Well depth detection method and device, computer device and storage medium
By using machine intelligence to identify well depth and calculating it using chemical dosing videos and design data, the problem of low efficiency in manual quality inspection has been solved, achieving efficient and accurate well depth detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA NAT PETROLEUM CORP
- Filing Date
- 2024-11-28
- Publication Date
- 2026-05-29
Smart Images
Figure CN122115299A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of seismic exploration technology, and in particular to a method, apparatus, computer equipment, and storage medium for detecting well depth. Background Technology
[0002] Well-shot induction plays a crucial role in oil seismic exploration. Specifically, explosives are lowered to a certain depth in the well and detonated. The resulting seismic waves propagate underground and are received by geophones placed on the surface. The detonation depth refers to the depth to which the explosives are lowered during well-shot induction, which affects the quality and safety of the process.
[0003] Currently, quality inspection of well depths for chemical injection is mostly carried out by recording construction videos on-site and then conducting manual inspections afterwards. However, this method requires a large number of quality inspectors, has high labor costs, low efficiency, and a long inspection cycle, and cannot meet the needs of timely guidance for field construction. Summary of the Invention
[0004] This application provides a method, apparatus, computer equipment, and storage medium for detecting well depth, transforming manual identification into machine intelligent identification. This reduces the need for quality inspectors, saves labor costs, and effectively improves the efficiency of quality inspection of well depths after chemical treatment. The technical solution is as follows:
[0005] On the one hand, a method for detecting well depth is provided, the method comprising:
[0006] Acquire drug administration video and design data, wherein the drug administration video is used to record the drug administration process;
[0007] Based on the drug delivery video, the horizontal coordinate of the wellhead, the vertical coordinate of the wellhead, the displayed height of the target operator, and the motion trajectory curve of the drug delivery rod are determined. The motion trajectory curve is used to reflect the position change of the upper end of the drug delivery rod over time during the drug delivery process.
[0008] Based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive string, the depth of the explosive well is determined. The depth of the explosive well is the sum of the reference length of the explosive string and the length of the explosive rod inside the well. The length of the explosive rod inside the well is the difference between the total length of the explosive rod and the length of the explosive rod outside the well at the end of the rod insertion.
[0009] Based on the design data and the well depth, the detection results of the drug delivery video are generated.
[0010] In some embodiments, the process of determining the wellhead abscissa based on the drug delivery video includes:
[0011] Based on the drug dispensing video, the projection distribution data of the drug dispensing rod is determined. The projection distribution data is used to reflect the number of times the drug dispensing rod is projected at each horizontal axis. The number of times the drug dispensing rod is projected at any horizontal axis is used to indicate the number of times the drug dispensing rod appears at the position corresponding to that horizontal axis in multiple video images of the drug dispensing video.
[0012] Based on the projection distribution data, the wellhead abscissa is determined. The wellhead abscissa is the median abscissa within the effective projection interval. The effective projection interval includes the abscissa corresponding to when the number of times the injection rod is projected is greater than a preset threshold.
[0013] In some embodiments, the wellhead ordinate is the average of the wellhead ordinates in multiple video images of the drug delivery video; the process of determining the wellhead ordinate in any video image of the drug delivery video includes:
[0014] Two candidate operators are identified in the video image, and the distance between the two candidate operators and the wellhead is smaller than the distance between the other operators in the video image and the wellhead.
[0015] Based on the foot coordinates of each candidate operator, the wellhead coordinates in the video image are determined, and the wellhead coordinates in the video image are the median of the foot coordinates of the two candidate operators.
[0016] In some embodiments, the displayed height of the target operator is the average of the displayed heights of the target operator in multiple video images of the drug administration video; the process of determining the displayed height of the target operator in any video image of the drug administration video includes:
[0017] Two candidate operators are identified in the video image, and the distance between the two candidate operators and the wellhead is smaller than the distance between the other operators in the video image and the wellhead.
[0018] Based on the head and foot coordinates of each candidate operator, the target operator in the video image is selected from the two candidate operators. The target operator in the video image is the operator in a standing posture.
[0019] The displayed height of the target operator in the video image is determined, and the displayed height of the target operator in the video image is the distance between the vertical coordinate of the target operator's head and the vertical coordinate of the feet in the video image.
[0020] In some embodiments, selecting the target operator from the two candidate operators based on the head and foot coordinates of each candidate operator includes:
[0021] Based on the head and foot coordinates of each candidate operator, the displayed height of each candidate operator is determined. The displayed height of any candidate operator is the distance between the head and foot coordinates of the target operator.
[0022] Based on the displayed height of the two candidate operators and the vertical coordinate of their heads, the target operator in the video image is selected from the two candidate operators.
[0023] In some embodiments, determining the two candidate operators in the video image includes:
[0024] Determine the number of operators appearing in the video image;
[0025] When the number of people is equal to two, the two operators appearing in the video image are identified as the two candidate operators;
[0026] If the number of people is greater than two, the two candidate operators are selected from the multiple operators based on the distance between the multiple operators appearing in the video image and the wellhead.
[0027] In some embodiments, determining the well depth based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive charge includes:
[0028] Based on the motion trajectory curve, determine the number of drug-feeding rods and the ordinate of the upper end of the drug-feeding rod at the end of the feeding.
[0029] The length of the external explosive rod is determined based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, and the ordinate of the upper end of the explosive rod.
[0030] Based on the number of feeding rods and the reference length of the pressing rod, the total length of the pressing rod is determined, and the total length of the pressing rod is the product of the number of feeding rods and the reference length of the pressing rod.
[0031] The depth of the well for drug delivery is determined based on the total length of the drug delivery rod, the length of the drug delivery rod outside the well, and the reference length of the drug string.
[0032] In some embodiments, the process of determining the number of bait sticks based on the motion trajectory curve includes:
[0033] Determine the drug placement segment point in the motion trajectory curve, where the drug placement segment point is the starting point for placing each drug-pressing rod;
[0034] Based on the drug dispensing segment points, the number of drug dispensing rods is determined, where the number of drug dispensing rods is the number of drug dispensing segment points.
[0035] In some embodiments, determining the length of the external explosive rod based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, and the ordinate of the upper end of the explosive rod includes:
[0036] Based on the wellhead ordinate and the upper ordinate of the charging rod, the displayed length of the charging rod outside the well is determined when the rod is lowered. The displayed length of the charging rod outside the well is the distance between the upper ordinate of the charging rod and the wellhead ordinate.
[0037] Based on the displayed height of the target operator, the reference height of the target operator, and the displayed length of the external injection rod, the length of the external injection rod is determined. The length of the external injection rod is the product of the ratio of the displayed length of the external injection rod and the displayed height of the target operator and the reference height of the target operator.
[0038] In some embodiments, after obtaining the drug administration video and design information, the method further includes:
[0039] Process any video image in a drug administration video to obtain a processed video image;
[0040] Determine the average amplitude value in the processed video image;
[0041] If the average amplitude value is greater than a preset threshold, the drug administration video is retained;
[0042] If the average amplitude value is not greater than the preset threshold, the drug administration video is discarded.
[0043] The processing steps include Fourier transform, removal of low-frequency signals, and inverse Fourier transform.
[0044] On the other hand, a well depth detection device is provided, the device comprising:
[0045] The acquisition module is used to acquire drug administration video and design data, wherein the drug administration video is used to record the drug administration process;
[0046] The parameter determination module is used to determine the wellhead horizontal coordinate, wellhead vertical coordinate, the displayed height of the target operator, and the motion trajectory curve of the pressure rod based on the drug delivery video. The motion trajectory curve is used to reflect the position change of the upper end of the pressure rod over time during the drug delivery process.
[0047] The well depth determination module is used to determine the depth of the well for dropping chemicals based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the chemical string. The depth of the well for dropping chemicals is the sum of the reference length of the chemical string and the length of the in-well pressure rod. The length of the in-well pressure rod is the difference between the total length of the pressure rod and the length of the external pressure rod at the end of the dropping process.
[0048] The result determination module is used to generate the detection results of the drug delivery video based on the design data and the drug delivery well depth.
[0049] In some embodiments, the parameter determination module is used to determine the projection distribution data of the injection rod based on the injection video. The projection distribution data reflects the number of injection rod projections corresponding to each horizontal coordinate. The number of injection rod projections corresponding to any horizontal coordinate represents the number of times the injection rod appears at the position corresponding to that horizontal coordinate in multiple video images of the injection video. Based on the projection distribution data, the wellhead horizontal coordinate is determined. The wellhead horizontal coordinate is the median horizontal coordinate within the effective projection interval. The effective projection interval includes the horizontal coordinate corresponding to when the number of injection rod projections is greater than a preset threshold.
[0050] In some embodiments, the wellhead ordinate is the average of the wellhead ordinates in multiple video images of the drug delivery video;
[0051] The parameter determination module is used to determine two candidate operators in the video image, wherein the distance between the two candidate operators and the wellhead is less than the distance between the other operators in the video image and the wellhead; and to determine the wellhead coordinate in the video image based on the foot coordinate of each candidate operator, wherein the wellhead coordinate in the video image is the median of the foot coordinates of the two candidate operators.
[0052] In some embodiments, the displayed height of the target operator is the average of the displayed height of the target operator in multiple video images of the drug administration video;
[0053] The parameter determination module is used to determine two candidate operators in the video image, the distance between the two candidate operators and the wellhead being less than the distance between other operators in the video image and the wellhead; based on the head and foot coordinates of each candidate operator, a target operator in the video image is selected from the two candidate operators, the target operator in the video image being an operator in a standing posture; and the displayed height of the target operator in the video image is determined, the displayed height of the target operator in the video image being the distance between the head and foot coordinates of the target operator in the video image.
[0054] In some embodiments, the parameter determination module is used to determine the displayed height of each candidate operator based on the head ordinate and foot ordinate of each candidate operator, wherein the displayed height of any candidate operator is the distance between the head ordinate and foot ordinate of the target operator; and to select the target operator in the video image from the two candidate operators based on the displayed heights of the two candidate operators and the head ordinates of the two candidate operators.
[0055] In some embodiments, the parameter determination module is used to determine the number of operators appearing in the video image; when the number is equal to two, determine two operators appearing in the video image as the two candidate operators; when the number is greater than two, select the two candidate operators from the plurality of operators based on the distance between the plurality of operators appearing in the video image and the wellhead.
[0056] In some embodiments, the well depth determination module includes:
[0057] The first determining unit is used to determine the number of drug-feeding rods and the ordinate of the upper end of the drug-feeding rod at the end of the drug-feeding process based on the motion trajectory curve.
[0058] The second determining unit is used to determine the length of the external explosive rod based on the wellhead horizontal coordinate, the wellhead vertical coordinate, the displayed height of the target operator, and the vertical coordinate of the upper end of the explosive rod;
[0059] The third determining unit is used to determine the total length of the pressing rod based on the number of feeding rods and the reference length of the pressing rod, wherein the total length of the pressing rod is the product of the number of feeding rods and the reference length of the pressing rod;
[0060] The third determining unit is also used to determine the depth of the well for drug delivery based on the total length of the drug delivery rod, the length of the drug delivery rod outside the well, and the reference length of the drug string.
[0061] In some embodiments, the first determining unit is configured to determine drug dispensing segment points in the motion trajectory curve, wherein the drug dispensing segment points are the starting points for dispensing each drug-pressing rod; and based on the drug dispensing segment points, determine the number of drug-pressing rods, wherein the number of drug-pressing rods is the number of drug dispensing segment points.
[0062] In some embodiments, the second determining unit is configured to determine the displayed length of the external injection rod at the end of the rod lowering process based on the wellhead ordinate and the upper ordinate of the injection rod, wherein the displayed length of the external injection rod is the distance between the upper ordinate of the injection rod and the wellhead ordinate; and to determine the length of the external injection rod based on the displayed height of the target operator, the reference height of the target operator, and the displayed length of the external injection rod, wherein the length of the external injection rod is the product of the ratio of the displayed length of the external injection rod to the displayed height of the target operator and the reference height of the target operator.
[0063] In some embodiments, the apparatus further includes:
[0064] The video processing module is used to process video images in any drug administration video to obtain processed video images; determine the average amplitude value in the processed video images; retain the drug administration video if the average amplitude value is greater than a preset threshold; and discard the drug administration video if the average amplitude value is not greater than the preset threshold. The processing steps include Fourier transform, removal of low-frequency signals, and inverse Fourier transform.
[0065] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded and executed by the processor to implement the well depth detection method in the embodiments of this application.
[0066] On the other hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor to implement the well depth detection method in the embodiments of this application.
[0067] On the other hand, a computer program product is provided, including a computer program that is executed by a processor to implement the well depth detection method in the embodiments of this application.
[0068] This application provides a method for detecting well depth. In this method, the horizontal and vertical coordinates of the wellhead, the displayed height of the target operator, and the trajectory curve of the charge rod are obtained from the video of the charge-laying operation. The total length of the charge rod, the length of the charge rod outside the well, and the length of the charge rod inside the well are then calculated. Combined with a reference length of the charge string, the well depth is obtained, and the detection result is generated. Compared to traditional manual quality inspection methods, this method transforms manual identification into machine intelligent identification. This not only reduces the need for quality inspectors and saves labor costs, but also reduces the error caused by subjective human factors in the identification results, improving the accuracy and precision of the identification, thereby effectively improving the efficiency of quality inspection of the charge-laying well depth. Attached Figure Description
[0069] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0070] Figure 1 This is a schematic diagram of the implementation environment of a well depth detection method provided in an embodiment of this application;
[0071] Figure 2 This is a flowchart of a well depth detection method provided according to an embodiment of this application;
[0072] Figure 3 This is a flowchart of another well depth detection method provided according to an embodiment of this application;
[0073] Figure 4 This is a schematic diagram of a work area design document provided according to an embodiment of this application;
[0074] Figure 5 This is a schematic diagram of a drug administration video provided according to an embodiment of this application;
[0075] Figure 6 This is a flowchart illustrating a method for identifying sharpness according to an embodiment of this application;
[0076] Figure 7 This is a schematic diagram of the projected distribution of a drug-pressing rod according to an embodiment of this application;
[0077] Figure 8 This is a flowchart illustrating the process of identifying the height of an operator according to an embodiment of this application;
[0078] Figure 9 This is a schematic diagram of the motion trajectory curve of a pressure rod according to an embodiment of this application;
[0079] Figure 10 This is a flowchart illustrating the splitting of a motion trajectory curve according to an embodiment of this application;
[0080] Figure 11 This is a schematic diagram illustrating the identification of the depth of a well for drug delivery, according to an embodiment of this application.
[0081] Figure 12 This is a schematic diagram of an intelligent recognition interface provided according to an embodiment of this application;
[0082] Figure 13This is a schematic diagram of an electronic report provided according to an embodiment of this application;
[0083] Figure 14 This is a block diagram of a well depth detection device provided according to an embodiment of this application;
[0084] Figure 15 This is a block diagram of another well depth detection device provided according to an embodiment of this application;
[0085] Figure 16 This is a schematic diagram of the structure of a terminal according to an embodiment of this application;
[0086] Figure 17 This is a schematic diagram of the structure of a server according to an embodiment of this application. Detailed Implementation
[0087] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0088] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.
[0089] In this application, the term "at least one" means one or more, and "multiple" means two or more.
[0090] The following is a brief description of the drug administration process described in this application.
[0091] The charge-laying process is an important step in the seismic exploration and acquisition process. The charge-laying process is mainly divided into the following four stages: (1) Well-clearing stage: the charge rod is lowered from the wellhead to the bottom of the well, and the charge rod is rotated to move the charge rod down to clear the borehole and unclog the shallow well passage; (2) Charge-laying stage: according to the designed charge amount and the designed charge column specifications, the corresponding charge column is lowered to a certain depth in the well; (3) Charge-pressing stage: after the charge-laying is completed, in order to ensure that the charge column has reached the designed charge-laying depth and that the charge column is stably and tightly filled in the borehole, the charge rod needs to be lowered to press the charge column down. Since the length of each charge rod is usually 2 meters, while the designed charge-laying well depth can be more than ten meters, it is usually impossible to reach the charge column with a single charge rod. Therefore, multiple charge rods need to be lowered to press the charge column down to the designed charge-laying well depth; (4) Rod-up stage: after the charge-up is completed, the charge rods are taken out of the well in sequence.
[0092] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the drug administration videos, design data, reference length of the drug column, and reference height involved in this application were all obtained with full authorization.
[0093] Figure 1 This is a schematic diagram illustrating the implementation environment of a well depth detection method provided in an embodiment of this application. See also... Figure 1 The implementation environment includes terminal 101 and server 102. Terminal 101 and server 102 can be connected directly or indirectly via wired or wireless communication, which is not limited herein.
[0094] Among them, terminal 101 can be various types of terminals such as mobile phones, desktop computers, laptops, and tablets. Server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
[0095] Optionally, the well depth detection method provided in this application embodiment can be executed by terminal 101 alone, by server 102 alone, or by terminal 101 and server 102 interacting.
[0096] In some embodiments, when the method is executed independently by terminal 101, terminal 101 can run the application offline. Based on this application, the drug administration video and design data are read, and the detection results are obtained through data analysis based on the drug administration video and design data.
[0097] In some embodiments, when the server 102 executes the method alone, the server 102 is capable of performing data calculations independently. It analyzes data such as drug administration videos and design data uploaded to the server by other devices and obtains detection results. After obtaining the detection results, the server 102 can store the results on the server, send the results to other devices for display to relevant personnel, or continue to perform other data calculations based on the results; there are no limitations on this.
[0098] In some embodiments, when the terminal 101 and server 102 interactively execute the method, the terminal 101 and server 102 are associated, and the server 102 provides background services to the terminal 101. Optionally, the server 102 undertakes the main computing work, and the terminal 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the main computing work; or, the server 102 and the terminal 101 use a distributed computing architecture for collaborative computing.
[0099] In other words, some steps in this method are executed by terminal 101, while others are executed by server 102. For example, terminal 101 acquires drug-dispensing video and design data, and then sends the drug-dispensing video and design data to server 102; server 102 performs data analysis based on the drug-dispensing video and design data to obtain the drug-dispensing well depth, and sends the drug-dispensing well depth to terminal 101; terminal 101 receives the data, generates detection results based on the drug-dispensing well depth and design data, and displays them.
[0100] It should be noted that in the following embodiments, the method for detecting well depth proposed in the embodiments of this application will be described as an example of a terminal executing the method alone.
[0101] Figure 2 This is a flowchart of a well depth detection method according to an embodiment of this application. The method is applied to a terminal. See [link to flowchart]. Figure 2 The method includes the following steps:
[0102] 201. The terminal acquires the drug dispensing video and design data. The drug dispensing video is used to record the drug dispensing process.
[0103] In this embodiment of the application, the terminal acquiring drug administration video and design data means that the terminal reads the drug administration video and design data related to the work area design files from the server or local storage space into the target application, so as to facilitate subsequent analysis based on the drug administration video and design data and obtain the detection results.
[0104] The design data indicates the design information for each station within the work area. Stations are used to identify and locate various positions within the work area; here, station numbers identify wells or boreholes within the work area. The design data includes at least the design well depth and design charge quantity.
[0105] 202. Based on the drug delivery video, the terminal determines the horizontal and vertical coordinates of the wellhead, the displayed height of the target operator, and the trajectory curve of the drug delivery rod.
[0106] In this embodiment, the motion trajectory curve reflects the positional change of the upper end of the detonator over time during the detonation process, reflecting the dynamic behavior of the detonator during detonation. The detonator is a tool used to press the explosive charge into the well. A single detonator is typically 2 meters long, and multiple detonators are usually needed to press the explosive charge. The wellhead's horizontal and vertical coordinates are used to locate the wellhead's position in the video. Correspondingly, when a coordinate system is established with a point in the video frame as the origin, the wellhead's horizontal and vertical coordinates correspond to the horizontal and vertical pixel distances of the wellhead relative to the origin in the video frame. That is, the unit of the coordinate system is pixels. The displayed height of the target operator refers to the target operator's height in the video, used for subsequent calculations of other parameters.
[0107] 203. The terminal determines the well depth based on the wellhead horizontal coordinate, wellhead vertical coordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive charge.
[0108] In this embodiment, the reference length of the propellant column can be the designed length, the actual recorded length, or the length identified from the propellant placement video; this embodiment does not impose any limitations on this. The well depth is the sum of the reference length of the propellant column and the length of the propellant rod inside the well. The length of the propellant rod inside the well is the difference between the total length of the propellant rod and the length of the propellant rod outside the well at the end of the propellant placement. The total length of the propellant rod represents the sum of the lengths of the multiple propellant rods placed into the well at the end of the propellant placement. The length of the propellant rod inside the well represents the length of the multiple propellant rods inside the well at the end of the propellant placement. The length of the propellant rod outside the well represents the length of the last propellant rod remaining outside the well at the end of the propellant placement.
[0109] 204. The terminal generates detection results of the drug delivery video based on the design data and the depth of the drug delivery well.
[0110] In this embodiment of the application, based on the design data and the well depth determined by the drug placement video, the identification result of the drug placement well depth can be obtained, that is, the judgment result of whether the drug placement well depth meets the design requirements, thereby obtaining the detection result of the corresponding drug placement video, providing a basis for the subsequent work.
[0111] This application provides a method for detecting well depth. In this method, the horizontal and vertical coordinates of the wellhead, the displayed height of the target operator, and the trajectory curve of the charge rod are obtained from the video of the charge-laying operation. The total length of the charge rod, the length of the charge rod outside the well, and the length of the charge rod inside the well are then calculated. Combined with a reference length of the charge string, the well depth is obtained, and a detection result is generated. Compared to traditional manual quality inspection methods, this method transforms manual identification into machine intelligent identification. This not only reduces the need for quality inspectors and saves labor costs, but also reduces the error caused by subjective human factors in the identification results, improving the accuracy and precision of the identification, thereby effectively improving the efficiency of quality inspection of the charge-laying well depth.
[0112] The above Figure 2 A simplified procedure for well depth detection is introduced below. Figure 3 As shown, the methods for detecting well depth are described in detail. Figure 3 This is a flowchart of another well depth detection method according to an embodiment of this application. The method is applied to a terminal and includes the following steps:
[0113] 301. The terminal obtains the drug administration video and design data.
[0114] In this embodiment of the application, the terminal acquiring drug administration video and design data means that the terminal reads the drug administration video and design data related to the work area design files from the server or local storage space into the target application.
[0115] The design data indicates the design information for each station within the work area. Stations are used to identify and locate various positions within the work area, specifically identifying wells or boreholes. The design data includes at least the design well depth and design charge quantity. Accordingly, based on the characteristics of the Qt5 framework, Excel file read / write functionality was developed. The terminal reads the work area design file into the corresponding target application of the intelligent quality control system for image acquisition, thereby obtaining the design information for each station within the work area, which serves as a reference for subsequent machine recognition. Before reading, an Excel-formatted work area design file is created based on the work area design information. See also... Figure 4 As shown, Figure 4 This is a schematic diagram of a work area design document provided according to an embodiment of this application. The work area design document is in Excel format and includes design data such as merged station numbers, the north coordinate of the corresponding station number, the east coordinate of the corresponding station number, the design charge quantity, the design well depth, and the completed well depth.
[0116] The drug administration video is used to record the drug administration process. Each drug administration video has its own name and storage path. Accordingly, when reading the drug administration video into the target application, the terminal can, based on the path input by the user, read the impact data under that path in batches; or, the terminal can, based on the path and video name input by the user, read the video corresponding to that video name under that path. This application embodiment does not limit or elaborate on this. See also Figure 5 As shown, Figure 5 This is a schematic diagram of a drug administration video provided according to an embodiment of this application.
[0117] 302. The terminal retains drug administration videos that meet the video quality requirements and discards drug administration videos that do not meet the video quality requirements.
[0118] In this embodiment, since some drug administration videos may have quality issues that make them unsuitable for automatic detection, it is necessary to automatically assess the video quality to filter the videos. Videos that meet the quality requirements are retained and the subsequent automatic detection steps are performed; videos that do not meet the quality requirements are discarded during the automatic detection process or can be switched to manual identification. Through this video preprocessing, videos that do not meet the quality requirements can be quickly removed, facilitating subsequent automatic detection of compliant videos and improving the efficiency and accuracy of drug administration video detection.
[0119] Optionally, a module for automatically judging video quality can be used, which is obtained by an information extraction algorithm based on the CIE domain of the image, to automatically judge parameters such as the clarity or brightness of the video, thereby realizing the judgment of video quality.
[0120] In some embodiments, the terminal judges the video quality based on sharpness. Accordingly, the terminal processes the video image in any medication dispensing video to obtain a processed video image; determines the average amplitude value in the processed video image; retains the medication dispensing video if the average amplitude value is greater than a preset threshold; and discards the medication dispensing video if the average amplitude value is not greater than the preset threshold. The processing steps include Fourier transform, removal of low-frequency signals, and inverse Fourier transform.
[0121] See Figure 6 As shown, Figure 6 This is a flowchart illustrating a method for identifying video sharpness according to an embodiment of this application. Accordingly, for the video image in the drug administration video, a Fourier transform, low-frequency signal removal, and inverse Fourier transform are performed sequentially. For the video image obtained after the above processing, the mean amplitude value is calculated. If the mean amplitude value is greater than a preset threshold, the video is determined to be sharp, meaning the video sharpness meets the requirements; if the mean amplitude value is not greater than the preset threshold, the video is determined to be blurry, meaning the video sharpness does not meet the requirements.
[0122] It should be noted that step 302 above is an optional step. That is, after executing step 301, steps 303 to 309 can be executed directly; or step 302 can be executed to filter the drug administration videos, and steps 303 to 309 can be executed on the drug administration videos retained in step 302, while the drug administration videos discarded in step 302 can be manually identified.
[0123] It should be noted that after screening and eliminating the drug delivery videos, based on the drug delivery videos, it is possible to determine various parameters such as the wellhead horizontal coordinate, the wellhead vertical coordinate, the displayed height of the target operator, and the movement trajectory curve of the drug delivery rod, as shown in steps 303 to 306 below.
[0124] 303. The terminal determines the horizontal coordinate of the wellhead based on the drug delivery video.
[0125] In this embodiment, since the charge rod must be lowered into the well, the horizontal coordinate position of the wellhead in the video image can be determined by identifying the projection distribution of the charge rod. This method achieves high accuracy in identifying the horizontal coordinate of the wellhead, which is beneficial for subsequent data analysis.
[0126] In some embodiments, the terminal performs analysis based on projection distribution data. Accordingly, based on the drug delivery video, the terminal determines the projection distribution data of the injection rod. This projection distribution data reflects the number of injection rod projections corresponding to each abscissa. The number of injection rod projections corresponding to any abscissa indicates the number of times the injection rod appears at the corresponding position in multiple video images of the drug delivery video. Based on the projection distribution data, the terminal determines the wellhead abscissa, which is the median abscissa within the effective projection interval. The effective projection interval includes the abscissa corresponding to when the number of injection rod projections exceeds a preset threshold. For example, the preset threshold is 60 or 65 times.
[0127] See Figure 7 As shown, Figure 7 This is a schematic diagram showing the projected distribution of a dispensing rod according to an embodiment of this application. See also... Figure 7 As shown in Figure (a), the horizontal axis of the image represents the horizontal position in the video image. The vertical axis represents the number of times the pressure rod is projected. The image illustrates the correspondence between the horizontal axis and the number of times the pressure rod is projected. The preset threshold for the number of projections is 60. Areas marked with valid values are the valid projection intervals, where the number of pressure rod projections corresponding to the horizontal axis is greater than 60. Areas marked with noise are the noisy projection areas outside the valid projection areas, where the number of pressure rod projections corresponding to the horizontal axis is no greater than 60. See also... Figure 7As shown in Figure (b), the horizontal interval marked with the projection interval refers to the interval indicated by the effective projection interval in the video image. A wellhead exists at the middle position of this horizontal interval.
[0128] Optionally, the terminal determines the projection distribution data of the dispensing rod based on all or part of the video images in the dispensing video. Taking part of the video images as an example: If the dispensing video contains 30 frames per second, the terminal determines the projection position of the dispensing rod 3 times per second, that is, at intervals of 10 frames, thus obtaining the projection distribution data of the dispensing rod.
[0129] 304. The terminal determines the wellhead vertical coordinates based on the drug delivery video.
[0130] In this embodiment, the wellhead coordinates are determined using the operators appearing in the drug delivery video as a reference. Since operators follow relevant rules and standards during seismic exploration and acquisition operations, using their data as a reference allows for accurate determination of the wellhead coordinates, resulting in more precise and accurate identification, which is beneficial for subsequent data processing.
[0131] In some embodiments, the wellhead ordinate is the average of the wellhead ordinates across multiple video images of the drug delivery video. Accordingly, the process by which the terminal determines the wellhead ordinate in any video image of the drug delivery video includes: the terminal identifying two candidate operators in the video image, where the distance between the two candidate operators and the wellhead is less than the distance between the two candidates and the wellhead; and the terminal determining the wellhead ordinate in the video image based on the foot ordinate of each candidate operator, where the wellhead ordinate in the video image is the median of the foot ordinates of the two candidate operators. Through this method, the wellhead ordinate can be accurately identified.
[0132] In some embodiments, the terminal determines candidate operators from the operators appearing in the drug delivery video. Accordingly, the terminal determines the number of operators appearing in the video image; if the number is equal to two, the terminal determines the two operators appearing in the video image as two candidate operators; if the number is greater than two, the terminal selects two candidate operators from the multiple operators based on the distances between the multiple operators appearing in the video image and the wellhead. The distance between each operator and the wellhead is determined by the horizontal coordinate of the operator's head, the vertical coordinate of the operator's head, the vertical coordinate of the operator's feet, and the horizontal coordinate of the wellhead.
[0133] By using the above method, the operators closest to the wellhead on both sides can be identified as candidate operators, eliminating interference from invalid operators in other locations in the video and improving the accuracy of data determination.
[0134] 305. The terminal determines the displayed height of the target operator based on the drug administration video.
[0135] In this embodiment of the application, since the operator performs the drug delivery process in accordance with the corresponding rules and standards during the seismic exploration and acquisition operation, the displayed height of the target operator can be used as a reference for determining the length of the external pressure rod. This method is sufficiently precise and accurate, which improves the efficiency and accuracy of determining the drug delivery depth.
[0136] In some embodiments, the displayed height of the target operator is the average of the displayed heights of the target operator in multiple video images of the drug delivery video. Accordingly, the process by which the terminal determines the displayed height of the target operator in any video image of the drug delivery video includes: the terminal identifying two candidate operators in the video image, wherein the distance between the two candidate operators and the wellhead is less than the distance between other operators in the video image and the wellhead; the terminal selecting the target operator in the video image from the two candidate operators based on the head and foot coordinates of each candidate operator, wherein the target operator in the video image is an operator in a standing posture; and the terminal determining the displayed height of the target operator in the video image, wherein the displayed height of the target operator in the video image is the distance between the head and foot coordinates of the target operator in the video image.
[0137] In some embodiments, the terminal determines the target operator from among the candidate operators. Accordingly, the terminal determines the displayed height of each candidate operator based on the head and foot coordinates of each candidate operator, wherein the displayed height of any candidate operator is the distance between the head and foot coordinates of the target operator; the terminal selects the target operator from the two candidate operators based on the displayed heights and head coordinates of the two candidate operators.
[0138] It should be noted that the target operator identified in different video images of the drug dispensing video is the same operator. This is because the standard drug dispensing procedure requires one operator to hold the dispensing lever while another operator lowers the lever; these two operators typically do not switch roles. Therefore, the target operator identified in different video images of the same drug dispensing video usually does not change. Optionally, if the operator changes, the operator who is more often standing is identified as the target operator; or, the operator who is standing in the video image corresponding to the end of drug dispensing is identified as the target operator.
[0139] See Figure 8 As shown, Figure 8 This is a flowchart for identifying the height of an operator according to an embodiment of this application.
[0140] See Figure 8 As shown in Figure (a), firstly, the positional information of the operators in the drug delivery video is obtained, and then the number of people is determined. If there are more than two people, the horizontal and vertical coordinates of the head and the vertical coordinates of the feet are obtained to determine the distance between the operators and the wellhead. The two operators closest to the wellhead are selected as two candidate operators, and their displayed heights are determined. If there are two people, the vertical coordinates of the head and the vertical coordinates of the feet are obtained to determine the displayed heights of the two candidate operators. The displayed heights and head positions of the two candidate operators are compared, and the candidate operator in a standing posture is selected as the target operator. The average displayed height and the average head vertical coordinate are determined. The displayed height and head position of the target operator can be used to determine the quality of the video image. For example, if the displayed height of the target operator exceeds a preset threshold, such as if the displayed height of the target operator is greater than 1 / 2 of the vertical frame of the video, it means that the target operator is too close to the camera position, and the video can be considered invalid.
[0141] See Figure 8 As shown in Figure (b), candidate operator 1 and candidate operator 2 are the two operators closest to the wellhead in the video image. Candidate operator 1 is the target operator, and the target operator's standing height is the target operator's height. Invalid operators are any other operators in the video image besides the two candidate operators. The wellhead's vertical coordinate is determined by the vertical coordinates of the feet of the two candidate operators.
[0142] 306. The terminal determines the motion trajectory curve based on the drug delivery video, and determines the number of drug delivery rods and the ordinate of the upper end of the drug delivery rod at the end of the delivery based on the motion trajectory curve.
[0143] In this embodiment, the terminal uses a pressure rod model to infer the motion trajectory curve of each frame of the drug-pressing stage in the drug-pressing video. The motion trajectory of the pressure rod is broken down using a trend segmentation approach, automatically adapting to different operating speeds and extracting each action. Noise is removed from some misidentified data to obtain the correct data for two key pieces of information: the number of drug-pressing rods and the ordinate of the upper end of the pressure rod at the end of the drug-pressing process. The number of drug-pressing rods is equal to the number of pressure rods used. The ordinate of the upper end of the pressure rod at the end of the drug-pressing process is the lowest point of the upper end of the pressure rod when the drug is fully pressed down.
[0144] See Figure 9 As shown, Figure 9This is a schematic diagram of the movement trajectory curve of a detonating rod according to an embodiment of this application. The horizontal axis of the image represents the shooting time, and the vertical axis represents the position of the upper end of the detonating rod. Following the shooting time sequence, the detonation video includes several stages: detonation start, rod lowering, detonation to the bottom, rod raising, and rod removal. During the rod lowering period after the detonation start, multiple detonating rods are lowered. During the lowering process of each rod, the upper end of the rod is initially at a high position and maintains this position for a certain period, then gradually lowers until it reaches a lower position, at which point one rod has been detonated below the wellhead. During the lowering period, the above process is repeated until the rod remains at a lower position for a certain period, indicating that detonation has reached the bottom, i.e., the detonation is complete. During the subsequent raising period, multiple detonating rods are pulled up. During the pulling up process of each rod, the position of the rod gradually rises until it reaches a high position and maintains this position for a period, at which point one rod has been removed. During the backswing, repeat the above process until the pressure bar returns to a higher position and remains there for a period of time before disappearing. At this point, the backswing is complete, and you can finish the swing and leave the course.
[0145] See Figure 10 As shown, Figure 10 This is a flowchart illustrating the splitting of a motion trajectory curve according to an embodiment of this application. See also... Figure 10 As shown in Figure (a), the input video is used; the corresponding motion trajectory curve is obtained based on the video; the height information of the curve's motion trajectory is obtained; the maximum height difference of the curve is calculated; redundant noise points such as zero points, rising points, and outliers are removed to smooth the motion trajectory curve; the drug placement segment points are calculated using the maximum height difference of the curve as a reference value; and the number of drug placement rods within the effective time window is determined. (See also...) Figure 10 As shown in Figure (b), each segment of the motion trajectory curve where the position of the detonator gradually decreases from a higher point to a lower point corresponds to the process of lowering one detonator; each segment where the position of the detonator gradually increases from a lower point to a higher point corresponds to the process of pulling up one detonator. Each effective time window corresponds to the process of lowering one detonator. The number of detonators lowered into the well is determined as the number of detonators, i.e., the total number of detonators. Optionally, the number of detonators retrieved from the well can also be determined as the total number of detonators; alternatively, the total number of detonators can be determined by combining the number of detonators lowered into the well and the number of detonators retrieved from the well. This will not be elaborated further.
[0146] 307. The terminal determines the length of the external explosive rod based on the wellhead horizontal coordinate, wellhead vertical coordinate, the displayed height of the target operator, and the vertical coordinate of the upper end of the explosive rod.
[0147] In this embodiment, the transition from the section where the position of the charging rod gradually decreases from a higher position to a lower position to the section where the position of the charging rod gradually increases from a lower position to a higher position corresponds to the transition from the rod lowering period to the rod raising period. By using the video images corresponding to the section where the charging rod reaches the bottom between the two periods, combined with the above-mentioned multiple parameters, the length of the charging rod outside the well at the end of the rod lowering period can be determined.
[0148] In some embodiments, the terminal calculates the length of the external explosive rod based on the wellhead location and the operator's height as reference points. Accordingly, the terminal determines the displayed length of the external explosive rod at the end of its lowering based on the wellhead's longitudinal coordinate and the longitudinal coordinate of the upper end of the explosive rod; the displayed length of the external explosive rod is the distance between the longitudinal coordinate of the upper end of the explosive rod and the wellhead's longitudinal coordinate. The terminal also determines the length of the external explosive rod based on the target operator's displayed height, the target operator's reference height, and the displayed length of the external explosive rod; the external explosive rod length is the product of the ratio of the displayed length of the external explosive rod to the target operator's displayed height and the target operator's reference height.
[0149] See Figure 11 As shown, Figure 11 This is a schematic diagram illustrating an identification of well depth for drug delivery according to an embodiment of this application. See also... Figure 11 As shown in Figure (a), 1101 represents the wellhead location, 1102 represents the operator's height, and 1103 represents the injection rod identification. Under the conditions indicated in this figure, the designed well depth for this well is 12.0 meters. The machine-identified injection depth is 15.2 meters, and the manually checked injection depth is 15.3 meters, with an error of 0.1 meters. In this case, the injection depth is sufficient and meets the corresponding requirements. See also... Figure 11 As shown in Figure (b), 1104 represents the wellhead location, 1105 represents the operator's height, and 1106 represents the injection rod identification. Under the conditions indicated in this figure, the designed well depth for this well is 12.0 meters. The machine identifies the injection depth as 10.2 meters, and the manual inspection yields an injection depth of 10.3 meters, with an error of 0.1 meters. In this case, the injection depth is insufficient and does not meet the corresponding requirements.
[0150] 308. The terminal determines the well depth based on the number of charge rods, the reference length of the charge rod, the length of the charge rod outside the well, and the reference length of the charge string.
[0151] In this embodiment, the length of the in-well charge rod is obtained by subtracting the length of the charge rod outside the well from the total length of the charge rod. Combined with the reference length of the charge string, the well depth can be accurately calculated. The reference length of the charge string can be the designed length, the actual recorded length, or the length identified from the charge delivery video; this embodiment does not impose any limitations on this.
[0152] Accordingly, the terminal determines the total length of the charging rod based on the number of charging rods and the reference length of the charging rod, which is the product of the number of charging rods and the reference length of the charging rod. The terminal also determines the length of the charging rod inside the well based on the total length of the charging rod and the length of the charging rod outside the well, which is the difference between the total length of the charging rod and the length of the charging rod outside the well at the end of charging. Finally, the terminal determines the charging depth based on the length of the charging rod inside the well and the reference length of the charge, which is the sum of the reference length of the charge and the length of the charging rod inside the well.
[0153] 309. The terminal generates detection results of the drug delivery video based on the design data and the depth of the drug delivery well.
[0154] In this embodiment, the user can specify the path and filename of the output file in the target application. The generated detection results are stored according to the filename and path. After all drug delivery videos have been processed, relevant personnel can obtain a batch processing result report of the drug delivery videos, i.e., a well depth and drug quantity information file, at the corresponding location on the path, thereby carrying out subsequent data analysis and other work. In other words, the detection results are organized in the form of an electronic report.
[0155] See Figure 12 As shown, Figure 12 This is a schematic diagram of an intelligent recognition interface provided according to an embodiment of this application. Each number in the video list corresponds to a drug-dispensing video. The video evaluation for each drug-dispensing video indicates the judgment result on the video quality, including compliance, recognition anomalies, and excessively close distances, among other things. The recognition result corresponding to each drug-dispensing video indicates the automatic detection result of the drug-dispensing well depth in that video, marking it as qualified. Clicking the run button in the diagram allows for the automatic processing and calculation of the required information, as shown in the diagram.
[0156] See Figure 13 As shown, Figure 13 This is a schematic diagram of an electronic report provided according to an embodiment of this application. The electronic report includes well location station number, completed well depth, tackling depth, amount of chemicals used, depth of chemicals used, inspection date, and inspection remarks. It should be noted that the above content is merely an example, and the detailed information included in the electronic report is not limited or elaborated upon.
[0157] This application provides a method for detecting well depth. In this method, the horizontal and vertical coordinates of the wellhead, the displayed height of the target operator, and the trajectory curve of the charge rod are obtained from the video of the charge-laying operation. The total length of the charge rod, the length of the charge rod outside the well, and the length of the charge rod inside the well are then calculated. Combined with a reference length of the charge string, the well depth is determined, and a detection result is generated. In other words, this application utilizes intelligent image recognition processing technology to automatically extract various information from the construction site reflected in the video, and uses multiple mathematical methods for fitting and judgment to finally obtain the charge-laying depth of the well. Compared to traditional manual quality inspection methods, the above method transforms manual identification work into machine intelligent identification. This method does not increase the difficulty of field construction, has strong noise resistance, and is more easily accepted by users. Previously, manual identification of each video took 3-5 minutes; now, machine identification takes only 1 minute, and the machine can work continuously even at night. This not only reduces the need for quality inspectors and saves labor costs, but also reduces the impact of subjective human factors on the identification results, improving accuracy and precision, thereby effectively enhancing the efficiency of quality inspection for well depths where drugs are deposited. Given the increasing intensity of current construction work, only combined human and machine inspections can improve the coverage and accuracy of quality control. Therefore, this application saves field labor, reduces labor costs, and improves work efficiency. While reducing the workload and error rate of manual fieldwork, it also effectively shortens the video self-inspection cycle, thus meeting the requirement of immediate data collection under the current trend of high-density acquisition.
[0158] Figure 14 This is a block diagram of a well depth detection device according to an embodiment of this application. The device is used to perform the steps of the well depth detection method described above, see below. Figure 14 The well depth detection device includes: an acquisition module 1401, a parameter determination module 1402, a well depth determination module 1403, and a result determination module 1404.
[0159] The acquisition module 1401 is used to acquire drug dispensing video and design data. The drug dispensing video is used to record the drug dispensing process.
[0160] The parameter determination module 1402 is used to determine the horizontal coordinate of the wellhead, the vertical coordinate of the wellhead, the displayed height of the target operator, and the motion trajectory curve of the pressure rod based on the drug delivery video. The motion trajectory curve is used to reflect the position change of the upper end of the pressure rod over time during the drug delivery process.
[0161] The well depth determination module 1403 is used to determine the depth of the well for dropping explosives based on the wellhead abscissa, wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive string. The depth of the well for dropping explosives is the sum of the reference length of the explosive string and the length of the explosive rod inside the well. The length of the explosive rod inside the well is the difference between the total length of the explosive rod and the length of the explosive rod outside the well at the end of the dropping process.
[0162] The result determination module 1404 is used to generate detection results of the drug delivery video based on the design data and the depth of the drug delivery well.
[0163] In some embodiments, the parameter determination module 1402 is used to determine the projection distribution data of the pressure rod based on the drug delivery video. The projection distribution data is used to reflect the number of times the pressure rod is projected at each horizontal coordinate. The number of times the pressure rod is projected at any horizontal coordinate is used to represent the number of times the pressure rod appears at the position corresponding to that horizontal coordinate in multiple video images of the drug delivery video. Based on the projection distribution data, the wellhead horizontal coordinate is determined. The wellhead horizontal coordinate is the median horizontal coordinate within the effective projection interval. The effective projection interval includes the horizontal coordinate corresponding to when the number of pressure rod projections is greater than a preset threshold.
[0164] In some embodiments, the wellhead ordinate is the average of the wellhead ordinates in multiple video images of the drug delivery video;
[0165] The parameter determination module 1402 is used to determine two candidate operators in the video image. The distance between the two candidate operators and the wellhead is less than the distance between the other operators in the video image and the wellhead. Based on the foot coordinate of each candidate operator, the wellhead coordinate in the video image is determined. The wellhead coordinate in the video image is the median of the foot coordinates of the two candidate operators.
[0166] In some embodiments, the displayed height of the target operator is the average of the displayed height of the target operator in multiple video images of the drug administration video;
[0167] The parameter determination module 1402 is used to determine two candidate operators in the video image, the distance between the two candidate operators and the wellhead is less than the distance between other operators in the video image and the wellhead; based on the head and foot coordinates of each candidate operator, the target operator in the video image is selected from the two candidate operators, the target operator in the video image is the operator in a standing posture; the displayed height of the target operator in the video image is determined, the displayed height of the target operator in the video image is the distance between the head and foot coordinates of the target operator in the video image.
[0168] In some embodiments, the parameter determination module 1402 is used to determine the displayed height of each candidate operator based on the head ordinate and foot ordinate of each candidate operator, wherein the displayed height of any candidate operator is the distance between the head ordinate and foot ordinate of the target operator; and to select the target operator in the video image from the two candidate operators based on the displayed height of the two candidate operators and the head ordinate of the two candidate operators.
[0169] In some embodiments, the parameter determination module 1402 is used to determine the number of operators appearing in the video image; when the number is equal to two, the two operators appearing in the video image are determined as two candidate operators; when the number is greater than two, two candidate operators are selected from the multiple operators based on the distance between the multiple operators appearing in the video image and the wellhead.
[0170] In some embodiments, Figure 15 This is a block diagram of another well depth detection device according to an embodiment of this application. See also Figure 15 Well depth determination module 1403 includes:
[0171] The first determining unit 14031 is used to determine the number of drug-feeding rods and the ordinate of the upper end of the drug-feeding rod at the end of the drug-feeding process based on the motion trajectory curve.
[0172] The second determining unit 14032 is used to determine the length of the external explosive rod based on the wellhead horizontal coordinate, the wellhead vertical coordinate, the displayed height of the target operator, and the vertical coordinate of the upper end of the explosive rod.
[0173] The third determining unit 14033 is used to determine the total length of the pressing rod based on the number of dropping rods and the reference length of the pressing rod. The total length of the pressing rod is the product of the number of dropping rods and the reference length of the pressing rod.
[0174] The third determining unit 14033 is also used to determine the depth of the well for drug delivery based on the total length of the drug delivery rod, the length of the drug delivery rod outside the well, and the reference length of the drug string.
[0175] In some embodiments, the first determining unit 14031 is used to determine the drug-feeding segment points in the motion trajectory curve, the drug-feeding segment points being the starting points for placing each drug-pressing rod; and based on the drug-feeding segment points, to determine the number of drug-feeding rods, the number of drug-feeding rods being the number of drug-feeding segment points.
[0176] In some embodiments, the second determining unit 14032 is used to determine the displayed length of the external pressure rod at the end of the rod lowering process based on the wellhead ordinate and the upper ordinate of the pressure rod, wherein the displayed length of the external pressure rod is the distance between the upper ordinate of the pressure rod and the wellhead ordinate; and to determine the length of the external pressure rod based on the displayed height of the target operator, the reference height of the target operator, and the displayed length of the external pressure rod, wherein the length of the external pressure rod is the product of the ratio of the displayed length of the external pressure rod and the displayed height of the target operator and the reference height of the target operator.
[0177] In some embodiments, the apparatus further includes:
[0178] The video processing module 1405 is used to process the video image in any drug administration video to obtain the processed video image; determine the average amplitude value in the processed video image; retain the drug administration video if the average amplitude value is greater than a preset threshold; and discard the drug administration video if the average amplitude value is not greater than the preset threshold. The processing steps include Fourier transform, removal of low-frequency signals, and inverse Fourier transform.
[0179] This application provides a well depth detection device that uses video recognition to obtain the wellhead's horizontal and vertical coordinates, the displayed height of the target operator, and the trajectory curve of the charge rod. It then calculates the total length of the charge rod, the length of the charge rod outside the well, and the length of the charge rod inside the well. Combined with a reference charge length, the well depth is determined, and the detection result is generated. Compared to traditional manual quality inspection methods, this device transforms manual identification into machine-based intelligent identification. This not only reduces the need for quality inspectors and saves labor costs but also reduces the error caused by subjective human factors, improving accuracy and precision, thereby effectively enhancing the efficiency of well depth quality inspection.
[0180] It should be noted that the well depth detection device provided in the above embodiments is only illustrated by the division of the above functional modules when running the application. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the terminal can be divided into different functional modules to complete all or part of the functions described above. In addition, the well depth detection device and the well depth detection method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.
[0181] Figure 16 This is a schematic diagram of a terminal according to an embodiment of this application. The terminal 1600 can be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 1600 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.
[0182] Typically, terminal 1600 includes a processor 1601 and a memory 1602.
[0183] Processor 1601 may include one or more processing cores, such as a quad-core processor or a 16-core processor. Processor 1601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 1601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0184] The memory 1602 may include one or more computer-readable storage media, which may be non-transitory. The memory 1602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1602 are used to store at least one computer program, which is executed by the processor 1601 to implement the well depth detection method provided in the method embodiments of this application.
[0185] In some embodiments, the terminal 1600 may also optionally include a peripheral device interface 1603 and at least one peripheral device. The processor 1601, memory 1602, and peripheral device interface 1603 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1604, a display screen 1605, a camera assembly 1606, an audio circuit 1607, and a power supply 1608.
[0186] Peripheral interface 1603 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1601 and memory 1602. In some embodiments, processor 1601, memory 1602 and peripheral interface 1603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1601, memory 1602 and peripheral interface 1603 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.
[0187] The radio frequency (RF) circuit 1604 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1604 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1604 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit 1604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1604 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1604 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.
[0188] Display screen 1605 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1605 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1601 for processing. In this case, display screen 1605 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1605, disposed on the front panel of terminal 1600; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1600 or in a folded design; in still other embodiments, display screen 1605 may be a flexible display screen, disposed on a curved or folded surface of terminal 1600. Furthermore, display screen 1605 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1605 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).
[0189] The camera assembly 1606 is used to acquire images or videos. In some embodiments, the camera assembly 1606 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1606 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.
[0190] The audio circuit 1607 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 1601 for processing, or to the radio frequency circuit 1604 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1600. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1601 or the radio frequency circuit 1604 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1607 may also include a headphone jack.
[0191] Power supply 1608 is used to power the various components in terminal 1600. Power supply 1608 can be AC power, DC power, a disposable battery, or a rechargeable battery. When power supply 1608 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.
[0192] In some embodiments, the terminal 1600 further includes one or more sensors 1609. The one or more sensors 1609 include, but are not limited to: an accelerometer 1610, a gyroscope 1611, a pressure sensor 1612, an optical sensor 1613, and a proximity sensor 1614.
[0193] Accelerometer 1610 can detect the magnitude of acceleration along the three axes of a coordinate system established by terminal 1600. For example, accelerometer 1610 can be used to detect the components of gravitational acceleration along the three axes. Processor 1601 can control display screen 1605 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1610. Accelerometer 1610 can also be used for games or for acquiring user motion data.
[0194] The gyroscope sensor 1611 can detect the orientation and rotation angle of the terminal 1600. The gyroscope sensor 1611 can work in conjunction with the accelerometer sensor 1610 to collect the user's 3D movements on the terminal 1600. Based on the data collected by the gyroscope sensor 1611, the processor 1601 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.
[0195] The pressure sensor 1612 can be disposed on the side bezel of the terminal 1600 and / or on the lower layer of the display screen 1605. When the pressure sensor 1612 is disposed on the side bezel of the terminal 1600, it can detect the user's grip signal on the terminal 1600, and the processor 1601 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1612. When the pressure sensor 1612 is disposed on the lower layer of the display screen 1605, the processor 1601 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1605. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.
[0196] An optical sensor 1613 is used to collect ambient light intensity. In one embodiment, the processor 1601 can control the display brightness of the display screen 1605 based on the ambient light intensity collected by the optical sensor 1613. Optionally, when the ambient light intensity is high, the display brightness of the display screen 1605 is increased; when the ambient light intensity is low, the display brightness of the display screen 1605 is decreased. In another embodiment, the processor 1601 can also dynamically adjust the shooting parameters of the camera assembly 1609 based on the ambient light intensity collected by the optical sensor 1613.
[0197] The proximity sensor 1614, also known as the distance sensor, is installed on the front panel of the terminal 1600. The proximity sensor 1614 is used to detect the distance between the user and the front of the terminal 1600. In one embodiment, when the proximity sensor 1614 detects that the distance between the user and the front of the terminal 1600 is gradually decreasing, the processor 1601 controls the display screen 1605 to switch from a screen-on state to a screen-off state; when the proximity sensor 1614 detects that the distance between the user and the front of the terminal 1600 is gradually increasing, the processor 1601 controls the display screen 1605 to switch from a screen-off state to a screen-on state.
[0198] Those skilled in the art will understand that Figure 16 The structure shown does not constitute a limitation on terminal 1600 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.
[0199] Figure 17This is a schematic diagram of a server structure according to an embodiment of this application. The server 1700 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1701 and one or more memories 1702. The memory 1702 stores at least one computer program, which is loaded and executed by the processor 1701 to implement the well depth detection method provided in the above-described method embodiments. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated here.
[0200] This application also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the well depth detection method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, or optical data storage device, etc.
[0201] This application also provides a computer program product, including a computer program that is executed by a processor to implement the well depth detection method in this application embodiment.
[0202] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.
[0203] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A method for detecting well depth, characterized in that, The method includes: Acquire drug administration video and design data, wherein the drug administration video is used to record the drug administration process; Based on the drug delivery video, the horizontal coordinate of the wellhead, the vertical coordinate of the wellhead, the displayed height of the target operator, and the motion trajectory curve of the drug delivery rod are determined. The motion trajectory curve is used to reflect the position change of the upper end of the drug delivery rod over time during the drug delivery process. Based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive string, the depth of the explosive well is determined. The depth of the explosive well is the sum of the reference length of the explosive string and the length of the explosive rod inside the well. The length of the explosive rod inside the well is the difference between the total length of the explosive rod and the length of the explosive rod outside the well at the end of the rod insertion. Based on the design data and the well depth, the detection results of the drug delivery video are generated.
2. The method according to claim 1, characterized in that, The process of determining the wellhead abscissa based on the drug delivery video includes: Based on the drug dispensing video, the projection distribution data of the drug dispensing rod is determined. The projection distribution data is used to reflect the number of times the drug dispensing rod is projected at each horizontal axis. The number of times the drug dispensing rod is projected at any horizontal axis is used to indicate the number of times the drug dispensing rod appears at the position corresponding to that horizontal axis in multiple video images of the drug dispensing video. Based on the projection distribution data, the wellhead abscissa is determined. The wellhead abscissa is the median abscissa within the effective projection interval. The effective projection interval includes the abscissa corresponding to when the number of times the injection rod is projected is greater than a preset threshold.
3. The method according to claim 1, characterized in that, The wellhead ordinate is the average of the wellhead ordinates in multiple video images of the drug delivery video; The process of determining the wellhead ordinate in any video image of the drug delivery video includes: Two candidate operators are identified in the video image, and the distance between the two candidate operators and the wellhead is smaller than the distance between the other operators in the video image and the wellhead. Based on the foot coordinates of each candidate operator, the wellhead coordinates in the video image are determined, and the wellhead coordinates in the video image are the median of the foot coordinates of the two candidate operators.
4. The method according to claim 1, characterized in that, The displayed height of the target operator is the average of the displayed height of the target operator in multiple video images of the drug administration video; The process of determining the displayed height of the target operator in any video image of the drug administration video includes: Two candidate operators are identified in the video image, and the distance between the two candidate operators and the wellhead is smaller than the distance between the other operators in the video image and the wellhead. Based on the head and foot coordinates of each candidate operator, the target operator in the video image is selected from the two candidate operators. The target operator in the video image is the operator in a standing posture. The displayed height of the target operator in the video image is determined, and the displayed height of the target operator in the video image is the distance between the vertical coordinate of the target operator's head and the vertical coordinate of the feet in the video image.
5. The method according to claim 3 or 4, characterized in that, The process of determining the two candidate operators in the video image includes: Determine the number of operators appearing in the video image; When the number of people is equal to two, the two operators appearing in the video image are identified as the two candidate operators; If the number of people is greater than two, the two candidate operators are selected from the multiple operators based on the distance between the multiple operators appearing in the video image and the wellhead.
6. The method according to claim 1, characterized in that, The process of determining the well depth based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the explosive charge includes: Based on the motion trajectory curve, determine the number of drug-feeding rods and the ordinate of the upper end of the drug-feeding rod at the end of the feeding. The length of the external explosive rod is determined based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, and the ordinate of the upper end of the explosive rod. Based on the number of feeding rods and the reference length of the pressing rod, the total length of the pressing rod is determined, and the total length of the pressing rod is the product of the number of feeding rods and the reference length of the pressing rod. The depth of the well for drug delivery is determined based on the total length of the drug delivery rod, the length of the drug delivery rod outside the well, and the reference length of the drug string.
7. The method according to claim 6, characterized in that, The determination of the length of the external explosive rod based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, and the ordinate of the upper end of the explosive rod includes: Based on the wellhead ordinate and the upper ordinate of the charging rod, the displayed length of the charging rod outside the well is determined when the rod is lowered. The displayed length of the charging rod outside the well is the distance between the upper ordinate of the charging rod and the wellhead ordinate. Based on the displayed height of the target operator, the reference height of the target operator, and the displayed length of the external injection rod, the length of the external injection rod is determined. The length of the external injection rod is the product of the ratio of the displayed length of the external injection rod and the displayed height of the target operator and the reference height of the target operator.
8. A device for detecting well depth, characterized in that, The device includes: The acquisition module is used to acquire drug administration video and design data, wherein the drug administration video is used to record the drug administration process; The parameter determination module is used to determine the wellhead horizontal coordinate, wellhead vertical coordinate, the displayed height of the target operator, and the motion trajectory curve of the pressure rod based on the drug delivery video. The motion trajectory curve is used to reflect the position change of the upper end of the pressure rod over time during the drug delivery process. The well depth determination module is used to determine the depth of the well for dropping chemicals based on the wellhead abscissa, the wellhead ordinate, the displayed height of the target operator, the movement trajectory curve, and the reference length of the chemical string. The depth of the well for dropping chemicals is the sum of the reference length of the chemical string and the length of the in-well pressure rod. The length of the in-well pressure rod is the difference between the total length of the pressure rod and the length of the external pressure rod at the end of the dropping process. The result determination module is used to generate the detection results of the drug delivery video based on the design data and the drug delivery well depth.
9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded by the processor and executed as the well depth detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store at least one computer program for performing the well depth detection method according to any one of claims 1 to 7.