CN112200067B - Intelligent video event detection method, system, electronic equipment and storage medium - Google Patents

Abstract

The invention provides an intelligent video event detection method, system, electronic device and storage medium. The method obtains a video source from a database, tags the video source, and determines the corresponding preset video template according to the tag of the video source; determines Based on the key frames of the video source, the video source is split into several video clips with the same number of frames based on the key frames. Based on the preset detection model, several video clips are scored and sorted according to the preset video template, and the video clip with the highest score is determined. is the target video clip; when the highest score is greater than or equal to the preset threshold, the frames in the target video clip with the same timestamp corresponding to the marked frame in the preset video template are determined as event evidence graphs, and the corresponding event type is determined at the same time . It can intelligently and automatically detect events in the video and output detection results. At the same time, the detection results contain key image evidence of the event, which improves the efficiency of event detection and makes event detection more accurate and credible.

Description

Intelligent video event detection method, system, electronic device and storage medium

Technical field

The invention belongs to the field of computer technology, and in particular relates to an intelligent video event detection method, system, electronic equipment and storage medium.

Background technique

With the improvement of social and economic level, it has become a popular technology to intelligently detect the content of videos and then apply it to specific scenarios to achieve event judgment in specific scenarios, such as video detection of traffic accidents, video monitoring of anti-theft security, and traffic flow monitoring. Statistics etc. The use of intelligent video event detection technology can greatly improve detection efficiency.

At present, the recognition and detection of video events mainly relies on manual screening and browsing, or only part of the video events can be recognized, and some parts need to be manually screened. It is impossible to intelligently and quickly identify the video content to determine the event information of specific scenes, and the detection efficiency is low.

Contents of the invention

The first purpose of embodiments of the present invention is to provide an intelligent video event detection method, aiming to solve the current problem of low efficiency in video event detection.

The embodiment of the present invention is implemented as follows: an intelligent video event detection method includes:

Obtain video sources from the database, tag the video sources, and determine the corresponding preset video template according to the tags of the video sources;

Determine the key frames of the video source, split the video source into several video clips with the same number of frames according to the key frames, and score the several video clips according to the preset video template based on a preset detection model Sort and determine the video clip with the highest score as the target video clip;

When the highest score is greater than or equal to the preset threshold, frames with the same timestamp in the target video clip corresponding to the marked frame in the preset video template are determined as event evidence graphs, and the corresponding events are determined at the same time. type.

In one embodiment, obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source includes: obtaining the video to be detected from the system database, and according to the Tag the video source with the basic information of the video to be detected, and select the corresponding preset video template from the preset video template library according to the label of the video source; the video to be detected is all the videos to be detected in the data The basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device.

In one embodiment, the preset video template includes several videos with tags that have the same frames as the target video clip, and the frames of the preset video template are processed in grayscale, and the frames of the preset video template are Tags include location information.

In one embodiment, selecting a corresponding preset video template from a preset video template library according to the tag of the video source includes: traversing the preset video template library according to the location information of the video source, and adding the location to the preset video template library. The preset video template whose information is the same as the position information of the video source is determined as the corresponding preset video template.

In one embodiment, the scoring and sorting of the several video clips according to the preset video template based on the preset detection model includes: performing grayscale on each frame of the video clip, based on the image similarity algorithm model, calculate the similarity between each frame of the video clip and the frame with the same timestamp of the preset video template to obtain the similarity of each frame, and perform a weighted calculation on all the frames of the video clip to obtain the Based on the similarity between the video clips and the preset video template, the video clips are scored and sorted according to the similarity. The higher the similarity, the higher the score. The higher the score, the higher the ranking.

Another object of embodiments of the present invention is to provide an intelligent video event detection system, including:

A video acquisition unit, configured to acquire a video source from a database, tag the video source, and determine a corresponding preset video template according to the tag of the video source;

The target video determination unit is used to determine the key frames of the video source, split the video source into several video segments with the same number of frames according to the key frames, and detect the target video based on the preset video template based on the preset detection model. The several video clips are ranked and sorted, and the video clip with the highest score is determined as the target video clip;

A detection result determination unit configured to determine frames with the same timestamp in the target video segment corresponding to the marked frame in the preset video template as event evidence when the highest score is greater than or equal to the preset threshold. Figure, while determining the corresponding event type.

In one embodiment, obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source includes: obtaining the video to be detected from the system database, and according to the Tag the video source with the basic information of the video to be detected, and select the corresponding preset video template from the preset video template library according to the label of the video source; the video to be detected is all the videos to be detected in the data The basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device.

In one embodiment, the preset video template includes several videos with tags that have the same frames as the target video clip, and the frames of the preset video template are processed in grayscale, and the frames of the preset video template are Tags include location information.

Another object of embodiments of the present invention is to provide an electronic device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor is caused to execute the Steps of intelligent video event detection method.

Another object of the embodiments of the present invention is a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it causes the processor to execute the intelligent video Steps of event detection method.

An intelligent video event detection method provided by an embodiment of the present invention obtains a video source from a database, tags the video source, and determines the corresponding preset video template according to the tag of the video source; determines the video source key frames, split the video source into several video clips with the same number of frames according to the key frames, score and sort the several video clips according to the preset video template based on a preset detection model, and select the one with the highest score The video segment is determined as the target video segment; when the highest score is greater than or equal to the preset threshold, the frame in the target video segment with the same timestamp corresponding to the marked frame in the preset video template is determined as Event evidence map, while determining the corresponding event type. It can intelligently and automatically detect events in the video and output the detection results. At the same time, the detection results contain key image evidence of the event. On the one hand, it improves the efficiency of event detection, and on the other hand, it makes the event detection more accurate and credible.

Description of drawings

Figure 1 is an implementation process of an intelligent video event detection method provided by an embodiment of the present invention;

Figure 2 is a schematic diagram of the main modules of an intelligent video event detection system provided by an embodiment of the present invention;

Figure 3 is an exemplary system architecture diagram that can be applied in the embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a computer system suitable for implementing a terminal device or server according to an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and are not intended to limit the present invention.

The terminology used in the embodiments of the present invention is only for the purpose of describing specific embodiments and is not intended to limit the present invention. As used in this embodiment and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, etc. may be used to describe various information in the embodiments of the present invention, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.

It should be noted that, without conflict, the embodiments and features of the embodiments of the present invention can be combined with each other.

In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended inventive purpose, the specific implementation manner, structure, features and effects of the present invention are described in detail below with reference to the drawings and preferred embodiments.

Figure 1 shows the implementation process of an intelligent video event detection method provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. The details are as follows:

An intelligent video event detection method, including:

S101: Obtain the video source from the database, label the video source, and determine the corresponding preset video template according to the label of the video source;

S102: Determine the key frames of the video source, split the video source into several video clips with the same number of frames based on the key frames, and detect the several video clips based on the preset video template based on a preset detection model. Perform scoring sorting and determine the video clip with the highest score as the target video clip;

S103: When the highest score is greater than or equal to the preset threshold, determine the frame with the same time stamp in the target video clip corresponding to the marked frame in the preset video template as an event evidence graph, and determine the corresponding event type.

In step S101, the video source is obtained from the database, the video source is tagged, and the corresponding preset video template is determined according to the label of the video source, so that the video shot by the video shooting device can be obtained for detection, and the The obtained video source is tagged, so that a preset video template corresponding to the tag can be selected from the preset video template library according to the tag.

In one embodiment, obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source includes: obtaining the video to be detected from the system database, and according to the Tag the video source with the basic information of the video to be detected, and select the corresponding preset video template from the preset video template library according to the label of the video source; the video to be detected is all the videos to be detected in the data The basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device. Therefore, the basic information of the video source can be determined through tags, such as the source of the video source (device information, which device shot it), geographical location information, shooting time information, etc., and then the tags can be used to select and select from the preset video template library. The preset video template matched by the tag can also determine the specific geographical location corresponding to the event type through the tag. When the event needs to be traced, the source of the video source reflected by the tag can be traced.

In one embodiment, the preset video template includes several videos with tags that have the same frames as the target video clip, and the frames of the preset video template are processed in grayscale, and the frames of the preset video template are Tags include location information.

In one embodiment, selecting a corresponding preset video template from a preset video template library according to the tag of the video source includes: traversing the preset video template library according to the location information of the video source, and adding the location to the preset video template library. The preset video template whose information is the same as the position information of the video source is determined as the corresponding preset video template.

Specifically, for example, if a video source is obtained, which was shot by device A at intersection B of street B, March 2nd, 9 am, A” matches the video template labeled X street intersection B in the default video template library as the corresponding default template.

Thus, the video source is obtained from the database, the video source is tagged, and the corresponding preset video template is determined according to the label of the video source; the key frame of the video source is determined, and the video is classified according to the key frame. The source is split into several video clips with the same number of frames, the several video clips are scored and sorted based on the preset video template based on a preset detection model, and the video clip with the highest score is determined as the target video clip; when the When the highest score is greater than or equal to the preset threshold, frames with the same timestamp in the target video clip corresponding to the marked frame in the preset video template are determined as event evidence graphs, and the corresponding event type is determined at the same time. This intelligent video event detection method can intelligently and automatically detect events in the video and output detection results. At the same time, the detection results contain key image evidence of the event. On the one hand, it improves the efficiency of event detection, and on the other hand, it makes the event detection more accurate. and credible.

In step S102: determine the key frames of the video source, split the video source into several video segments with the same number of frames according to the key frames, and detect the video source based on the preset detection model according to the preset video template. Several video clips are sorted by scoring, and the video clip with the highest score is determined as the target video clip. From this, it can be determined whether the video source is a video that meets the event type, and subsequent processing is not prepared.

In step S103: when the highest score is greater than or equal to the preset threshold, determine the frame in the target video clip with the same timestamp corresponding to the marked frame in the preset video template as an event evidence graph, Also determine the corresponding event type.

Here, the preset threshold can be set according to specific scenarios. For example, in vehicle violation information monitoring, the preset threshold can be set to 95%, and in accident detection, it can be set to 80%.

In one embodiment, the determined time evidence graph and corresponding event type generation interface can be output to the client for display. The interface information can include the evidence graph, event time and event type. For example, when the video source is in March 2020 At 9 a.m. on the 2nd of the month, a vehicle was driving on the crossing line at intersection B of Street

In one embodiment, the scoring and sorting of the several video clips according to the preset video template based on the preset detection model includes: performing grayscale on each frame of the video clip, based on the image similarity algorithm model, calculate the similarity between each frame of the video clip and the frame with the same timestamp of the preset video template to obtain the similarity of each frame, and perform a weighted calculation on all the frames of the video clip to obtain the Based on the similarity between the video clips and the preset video template, the video clips are scored and sorted according to the similarity. The higher the similarity, the higher the score. The higher the score, the higher the ranking.

Figure 2 shows a schematic diagram of the main modules of an intelligent video event detection system provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. The details are as follows:

An intelligent video event detection system 200, including:

The video acquisition unit 201 is used to acquire video sources from the database, tag the video sources, and determine the corresponding preset video template according to the tags of the video sources;

The target video determination unit 202 is used to determine key frames of the video source, split the video source into several video segments with the same number of frames according to the key frames, and based on the preset video template based on a preset detection model Score and sort the several video clips, and determine the video clip with the highest score as the target video clip;

The detection result determination unit 203 is configured to determine, as an event, frames in the target video clip with the same timestamp corresponding to the marked frame in the preset video template when the highest score is greater than or equal to the preset threshold. Evidence map, while determining the corresponding event type.

In one embodiment, obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source includes: obtaining the video to be detected from the system database, and according to the Tag the video source with the basic information of the video to be detected, and select the corresponding preset video template from the preset video template library according to the label of the video source; the video to be detected is all the videos to be detected in the data The basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device. Therefore, the basic information of the video source can be determined through tags, such as the source of the video source (device information, which device shot it), geographical location information, shooting time information, etc., and then the tags can be used to select and select from the preset video template library. The preset video template matched by the tag can also determine the specific geographical location corresponding to the event type through the tag. When the event needs to be traced, the source of the video source reflected by the tag can be traced.

In one embodiment, the preset video template includes several videos with tags that have the same frames as the target video clip, and the frames of the preset video template are processed in grayscale, and the frames of the preset video template are Tags include location information.

In one embodiment, selecting a corresponding preset video template from a preset video template library according to the tag of the video source includes: traversing the preset video template library according to the location information of the video source, and adding the location to the preset video template library. The preset video template whose information is the same as the position information of the video source is determined as the corresponding preset video template.

Specifically, for example, if a video source is obtained, which was shot by device A at intersection B of street B, March 2nd, 9 am, A” matches the video template labeled X street intersection B in the default video template library as the corresponding default template.

In one embodiment, the scoring and sorting of the several video clips according to the preset video template based on the preset detection model includes: performing grayscale on each frame of the video clip, based on the image similarity algorithm model, calculate the similarity between each frame of the video clip and the frame with the same timestamp of the preset video template to obtain the similarity of each frame, and perform a weighted calculation on all the frames of the video clip to obtain the Based on the similarity between the video clips and the preset video template, the video clips are scored and sorted according to the similarity. The higher the similarity, the higher the score. The higher the score, the higher the ranking.

Here, the preset threshold can be set according to specific scenarios. For example, in vehicle violation information monitoring, the preset threshold can be set to 95%, and in accident detection, it can be set to 80%.

In one embodiment, the determined time evidence graph and corresponding event type generation interface can be output to the client for display. The interface information can include the evidence graph, event time and event type. For example, when the video source is in March 2020 At 9 a.m. on the 2nd of the month, a vehicle was driving on the crossing line at intersection B of Street

Therefore, the intelligent video event detection system 200 provided by the embodiment of the present invention includes: a video acquisition unit 201, used to obtain a video source from a database, label the video source, and determine the corresponding video source according to the label of the video source. Preset video template; target video determination unit 202, used to determine key frames of the video source, split the video source into several video segments with the same number of frames based on the key frames, and based on the preset detection model The preset video template is used to score and sort the several video clips, and the video clip with the highest score is determined as the target video clip; the detection result determination unit 203 is used to determine when the highest score is greater than or equal to the preset threshold. Frames in the target video clip with the same timestamp corresponding to the marked frame in the preset video template are determined as event evidence graphs, and the corresponding event type is determined at the same time. It can intelligently and automatically detect events in the video and output the detection results. At the same time, the detection results contain key image evidence of the event. On the one hand, it improves the efficiency of event detection, and on the other hand, it makes the event detection more accurate and credible.

Another object of embodiments of the present invention is to provide an electronic device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor is caused to execute the Steps of intelligent video event detection method.

Another object of the embodiments of the present invention is a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it causes the processor to execute the intelligent video Steps of event detection method.

FIG. 3 shows an exemplary system architecture 500 to which the detection method or detection device according to the embodiment of the present invention can be applied.

As shown in Figure 3, the system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

The terminal devices 501, 502, and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and so on.

The server 505 may be a server that provides various services, such as a background management server that provides support for messages sent by users using the terminal devices 501, 502, and 503. The background management server can perform analysis and other processing after receiving the request from the terminal device, and feed the processing results back to the terminal device.

It should be noted that the intelligent video event detection method provided by the embodiment of the present invention can be executed by the server 505, or can be executed by the terminal devices 501, 502, 503. Correspondingly, the intelligent video event detection system can be executed by the server 505, or Can be executed by terminal devices 501, 502, 503.

It should be understood that the number of terminal devices, networks and servers in Figure 3 is only illustrative. Depending on implementation needs, there can be any number of end devices, networks, and servers.

Referring now to FIG. 4 , a schematic structural diagram of a computer system 600 suitable for implementing an electronic device according to an embodiment of the present invention is shown. The computer system shown in FIG. 4 is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

As shown in FIG. 4, computer system 600 includes a central processing unit (CPU) 601 that can operate according to a program stored in a read-only memory (ROM) 602 or loaded from a storage portion 608 into a random access memory (RAM) 603. And perform various appropriate actions and processing. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., speakers, etc.; and a storage section 608 including a hard disk, etc. ; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. Driver 610 is also connected to I/O interface 605 as needed. Removable media 611, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

In particular, according to embodiments disclosed in the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the disclosed embodiments of the present invention include a computer program product including a computer program carried on a computer-readable medium, the computer program including program code for executing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from the network via communication portion 609, and/or installed from removable media 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are performed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmed read-only memory (EPROM or flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device . Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved. It will also be noted that each block in the block diagram or flowchart illustration, and combinations of blocks in the block diagram or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or may be implemented by special purpose hardware-based systems that perform the specified functions or operations. Achieved by a combination of specialized hardware and computer instructions.

The units involved in the embodiments of the present invention can be implemented in software or hardware. The described unit may also be provided in a processor. For example, it may be described as follows: a processor includes a determination unit, an extraction unit, a training unit and a screening unit. The names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the determining unit may also be described as "the unit that determines the candidate user set."

The above-mentioned embodiments only express several implementation modes of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present invention. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the scope of protection of the patent of the present invention should be determined by the appended claims.

The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.

Claims (4)

1. An intelligent video event detection method, characterized by including: Obtain video sources from the database, tag the video sources, and determine the corresponding preset video template according to the tags of the video sources; Determine the key frames of the video source, split the video source into several video clips with the same number of frames according to the key frames, and score the several video clips according to the preset video template based on a preset detection model Sort and determine the video clip with the highest score as the target video clip; When the highest score is greater than or equal to the preset threshold, frames with the same timestamp in the target video clip corresponding to the marked frame in the preset video template are determined as event evidence graphs, and the corresponding events are determined at the same time. type; Obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source include: obtaining the video to be detected from the system database, and based on the video to be detected The video source is tagged with the information, and the corresponding preset video template is selected from the preset video template library according to the tag of the video source; the video to be detected is the video with the earliest shooting time among all the videos to be detected in the data. , the basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device; The preset video template includes several videos with labels that have the same frame as the target video clip, and the frames of the preset video template are processed in grayscale, and the labels of the preset video template include position information; Selecting the corresponding preset video template from the preset video template library according to the tag of the video source includes: traversing the preset video template library according to the location information of the video source, and combining the location information and the video source The preset video template with the same location information is determined as the corresponding preset video template; The scoring and sorting of the several video clips according to the preset video template based on the preset detection model includes: grayscale each frame of the video clip, based on the image similarity algorithm model, The similarity of each frame of the clip and the frame with the same timestamp of the preset video template is calculated to obtain the similarity of each frame. After weighted calculation of all frames of the video clip, the video clip and the preset video are obtained. Based on the similarity of the template, the several video clips are scored and sorted according to the similarity. The higher the similarity, the higher the score. The higher the score, the higher the ranking. 2. An intelligent video event detection system, characterized by including: A video acquisition unit, configured to acquire a video source from a database, tag the video source, and determine a corresponding preset video template according to the tag of the video source; The target video determination unit is used to determine the key frames of the video source, split the video source into several video segments with the same number of frames according to the key frames, and detect the target video based on the preset video template based on the preset detection model. The plurality of video clips are ranked and sorted, and the video clip with the highest score is determined as the target video clip; A detection result determination unit configured to determine frames with the same timestamp in the target video segment corresponding to the marked frame in the preset video template as event evidence when the highest score is greater than or equal to the preset threshold. Figure, while determining the corresponding event type; Obtaining the video source from the database, labeling the video source, and determining the corresponding preset video template according to the label of the video source include: obtaining the video to be detected from the system database, and based on the video to be detected The video source is tagged with the information, and the corresponding preset video template is selected from the preset video template library according to the tag of the video source; the video to be detected is the video with the earliest shooting time among all the videos to be detected in the data. , the basic information includes video shooting location information, video shooting time information, and equipment information of the corresponding video shooting device; The preset video template includes several videos with labels that have the same frame as the target video clip, and the frames of the preset video template are processed in grayscale, and the labels of the preset video template include position information; Selecting the corresponding preset video template from the preset video template library according to the tag of the video source includes: traversing the preset video template library according to the location information of the video source, and combining the location information and the video source The preset video template with the same location information is determined as the corresponding preset video template; The scoring and sorting of the several video clips according to the preset video template based on the preset detection model includes: grayscale each frame of the video clip, based on the image similarity algorithm model, The similarity of each frame of the clip and the frame with the same timestamp of the preset video template is calculated to obtain the similarity of each frame. After weighted calculation of all frames of the video clip, the video clip and the preset video are obtained. Based on the similarity of the template, the several video clips are scored and sorted according to the similarity. The higher the similarity, the higher the score. The higher the score, the higher the ranking. 3. An electronic device, characterized in that it includes a memory and a processor, and a computer program is stored in the memory. When the computer program is executed by the processor, it causes the processor to execute the method of claim 1. Steps of intelligent video event detection method. 4. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it causes the processor to execute the intelligent method of claim 1. Steps of video event detection method.