Acquisition quality control video automatic naming method, device and equipment based on two-dimensional code

Abstract

The invention discloses an acquisition quality control video automatic naming method, device and equipment based on a two-dimensional code, and the method comprises the steps: obtaining each to-be-recognized image in a video frame picture through the detection of a recognition frame for any video frame picture obtained through the analysis of an acquisition quality control video containing the two-dimensional code; judging whether each included angle of the to-be-recognized image is within a first preset threshold range or not and whether the length ratio of each two adjacent edges of the to-be-recognized image is within a second preset threshold range or not; if yes, denoising the to-be-recognized image to obtain a two-dimensional code image; identifying the two-dimensional code image to obtain a two-dimensional code number; matching the two-dimensional code number with a preset blast well pile number and two-dimensional code number corresponding table, and determining a blast well pile number corresponding to the acquired quality control video; and naming the acquired quality control video according to the blast well pile number. According to the method, the renaming efficiency of quality control video acquisition can be improved, the labor cost is reduced, the self-inspection period of the video is shortened, and the quality and efficiency of exploration area acquisition operation are improved.

Description

Technical Field

[0001] The present invention relates to a method, device and equipment for automatically naming a captured quality control video based on a two-dimensional code. Background Art

[0002] During the process of well-shot excitation acquisition in seismic exploration, the pass rate of the depth of the well involves safety and environmental protection issues, and directly affects the quality of single-shot acquisition. At present, high-density acquisition mainly adopts a four-step method for the quality control of the depth of the well: on-site video recording by the operation team, manual point-by-point correspondence to the well pile number in the room, manual identification and inspection of process quality, and manual statistics of quality results and feedback for rectification. Among them, the second step is to manually correspond to the well pile number point by point. Since each well corresponds to a unique well pile number, the video must be named with the well pile number file for subsequent inspection and statistics. Currently, this work can only be handled manually. Summary of the invention

[0003] In order to more efficiently realize the naming of collected quality control videos, the embodiments of the present application provide a method, device and equipment for automatically naming collected quality control videos based on QR codes.

[0004] In a first aspect, an embodiment of the present application provides a method for automatically naming a captured quality control video based on a QR code, the method comprising:

[0005] For any video frame image obtained by parsing the acquisition quality control video containing the QR code, each image to be identified in the video frame image is obtained by detecting the identification frame;

[0006] Determine whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range;

[0007] If yes, perform denoising on the image to be identified to obtain a two-dimensional code image;

[0008] Identify the two-dimensional code image to obtain a two-dimensional code number;

[0009] Match the QR code number with a preset table of correspondence between turret pile number and QR code number to determine the turret pile number corresponding to the collected quality control video;

[0010] The collected quality control video is named according to the turret pile number.

[0011] In one or some optional implementations of the embodiment of the present application, the denoising process is performed on the image to be identified to obtain a two-dimensional code image, including:

[0012] Perform edge search on the image to be identified to obtain a valid information image;

[0013] The effective information image is stretched to obtain the two-dimensional code image.

[0014] In one or some optional implementations of the embodiment of the present application, stretching the effective information image to obtain the two-dimensional code image includes:

[0015] The effective information image is subjected to Hough line detection and affine transformation to obtain the two-dimensional code image.

[0016] In one or some optional implementations of the embodiment of the present application, before the two-dimensional code image is recognized to obtain the two-dimensional code number, the following step is further included:

[0017] Corner point verification is performed on each vertex of the stretched image.

[0018] In one or some optional implementations of the embodiments of the present application, further comprising:

[0019] If the stretched image fails the corner point verification, the stretched image is no longer processed.

[0020] In one or some optional implementations of the embodiments of the present application, further comprising:

[0021] If the stretched image passes the corner point verification, the video frame image that is later in time than the video frame image is no longer obtained.

[0022] In one or some optional implementations of the embodiments of the present application, further comprising:

[0023] If any angle of the image to be identified is not within the first preset threshold range, and / or the ratio of the lengths of any two adjacent sides of the image to be identified is not within the second preset threshold range, the image to be identified is no longer processed.

[0024] In a second aspect, an embodiment of the present application provides a device for automatically naming a captured quality control video based on a QR code, the device comprising:

[0025] The recognition frame detection module is used to obtain each image to be recognized in any video frame image obtained by parsing the acquisition quality control video containing the QR code through recognition frame detection;

[0026] A judging module, used for judging whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range;

[0027] A denoising module, used for performing denoising processing on the image to be identified to obtain a two-dimensional code image;

[0028] An identification module, used to identify the two-dimensional code image and obtain a two-dimensional code number;

[0029] A matching module, used to match the QR code number with a preset turret pile number and QR code number correspondence table to determine the turret pile number corresponding to the collected quality control video;

[0030] A naming module is used to name the collected quality control video according to the turret pile number.

[0031] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for automatically naming captured quality control videos based on QR codes.

[0032] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the automatic naming method for acquired quality control videos based on QR codes as described above is implemented.

[0033] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a computer device, the computer device executes the above-mentioned method for automatically naming captured quality control videos based on QR codes.

[0034] In a sixth aspect, an embodiment of the present application provides a chip, the chip including a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a computer program or instruction to implement the automatic naming method for acquired quality control videos based on a QR code as described above.

[0035] The beneficial effects of the above technical solution provided by the embodiment of the present application include at least:

[0036] The automatic naming method for the collection quality control video based on QR code provided in the embodiment of the present application, the inventor uses QR code to represent the well gun information for the drug placement video recorded in the oil exploration collection, and uses computer recognition of QR code instead of manual recognition of handwritten pile number information. The function of automatically naming the collection quality control video with the gun well pile number is realized through the QR code recognition technology. The method is simple to use, has low operation requirements for the collection personnel, and can greatly improve the renaming efficiency of the collection quality control video; the method converts the original manual renaming method into computer automatic recognition, reduces labor costs, and greatly saves the cost of geophysical exploration operations. On average, it only takes a few seconds to successfully rename a video, which can be dozens of times faster than manual operation, improves timeliness, and can greatly reduce the field manual workload and operation error rate, shorten the video self-inspection cycle, meet the "down and collect" requirements proposed under the current development trend of high-density collection, and improve the quality and efficiency of exploration area collection operations.

[0037] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 A schematic diagram of the steps of the automatic naming method for acquired quality control videos based on QR codes provided in an embodiment of the present application;

[0041] Figure 2 A QR code image that can identify the QR code number information provided in the embodiment of the present application;

[0042] Figure 3 A schematic diagram of an operation interface for generating a typeset image with a QR code image and a gun well pile number provided in an embodiment of the present application;

[0043] Figure 4 A typeset image containing a QR code image provided in an embodiment of the present application;

[0044] Figure 5 This is a diagram showing the actual effect of printing a typesetting picture provided in an embodiment of the present application;

[0045] Figure 6 A schematic diagram of a correct way to paste a picture with a QR code image provided in an embodiment of the present application;

[0046] Figure 7 A schematic diagram of an incorrect pasting method of a picture with a QR code image provided in an embodiment of the present application;

[0047] Figure 8 A schematic diagram of a table showing the correspondence between the turret pile number and the QR code number provided in the embodiment of the present application;

[0048] Fig. 9 A schematic diagram of a correct display method of a picture with a QR code image provided in an embodiment of the present application;

[0049] Fig.10 A schematic diagram of a first incorrect display method of a picture with a QR code image provided in an embodiment of the present application;

[0050] Fig.11 A schematic diagram of a second incorrect display method of a picture with a QR code image provided in an embodiment of the present application;

[0051] Fig.12 A flowchart of the idea of ​​automatically naming the collected quality control video provided in the embodiment of the present application;

[0052] Fig.13 A schematic diagram of an operation interface for selecting a processing file and the number of multi-threaded processes provided in an embodiment of the present application;

[0053] Fig.14 A schematic diagram of the file names of three videos before they are automatically renamed provided in an embodiment of the present application;

[0054] Fig.15 A schematic diagram of the file names of three videos after automatic renaming provided in an embodiment of the present application;

[0055] Fig.16 A schematic diagram of the structure of the device for automatically naming captured quality control videos based on QR codes provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0058] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0060] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0061] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] It should be understood that the size of the serial numbers of the steps in the following embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0064] The inventor found that in the prior art, the naming step of the quality control video collected in the quality control of the depth of the drug well can only be completed manually. This step has a large workload, poor timeliness, and a high probability of subjective judgment of quality. It will consume a lot of manpower and material resources, and reduce the timeliness of process quality control. It is estimated that based on the current acquisition speed, it will take two days to manually name the blast well pile number for the collected quality control video, which seriously lags behind the effect of process quality management and control, and cannot meet the demand of "collecting immediately after drug placement". On the other hand, considering the labor cost, taking a geophysical exploration team with 10 people, each working 10 months a year, and a monthly salary of 5,000 yuan / month as an example, a geophysical exploration team will spend about 500,000 yuan on video detection each year, which will also lead to a large increase in the cost of geophysical exploration operations. In addition, due to the urgency of tasks under the trend of high-density acquisition, higher requirements are put forward for safe construction. In order to cooperate with seismic exploration management, the inventor considers conducting research on intelligent identification of safety quality inspection content. Based on the above problems, in order to further reduce manual labor and improve work efficiency, the inventor has made the present invention after further research and development, providing a method, device and equipment for automatic naming of acquisition quality control videos based on QR code.

[0065] A QR code is a black and white graphic that uses a certain geometric shape arranged in a two-dimensional direction according to a certain distribution rule to record data information. Taking the QR code as an example, its shape is generally a square. Like the 1D barcode, the QR code has different code standards, and each code has different encoding rules. Each character information in the QR code symbol occupies a certain width and has a specific character set, which makes the QR code have strong verification and error correction functions, information recognition functions, and image processing functions.

[0066] Embodiment 1

[0067] The present application embodiment provides a method for automatically naming a captured quality control video based on a QR code, referring to Figure 1 As shown, the method includes:

[0068] S101: For any video frame image obtained by parsing a captured quality control video containing a QR code, each image to be identified in the video frame image is obtained through identification frame detection.

[0069] During the process of seismic exploration well blasting acquisition, it is necessary to manually name the well pile numbers one by one in the on-site video, which has high labor costs and poor timeliness. However, the inventors found that if a QR code is used to record each well pile number, the QR code is displayed in the corresponding video, and then the QR code in the video is recognized, the purpose of automatically naming the video can be achieved.

[0070] Based on this, the inventor downloaded a QR code open source library, such as the Zbar QR code open source library, where Zbar is an open source barcode recognition library that supports multiple barcode types, including QR codes, developed the function of generating QR code images with specified information, built a development environment above OpenCV 3.0, and designed and generated a QR code image that can identify the QR code number information according to the turret pile number template provided by the geophysical exploration team. The QR code image, line number, point number and other information were then typeset, and printed according to the number of one sheet per well. Each QR code image with a QR code image was pasted on the corresponding turret.

[0071] In a specific embodiment, the designed two-dimensional code image capable of identifying the two-dimensional code number information can be as follows: Figure 2 As shown in the figure, the QR code image can identify the QR code number on the figure. After the QR code image is designed, it can be used as follows Figure 3 The operation interface shown generates a QR code picture with a QR code image and a turret pile number through human-computer interaction. The "Merge pile number" in the operation interface is one of the judgment parameters for the corresponding table between the input turret pile number and the QR code number during subsequent renaming. Among them, the pile number is the turret pile number, which can be composed of a point number and a line number. If it is "Merge pile number" here, only one column of information in the table, namely the turret pile number, will be read. If it is "Separate pile number", that is, the point number and line number are recorded separately in the table, then two columns of information in the table, namely the line number and the point number, will be read. The generated QR code picture can be as follows Figure 4 As shown in the figure, it contains a QR code image, line number, point number and project name; Figure 5 The following is the actual printing effect of the QR code image. After printing out the QR code images of all the blast well pile numbers, you can Figure 6 The method shown is used to paste correctly to facilitate the display of the QR code; and Figure 7 As shown in the figure, this is an incorrect pasting method. The QR code in the picture is not fully displayed, which will affect the subsequent recognition accuracy. However, in the complex working environment in the field, it is difficult to avoid the QR code being stained or other influencing factors that make it impossible to accurately recognize it. At this time, you can also manually view the video and manually identify and name the video according to the line number and point number of the blasthole displayed in the QR code picture.

[0072] In the process of drilling, since the punctuality rate of data collection in Sichuan is very low, after the well location is determined, the blast hole pile number must be recorded. The blast hole pile number and the corresponding QR code number displayed here are recorded in a table. The format of the record table can be set according to the needs, for example, as follows Figure 8The blast well pile number and QR code number are recorded in a corresponding table format. The table content in the figure includes the serial number, point category, measurement point number and QR code number, where the measurement point number is the combination of the point number and the line number, that is, the blast well pile number. Each well needs to record the acquisition quality control video and record it. During the recording process, the on-site personnel need to correctly and completely display the QR code image pasted there in the camera. After the acquisition process is completed, all the acquisition quality control videos and complete record sheets are collected.

[0073] In a specific embodiment, the acquisition quality control video is obtained in the seismic exploration well blasting acquisition process. When recording the acquisition quality control video, you can follow the following steps: Fig. 9 In the manner shown, the picture with the QR code is displayed in the camera. This display method requires grasping the two unfixed corners of the QR code picture to fully expand the QR code picture, and fully display the QR code image, line number and point number information in the picture; and as shown in FIG. Fig.10 , 11 The two methods shown are both incorrect display methods. Neither of them fully displays the QR code image in the figure, which will affect the subsequent recognition work.

[0074] After completing the above acquisition work, it is necessary to automatically name all the acquired quality control videos. First, the video needs to be parsed into a frame-by-frame picture format, namely a video frame picture, and then for any video frame picture, the image information in the picture is obtained through recognition frame detection, and all the images to be identified in the current video frame picture are obtained. Each image to be identified is selected by a recognition box of a corresponding shape. The specific implementation method of the above-mentioned parsing of video frame pictures can refer to the detailed description in the prior art and is not specifically limited here.

[0075] S102: Determine whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range; if so, execute S103; if not, execute step S107.

[0076] In an embodiment of the present application, in step S102, after all images to be identified are acquired through identification frame detection, it is necessary to judge the shape of the image to be identified, in order to determine whether it is approximately consistent with the shape of the QR code used. It is necessary to separately judge whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of each adjacent side of the image to be identified is within a second preset threshold range.

[0077] In a specific embodiment, the above-mentioned determination of whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of each adjacent two side lengths of the image to be identified is within a second preset threshold range, further includes:

[0078] If any angle of the image to be identified is not within the first preset threshold range, and / or the ratio of the lengths of any two adjacent sides of the image to be identified is not within the second preset threshold range, the image to be identified is no longer processed.

[0079] In the embodiment of the present application, in the above judgment process, if both conditions are met, it is determined that the shape of the image to be identified is approximately consistent with the shape of the two-dimensional code used, and step S103 is continued to be performed on the image to be identified; if any one of the conditions is met, it is determined that the shape of the image to be identified is inconsistent with the shape of the two-dimensional code used, and step S107 is executed, and the image to be identified is no longer processed. Among them, the specific values ​​of the first preset threshold range and the second preset threshold range are set according to the shape of the two-dimensional code actually used and the accuracy requirements.

[0080] In a specific embodiment, taking a square QR code as an example, it is necessary to determine whether the shape of the image to be identified is approximately a square. The angles of the four sides of the square are all 90°, and the ratio of the lengths of two adjacent sides is 1. Therefore, the first preset threshold range can be set to 85° to 95°, and the second preset threshold range can be set to 0.9 to 1.1 to determine whether the shape of the image to be identified is approximately a square.

[0081] The present invention can eliminate erroneous recognition frames, reduce the number of images to be recognized, and reduce the amount of calculation by calculating the angle and judging the ratio of the long and short sides.

[0082] S103: performing denoising processing on the image to be identified to obtain a two-dimensional code image.

[0083] In the above step S103, the denoising process is performed on the image to be identified to obtain a two-dimensional code image, which specifically includes:

[0084] Perform edge search on the image to be identified to obtain a valid information image;

[0085] The effective information image is stretched to obtain the two-dimensional code image.

[0086] In the embodiment of the present application, since the acquisition work belongs to field work and the field environment is complex, the acquired acquisition quality control video has a lot of noise, and the image to be identified obtained in step S102 needs to be denoised. Performing edge search on the image to be identified can detect the boundary contour of the QR code, distinguish the QR code image from the surrounding non-related information, and improve the detection accuracy. Therefore, it is possible to remove part of the image to be identified that cannot provide valid information in the complex image, leaving the image with valid information. The edge search method is selected according to actual needs, such as Canny edge detection and Sobel edge detection.

[0087] In a specific embodiment, Canny edge detection can be used to find the edges of the image to be identified and extract the edge information in the image. The Canny edge detection algorithm includes four steps: (1) Gaussian filtering; (2) using the Sobel operator to calculate the x- and y-direction gradient components and gradient directions respectively; (3) performing non-maximum suppression on the gradient; (4) using a double threshold to further detect and enhance the edge. The Canny algorithm provides non-maximum suppression and a double threshold method to eliminate interference from non-boundary points and can extract the boundary well. The Canny edge detection algorithm can ensure that the edge information of the QR code area is not lost and the area outside the QR code can be effectively distinguished.

[0088] In a specific embodiment, the stretching of the effective information image to obtain the two-dimensional code image specifically includes:

[0089] The effective information image is subjected to Hough line detection and affine transformation to obtain the two-dimensional code image.

[0090] Due to the complex working environment during the acquisition process, it is inevitable that the staff will not paste or display the QR code in a standardized manner, resulting in the QR code image being bent and deformed in the recorded acquisition quality control video. Therefore, after obtaining the effective information image, the effective information image needs to be stretched. The stretching method includes Hough line detection and affine transformation. Among them, the steps of Hough line detection include: (1) converting the color image to a grayscale image; (2) using a Gaussian kernel for denoising; (3) performing edge search on the image; (4) performing binarization processing, and judging whether each part of the image is an edge point by judging whether the grayscale value is 255; (5) mapping to Hough space. In this step, two containers need to be prepared, one for displaying the Hough-space overview and an array Hough-space for storing voting values. Because the voting process often has a maximum value exceeding the threshold, up to several thousand, it is not possible to directly use a grayscale image to record voting information; (6) taking the local maximum value, setting the threshold, and filtering interference lines; (7) drawing lines and calibrating corner points.

[0091] After Hough line detection, the image to be identified is stretched using affine transformation according to the straight lines and corner points of the image to be identified. Affine transformation includes operations such as translation, scaling, rotation, and flipping of the image to be identified. When performing affine transformation, it is necessary to pay attention to the straight line part of the image to be identified. The straight line before the transformation is still a straight line after the transformation, and the proportion of the straight line remains unchanged. Through Hough line detection, the straight lines in the image to be identified are extracted to extract the contour of the target object, and the affine transformation method is used to correct the distortion of the image to be identified, correcting the rotation, perspective, and distortion of the image. After undergoing the stretching operation of Hough line detection and affine transformation, the recognizability of the QR code image in the effective information image is enhanced.

[0092] S104: Identify the two-dimensional code image to obtain a two-dimensional code number.

[0093] In the embodiment of the present application, before executing the above step S104 to identify the two-dimensional code image and obtain the two-dimensional code number, the following is further included:

[0094] Corner point verification is performed on each vertex of the stretched image.

[0095] After the image to be identified is subjected to Hough line detection, the corner points of the image to be identified are obtained, that is, the vertices of the stretched image. The process of corner point verification is to count the local features of each corner point for image matching. The QR code corner point detection algorithm can be applied to find the corner points in the image. Among them, the corner point is usually the local maximum value of the curvature on the target contour, which plays a decisive role in grasping the contour features of the target and is often used as a feature description point in image matching. By performing corner point verification on the image to be identified, it is determined whether the image to be identified is a QR code image. Corner point verification is used to eliminate false detection or noise and verify whether the image is a QR code image. If the image fails the corner point verification, then, if there is no image to be identified in the current video frame, the video frame image in the video that is after the current video frame is taken, and the recognition frame detection is continued.

[0096] In a specific embodiment, the above-mentioned corner point verification of each vertex of the stretched image further includes:

[0097] If the stretched image fails the corner point verification, the stretched image is no longer processed.

[0098] If the stretched image passes the corner point verification, the video frame image that is later in time than the video frame image is no longer obtained.

[0099] Since there are many video frame images obtained by analyzing the collected quality control video, it is necessary to perform recognition frame detection on each video frame image in turn starting from the first frame and then execute steps S102 to S104. If the stretched image obtained in the current video frame image fails to pass the corner point verification, that is, it is determined that the stretched image is not a two-dimensional code image, then continue to obtain the next frame of the current video frame image, perform recognition frame detection and then execute steps S102 to S104; if the stretched image obtained in the current video frame image passes the corner point verification, it is determined that the recognizable two-dimensional code image in the collected quality control video has been obtained, and there is no need to process the images of other video frames.

[0100] In the above step S104, after obtaining the recognizable QR code image, it is necessary to identify the QR code image to obtain the QR code number. The specific implementation method of identifying the QR code can refer to the detailed description in the prior art and is not specifically limited here.

[0101] S105: Match the QR code number with a preset correspondence table between turret pile number and QR code number to determine the turret pile number corresponding to the collected quality control video.

[0102] In the above step S105, after the QR code number is identified, the gun well pile number that matches the QR code number is found according to the corresponding table of gun well pile numbers and QR code numbers retrieved during the acquisition process. If no recognizable QR code image is obtained after the entire acquisition quality control video is processed, the video can be manually viewed at this time, and the line number and point number on the QR code image can be matched with the corresponding table of gun well pile numbers and QR code numbers, and then the acquisition quality control video can be manually named.

[0103] S106: Name the collected quality control video according to the turret pile number.

[0104] In the embodiment of the present application, after matching the gun well pile number corresponding to the collected quality control video, the collected quality control video is named with the gun well pile number as the file name, and the collected quality control video can be batch processed and named by multi-threaded operation. After the renaming is completed, the collected quality control video named with the gun well pile number will be sent to the video group for subsequent work.

[0105] S107: The image to be recognized is no longer processed.

[0106] like Fig.12 As shown, in the embodiment of the present application, in order to accurately realize the automatic naming of the collected quality control video, in the process of executing the automatic naming method of the collected quality control video based on the QR code, it should be as follows Fig.12The execution order of the steps shown in is executed in sequence. After the quality control video is collected and read, when judging each frame of the video frame, the recognition frame is first obtained, that is, the image to be identified in the video frame is obtained through recognition frame detection, and the angle of the image to be identified is calculated to determine whether the angles of the image to be identified are all within the first preset threshold range, and the ratio of the long and short sides of the image to be identified is judged to determine whether the ratio of the lengths of each adjacent two sides of the image to be identified is within the second preset threshold range; if the angles and the ratio of the long and short sides of the image to be identified meet the threshold requirements, the image to be identified is denoised, the edge search is performed on the image to be identified, and a valid information image is obtained. Then, the valid information image is subjected to Hough line detection and affine transformation to obtain a two-dimensional code image. Then, each vertex of the obtained two-dimensional code image is verified by corner point verification, and information recognition is performed on the two-dimensional code image after the corner point verification is passed to obtain a two-dimensional code number. Since a correspondence table between turret pile numbers and QR code numbers has been compiled in advance before executing this method, the turret pile number corresponding to the collected quality control video can be determined based on the obtained QR code number and the correspondence table; the collected quality control video is renamed with the determined turret pile number, thereby realizing automatic renaming of the file of the collected quality control video.

[0107] In a specific embodiment, the Fig.13 The operation interface shown in the figure uses human-computer interaction to select the processed files and the number of multi-threaded processing, and can quickly locate the time position of the QR code image display in the video through "skip frame" and select the end time of processing through "process to", which can improve the processing efficiency of a single acquisition quality control video, because in general, the display of the QR code image in the video can be basically completed in the first 20-30 seconds. Take the automatic naming of three acquisition quality control videos as an example, Fig.14 As shown in the figure, these are the file names of the three videos before automatic naming; Fig.15 As shown in the figure, the file names of the three videos are all modified after automatic naming. It can be seen that the file name now becomes the turret pile number where the quality control video was recorded.

[0108] The automatic naming method for the collection quality control video based on QR code provided in the embodiment of the present application, the inventor uses QR code to represent the well gun information for the drug placement video recorded in the oil exploration collection, and uses computer recognition of QR code instead of manual recognition of handwritten pile number information. The function of automatically naming the collection quality control video with the gun well pile number is realized through the QR code recognition technology. The method is simple to use, has low operation requirements for the collection personnel, and can greatly improve the renaming efficiency of the collection quality control video; the method converts the original manual renaming method into computer automatic recognition, reduces labor costs, and greatly saves the cost of geophysical exploration operations. On average, it only takes a few seconds to successfully rename a video, which can be dozens of times faster than manual operation, improves timeliness, and can greatly reduce the field manual workload and operation error rate, shorten the video self-inspection cycle, meet the "down and collect" requirements proposed under the current development trend of high-density collection, and improve the quality and efficiency of exploration area collection operations.

[0109] Embodiment 2

[0110] Based on the same inventive concept, the embodiment of the present application also provides a device for automatically naming a captured quality control video based on a QR code, referring to Fig.16 As shown, the device comprises:

[0111] The recognition frame detection module 101 is used to obtain each image to be recognized in any video frame image obtained by parsing the acquisition quality control video containing the QR code through recognition frame detection;

[0112] The judging module 102 is used to judge whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range;

[0113] A denoising module 103 is used to perform denoising on the image to be identified to obtain a two-dimensional code image;

[0114] The recognition module 104 is used to recognize the two-dimensional code image and obtain a two-dimensional code number;

[0115] A matching module 105 is used to match the two-dimensional code number with a preset corresponding table of turret pile numbers and two-dimensional code numbers to determine the turret pile number corresponding to the collected quality control video;

[0116] The naming module 106 is used to name the collected quality control video according to the turret pile number.

[0117] Embodiment 3

[0118] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for automatically naming the acquired quality control video based on a QR code as described in the above embodiment 1 is implemented.

[0119] Embodiment 4

[0120] Based on the same inventive concept, an embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for automatically naming the acquired quality control videos based on QR codes as described in the above-mentioned embodiment 1 is implemented.

[0121] Embodiment 5

[0122] Based on the same inventive concept, an embodiment of the present application also provides a computer program product comprising instructions. When the computer program product is run on a computer device, the computer device executes the automatic naming method for acquired quality control videos based on QR codes as described in the above-mentioned embodiment 1.

[0123] Embodiment 6

[0124] Based on the same inventive concept, an embodiment of the present application also provides a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a computer program or instruction to implement the automatic naming method for acquired quality control videos based on QR codes as described in the above embodiment one.

[0125] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0126] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatically naming collected quality control videos based on QR code recognition, characterized in that: include: For any video frame image obtained by parsing the acquisition quality control video containing the QR code, each image to be identified in the video frame image is obtained by detecting the identification frame; Determine whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range; If yes, perform denoising on the image to be identified to obtain a two-dimensional code image; Identify the two-dimensional code image to obtain a two-dimensional code number; Match the QR code number with a preset table of correspondence between turret pile number and QR code number to determine the turret pile number corresponding to the collected quality control video; The collected quality control video is named according to the turret pile number.

2. The method according to claim 1, characterized in that The step of performing denoising on the image to be identified to obtain a two-dimensional code image includes: Perform edge search on the image to be identified to obtain a valid information image; The effective information image is stretched to obtain the two-dimensional code image.

3. The method according to claim 2, characterized in that Stretching the effective information image to obtain the two-dimensional code image includes: The effective information image is subjected to Hough line detection and affine transformation to obtain the two-dimensional code image.

4. The method according to claim 2, characterized in that Before identifying the two-dimensional code image and obtaining the two-dimensional code number, the method further includes: Corner point verification is performed on each vertex of the stretched image.

5. The method according to claim 4, characterized in that Also includes: If the stretched image fails the corner point verification, the stretched image is no longer processed.

6. The method according to claim 4, characterized in that Also includes: If the stretched image passes the corner point verification, the video frame image that is later in time than the video frame image is no longer obtained.

7. The method according to claim 4, characterized in that Also includes: If any angle of the image to be identified is not within the first preset threshold range, and / or the ratio of the lengths of any two adjacent sides of the image to be identified is not within the second preset threshold range, the image to be identified is no longer processed.

8. An automatic naming device for acquisition quality control videos based on QR code recognition, characterized in that: include: The recognition frame detection module is used to obtain each image to be recognized in any video frame image obtained by parsing the acquisition quality control video containing the QR code through recognition frame detection; A judging module, used for judging whether each angle of the image to be identified is within a first preset threshold range, and whether the ratio of the lengths of two adjacent sides of the image to be identified is within a second preset threshold range; A denoising module, used for performing denoising processing on the image to be identified to obtain a two-dimensional code image; An identification module, used to identify the two-dimensional code image and obtain a two-dimensional code number; A matching module, used to match the QR code number with a preset turret pile number and QR code number correspondence table to determine the turret pile number corresponding to the collected quality control video; A naming module is used to name the collected quality control video according to the turret pile number.

9. A computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal, the terminal executes the automatic naming method for acquired quality control videos based on QR code recognition as described in any one of claims 1 to 7.

10. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the automatic naming method for acquired quality control videos based on QR code recognition as described in any one of claims 1 to 7 is implemented.

11. A computer program product comprising instructions, which, when executed on a computer device, enables the computer device to execute the method for automatically naming captured quality control videos based on QR code recognition as described in any one of claims 1 to 7.

12. A chip, comprising a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run a computer program or instruction to implement the automatic naming method for acquired quality control videos based on QR code recognition as described in any one of claims 1 to 7.

Images