Auxiliary method and auxiliary device for standard installation of explosive packages based on AI recognition algorithm

Abstract

The present invention provides an auxiliary method and device for installing explosive packs based on AI recognition algorithm specifications, and belongs to the technical field of explosive pack installation. The auxiliary method comprises: obtaining an installation video including the overall installation process of the explosive pack, wherein the installation video includes the corresponding body language made by the installer before each installation step of the explosive pack is implemented; using the AI ​​recognition algorithm to recognize each body language in the installation video, and forming corresponding key frames in the installation video; uploading the installation video formed by shooting the overall installation process of installing the explosive pack to the back end for review, and the reviewer checks whether the installation steps meet the specifications based on the key frames. The method quickly locates the video node of the installation step through the key frame, reduces the time spent by the reviewer to find the video clip of the installation step, directly improves the review efficiency, and indirectly improves the installation efficiency of the explosive pack.

Description

Technical Field

[0001] The present invention relates to the technical field of explosive pack installation, and in particular to an auxiliary method for installing explosive packs based on AI recognition algorithm specifications, an auxiliary device for installing explosive packs based on AI recognition algorithm specifications, a computer-readable storage medium and an electronic device. Background Art

[0002] During geophysical oil surveys, workers install multiple explosive packs at a certain distance and detonate them simultaneously to generate seismic waves that are used to detect the distribution of oil below the surface.

[0003] The explosive packs must be installed in accordance with the specifications and safely. Each operation requires the installation of hundreds of explosive packs and their detonation at one time. If the operation is not standardized, duds will result, which will cause incomplete distribution of seismic waves and incomplete data chains, resulting in huge losses.

[0004] Therefore, installers are required to install each explosive package in accordance with the specifications, and each explosive installation process must be recorded on video for 25-30 minutes. Inspectors have to watch hundreds of videos to confirm that the installation is correct. However, during the video review process, inspectors often cannot locate the video clips of the explosive package installation at the first time, and need to search step by step in the recorded video, which is a huge workload. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an auxiliary method for installing explosive packages based on AI recognition algorithm specifications, an auxiliary device for installing explosive packages based on AI recognition algorithm specifications, a computer-readable storage medium and an electronic device, so as to at least solve the problem of large workload of video review mentioned above.

[0006] In order to achieve the above-mentioned object, the first aspect of the present invention provides an auxiliary method for installing explosive packages based on AI recognition algorithm specifications, comprising:

[0007] Obtaining an installation video including the overall installation process of the explosive package, wherein the installation video includes corresponding body language performed by the installer before each installation step of the explosive package is performed;

[0008] AI recognition algorithms are used to identify various body languages ​​in the installation video and form corresponding key frames in the installation video.

[0009] In this method, body language is added before each installation step to serve as a key frame in the later video review process. The reviewer can quickly locate the installation step through the reminder of the key frame, which greatly improves the review efficiency.

[0010] Optionally, also include:

[0011] Upload the installation video to the backend for review, which includes:

[0012] Check whether the corresponding installation steps meet the specifications based on the key frames in the installation video.

[0013] Optionally, checking whether corresponding installation steps comply with specifications based on key frames in the installation video includes:

[0014] Based on the key frames, locate the corresponding installation step video node in the installation video to check whether the corresponding installation step in the installation video meets the specifications.

[0015] Keyframes have the effect of rapid positioning. Auditors can use keyframes to quickly find video clips that record installation steps, and then review whether the installation steps comply with specifications, thereby improving review efficiency.

[0016] Optionally, the installation video is transmitted to the back end in real time via 4G / 5G. 4G / 5G transmission has the advantages of fast speed and no space limitation.

[0017] Optionally, the AI ​​recognition algorithm is trained using a deep learning method based on body language videos or body language pictures stored in an existing database.

[0018] The AI ​​recognition algorithm trained by deep learning methods has the advantages of high recognition rate and fast recognition efficiency.

[0019] Optionally, the body language includes gestures, bending and jumping.

[0020] A second aspect of the present invention provides an auxiliary device for installing explosive packs based on AI recognition algorithm specifications, comprising:

[0021] A filming module, used to film the installation process of the explosive pack;

[0022] An AI recognition module is used to use an AI recognition algorithm to recognize various body languages ​​in the installation video and form corresponding key frames in the installation video;

[0023] A data transmission module, used to upload the installation video shot by the shooting module;

[0024] The review module is used to receive the installation video and check whether the corresponding installation steps meet the specifications based on the key frames in the installation video.

[0025] The AI ​​recognition module provided by this device can clearly identify the body language of the installer and generate key frames for quickly locating the installation steps in the subsequent video review process. Based on the key frames, the review module can quickly review whether the installation steps meet the specifications.

[0026] Optionally, the data transmission module uploads the installation video in real time via 4G / 5G.

[0027] A third aspect of the present invention provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the method according to the first aspect.

[0028] The present invention also provides an electronic device, comprising: at least one processor and a memory;

[0029] The memory stores computer-executable instructions;

[0030] The at least one processor executes the computer-executable instructions stored in the memory, so that the electronic device performs the method described in the first aspect.

[0031] Through the above technical solution, the video clips of the installation steps can be quickly located in the installation video, reducing the time spent by auditors to find the video clips of the installation steps, improving the audit efficiency, and then improving the installation efficiency of the explosive package, greatly shortening the overall installation time of the explosive package.

[0032] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0034] Figure 1 The present invention provides a flowchart of an auxiliary method for installing explosive packages based on AI recognition algorithm specifications, according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0036] Figure 1 The flowchart of an auxiliary method for installing explosive packs based on AI recognition algorithm specifications is provided in one embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides an auxiliary method for installing explosive packages based on AI recognition algorithm specifications, the method comprising:

[0037] S1: Obtain an installation video including the overall installation process of the explosive package, wherein the installation video includes corresponding body language made by the installer before each installation step of the explosive package is performed. In this embodiment, before each installation step, the installer makes a specific body language, and uses a camera to shoot the overall installation process of the explosive package to obtain the installation video. The camera has a high-definition image acquisition function, and can clearly capture human body movements during the installation process of the explosive package.

[0038] The body language in this embodiment can be gestures, bending or jumping and other actions, so the camera needs to be able to locate and detect the hands, head, shoulders, feet and other parts of the human body, and have functions such as supporting half-body detection, position framing, and motion tracking.

[0039] S2: Use AI recognition algorithm to identify body language and form key frames. Key frames are used as labels to represent the node position of the installation step video segment in the installation video. Through key frames, the installation step video segment can be directly located in the installation video of the explosive package.

[0040] In a specific implementation example, the installation steps of the explosive pack are divided into five steps. Correspondingly, the installer makes gestures from one to five, and one gesture corresponds to one step. For example, when gesture one is made, it indicates installation step one, when gesture two is made, it indicates installation step two, and so on. The camera captures the gestures made by the installer, and the AI ​​recognition algorithm recognizes these gestures to form key frames representing the installation steps.

[0041] S3: The explosive pack installation video shot by the camera is uploaded to the backend. The auditor reviews the installation video and locates the installation step video node through the key frame in the installation video to check whether the installation step complies with the specifications.

[0042] Normally, an installation video is about half an hour long, but the video segment of the installation steps is very short. In the traditional audit process, auditors need to spend a lot of time to find the video segment of the installation steps. The key frames proposed by this method can help auditors quickly find the installation step video nodes, reducing the time spent by auditors on finding the installation step video nodes in the installation video, greatly improving the audit efficiency, and indirectly improving the installation efficiency of the explosive package.

[0043] In some feasible embodiments, since the AI ​​recognition algorithm in this embodiment involves the detection and recognition of multiple parts of the human body, the detection content is relatively large and the detection content is relatively complex, in this embodiment, a deep learning method is used to train the AI ​​recognition algorithm through a large number of videos or pictures that record human body language. The video or picture can be searched in an existing database on the Internet, such as Baidu Gallery. The recognition rate of the AI ​​recognition algorithm trained in this way is as high as 99% or more, ensuring the accuracy of recognition.

[0044] In some feasible embodiments, the installation video is transmitted to the back-end in real time via 4G / 5G for review. Since there is a certain distance between the location where the explosives are installed and the location where the installation video is reviewed, the 4G / 5G transmission method has the advantages of being able to transmit anytime and anywhere, and the transmission rate is fast enough, which is very suitable for transmitting installation videos.

[0045] An embodiment of the present invention provides an auxiliary device for installing explosive packages based on AI recognition algorithm specifications, including: a shooting module, an AI recognition module, a data transmission module and an audit module; wherein the shooting module is used to shoot the installation process of the explosive package to form an installation video, and the installation video is transmitted to the audit module through the data transmission module for audit.

[0046] The AI ​​recognition module is used to recognize the body language of the installer to form a key frame. Before each installation step, the installer will make corresponding body language, such as gestures or jumping. The AI ​​recognition module has a built-in AI recognition algorithm, which recognizes body language. It should be noted that the AI ​​recognition algorithm built into the AI ​​recognition module is the AI ​​recognition algorithm recorded in the auxiliary method for installing explosive packages based on AI recognition algorithm specifications provided in this embodiment, and the two are the same algorithm.

[0047] The data transmission module is used to upload the installation video taken by the shooting module to the review module. In this embodiment, the data transmission module transmits the installation video via 4G / 5G. Since the location where the explosives are installed is a certain distance away from the location where the installation video is reviewed, and 4G / 5G has the advantage of being able to transmit anytime and anywhere, it is very suitable for transmitting the installation video of the explosive package.

[0048] The audit module is used to receive the installation video and audit whether the installation steps meet the specifications based on the key frames. The audit module can easily locate the video node of the installation step of the explosive package through the key frames, and then check whether the installation steps in the video meet the specifications. The method of locating the installation step video node through the key frames greatly reduces the time spent on the search process in the audit work, directly improves the audit efficiency, and indirectly improves the installation efficiency of the explosive package.

[0049] An embodiment of the present invention further provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes an auxiliary method for installing explosive packages based on AI recognition algorithm specifications provided in this embodiment.

[0050] An embodiment of the present invention further provides an electronic device, comprising: at least one processor and a memory;

[0051] The memory stores computer-executable instructions;

[0052] The at least one processor executes the computer-executable instructions stored in the memory, so that the electronic device executes an auxiliary method for installing explosive packages based on AI recognition algorithm specifications provided in this embodiment.

[0053] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0054] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0055] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. An auxiliary method for installing explosive packages based on AI recognition algorithm specifications, characterized in that: include: Obtaining an installation video including the entire installation process of the explosive package, wherein the installation video includes corresponding body language performed by the installer before each installation step of the explosive package is performed; wherein each body language corresponds to one installation step; An AI recognition algorithm is used to identify various body languages ​​in the installation video, and corresponding key frames are formed in the installation video; wherein the key frames are used to locate the corresponding installation step video nodes in the installation video to check whether the corresponding installation steps in the installation video meet the specifications.

2. The auxiliary method for installing explosive packages based on AI recognition algorithm specifications according to claim 1 is characterized in that: Also includes: Upload the installation video to the backend for review, which includes: Check whether the corresponding installation steps meet the specifications based on the key frames in the installation video.

3. The auxiliary method for installing explosive packages based on AI recognition algorithm specifications according to claim 2 is characterized in that: The installation video is transmitted to the backend in real time via 4G / 5G.

4. The auxiliary method for installing explosive packages based on AI recognition algorithm specifications according to claim 1 is characterized in that: Based on the body language videos or body language pictures stored in the existing database, the AI ​​recognition algorithm is trained using a deep learning method.

5. The auxiliary method for installing explosive packages based on AI recognition algorithm specifications according to claim 1 is characterized in that: The body language includes hand gestures, bending over, and jumping.

6. An auxiliary device for installing explosive packs based on AI recognition algorithm specifications, characterized in that: include: A filming module, used to film the installation process of the explosive pack; The AI ​​recognition module is used to use the AI ​​recognition algorithm to recognize each body language in the installation video and form corresponding key frames in the installation video; wherein the installation video contains the corresponding body language made by the installer before each installation step of the explosive package is implemented, and each body language corresponds to one installation step; A data transmission module, used to upload the installation video shot by the shooting module; The review module is used to receive the installation video and check whether the corresponding installation steps meet the specifications based on the key frames in the installation video.

7. The auxiliary device for installing explosive packs based on AI recognition algorithm specifications according to claim 6 is characterized in that: The data transmission module uploads the installation video in real time via 4G / 5G.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 5.

9. An electronic device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 5.

Images