 1 if the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold;

[0025] The depth calculation module is used to calculate the drilling depth according to the known drill rod length and the number of drill rods.

[0026] Furthermore, the system includes:

[0027] A plug coordinate calculation module, used for calculating the average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame before the distance calculation module calculates the pixel distance between the plug and the tail of the drill rod according to the first recognition result;

[0028] The distance calculation module is specifically used for:

[0029] The pixel distance between the plug and the tail of the drill rod is calculated according to the average value of the coordinates of the drill plug and the coordinates of the tail of the drill rod.

[0030] Furthermore, the object recognition module is also used for:

[0031] Identify the coordinates of the drill pipe tail of the drilling rig and the main machine in the image frame and the previous image frame separated by a preset number of frames to obtain a second identification result;

[0032] The system further comprises:

[0033] A drill rod tail coordinate screening module, used for judging whether the coordinates of the drill rod tail in the first recognition result are valid according to the second recognition result;

[0034] The distance calculation module is used to calculate the pixel distance between the plug and the drill rod tail according to the first recognition result if the drill rod tail coordinate screening module determines that the coordinates of the drill rod tail in the first recognition result are valid.

[0035] Furthermore, the drill pipe tail coordinate screening module specifically includes:

[0036] A motion vector calculation unit, used to calculate the motion vector of the drill rod tail and the main machine according to the coordinates of the drill rod tail and the main machine in the image frame and the previous image frames separated by a preset number of frames;

[0037] The angle judgment unit is used to judge whether the coordinates of the drill rod tail in the first recognition result are valid according to the angle between the motion vectors of the drill rod tail and the main machine.

[0038] According to a third aspect of an embodiment of the present invention, a terminal device is provided, including:

[0039] Processor; and

[0040] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0041] According to a fourth aspect of an embodiment of the present invention, there is provided a non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method as described above.

[0042] The technical solution provided by the embodiment of the present invention uses existing cameras to collect images of the drilling rig during the drilling process such as water exploration and drainage, extracts the characteristic information of the key equipment of the drilling rig through the target detection algorithm, and combines the action rules of the rear-upper-pole construction to design a drilling depth statistics algorithm for the rear-upper-pole drilling rig, so as to achieve real-time, efficient and accurate drilling statistics, and has the advantages of strong pertinence, high recognition rate and strong generalization ability. Compared with traditional methods, it can greatly improve the real-time performance of drilling depth statistics, improve statistical accuracy and reduce labor costs. In addition, this solution does not require hardware changes to existing drilling rig equipment, reducing transformation costs.

[0043] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.

[0045] Figure 1 is a flow chart of a drilling depth statistics method based on target detection according to an exemplary embodiment of the present invention;

[0046] Figure 2 For yolov4 framework;

[0047] Figure 3 Mark the characteristic points of the drilling rig;

[0048] Figure 4 The schematic diagram for camera installation is as follows;

[0049] Figure 5 This is a schematic diagram of the framework of the statistical model for water exploration and release;

[0050] Figure 6 It is a schematic diagram showing the structure of a computing device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0051] The preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0052] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0053] It should be understood that although the terms "first", "second", "third", etc. may be used to describe various information in the present invention, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0054] The hardware devices involved in the present invention include cameras, GPU servers, etc., wherein the camera can select the existing network camera in the mine, which is responsible for image acquisition, and the camera can be installed on the side of the drilling rig to ensure that the drilling rig is within the field of view of the camera. The GPU server completes the algorithm reasoning and is placed in the machine room above the well. The embodiment of the present invention is applied to the GPU server, and the technical solution of the embodiment of the present invention is described in detail below with reference to the accompanying drawings.

[0055] like Figure 3 As shown, the main components of the rear-up rod drilling rig include a head, a main machine, and a drill rod, wherein the head is installed in front of the drilling rig to control the drilling direction, and the main machine is installed on a guide rail and clamps the drill rod. Through reciprocating motion, the drill rod is driven to move to achieve drilling. Specifically, the main machine drives the drill rod to move toward the head, so that the drill rod drills into the wall. After that, the main machine retreats, reconnects a drill rod, and moves toward the head again. This reciprocating motion is repeated. As the number of drill rods driven in increases, the drilling depth can be increased accordingly.

[0056] In the embodiment of the present invention, it is necessary to collect images of the drilling rig during the drilling process such as water exploration and drainage through a network camera installed at the drilling site of the mine, extract feature information of key equipment such as the drilling rig's plug, main machine and drill rod through the target detection algorithm pre-set in the GPU server, and design a drilling depth statistics algorithm for the rear-upper-rod drilling rig in combination with the rear-upper-rod construction action rules.

[0057] Figure 1 It is a flowchart of a drilling depth statistics method based on target detection according to an exemplary embodiment of the present invention.

[0058] See also Figure 1 , the method comprising:

[0059] 110. Input the image frame of the drilling rig into a pre-trained target detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result;

[0060] Specifically, a target detection model is obtained by pre-training the features of the plug and the tail of the drill rod of the rear-up rod drilling rig. The target training model here can be implemented using existing models such as yolov4. The trained yolov4 model can extract statistical information such as the category and quantity of the plug and the tail of the drill rod in the image frame, as well as geometric information such as the size and spatial coordinates of each feature.

[0061] 120. Calculate the pixel distance between the plug and the tail of the drill pipe according to the first recognition result;

[0062] In this step, the distance between the center points of the identified marking frames of the plug and the tail of the drill rod may be used as the pixel distance between the plug and the tail of the drill rod.

[0063] 130. If the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold, the number of drill rods is increased by 1;

[0064] Specifically, when drilling, the tail of the drill rod will move toward the plug, and the distance between the tail of the drill rod and the plug will decrease. Correspondingly, in the image, the pixel distance between the tail of the drill rod and the plug becomes smaller. Therefore, in this step, by judging whether the difference in pixel distance between the plug and the tail of the drill rod in two adjacent frames exceeds a preset threshold, it can be judged whether the number of drill rods used for drilling has increased.

[0065] 140. Calculate the drilling depth based on the known drill rod length and the number of drill rods.

[0066] Specifically, since the length of the drill rod is known, in this step, the water exploration depth at the current moment can be calculated according to the length of the drill rod on site multiplied by the number of drill rods, thereby realizing drilling depth statistics.

[0067] The technical solution provided by the embodiment of the present invention has the following advantages:

[0068] 1. Compared with traditional methods: This solution uses cameras to collect images and uses algorithms to analyze drilling depth instead of traditional methods such as manual rod counting and video verification. It can greatly improve the real-time nature of water exploration and release statistics, improve statistical accuracy, and reduce labor costs.

[0069] 2. Compared with the method of adding peripherals: this solution does not require hardware changes to the existing water exploration and release equipment, reducing the cost of transformation.

[0070] 3. Compared with the front-up rod type water exploration and release statistics method: The front-up rod type water exploration and release statistics method performs drill rod statistics by identifying whether there is a drill rod on the drilling rig with the something (with drill rod) and nothing (without drill rod) features. In the rear-up rod type water exploration and release scenario, this scheme collects head, machine, and tail features instead of the something and nothing features of the front rod. The features collected in this scheme are more obvious, with low generalization difficulty, and have the advantages of strong targeting, high recognition rate, and strong generalization ability.

[0071] Optionally, as an embodiment of the present invention, the method includes:

[0072] 210. Input the image frame of the drilling rig into a pre-trained target detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result;

[0073] 220. Calculate the average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame;

[0074] 230. Calculate the pixel distance between the plug and the tail of the drill rod according to the average coordinates of the drill plug and the coordinates of the tail of the drill rod.

[0075] 240. If the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold, the number of drill rods is increased by 1;

[0076] 250. Calculate the drilling depth based on the known drill rod length and the number of drill rods.

[0077] In this embodiment, by calculating the average value of the coordinates of the drilling rig plug in a preset number of image frames, interference caused by factors such as image jitter can be reduced and the accuracy of the calculation can be improved.

[0078] Optionally, in this embodiment, the method further includes:

[0079] 310. Input the image frame of the drilling rig into a pre-trained target detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result; and identify the coordinates of the tail of the drill rod and the host machine in the image frame and the image frame separated by a preset number of frames, and obtain a second recognition result;

[0080] 320. Determine whether the coordinates of the drill pipe tail in the first recognition result are valid according to the second recognition result;

[0081] 330. If valid, calculate the pixel distance between the plug and the tail of the drill pipe according to the first recognition result;

[0082] 340. If the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold, the number of drill rods is increased by 1;

[0083] 350. Calculate the drilling depth based on the known drill rod length and the number of drill rods.

[0084] In this embodiment, in order to prevent mine workers from moving the drill rod with their hands, which may cause drill rod counting errors, the algorithm accuracy is improved by screening the valid coordinate values ​​of the tail of the drill rod.

[0085] Optionally, in this embodiment, step 320 specifically includes:

[0086] 3201. Calculate the motion vectors of the drill pipe tail and the main machine according to the coordinates of the drill pipe tail and the main machine in the image frame and the previous image frames separated by a preset number of frames;

[0087] 3202. Determine whether the coordinates of the drill pipe tail in the first recognition result are valid based on the angle between the motion vectors of the drill pipe tail and the host.

[0088] Since the movement directions of the drill pipe tail and the main machine are basically the same during normal drilling, in this embodiment, by calculating the angle between the movement vectors of the drill pipe tail and the main machine, it is possible to determine whether the movement directions of the two are the same, thereby realizing the validity judgment of the coordinates of the drill pipe tail.

[0089] A specific example is described below.

[0090] First, the Yolov4 algorithm is used to train the features of the rear-end drilling rig plug, main engine, and drill rod. The Yolov4 framework is as follows: Figure 2 shown.

[0091] like Figure 3As shown, through the trained yolov4 model, this method can extract statistical information such as the category and quantity of the plug (head), main machine (machine), and drill pipe tail (tail), as well as the size of each feature and the geometric information of the spatial coordinates.

[0092] like Figure 4 As shown, the camera is mounted on the side of the drilling rig to ensure that the head and machine features are always within the camera's field of view. In the second half of the drilling stroke, the tail must be within the camera's field of view.

[0093] Figure 5 This is a schematic diagram of the water exploration and release model framework. Figure 5 As shown in the figure, at the beginning of water exploration, the model initialization length mark (pd) is 10000 pixels, which is used to record the pixel distance between the tail of the drill pipe and the plug in the previous frame image. The coordinates of the head feature of 25 frames are collected and the average value (Formula 1-1) is calculated as the effective coordinates of the head feature.

[0094]

[0095] Among them, x1…x 25 Indicates the x coordinate of the head in 25 consecutive frames of images, x m Represents the average x-coordinate of the head feature. m Represents the average y-coordinate of the head feature.

[0096] By collecting the spatial coordinates of machine and tail features for 75 consecutive frames, extracting the coordinates of the first and last frames, and calculating the motion vectors of machine and tail, we determine whether the movement of tail and machine is in the same direction by calculating the cosθ (>0.75) value of the vector (Formula 1-2), and then filter out the valid tail coordinates.

[0097] cosθ=V m ·V t / |V m |*|V t | Formula 1-2

[0098] Among them, V m 、V t Respectively represent the running vectors of the machine and the tail of the drill pipe in the first and last frames of images. m ·V t is the inner product of the machine and tail motion vectors, |V m |*|V t | is the product of the movement distance of machine and tail.

[0099] Based on the extraction of the above effective head coordinates and effective tail coordinates, the Euclidean distance L of the head and tail is calculated by the norm operator (Formula 1-3). If L≤pd+200, the number of rods remains unchanged. When L>pd+200, the number of drill rods is increased by 1 (Formula 1-4), and pd=L is finally updated.

[0100]

[0101]

[0102] Where L represents the Euclidean distance from the plug head to the tail of the drill pipe. n is the number of drill pipes that have been completed in the drilling operation at the current moment.

[0103] The length of the drill rod on site, l, is multiplied by the number of drill rods, n, and the current water exploration depth is calculated to achieve drilling depth statistics.

[0104] This solution uses existing cameras to collect water exploration and release images, extracts key equipment feature information of the drilling rig through the target detection yolov4 algorithm, and designs a statistical algorithm for the depth of water exploration and release drilling for the rear upper pole in combination with the construction action rules of the rear upper pole, so as to achieve real-time, efficient and accurate drilling statistics. Under the premise that the scene meets the basic recognition requirements, the algorithm accuracy of this solution is >95% and the delay is <1s.

[0105] Corresponding to the above method embodiment, an embodiment of the present invention provides a drilling depth statistics system based on target detection, comprising:

[0106] An object recognition module, used to input the image frame of the drilling rig into a pre-trained object detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result;

[0107] A distance calculation module, used for calculating the pixel distance between the plug and the tail of the drill pipe according to the first recognition result;

[0108] A drill rod technology module, for increasing the number of drill rods by 1 if the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold;

[0109] The depth calculation module is used to calculate the drilling depth according to the known drill rod length and the number of drill rods.

[0110] Optionally, in this embodiment, the system further includes:

[0111] A plug coordinate calculation module, used for calculating the average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame before the distance calculation module calculates the pixel distance between the plug and the tail of the drill rod according to the first recognition result;

[0112] The distance calculation module is specifically used for:

[0113] The pixel distance between the plug and the tail of the drill rod is calculated according to the average value of the coordinates of the drill plug and the coordinates of the tail of the drill rod.

[0114] Optionally, in this embodiment, the object recognition module is further used to:

[0115] Identify the coordinates of the drill pipe tail of the drilling rig and the main machine in the image frame and the previous image frame separated by a preset number of frames to obtain a second identification result;

[0116] The system further comprises:

[0117] A drill rod tail coordinate screening module, used for judging whether the coordinates of the drill rod tail in the first recognition result are valid according to the second recognition result;

[0118] The distance calculation module is used to calculate the pixel distance between the plug and the drill rod tail according to the first recognition result if the drill rod tail coordinate screening module determines that the coordinates of the drill rod tail in the first recognition result are valid.

[0119] Optionally, in this embodiment, the drill pipe tail coordinate screening module specifically includes:

[0120] A motion vector calculation unit, used to calculate the motion vector of the drill rod tail and the main machine according to the coordinates of the drill rod tail and the main machine in the image frame and the previous image frames separated by a preset number of frames;

[0121] The angle judgment unit is used to judge whether the coordinates of the drill rod tail in the first recognition result are valid according to the angle between the motion vectors of the drill rod tail and the main machine.

[0122] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0123] Figure 6 It is a schematic diagram showing the structure of a computing device according to an exemplary embodiment of the present invention.

[0124] See also Figure 6 , the computing device 600 includes a memory 610 and a processor 620 .

[0125] The processor 620 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0126] The memory 610 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. Among them, ROM can store static data or instructions required by the processor 620 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 610 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 610 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0127] The memory 610 stores executable codes, and when the executable codes are processed by the processor 620 , the processor 620 can execute part or all of the above-mentioned methods.

[0128] In addition, the method according to the present invention may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing part or all of the steps in the above method of the present invention.

[0129] Alternatively, the present invention may also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or computing device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present invention.

[0130] The scheme of the present invention has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the specification are not necessarily required by the present invention. In addition, it can be understood that the steps in the method of the embodiment of the present invention can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present invention can be merged, divided and deleted according to actual needs.

[0131] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or a combination of both.

[0132] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A drilling depth statistics method based on target detection, characterized in that: include: Inputting the image frame of the drilling rig into a pre-trained target detection model, identifying the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtaining a first recognition result; Calculating an average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame; Calculating the pixel distance between the plug and the tail of the drill rod according to the first recognition result, specifically comprising: calculating the pixel distance between the plug and the tail of the drill rod according to the average value of the coordinates of the drill plug and the coordinates of the tail of the drill rod; If the difference between the pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold, the number of drill rods is increased by 1; The drilling depth is calculated based on the known drill rod length and the number of drill rods.

2. The method according to claim 1, characterized in that Before calculating the pixel distance between the plug and the tail of the drill pipe according to the first recognition result, the method further includes: Identify the coordinates of the drill pipe tail of the drilling rig and the main machine in the image frame and the previous image frame separated by a preset number of frames to obtain a second identification result; Determining whether the coordinates of the drill pipe tail in the first recognition result are valid according to the second recognition result; If it is valid, the step of calculating the pixel distance between the plug and the tail of the drill rod according to the first recognition result is executed; otherwise, it is not executed.

3. The method according to claim 2, characterized in that The determining, according to the second recognition result, whether the coordinates of the drill pipe tail in the first recognition result are valid specifically includes: Calculate the motion vectors of the drill rod tail and the main machine according to the coordinates of the drill rod tail and the main machine in the image frame and the previous image frames separated by a preset number of frames; Whether the coordinates of the drill rod tail in the first recognition result are valid is determined according to the angle between the motion vectors of the drill rod tail and the host.

4. A drilling depth statistics system based on target detection, characterized in that: include: An object recognition module, used to input the image frame of the drilling rig into a pre-trained object detection model, identify the coordinates of the plug and the tail of the drill rod of the drilling rig in the image frame, and obtain a first recognition result; A plug coordinate calculation module, used for calculating the average value of the coordinates of the drilling rig plug in a preset number of image frames before the image frame before the distance calculation module calculates the pixel distance between the plug and the tail of the drill rod according to the first recognition result; a distance calculation module, used to calculate the pixel distance between the plug and the tail of the drill rod according to the first recognition result, specifically used to: calculate the pixel distance between the plug and the tail of the drill rod according to the average value of the coordinates of the drilling rig plug and the coordinates of the tail of the drill rod; A drill rod technology module, for increasing the number of drill rods by 1 if the difference in pixel distance between the plug and the tail of the drill rod in the image frame and the previous image frame is greater than a preset threshold; The depth calculation module is used to calculate the drilling depth according to the known drill rod length and the number of drill rods.

5. The system according to claim 4, characterized in that The object recognition module is further used for: Identify the coordinates of the drill pipe tail of the drilling rig and the main machine in the image frame and the previous image frame separated by a preset number of frames to obtain a second identification result; The system further comprises: A drill rod tail coordinate screening module, used for judging whether the coordinates of the drill rod tail in the first recognition result are valid according to the second recognition result; The distance calculation module is used to calculate the pixel distance between the plug and the drill rod tail according to the first recognition result if the drill rod tail coordinate screening module determines that the coordinates of the drill rod tail in the first recognition result are valid.

6. The system according to claim 5, characterized in that The drill pipe tail coordinate screening module specifically includes: A motion vector calculation unit, used to calculate the motion vector of the drill rod tail and the main machine according to the coordinates of the drill rod tail and the main machine in the image frame and the previous image frames separated by a preset number of frames; The angle judgment unit is used to judge whether the coordinates of the drill rod tail in the first recognition result are valid according to the angle between the motion vectors of the drill rod tail and the main machine.

7. A terminal device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 3.

8. A non-transitory machine-readable storage medium having executable code stored thereon, characterized in that: When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 3.

Images