Industrial video real-time supervision platform with cloud storage

Abstract

The invention relates to the technical field of data processing, and discloses an industrial video real-time supervision platform with cloud storage, which comprises the following steps: S01, acquiring monitoring data of a moving fuzzy unit in shooting under a monitoring point; s02, calculating height data of a fuzzy unit according to the monitoring data; s03, correcting the height data based on an integrated algorithm of a random forest and a gradient boosting tree to obtain a moving track of the current fuzzy unit, and judging the data confidence of the moving track; and S04, performing feature statistical analysis through OpenCV background modeling according to the height data and the data confidence, and obtaining features of a fuzzy unit. The method has remarkable advantages and effects in the aspects of fuzzy region recognition, height data calculation, trajectory prediction, feature extraction and matching, action recognition and comparison, system robustness and the like, and provides guarantee for real-time monitoring and safety management of industrial production.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an industrial video real-time monitoring platform with cloud storage. Background Art

[0002] Real-time industrial video monitoring is an important part of the industrial manufacturing field. It uses video monitoring technology combined with artificial intelligence (AI) and other advanced technologies to achieve real-time monitoring, management, analysis and early warning of the production process. By real-time monitoring of the operating status of the production line and the operation of workers, production anomalies can be discovered and handled in a timely manner to ensure the stability and efficiency of the production process.

[0003] Publication (announcement) number: CN112969058B, Publication (announcement) date: 2021-08-03, a real-time industrial video monitoring platform and method with cloud storage function is disclosed, including a cloud computing-based data processing server, a database server, a relay server, an application server, an intelligent communication gateway, an Internet of Things controller, a control terminal, and a video acquisition terminal. The cloud computing-based data processing server and application server are connected to the intelligent communication gateway, the intelligent communication gateway is connected to the database server, the relay server and the control terminal, and the Internet of Things controller establishes a data connection with the intelligent communication gateway and is connected to the video acquisition terminal. The method includes four steps: system assembly, system prefabrication, video signal acquisition and video data supervision. The present invention can effectively meet the needs of efficient acquisition operations of various video signals in various usage environments; while greatly improving the flexibility, stability and reliability of video monitoring operations, it also effectively improves the working accuracy of video data management and monitoring operations.

[0004] In the prior art including the above patents, the basic framework of real-time industrial video monitoring is to collect high-definition video images, store the video data in a cloud disk, and then extract the cloud disk data for analysis to achieve production monitoring. The core of the processing in the prior art is how to store data and respond quickly to the input video data. However, due to the problem of pixels, for a farther monitoring area, the images taken by the high-definition camera are difficult to be recognized by the system, so multiple high-definition cameras are needed to assist in forming a complete and clear monitoring. However, if the high-definition camera at a certain monitoring point is damaged or the data is lost, this relative clarity will be broken. How to solve this problem is expected to be well solved. Summary of the invention

[0005] The purpose of this invention is to provide an industrial video real-time monitoring platform with cloud storage.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An industrial video real-time monitoring platform with cloud storage includes the following steps:

[0008] S01, obtaining monitoring data of the moving blur unit in the shooting under the monitoring point;

[0009] S02, calculating the height data of the fuzzy unit according to the monitoring data;

[0010] S03, modifying the height data based on an integrated algorithm of random forest and gradient boosting tree to obtain a moving trajectory of the current fuzzy unit and determine the data confidence of the moving trajectory;

[0011] S04, performing feature statistical analysis through OpenCV background modeling according to the height data and the data confidence, to obtain the features of the fuzzy unit;

[0012] S05. Based on the characteristics of the fuzzy unit, determine the action performed by the fuzzy unit, compare each frame of image with a preset dangerous action, and locate the fuzzy unit that meets the dangerous action and feed it back to the background.

[0013] Preferably, determining the moving blur unit in step S01 includes:

[0014] S11, based on each frame of the acquired image and the frequency spectrum after Fourier transformation, determining an area in the image where the high-frequency component is reduced to a greater extent, and determining it as a blurred area;

[0015] S12, extracting the blurred area and automatically and intelligently sharpening it to form a state sufficient for being recognized by the system, and then extracting characteristic units of the blurred area;

[0016] S13, performing the processing of step S11 and step S12 on the images of adjacent predetermined periods, comparing and correcting a plurality of feature units, thereby determining the blur unit in motion, and setting a capture frame for tracking.

[0017] Preferably, the processing step of obtaining the target height data in step S02 includes:

[0018] S21, based on the frequency of each data collection being 1s / 2, to form the collection of continuous data within a window of a predetermined length, and marking them as X1, X2, ..., Xn;

[0019] S22, extracting the moving fuzzy units identified in the multiple frames of images in the multiple windows, and then extracting the determined features around the moving fuzzy units to determine the feature type;

[0020] S23, based on a given feature type, obtaining height data about the feature type, and converting the height data of the moving fuzzy unit by geometric conversion;

[0021] S24, based on the height data of the moving blur unit given by each window, several similar height data in multiple windows are averaged to determine the height data of the moving blur unit.

[0022] Preferably, the processing step of correcting the target height data by the integrated algorithm of random forest and gradient boosting tree in step S03 includes:

[0023] S31, extracting features and integrating targets based on the monitoring data, obtaining multiple trajectory points of fuzzy units moving under continuous windows, random forest, and scatter point regression results, and finally determining multiple moving routes to form first data;

[0024] S32, based on the data acquired by the radar, obtaining a spatiotemporal value within a nearby threshold range;

[0025] S33, performing vector analysis on the navigation trajectory according to the time node of acquiring the data to obtain multiple estimated trajectory samples, and fitting the multiple samples to form a gradient boosting tree;

[0026] S34, matching the fitted unique / multiple targets with the multiple track points of the moving fuzzy unit to determine the moving direction of the moving fuzzy unit.

[0027] Preferably, in step S04, feature statistical analysis is performed through OpenCV background modeling to obtain the features of the blur unit, including:

[0028] S41, transmitting the first data to the OpenCV background model;

[0029] S42, extracting the first data to perform preset feature matching to determine whether it is a target type;

[0030] S43. The height data of the moving fuzzy unit is extracted through a random window period of data to generate second data, and the second data is imported into step S41 and step S42. The judgment result is compared with the target type determined in step S42. If they are consistent, the target type is established; if they are inconsistent, a warning feedback is generated.

[0031] Preferably, in step S05, judging the action to be performed by the fuzzy unit based on the characteristics of the fuzzy unit includes:

[0032] S51, detecting and identifying a human body in the image, and then extracting key point information of the human body, wherein the key point information is a moving point sufficient to reflect the posture of the human body's limbs;

[0033] S52, extracting motion data by analyzing changes in key points of the human body between consecutive frames of each window.

[0034] Preferably, comparing each frame of image with a preset dangerous action in step S05 includes:

[0035] S53, identifying several combinations of the extracted action data, and then matching the combinations with the features in the comparison database to find the most similar feature combination;

[0036] S54, calculating the similarity between the action to be identified and each dangerous action in the database based on the distance or similarity between the feature vectors;

[0037] S55. Evaluate the dangerousness of the action to be identified based on the similarity calculation result.

[0038] In the above technical solution, the present invention provides an industrial video real-time monitoring platform with cloud storage, which has the following beneficial effects:

[0039] 1. The fuzzy area is determined through Fourier transform and spectrum analysis, and the image is automatically and intelligently sharpened, which improves the recognition accuracy of fuzzy units and can effectively capture and identify targets even in distant monitoring areas.

[0040] 2. Through multi-frame image data sampling and feature extraction, combined with geometric conversion and averaging processing, more accurate target height data can be obtained, providing a reliable foundation for subsequent trajectory analysis and action recognition.

[0041] 3. The integrated algorithm of random forest and gradient boosting tree is used to correct the altitude data, and combined with radar data and spatiotemporal numerical analysis, the prediction accuracy and data confidence of the movement trajectory are improved, and the risk of false alarm and missed alarm is reduced.

[0042] 4. Through OpenCV background modeling and feature statistical analysis, the features of fuzzy units are extracted quickly and accurately, and compared with preset dangerous actions, achieving real-time warning and feedback of dangerous behaviors.

[0043] 5. Through human body detection and key point extraction, combined with the key point change analysis between consecutive frames, action data is extracted and matched with the dangerous action features in the comparison database, realizing real-time recognition and danger assessment of the actions performed by fuzzy units.

[0044] 6. It not only improves the recognition ability of fuzzy areas and the accuracy of data processing, but also enhances the overall robustness of the system through multi-camera collaboration and data fusion technology. Even if the high-definition camera at a certain monitoring point is damaged or data is lost, it can be supplemented and corrected through data from other monitoring points to ensure the continuity and integrity of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0046] Figure 1 A flowchart provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] like Figure 1 As shown, a real-time industrial video monitoring platform with cloud storage includes the following steps:

[0049] S01, obtaining monitoring data of the moving blur unit in the shooting under the monitoring point;

[0050] The blur units that determine movement include:

[0051] S11, based on each frame of the acquired image and the frequency spectrum after Fourier transformation, determining an area in the image where the high-frequency component is reduced to a greater extent, and determining it as a blurred area;

[0052] S12, extracting the blurred area and automatically and intelligently sharpening it to form a state sufficient for being recognized by the system, and then extracting characteristic units of the blurred area;

[0053] S13, performing the processing of step S11 and step S12 on the images of adjacent predetermined periods, comparing and correcting the multiple feature units, thereby determining the blurred units in motion, and setting a capture frame for tracking.

[0054] The above-mentioned method determines the blurred area through Fourier transform and spectrum analysis, and automatically and intelligently sharpens it, which improves the recognition accuracy of blurred units and can effectively capture and identify targets even in farther monitoring areas.

[0055] S02, calculating the height data of the fuzzy unit according to the monitoring data;

[0056] The processing steps to obtain target height data include:

[0057] S21, based on the frequency of each data collection being 1s / 2, to form the collection of continuous data within a window of a predetermined length, and marking them as X1, X2, ..., Xn;

[0058] S22, extracting the moving fuzzy units identified in the multiple frames of images in the multiple windows, and then extracting the determined features around the moving fuzzy units to determine the feature type;

[0059] S23, based on a given feature type, obtaining height data about the feature type, and converting the height data of the moving fuzzy unit by geometric conversion;

[0060] S24, based on the height data of the moving blur unit given by each window, several similar height data in multiple windows are averaged to determine the height data of the moving blur unit.

[0061] By sampling and extracting features from multiple frames of image data, combined with geometric conversion and averaging processing, more accurate target height data can be obtained, providing a reliable basis for subsequent trajectory analysis and action recognition.

[0062] S03. Correct the height data based on the integrated algorithm of random forest and gradient boosting tree to obtain the moving trajectory of the current fuzzy unit and determine the data confidence of the moving trajectory;

[0063] The processing steps include:

[0064] S31, extracting features and integrating targets based on monitoring data, obtaining multiple trajectory points of fuzzy units moving under continuous windows, random forest, and scatter point regression results, and finally determining multiple moving routes to form first data;

[0065] S32, based on the data acquired by the radar, obtaining a spatiotemporal value within a nearby threshold range;

[0066] S33, performing vector analysis on the navigation trajectory according to the time node of acquiring the data to obtain multiple estimated trajectory samples, and fitting the multiple samples to form a gradient boosting tree;

[0067] S34, matching the fitted unique / multiple targets with the multiple track points of the moving fuzzy unit to determine the moving direction of the moving fuzzy unit.

[0068] The above-mentioned integrated algorithm of random forest and gradient boosting tree is used to correct the altitude data, and combined with radar data and spatiotemporal numerical analysis, it improves the prediction accuracy and data confidence of the movement trajectory and reduces the risk of false alarms and missed alarms.

[0069] S04. According to the height data and data confidence, feature statistical analysis is performed through OpenCV background modeling to obtain the features of the blur unit;

[0070] The above feature statistical analysis is performed through OpenCV background modeling to obtain the characteristics of the blur unit, including:

[0071] S41, transmitting the first data to the OpenCV background model;

[0072] S42, extracting the first data to perform preset feature matching to determine whether it is a target type;

[0073] S43, extracting the height data of the moving fuzzy unit through a random window period of data, generating second data, and importing the second data into step S41 and step S42, comparing the determination result with the target type determined in step S42, if they are consistent, the target type is established; if they are inconsistent, generating a warning feedback

[0074] Through OpenCV background modeling and feature statistical analysis, the features of fuzzy units are extracted quickly and accurately, and compared with preset dangerous actions, thus achieving real-time warning and feedback of dangerous behaviors.

[0075] S05. Based on the characteristics of the fuzzy unit, determine the action performed by the fuzzy unit, compare each frame of the image with a preset dangerous action, and locate the fuzzy unit that meets the dangerous action and feed it back to the background.

[0076] The above-mentioned action of determining the fuzzy unit to be executed according to the characteristics of the fuzzy unit includes:

[0077] S51, detecting and identifying a human body in the image, and then extracting key point information of the human body, where the key point information is a moving point sufficient to reflect the posture of the human body's limbs;

[0078] S52, extracting action data by analyzing changes in key points of the human body between consecutive frames of each window;

[0079] S53, identifying several combinations of the extracted action data, and then matching the combinations with the features in the comparison database to find the most similar feature combination;

[0080] S54, calculating the similarity between the action to be identified and each dangerous action in the database based on the distance or similarity between the feature vectors;

[0081] S55. Evaluate the dangerousness of the action to be identified based on the similarity calculation result.

[0082] In summary, the blurred area is determined through Fourier transform and spectrum analysis, and automatic intelligent sharpening is performed, which improves the recognition accuracy of blurred units and can effectively capture and identify targets even in farther monitoring areas.

[0083] The above-mentioned human body detection and key point extraction, combined with the key point change analysis between consecutive frames, extracts action data and matches it with the dangerous action features in the comparison database, thus achieving real-time recognition and risk assessment of the actions performed by the fuzzy units. It not only improves the recognition ability and data processing accuracy of the fuzzy area, but also enhances the overall robustness of the system through multi-camera collaboration and data fusion technology. Even if the high-definition camera at a certain monitoring point is damaged or the data is lost, it can be supplemented and corrected through the data of other monitoring points to ensure the continuity and integrity of monitoring.

[0084] 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, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to 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 process and / or block in the flowchart and / or block diagram, as well as the combination of 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 produce 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 1 A device that provides the functions specified in a block or multiple blocks.

[0086] 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.

[0087] 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.

[0088] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0089] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0090] Processor, memory, communications interface and bus;

[0091] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0092] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0093] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0094] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps described in the embodiment or flow chart, more or less operation steps can be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the process and / or box 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0096] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A real-time industrial video monitoring platform with cloud storage, characterized in that: The following steps are involved: S01, obtaining monitoring data of the moving blur unit in the shooting under the monitoring point; S02, calculating the height data of the fuzzy unit according to the monitoring data; S03, modifying the height data based on an integrated algorithm of random forest and gradient boosting tree to obtain a moving trajectory of the current fuzzy unit and determine the data confidence of the moving trajectory; S04, performing feature statistical analysis through OpenCV background modeling according to the height data and the data confidence, to obtain the features of the fuzzy unit; S05. Based on the characteristics of the fuzzy unit, determine the action performed by the fuzzy unit, compare each frame of image with a preset dangerous action, and locate the fuzzy unit that meets the dangerous action and feed it back to the background.

2. The industrial video real-time monitoring platform with cloud storage according to claim 1 is characterized in that: Determining the moving blur unit in step S01 includes: S11, based on each frame of the collected image and the frequency spectrum after Fourier transformation, determining an area in the image where the high-frequency component is reduced to a greater extent, and determining it as a blurred area; S12, extracting the blurred area and automatically and intelligently sharpening it to form a state sufficient for being recognized by the system, and then extracting characteristic units of the blurred area; S13, performing the processing of step S11 and step S12 on the images of adjacent predetermined periods, comparing and correcting a plurality of feature units, thereby determining the blur unit in motion, and setting a capture frame for tracking.

3. The industrial video real-time monitoring platform with cloud storage according to claim 1 is characterized in that: The processing steps for obtaining the target height data in step S02 include: S21, based on the frequency of each data collection being 1s / 2, to form the collection of continuous data within a predetermined length window, and marking them as X1, X2, ..., Xn; S22, extracting the moving fuzzy units identified in the multiple frames of images in the multiple windows, and then extracting the determined features around the moving fuzzy units to determine the feature type; S23, based on a given feature type, obtaining height data about the feature type, and converting the height data of the moving fuzzy unit by geometric conversion; S24, based on the height data of the moving blur unit given by each window, several similar height data in multiple windows are averaged to determine the height data of the moving blur unit.

4. The industrial video real-time monitoring platform with cloud storage according to claim 1 is characterized in that: The processing steps of correcting the target height data by the integrated algorithm of random forest and gradient boosting tree in step S03 include: S31, extracting features and integrating targets based on the monitoring data, obtaining multiple trajectory points of fuzzy units moving under continuous windows, random forest, and scatter point regression results, and finally determining multiple moving routes to form first data; S32, based on the data acquired by the radar, obtaining a spatiotemporal value within a nearby threshold range; S33, performing vector analysis on the navigation trajectory according to the time node of acquiring the data to obtain multiple estimated trajectory samples, and fitting the multiple samples to form a gradient boosting tree; S34, matching the fitted unique / multiple targets with the multiple track points of the moving fuzzy unit to determine the moving direction of the moving fuzzy unit.

5. The industrial video real-time monitoring platform with cloud storage according to claim 1 is characterized in that: In step S04, feature statistical analysis is performed through OpenCV background modeling to obtain the features of the blur unit, including: S41, transmitting the first data to the OpenCV background model; S42, extracting the first data to perform preset feature matching to determine whether it is a target type; S43. The height data of the moving fuzzy unit is extracted through a random window period of data to generate second data, and the second data is imported into step S41 and step S42. The judgment result is compared with the target type determined in step S42. If they are consistent, the target type is established; if they are inconsistent, a warning feedback is generated.

6. The real-time industrial video monitoring platform with cloud storage according to claim 1 is characterized in that: In step S05, based on the characteristics of the fuzzy unit, determining the action to be performed by the fuzzy unit includes: S51, detecting and identifying a human body in the image, and then extracting key point information of the human body, wherein the key point information is a moving point sufficient to reflect the posture of the human body's limbs; S52, extracting motion data by analyzing changes in key points of the human body between consecutive frames of each window.

7. The real-time industrial video monitoring platform with cloud storage according to claim 1 is characterized in that: The step S05 of comparing each frame of image with the preset dangerous action includes: S53, identifying several combinations of the extracted action data, and then matching the combinations with the features in the comparison database to find the most similar feature combination; S54, calculating the similarity between the action to be identified and each dangerous action in the database based on the distance or similarity between the feature vectors; S55. Evaluate the dangerousness of the action to be identified based on the similarity calculation result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the industrial video real-time monitoring platform with cloud storage as claimed in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the industrial video real-time monitoring platform with cloud storage as described in any one of claims 1 to 7 are implemented.

Images