CN114332672A - Video analysis method, device, electronic device and storage medium - Google Patents

Abstract

The present disclosure provides a video analysis method, device, electronic device and storage medium. The method includes: determining a variety of target video information, where the target video information includes: video data frame, video abstract, and target image; determining a variety of scene rules; Various scene rules analyze and process various target video information respectively to generate target video analysis results. Through the present disclosure, the video data of the coal collection scene can be efficiently analyzed, the analysis efficiency of the video information can be improved, and the reliability of the monitoring of the coal collection scene can be improved.

Description

Video analysis method, device, electronic device and storage medium

technical field

The present disclosure relates to the technical field of coal collection video monitoring, and in particular, to a video analysis method, device, electronic device and storage medium.

Background technique

In large-scale coal mine projects, there are more than 200 channels of video data underground, providing a large amount of data information, which requires the monitoring personnel to have extremely high attention, vigilance, and ability to detect abnormal situations, as well as video transmission efficiency and video quality.

In the related technologies, for the coal industry, there is a lack of efficient video intelligent analysis capabilities, and the automatic supervision role of video surveillance itself is not fully exerted.

SUMMARY OF THE INVENTION

The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

Therefore, the purpose of the present disclosure is to provide a video analysis method, device, electronic device and storage medium, which can efficiently analyze video data of coal collection scenes, improve the analysis efficiency of video information, and further improve the reliability of coal collection scene monitoring.

In order to achieve the above purpose, the video analysis method proposed by the embodiment of the first aspect of the present disclosure includes: determining various target video information, the target video information includes: video data frame, video summary, target image; determining various scene rules; Each scene rule analyzes and processes various target video information to generate target video analysis results.

The video analysis method proposed by the embodiment of the first aspect of the present disclosure determines a variety of target video information, the target video information includes: a video data frame, a video summary, and a target image, determines a variety of scene rules, and analyzes multiple scene rules according to the scene rules. A variety of target video information is analyzed and processed to generate target video analysis results, which can efficiently analyze the video data of coal collection scenes, improve the analysis efficiency of video information, and then improve the reliability of coal collection scene monitoring.

In order to achieve the above purpose, the video analysis device proposed by the embodiment of the second aspect of the present disclosure includes: a first determination module, configured to determine a variety of target video information, and the target video information includes: video data frame, video abstract, and target image; The second determination module is used to determine various scene rules; the analysis module is used to analyze and process various target video information according to the various scene rules, so as to generate target video analysis results.

The video analysis apparatus proposed by the embodiment of the second aspect of the present disclosure determines a variety of target video information, the target video information includes: a video data frame, a video summary, and a target image, determines a variety of scene rules, and analyzes multiple scene rules according to the scene rules. A variety of target video information is analyzed and processed to generate target video analysis results, which can efficiently analyze the video data of coal collection scenes, improve the analysis efficiency of video information, and then improve the reliability of coal collection scene monitoring.

According to a third aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by at least one processor. One processor executes to enable at least one processor to execute the video analysis method of the embodiment of the first aspect of the present disclosure.

According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is proposed, wherein the computer instructions are used to cause the computer to execute the video analysis method of the embodiment of the first aspect of the present disclosure.

According to a fifth aspect of the present disclosure, there is provided a computer program product, including a computer program that, when executed by a processor, implements the video analysis method of the embodiment of the first aspect of the present disclosure.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The above and/or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

1 is a schematic flowchart of a video analysis method proposed by an embodiment of the present disclosure;

2 is a schematic flowchart of a video analysis method proposed by another embodiment of the present disclosure;

3 is a schematic flowchart of a video analysis method proposed by another embodiment of the present disclosure;

4 is a schematic structural diagram of a video analysis apparatus proposed according to an embodiment of the present disclosure;

5 is a schematic structural diagram of a video analysis apparatus proposed according to another embodiment of the present disclosure;

6 shows a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.

Detailed ways

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure and should not be construed as a limitation of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications and equivalents falling within the spirit and scope of the appended claims.

FIG. 1 is a schematic flowchart of a video analysis method proposed by an embodiment of the present disclosure.

It should be noted that the executive body of the video analysis method in this embodiment is a video analysis device, which may be implemented by software and/or hardware, and the device may be configured in an electronic device, which may include but not Limited to terminal, server, etc.

As shown in Figure 1, the video analysis method includes:

S101: Determine a variety of target video information, where the target video information includes: a video data frame, a video abstract, and a target image.

Among them, each frame of video data obtained by frame parsing of the video data may be called a video data frame, and the video data frame containing the required video semantics obtained by parsing from multiple video data frames may be called a key frame, The key frame may also be referred to as a video abstract, and the video image in the key frame may be referred to as a target image. Therefore, the aforementioned video data frame, video abstract, and target image may be collectively referred to as target video information.

Optionally, in some embodiments, when determining various target video information, various initial video data may be obtained from the coal collection scene; the corresponding initial video data are respectively input into the pre-trained video data processing model. , to obtain the video processing result output by the video data processing model; according to the video processing result, the video data frame, video abstract, and target image are parsed from the initial video data, and the video data frame, video abstract, and target image are taken as the target video By using the pre-trained video data processing model to process a variety of initial video data, it is convenient to determine the target video information. By adjusting the pre-trained video data processing model, it can adapt to the selection requirements of various video formats and target video information, ensuring the target video information. The convenience and diversity of video information acquisition.

In the embodiment of the present disclosure, the collection of various initial video data may be real-time video data captured by a monitoring device in a scene as required, or pre-stored video data collected, which is not limited .

Among them, the pre-trained video data processing model may be a processing model for encoding, decoding, and image processing of the collected video data. For example, the encoding and decoding of the video may be a traditional hybrid encoding framework based on block segmentation. Video coding can also be used according to the needs of the coal collection scene, using high-resolution (such as 2K, 4K resolution, etc.) video coding and decoding technology, etc., the image processing can be based on the Bayesian-full probability formula and other algorithm formulas. The image is segmented, or the temporal change and correlation of the pixel intensity data in the image sequence is used to determine the change of the respective pixel position by the optical flow method, or the combination of the optical flow method and the Bayes-total probability formula is used to determine the change of the pixel position. This does not limit.

After being processed by the above-mentioned pre-trained video data processing model, a video processing result is generated. According to the video generation result, the initial video is parsed to obtain a data set of types such as video data frame, video summary, and target image, and use it as the target video. information is stored.

In other embodiments, the method of extracting key frames and key features can also be used to determine various target video information, for example, the method of using key frame and key feature extraction algorithms, the method of manually labeling key features, etc. No restrictions.

In the embodiments of the present disclosure, for the determination of various target video information, technologies such as video acquisition and compression technology, encoding and decoding technology, and mass video storage technology can be used to build a mine scene video distributed object storage system to provide targets for intelligent video analysis. Video information, video sample annotation technology can also be used to build a video data annotation platform to form a video training sample library to further provide more target video information.

S102: Determine multiple scene rules.

Among them, a variety of video information analysis rules corresponding to the various scenes in the coal collection task are set according to the particularity of the scene, which may be called scene rules.

In the embodiment of the present disclosure, the scene rule may be, for example, a single virtual warning line rule: a virtual detection line is added to the video scene, and if the center of the target moves to the single virtual warning line, it can be determined that the target violates the single virtual warning line rule; virtual rectangle warning area rule: a virtual rectangular frame is added to the video sequence, if the center of the target moves to the virtual rectangular warning area, it can be determined that the target violates the virtual rectangular warning area rule; and virtual polygon warning area rule: establish a The polygon target abnormality determination model determines whether the target enters the virtual polygon drawn in the video scene, and determines whether the target is abnormal in the polygon.

S103: Perform analysis and processing on a variety of target video information according to a variety of scene rules to generate a target video analysis result.

Among them, according to the various scene rules set in different scenes in the coal collection task, the target in the corresponding various target video information is determined respectively, and the target behavior is judged and analyzed, and the generated result can be called the target video analysis result.

In the embodiment of the present disclosure, for the generation of target analysis results, the extracted targets can be judged and classified, and corresponding to the things in the coal collection scene, so as to better provide data support for image understanding and behavior analysis.

In this embodiment, by determining a variety of target video information, the target video information includes: a video data frame, a video summary, and a target image, determining a variety of scene rules, and analyzing and processing the various target video information according to the scene rules, respectively, In order to generate the target video analysis results, the video data of the coal collection scene can be efficiently analyzed, the analysis efficiency of the video information can be improved, and the reliability of the monitoring of the coal collection scene can be improved.

FIG. 2 is a schematic flowchart of a video analysis method proposed by another embodiment of the present disclosure.

As shown in Figure 2, the video analysis method includes:

S201: Determine a variety of target video information, where the target video information includes: a video data frame, a video summary, and a target image.

The description of S201 may refer to the above-mentioned embodiment for details, and details are not repeated here.

S202: In response to the rule confirmation instruction, parsing the rule confirmation instruction to obtain the scene type identifier.

Among them, the identification of a plurality of different coal production scene types is used to distinguish different scene types, which may be referred to as scene type identification.

In the embodiment of the present disclosure, the multiple scene types may be different service scene types divided according to different service types, or different device scene types divided according to different devices, which are not limited.

For example, in a coal mining scenario, according to the business type, the scenario types can be divided into coal breaking scenarios, coal loading scenarios, coal transportation scenarios, support scenarios, and gob processing scenarios.

S203: Acquire multiple scene types corresponding to multiple target video information according to the scene type identifier.

In this embodiment of the present disclosure, one target video information may contain multiple scene type identifiers. Therefore, one type of target video information may correspond to one or more scene types, and one type of scene may also correspond to multiple types of target video information. There is no restriction on this.

S204: Determine multiple scene rules to which multiple scene types belong according to the scene type identifier and the scene identification result, where the scene identification result is the identification result of the target video information in the multiple scene types.

In the embodiment of the present disclosure, different scene types may correspond to the same or different scene rules, and in the same scene type, different targets may also correspond to different scene rules, and the confirmation of scene rules may be set according to actual scene needs. Exclusive rule design, or pre-set scene rules.

S205: Perform analysis and processing on various target video information according to various scene rules to generate target video analysis results.

The description of S205 may refer to the above-mentioned embodiment for details, and details are not repeated here.

S206: Configure multiple alarm rules corresponding to multiple scene types respectively.

In the embodiment of the present disclosure, various alarm rules may be configured by using sound alarm or light alarm at the console, or a combination of sound and light, through the flashing frequency of the light, the color of the light, and different sound signals for different scene types The alarm rule can also use a remote device to alarm on the mobile terminal, which is not limited.

S207: When the target video analysis result exceeds the alarm threshold indicated by the alarm rule, start an alarm rule corresponding to the target video analysis result.

Among them, the preset critical point for starting the alarm can be called the alarm threshold, and the alarm threshold can be a numerical value representing a degree or a numerical range representing a certain degree. For example, the temperature alarm can be determined when the temperature is determined. The alarm is triggered when a specific value is exceeded, and the distance alarm can be triggered when the target is within a certain range from a certain point.

In the embodiment of the present disclosure, one alarm rule may correspond to one type of scenario, and multiple alarm rules may be combined according to the actual situation in the scenario to distinguish different analysis results.

In this embodiment, by determining a variety of target video information, the target video information includes: video data frame, video summary, target image, in response to the rule confirmation instruction, the scene type identifier is obtained by parsing the rule confirmation instruction, and according to the scene type identifier, Obtain multiple scene types corresponding to multiple target video information, and determine multiple scene rules to which multiple scene types belong according to scene type identifiers and scene recognition results. The scene recognition result is the identification of target video information in multiple scene types. As a result, various target video information is analyzed and processed according to various scene rules to generate target video analysis results, and various alarm rules corresponding to various scene types are configured respectively. When the target video analysis result exceeds the alarm indicated by the alarm rule When the threshold is reached, the alarm rule corresponding to the target video analysis result is activated. By determining the scene type and the scene recognition result, a variety of scene rules can be accurately determined, and the scene type can be subdivided to ensure the applicability of the scene rules. Different alarm rules are preset in different business scenarios, which can timely feedback abnormal situations in the scenario, making video analysis more intelligent.

FIG. 3 is a schematic flowchart of a video analysis method proposed by another embodiment of the present disclosure.

As shown in Figure 3, the video analysis method includes:

S301: Determine a variety of target video information, where the target video information includes: a video data frame, a video summary, and a target image.

S302: Determine multiple scene rules.

S303: Perform analysis and processing on a variety of target video information according to a variety of scene rules to generate a target video analysis result.

For the description and description of S301-S303, reference may be made to the foregoing embodiments, and details are not repeated here.

S304: Identify the target feature according to the target video analysis result.

In the embodiment of the present disclosure, the identification of the target feature may be through the salient points of the image, etc., the salient points are used as the key feature vector, the key feature vector is identified, and then the target feature is identified, or the direction and locality of the feature may be used. The structure acts as an edge feature describing the boundary of the object.

For example, to analyze the characteristics of the coal breaking business in the coal mining scene, it can be based on the difference in the color of the coal itself, using the color of the coal as the prominent point of the image to identify the characteristics of the coal, or it can be based on the color to define the edge of the coal. The contour is used as the target feature.

S305: Track and identify the target feature to determine a change trend corresponding to the target feature.

After identifying the target features above, the target features are tracked and identified, and the target feature tracking can be divided into different types. According to the difference of target features extracted from the tracked target, target tracking can be divided into four categories: target area-based tracking, target feature point-based tracking, target active contour-based tracking and model-based tracking.

In the embodiment of the present disclosure, the tracking and identification of target features can be performed by using the multi-target tracking function in the Bayesian-full probability formula model to solve the problem of target occlusion or the problem of tracking failure in the case of large-area similar color interference. The Bayesian-total probability foreground detection algorithm extracts the foreground moving objects in the video scene, and automatically initializes the search port with the circumscribed rectangle of the foreground mask of the extracted moving objects, so as to realize the automatic tracking using the correlation algorithm.

In this embodiment, by determining a variety of target video information, the target video information includes: a video data frame, a video summary, and a target image, determining a variety of scene rules, and analyzing and processing the various target video information according to the scene rules, respectively, To generate target video analysis results, then identify target features according to the target video analysis results, track and identify the target features to determine the changing trend corresponding to the target features, identify the target features, track and analyze the behavior, and be able to understand the changing trend of the target And further predict the next behavior of the target, improve the applicability of video analysis, and predict the behavior of the target, which can assist in timely detection of various abnormal situations in the scene, making video analysis more intelligent.

FIG. 4 is a schematic structural diagram of a video analysis apparatus according to an embodiment of the present disclosure.

As shown in Figure 4, the video analysis device 40 includes:

The first determination module 401 is used to determine various target video information, the target video information includes: video data frame, video summary, and target image;

a second determining module 402, configured to determine multiple scene rules;

The analysis module 403 is configured to analyze and process a variety of target video information according to a variety of scene rules, so as to generate a target video analysis result.

In some embodiments of the present disclosure, as shown in FIG. 5 , which is a schematic structural diagram of a video analysis apparatus proposed according to another embodiment of the present disclosure, the first determination module 401 is specifically used for:

Obtain a variety of initial video data from coal collection scenarios;

respectively input the corresponding initial video data into the pre-trained video data processing model to obtain the video processing result output by the video data processing model;

According to the video processing result, the video data frame, video abstract, and target image are obtained by parsing the initial video data, and the video data frame, video abstract, and target image are used as target video information.

In some embodiments of the present disclosure, as shown in FIG. 5 , the second determination module 402 includes:

The parsing submodule 4021 is used to parse and obtain the scene type identifier from the rule confirmation instruction in response to the rule confirmation instruction;

Obtaining submodule 4022, configured to obtain multiple scene types corresponding to multiple target video information according to the scene type identifier;

The determination sub-module 4023 is configured to determine multiple scene rules to which multiple scene types belong according to the scene type identifier and the scene identification result, where the scene identification result is the identification result of the target video information in the multiple scene types.

In some embodiments of the present disclosure, as shown in FIG. 5 , it further includes:

The configuration module 404 is configured to, after analyzing and processing a variety of target video information according to a variety of scene rules, respectively, to generate a target video analysis result, configure corresponding multiple alarm rules for a variety of scene types;

The starting module 405 is configured to start an alarm rule corresponding to the target video analysis result when the target video analysis result exceeds the alarm threshold indicated by the alarm rule.

In some embodiments of the present disclosure, as shown in FIG. 5 , the apparatus further includes:

The identification module 406 is used for identifying the target feature according to the target video analysis result;

The third determining module 407 is configured to track and identify the target feature to determine a change trend corresponding to the target feature.

Corresponding to the video analysis methods provided by the above embodiments of FIGS. 1 to 3 , the present disclosure further provides a video analysis apparatus, because the video analysis apparatus provided by the embodiments of the present disclosure is the same as the video analysis provided by the above embodiments of FIGS. 1 to 3 . Therefore, the implementation of the video analysis method is also applicable to the video analysis apparatus provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

In this embodiment, by determining a variety of target video information, the target video information includes: a video data frame, a video summary, and a target image, determining a variety of scene rules, and analyzing and processing the various target video information according to the scene rules, respectively, In order to generate the target video analysis results, the video data of the coal collection scene can be efficiently analyzed, the analysis efficiency of the video information can be improved, and the reliability of the monitoring of the coal collection scene can be improved.

In order to realize the above-mentioned embodiments, the present disclosure also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the video analysis method proposed in the foregoing embodiments of the present disclosure.

In order to implement the above-mentioned embodiments, the present disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the above-mentioned embodiments of the present disclosure are implemented. The proposed video analysis method.

In order to implement the above embodiments, the present disclosure also provides a computer program product, when an instruction processor in the computer program product executes, executes the video analysis method proposed in the foregoing embodiments of the present disclosure.

6 shows a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, the electronic device 12 takes the form of a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16 , system memory 28 , and a bus 18 connecting various system components including system memory 28 and processing unit 16 . Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (hereinafter referred to as: ISA) bus, MicroChannel Architecture (hereinafter referred to as: MAC) bus, enhanced ISA bus, video electronic standard Association (VideoElectronics Standards Association; hereinafter referred to as: VESA) local bus and peripheral component interconnection (Peripheral Component Interconnection; hereinafter referred to as: PCI) bus.

Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including both volatile and non-volatile media, removable and non-removable media.

The memory 28 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (Random Access Memory; hereinafter referred to as: RAM) 30 and/or a cache memory 32 . Electronic device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive").

Although not shown in FIG. 6, a magnetic disk drive for reading and writing to removable non-volatile magnetic disks (eg "floppy disks") and removable non-volatile optical disks (eg compact disk read only memory) may be provided Disc Read OnlyMemory; hereinafter referred to as: CD-ROM), Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM) or other optical media) read and write optical disc drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present disclosure.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data , each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described in this disclosure.

The electronic device 12 may also communicate with one or more external devices 14 (eg, a keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the electronic device 12, and/or with Any device (eg, network card, modem, etc.) that enables the electronic device 12 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 22 . In addition, the electronic device 12 can also communicate with one or more networks (eg, Local Area Network (hereinafter referred to as: LAN), Wide Area Network (hereinafter referred to as: WAN) and/or public networks, such as Internet) communication. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives and data backup storage systems.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the video analysis method mentioned in the foregoing embodiments.

Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common general knowledge or techniques in the technical field not disclosed by this disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

It should be noted that, in the description of the present disclosure, the terms "first", "second", etc. are only used for description purposes, and cannot be understood as indicating or implying relative importance. Also, in the description of the present disclosure, unless stated otherwise, "plurality" means two or more.

Any description of a process or method in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing a specified logical function or step of the process , and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present disclosure pertain.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program is stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structures, materials, or features are included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above-described embodiments are exemplary and should not be construed as limitations of the present disclosure, and those of ordinary skill in the art may interpret the above-described embodiments within the scope of the present disclosure. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (10)

1. a video analysis method, is characterized in that, is applied to coal collection scene, described method comprises: Determine a variety of target video information, the target video information includes: video data frame, video summary, target image; Determine a variety of scene rules; The various target video information is analyzed and processed according to the various scene rules, so as to generate a target video analysis result. 2. The method of claim 1, wherein the determining of multiple target video information comprises: Obtain a variety of initial video data from the coal collection scene; respectively inputting the corresponding initial video data into a pre-trained video data processing model to obtain a video processing result output by the video data processing model; According to the video processing result, the video data frame, the video abstract, and the target image are parsed from the initial video data, and the video data frame, the video abstract, and the target image are as the target video information. 3. The method of claim 1, wherein the determining multiple scene rules comprises: In response to the rule confirmation instruction, the scene type identifier is obtained by parsing the rule confirmation instruction; According to the scene type identifier, obtain multiple scene types corresponding to the multiple target video information; A variety of scene rules to which the multiple scene types belong are determined according to the scene type identifier and the scene identification result, and the scene identification result is the identification result of the target video information in the multiple scene types. 4. The method according to claim 3, wherein after the analysis and processing of the various target video information according to the various scene rules are respectively performed to generate a target video analysis result, the method further comprises: Configure corresponding multiple alarm rules for the multiple scene types respectively; When the target video analysis result exceeds the alarm threshold indicated by the alarm rule, an alarm rule corresponding to the target video analysis result is activated. 5. The method of claim 1, wherein the method further comprises: Identify target features according to the target video analysis result; Track and identify the target feature to determine a change trend corresponding to the target feature. 6. A video analysis device, characterized in that, applied to a coal collection scene, the device comprising: a first determining module, configured to determine a variety of target video information, the target video information including: video data frame, video summary, target image; The second determination module is used to determine a variety of scene rules; The analysis module is configured to analyze and process the various target video information according to the various scene rules, so as to generate the target video analysis result. 7. The apparatus of claim 6, wherein the first determining module is specifically configured to: Obtain a variety of initial video data from the coal collection scene; respectively inputting the corresponding initial video data into a pre-trained video data processing model to obtain a video processing result output by the video data processing model; According to the video processing result, the video data frame, the video abstract, and the target image are parsed from the initial video data, and the video data frame, the video abstract, and the target image are as the target video information. 8. The apparatus of claim 6, wherein the second determining module comprises: A parsing submodule, configured to parse and obtain the scene type identifier from the rule confirmation instruction in response to the rule confirmation instruction; an acquisition submodule, configured to acquire multiple scene types corresponding to the multiple target video information according to the scene type identifier; A determination submodule, configured to determine a variety of scene rules to which the multiple scene types belong according to the scene type identifier and the scene recognition result, where the scene recognition result is that the target video information is in the multiple scene types recognition results. 9. An electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-5 Methods. 10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any of claims 1-5.

Images