Method, system and device for identifying illegal behaviors on drilling site

Abstract

The embodiment of the invention provides a method, a system and a device for identifying illegal behaviors on a drilling site. The method comprises the following steps: acquiring real-time video data of the drilling production site; converting the video data into corresponding frame images; extracting feature data of behaviors and actions in the frame image data; and inputting the extracted feature vectors into a pre-trained drilling field violation behavior identification model, and determining whether a preset violation behavior occurs in the drilling production field according to an output result of the drilling field violation behavior identification model. According to the embodiment of the invention, the drilling site is monitored in real time, dangerous articles and dangerous behaviors in the drilling site can be detected in time, and an alarm is given, so that dangerous accidents are effectively prevented, the safety of workers in the drilling site is guaranteed, and the safety of the drilling site is also guaranteed; and the standard operation of drilling field workers can be effectively supervised, and the working efficiency of the drilling field workers is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of seismic exploration, and particularly to a method, system and device for identifying illegal behaviors at a drilling site. Background Art

[0002] In the drilling field, the current traditional safety control measures are carried out in the form of having people, posts, and sites stationed. A large number of on-site management personnel are relied on to supervise the safe behaviors of high-position drilling operations and conduct hidden danger investigations on the unsafe states of objects, which has the disadvantage of poor timeliness.

[0003] Although the drilling industry has initially established a monitoring system for the operation site through the informatization work carried out in recent years, the existing system only stays in the stage of manual screening, which has relatively high requirements for the quality and ability of safety monitoring personnel. In the actual control process, due to the complex and changeable outdoor environment, the effect is not good. Moreover, due to the complex and changeable outdoor environment, even for the same behavior, it is difficult to determine whether it is illegal without comprehensively judging in combination with the context environment, which poses a certain challenge to the reliability of the system. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a method, system and device for identifying illegal behaviors at a drilling site that can overcome or at least partially solve the above problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for identifying illegal behaviors at a drilling site, including:

[0006] Obtaining real-time video data of the drilling production site;

[0007] Converting the video data into corresponding frame images;

[0008] Extracting characteristic data of behaviors and actions from the frame image data;

[0009] Inputting the extracted feature vectors into a pre-trained illegal behavior identification model for the drilling site, and determining whether a preset illegal behavior has occurred at the drilling production site according to the output result of the illegal behavior identification model for the drilling site.

[0010] In one embodiment, the illegal behavior identification model for the drilling site is trained in the following manner:

[0011] Collecting video and image data of the drilling site;

[0012] Calibrating the video and image data of the illegal behaviors at the drilling site according to the relevant regulations on the illegal behaviors at the drilling site preset and the operating procedures of the drilling operation, and obtaining the calibrated video and image data of the illegal behaviors at the drilling site;

[0013] Extract the features of corresponding behaviors and actions from the calibrated drilling site violation videos and image data to obtain the drilling site violation behavior features;

[0014] Train a neural network with the features of the drilling site violation behaviors to obtain the drilling site violation behavior recognition model.

[0015] In one embodiment, training the neural network according to the features of the drilling site violation behaviors to obtain the neural network for recognizing the drilling site violation behaviors further includes:

[0016] Collect new video data of the drilling site;

[0017] Use the new video data of the drilling site as a training set to repeatedly train the drilling site violation behavior recognition model to obtain the optimized drilling site violation behavior recognition model.

[0018] In one embodiment, the method further includes:

[0019] Determine the recognition scope and area of the drilling site violation behaviors according to the video data of the drilling site violation behaviors, the relevant regulations of the drilling site violation behaviors, and the operating procedures of the drilling operations;

[0020] Correspondingly, obtain the real-time video data within the determined recognition scope and area.

[0021] In one embodiment, the method further includes:

[0022] If a violation behavior occurs at the drilling production site, then according to the preset warning method corresponding to the drilling site violation behavior, an alarm message is sent in real time, and / or the violation behavior information is stored.

[0023] In a second aspect, an embodiment of the present invention provides an identification device for drilling site violation behaviors, including:

[0024] An acquisition module, configured to acquire real-time video data of the drilling production site;

[0025] A frame conversion module, configured to convert the video data into corresponding frame images;

[0026] An extraction module, configured to extract the feature data of behaviors and actions from the frame image data;

[0027] An identification module, configured to input the extracted feature vectors into a pre-trained drilling site violation behavior recognition model, and determine whether a preset violation behavior occurs at the drilling production site according to the output result of the drilling site violation behavior recognition model.

[0028] In a third aspect, an embodiment of the present invention provides a server, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for identifying illegal behaviors at a drilling site is implemented.

[0029] In a fourth aspect, an embodiment of the present invention provides a system for identifying illegal behaviors at a drilling site, including:

[0030] Video monitoring equipment at the drilling site and the server as claimed in claim 7;

[0031] The video monitoring equipment at the drilling site is used to collect real-time video data of the drilling production site and output it to the server.

[0032] In one embodiment, it further includes:

[0033] An early warning device, which is used to issue corresponding forms of early warning information according to the early warning signal determined by the server that a preset illegal behavior has occurred at the drilling production site, and / or store the information on the illegal behavior.

[0034] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for identifying illegal behaviors at a drilling site described above is implemented.

[0035] The beneficial effects of the above technical solutions provided by the embodiments of the present invention at least include:

[0036] An embodiment of the present invention provides a method for identifying illegal behaviors at a drilling site, including: obtaining real-time video data of the drilling production site; converting the video data into corresponding frame images; extracting feature data of behaviors and actions from the frame image data; inputting the extracted feature vectors into a pre-trained model for identifying illegal behaviors at a drilling site, and determining whether a preset illegal behavior has occurred at the drilling production site according to the output result of the model for identifying illegal behaviors at a drilling site. The embodiment of the present invention conducts real-time monitoring of the drilling site, can timely detect dangerous items and dangerous behaviors existing at the drilling site, and give an alarm, thereby effectively preventing the occurrence of dangerous accidents, thus ensuring the safety of the staff at the drilling site and also ensuring the safety of the drilling site; it can also effectively supervise the standardized operation of the staff at the drilling site and enhance the work efficiency of the staff at the drilling site.

[0037] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention may be realized and attained by the structure particularly pointed out in the written description, claims, as well as the appended drawings.

[0038] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments. Description of the Drawings

[0039] The 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 to the present invention. In the drawings:

[0040] Figure 1 It is a flowchart of a method for identifying illegal behaviors at a drilling site provided by an embodiment of the present invention;

[0041] Figure 2 It is an illegal image of not wearing labor protection and safety helmets in a standardized manner provided by an embodiment of the present invention;

[0042] Figure 3 It is an illegal image of smoking provided by an embodiment of the present invention;

[0043] Figure 4 It is an illegal image of making or answering calls illegally provided by an embodiment of the present invention;

[0044] Figure 5 It is an illegal image of covering the camera and illegally entering the dangerous area provided by an embodiment of the present invention;

[0045] Figure 6 It is an illegal image of smoke and fire provided by an embodiment of the present invention;

[0046] Figure 7 It is a flowchart of a method for training an illegal behavior identification model at a drilling site provided by an embodiment of the present invention;

[0047] Figure 8 It is a structural block diagram of a device for identifying illegal behaviors at a drilling site provided by an embodiment of the present invention. Detailed Embodiments

[0048] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully communicated to those skilled in the art.

[0049] To solve the problem of difficulty in identifying illegal behaviors at the drilling site, an embodiment of the present invention provides a method for identifying illegal behaviors at the drilling site, and its flowchart is as Figure 1 shown, including:

[0050] Step S11, obtain real-time video data of the drilling production site;

[0051] Step S12, convert the video data into corresponding frame images;

[0052] Step S13, extract the characteristic data of behaviors and actions from the frame image data;

[0053] Step S14, input the extracted feature vectors into a pre-trained illegal behavior recognition model for the drilling site, and determine whether a preset illegal behavior has occurred at the drilling production site according to the output result of the illegal behavior recognition model for the drilling site.

[0054] Examples of illegal behaviors at the drilling site in the embodiments of the present invention may include not wearing labor protection and safety helmets in a standardized manner, smoking illegally, making or answering calls illegally, blocking the camera, entering dangerous areas illegally, smoke and fire, etc.; in Figure 2 , there is a on-site worker not wearing labor protection and safety helmets in a standardized manner in the left and right figures respectively; in Figure 3 , there is a smoking person in the left and right figures respectively; in Figure 4 , there is a person making or answering calls illegally in the left and right figures respectively; in Figure 5 , the camera is blocked in the left figure, and there is a person crossing the boundary in the right figure; in Figure 6 , there are situations of flames and smoke.

[0055] In the above step S12, to convert the video data into corresponding frame images, for example, the optical flow method can be used to perform optical flow calculation on the video data to obtain adjacent optical flow image data, which are the aforementioned frame images, as well as the velocity vectors of each pixel of the frame image in the x direction and the velocity vectors in the y direction;

[0056] Next, in the above step S13, to extract the characteristic data of behaviors and actions from the frame image data, the following method can be used:

[0057] For pixel I(x, y, t), where x and y represent the spatial coordinates of pixel I, and t represents the data in the time dimension of pixel I, the position where pixel I moves from the current frame image to the next frame image is (dx, dy), and the time used is dt. The velocity vector u of pixel I in the x direction:

[0058]

[0059] The velocity vector v of pixel I in the y direction:

[0060]

[0061] The data of the pixel I is input into the space and time channels of the dual-channel convolutional neural network to obtain the corresponding drilling site violation classification feature values ​​c1 and c2 based on the space and time characteristics. The feature values ​​c1 and c2 are weighted averaged to obtain the final feature value c. The calculation formula of the feature value c can be, for example:

[0062] c=ac1+(1-a)c2, where a is a sensitivity parameter, ranging from 0.1 to 1, and 0.4 in the embodiment of the present invention;

[0063] Combined with the preset regulations on drilling site violations and the operating procedures for drilling operations, the characteristic values ​​can be classified according to the above-mentioned drilling site violations, such as failure to properly wear labor protection and safety helmets, illegal smoking, and illegal use of mobile phones.

[0064] In the above step S14, the drilling site violation identification model can be trained using the following method, and its flowchart is shown in FIG. Figure 7 :

[0065] Step S71, collecting video and image data of the drilling site;

[0066] Step S72: calibrate the video and image data of the drilling site violations according to the preset regulations on drilling site violations and the operating procedures of the drilling operation, and obtain the calibrated video and image data of the drilling site violations;

[0067] Step S73, extracting the features of corresponding behaviors and actions according to the calibrated drilling site violation videos and image data to obtain the features of the drilling site violation behaviors;

[0068] Step S74: training a neural network based on the characteristics of the drilling site violations to obtain a drilling site violation recognition model.

[0069] In the aforementioned step S74, in order to make the aforementioned drilling site violation behavior identification model prediction more accurate, the following operations may also be performed:

[0070] Collect new video data from the drilling site;

[0071] The new video data of the drilling site is used as a training set, and the drilling site violation identification model is repeatedly trained to obtain an optimized drilling site violation identification model.

[0072] Regarding the aforementioned method for identifying illegal behaviors at a drilling site, before performing step S11, the following operations may also be performed:

[0073] Determine the identification scope and area of the drilling site violation behavior according to the video data of the drilling site violation behavior, the relevant regulations of the drilling site violation behavior, and the operating procedures of the drilling operation;

[0074] Correspondingly, obtain the real-time video data within the determined identification scope and area.

[0075] After identifying the drilling site violation behavior, in order to contain the violation behavior, the following operations can also be performed:

[0076] If a violation behavior is identified at the drilling production site, then according to the preset warning method corresponding to the drilling site violation behavior, an alarm message is sent in real time, and / or the violation behavior information is stored.

[0077] Based on the same inventive concept, an embodiment of the present invention also provides an identification device for drilling site violation behavior, and its structural block diagram is as Figure 8 shown, including:

[0078] An acquisition module 81, configured to acquire real-time video data of the drilling production site;

[0079] A frame conversion module 82, configured to convert the video data into corresponding frame images;

[0080] An extraction module 83, configured to extract the feature data of behaviors and actions from the frame image data;

[0081] An identification module 84, configured to input the extracted feature vectors into a pre-trained identification model for drilling site violation behavior, and determine whether a preset violation behavior has occurred at the drilling production site according to the output result of the identification model for drilling site violation behavior.

[0082] Based on the same inventive concept, an embodiment of the present invention also provides a server, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the identification method for drilling site violation behavior.

[0083] Based on the same inventive concept, an embodiment of the present invention also provides an identification system for drilling site violation behavior, including:

[0084] Drilling site video monitoring equipment and the server as described in the foregoing embodiment;

[0085] The drilling site video monitoring equipment is configured to collect real-time video data of the drilling production site and output it to the server.

[0086] In one embodiment, the foregoing system further includes:

[0087] An early warning device is configured to issue corresponding forms of early warning information based on an early warning signal determined by the server indicating that a preset violation has occurred at the drilling production site, and / or store the information on the violation behavior.

[0088] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for identifying violation behaviors at a drilling site.

[0089] Since the principles of the problems solved by these devices are similar to those of the aforementioned method for identifying violation behaviors at a drilling site, the implementation of these devices can refer to the implementation of the aforementioned method, and the repeated parts will not be elaborated.

[0090] An embodiment of the present invention provides a method for identifying violation behaviors at a drilling site, including: obtaining real-time video data of the drilling production site; converting the video data into corresponding frame images; extracting feature data of behaviors and actions from the frame image data; inputting the extracted feature vectors into a pre-trained model for identifying violation behaviors at the drilling site, and determining whether a preset violation has occurred at the drilling production site according to the output result of the model for identifying violation behaviors at the drilling site. The embodiment of the present invention monitors the drilling site in real time, can timely detect dangerous items and dangerous behaviors existing at the drilling site, and give an alarm, thereby effectively preventing the occurrence of dangerous accidents, ensuring the safety of the staff at the drilling site, and also ensuring the safety of the drilling site; it can also effectively supervise the standardized operation of the staff at the drilling site and enhance the work efficiency of the staff at the drilling site.

[0091] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories and optical memories, etc.) containing computer-usable program codes.

[0092] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1means for the functions specified in one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0093] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions in the process Figure 1 means for the functions specified in one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions in the process Figure 1 means for the functions specified in one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks. Obviously, those skilled in the art can make various modifications and variations 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 equivalent technologies, the present invention is also intended to include these modifications and variations therein.

Claims

1. A method for identifying illegal behaviors at a drilling site, characterized in that, Including: Obtain real-time video data of the drilling production site; Convert the video data into corresponding frame images; Extract the feature data of behaviors and actions from the frame image data; Input the extracted feature vectors into a pre-trained drilling site violation behavior recognition model, and determine whether a preset violation behavior occurs at the drilling production site according to the output result of the drilling site violation behavior recognition model.

2. The method according to claim 1, characterized in that, The drilling site violation behavior recognition model is trained in the following manner: Collect video and image data of the drilling site; According to the relevant regulations on drilling site violation behaviors preset and the operating procedures of drilling operations, calibrate the video and image data of the drilling site violation behaviors to obtain calibrated video and image data of the drilling site violation behaviors; Extract the corresponding features of behaviors and actions from the calibrated video and image data of the drilling site violation behaviors to obtain drilling site violation behavior features; Train a neural network through the features of the drilling site violation behaviors to obtain the drilling site violation behavior recognition model.

3. The method according to claim 2, characterized in that, Training the neural network according to the features of the drilling site violation behaviors to obtain the neural network for recognizing drilling site violation behaviors further includes: Collect new video data of the drilling site; Use the new video data of the drilling site as a training set to repeatedly train the drilling site violation behavior recognition model to obtain an optimized drilling site violation behavior recognition model.

4. The method according to claim 2, wherein The method further includes: Determine the recognition scope and area of the drilling site violation behavior according to the video data of the drilling site violation behavior, the relevant regulations on the drilling site violation behavior, and the operating procedures of drilling operations; Correspondingly, obtain real-time video data within the determined recognition scope and area.

5. The method according to claim 1, wherein The method further includes: If it is recognized that a violation behavior occurs at the drilling production site, then issue an alarm message in real time according to the preset warning method corresponding to the drilling site violation behavior, and / or store the violation behavior information.

6. An identification device for illegal acts at a drilling site, characterized in that, Including: An acquisition module for obtaining real-time video data of the drilling production site; A frame conversion module for converting the video data into corresponding frame images; An extraction module for extracting the feature data of behaviors and actions from the frame image data; A recognition module for inputting the extracted feature vectors into a pre-trained drilling site violation behavior recognition model and determining whether a preset violation behavior occurs at the drilling production site according to the output result of the drilling site violation behavior recognition model.

7. A server, characterized in that, Including: A memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the recognition method of the drilling site violation behavior according to any one of claims 1-5 is implemented.

8. An identification system for illegal acts at a drilling site, characterized in that, Including: Drilling site video monitoring equipment and a server as claimed in claim 7; The drilling site video monitoring equipment is used for collecting real-time video data of the drilling production site and outputting it to the server.

9. The system according to claim 8, wherein Further including: An early warning device is configured to issue early warning information in a corresponding form based on an early warning signal determined by the server that a preset violation has occurred at the drilling production site, and / or store the violation information.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying violations at the drilling site according to any one of claims 1-5 is implemented.

Images