WO2022227764A1

WO2022227764A1 - Event detection method and apparatus, electronic device, and readable storage medium

Info

Publication number: WO2022227764A1
Application number: PCT/CN2022/075019
Authority: WO
Inventors: 张滨; 王云浩; 辛颖; 冯原; 王晓迪; 龙翔; 贾壮; 彭岩; 郑弘晖; 谷祎; 李超; 韩树民
Original assignee: 北京百度网讯科技有限公司
Priority date: 2021-04-28
Filing date: 2022-01-29
Publication date: 2022-11-03
Also published as: CN113205037A; JP2023527100A; CN113205037B; KR20220149508A

Abstract

The present disclosure relates to the technical field of artificial intelligence, and specifically to the technical fields of computer vision and deep learning, and can be applied to a smart city scenario. Disclosed is an event detection method. The event detection method comprises: obtaining image data, and identifying a city scenario for the image data; determining target and event, which are to be detected, corresponding to the city scenario; detecting said target in the image data to obtain a detection state of said event; and obtaining an event detection result of the image data according to the detection state of said event. According to the present disclosure, the accuracy and efficiency of event detection can be improved.

Description

Method, apparatus, electronic device, and readable storage medium for event detection

This application claims the priority of a Chinese patent application with an application date of April 28, 2021 and an application number of 202110466781.3 with the invention title of "Event Detection Method, Device, Electronic Device, and Readable Storage Medium".

technical field

The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of computer vision and deep learning, and can be applied to smart city scenarios. A method, apparatus, electronic device, and readable storage medium for event detection are provided.

Background technique

According to the current planning and layout of urban management, a large number of video devices are installed in various locations of the city for monitoring. By using these massive amounts of data, it will play a positive role in the standardization of urban management and the intelligentization of urban grids. However, when using monitoring video stream data for event detection in the prior art, there are technical problems of poor stability and low accuracy of detection results.

SUMMARY OF THE INVENTION

The present disclosure provides an event detection method, apparatus, electronic device, and readable storage medium, which are used to improve the accuracy and efficiency of event detection.

According to a first aspect of the present disclosure, a method for event detection is provided, comprising: acquiring image data, identifying an urban scene of the image data; determining a target to be detected and an event to be detected corresponding to the urban scene; The object to be detected in the image data is detected to obtain the detection state of the event to be detected; and the event detection result of the image data is obtained according to the detection state of the event to be detected.

According to a second aspect of the present disclosure, there is provided an apparatus for event detection, comprising: an acquisition unit for acquiring image data and identifying an urban scene of the image data; a determining unit for determining an image corresponding to the urban scene A target to be detected and an event to be detected; a detection unit, used for detecting the target to be detected in the image data, to obtain a detection state of the event to be detected; a processing unit, used to detect the state of the event to be detected according to the detection state to obtain the event detection result of the image data.

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 information that can be used by the at least one processor Instructions that are executed, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method as described above.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method as described above.

It can be seen from the above technical solutions that the present disclosure first identifies the urban scene of the acquired image data, then determines the to-be-detected target and the to-be-detected event corresponding to the urban scene, and finally detects the to-be-detected target in the image data, thereby The event detection result of the image data is obtained according to the obtained detection state of the event to be detected. Since different urban scenes, different targets to be detected and the event to be detected are corresponding to the event to be detected, the present disclosure can improve the accuracy and efficiency of event detection .

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 accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:

1 is a schematic diagram according to a first embodiment of the present disclosure;

2 is a schematic diagram according to a second embodiment of the present disclosure;

3 is a schematic diagram according to a third embodiment of the present disclosure;

4 is a schematic diagram according to a fourth embodiment of the present disclosure;

FIG. 5 is a block diagram of an electronic device used to implement the method of event detection according to an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and mechanisms are omitted from the following description for clarity and conciseness.

FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure. As shown in FIG. 1 , the method for event detection in this embodiment may specifically include the following steps:

S101, acquiring image data, and identifying the urban scene of the image data;

S102, determining the target to be detected and the event to be detected corresponding to the urban scene;

S103. Detect the target to be detected in the image data to obtain the detection state of the event to be detected;

S104. Obtain an event detection result of the image data according to the detection state of the to-be-detected event.

The event detection method of this embodiment firstly identifies the urban scene of the acquired image data, then determines the to-be-detected target and the to-be-detected event corresponding to the urban scene, and finally detects the to-be-detected target in the image data. The event detection result of the image data is obtained by obtaining the detection state of the to-be-detected event. Since different urban scenes, different to-be-detected targets and to-be-detected events are corresponding, this embodiment can improve the accuracy and efficiency of event detection.

The image data obtained by executing S101 in this embodiment may be extracted from video stream data captured in real time by a camera device in a certain monitoring area of the city; the obtained image data includes at least one image of the city, so The included urban images may correspond to at least one of urban scenes such as roads, squares, and schools.

When performing S101 to acquire image data in this embodiment, an optional implementation method that may be adopted is: acquiring video stream data of a city, where different video stream data correspond to different urban scenes; extracting at least one image from the acquired video stream data key frame images as image data.

In this embodiment, after performing S101 to acquire the image data, the city scene of the acquired image data is identified. Under normal circumstances, the city scene recognized in this embodiment is only one of a road, a square, a school, etc., but there are cases where multiple city scenes are obtained by recognizing image data.

When performing S101 to identify the urban scene of the image data in this embodiment, an optional implementation method that may be adopted is: inputting the acquired image data into the first recognition model, and obtaining the urban scene of the image data according to the output result of the first recognition model, The first recognition model in this embodiment is obtained by pre-training, and can recognize the urban scene corresponding to the image data.

In addition, when S101 is performed to identify the urban scene of the image data in this embodiment, the urban scene corresponding to the standard image most similar to the image data can also be calculated by calculating the similarity between the image data and different standard images, City scene as acquired image data.

In this embodiment, after S101 is executed to identify the urban scene of the acquired image data, S102 is executed to determine the target to be detected and the event to be detected corresponding to the identified urban scene. Wherein, the target to be detected determined by executing S102 in this embodiment may be one or multiple; the determined event to be detected may be one or multiple.

In this embodiment, different urban scenes correspond to different objects to be detected and different events to be detected. By distinguishing the objects to be detected corresponding to the urban scenes, only specific objects to be detected in the image data are detected. The purpose is to effectively avoid the blindness of detection and improve the efficiency of event detection.

For example, if the urban scene is a market, the targets to be detected corresponding to the market may include people, booths, tables and chairs, billboards, garbage, and standing water, etc., and the events to be detected corresponding to the market may include illegal business events, water accumulation events, etc. ;If the urban scene is a road, the targets to be detected corresponding to the road can include vehicles, motorcycles, rickshaws, street signs, green space, water, etc., and the events to be detected corresponding to the road can include illegal parking events, road occupation events, water events, etc. .

In this embodiment, when the target to be detected and the event to be detected corresponding to the urban scene are determined in S102, the determination may be based on a preset corresponding relationship, and the preset corresponding relationship includes each urban scene and the to-be-detected event corresponding to each urban scene. Detection targets and events to be detected.

In this embodiment, after S102 is performed to determine the object to be detected and the event to be detected corresponding to the urban scene, S103 is performed to detect the object to be detected in the image data to obtain the detection status of the event to be detected. The detection state of the to-be-detected event obtained by executing S103 in this embodiment is one of a normal state and an abnormal state.

It can be understood that, if multiple events to be detected are determined by executing S102 in this embodiment, the detection status corresponding to each event to be detected can be obtained respectively by executing S103 in this embodiment.

Specifically, in this embodiment, when S103 is executed to detect the object to be detected in the image data, and the detection state of the event to be detected is obtained, an optional implementation manner that may be adopted is: combining the acquired image data with the determined to-be-detected event The target is input into the second recognition model, and the detection state of the event to be detected is obtained according to the output result of the second recognition model. The second recognition model in this embodiment is obtained by pre-training, and can be obtained according to the image data and the target to be detected. The detection status of each to-be-detected event corresponding to the image data.

In addition, in this embodiment, when S103 is executed to detect the object to be detected in the image data to obtain the detection state of the event to be detected, the detection of the event to be detected may also be obtained according to the detection result of whether the object to be detected exists in the image data. If there is stagnant water in the image data corresponding to the road, it is determined that the stagnant water event is in an abnormal state.

In this embodiment, after S103 is executed to obtain the detection state of the event to be detected, S104 is executed to obtain the event detection result of the image data according to the obtained detection state of the event to be detected.

In this embodiment, when S104 is executed, the obtained detection state of the event to be detected may be directly used as the event detection result of the image data.

Since there may be errors in the detection state of the to-be-detected event obtained when this embodiment executes S103, in order to improve the accuracy of the obtained event detection result, this embodiment executes S104 to obtain an image according to the detection state of the to-be-detected event When the event detection result of the data is used, an optional implementation method that can be adopted is: sending the obtained image data and the obtained event state of the event to be detected to the user, so that the user can confirm the event state of the event to be detected; The confirmation result returned by the user obtains the event detection result of the image data.

That is, in this embodiment, the user can also check the obtained event state of the event to be detected, so as to remove the wrong event state of the event to be detected as much as possible, and further improve the accuracy of the obtained event detection result. In this embodiment, the confirmation result returned by the user can also be used to optimize the second recognition model, that is, the image data, the target to be detected and the confirmation result of the image data are used as training data, and the second recognition model is continued to be updated, so that the second recognition model is updated. The recognition model can output a more accurate detection state of the event to be detected.

In addition, after executing S104 to obtain the event detection result of the acquired image data, the present embodiment may further include the following content: determine whether there is an event to be detected in an abnormal state in the obtained event detection result; in determining the event detection result When there is an event to be detected in an abnormal state, an alarm message is issued, and the issued alarm message includes the abnormal state of the event to be detected and the location information of the event to be detected in an abnormal state, thereby improving the accuracy of the alarm and the abnormal event. disposal efficiency.

It can be understood that, in this embodiment, alarm information can be sent to relevant department personnel, so that the relevant department personnel can quickly deal with abnormal events that occur in the city.

FIG. 2 is a schematic diagram of a second embodiment according to the present disclosure. Figure 2 shows an event detection system 200, which includes a basic configuration module, a video playback storage module, a video analysis module, an alarm information storage module, and an information processing module. Among them, the basic configuration module is used to flexibly configure the processing rules of different video data streams according to user needs, so that the video data streams can be processed in a time-sharing manner or in batches; the video playback storage module is used to complete the real-time playback and processing of video data streams. storage, and supports the retrieval and browsing of video data streams; the video analysis module is used to complete the event detection of the above-mentioned embodiment and the alarm of abnormal events; the alarm information storage module is used to realize the classified retrieval and query display of the alarm information; the information processing module Used to implement the handling of abnormal events.

FIG. 3 is a schematic diagram of a third embodiment according to the present disclosure. Fig. 3 shows the processing flow chart of the information processing unit: after the video data stream is input into the video analysis module, the video analysis module performs event detection; after the video analysis module detects an abnormal event, alarm information is generated and reported to the information processing unit; The information processing unit sends the alarm information to the relevant personnel for confirmation. If the abnormal event is detected incorrectly, the confirmation result will be returned to the video analysis module; if the abnormal event does not need to be processed, the process will end; if the abnormal event needs to be processed, it will be issued Disposal, and if it is determined that the disposal has been completed, check to determine whether the abnormal event has been processed.

FIG. 4 is a schematic diagram of a fourth embodiment according to the present disclosure. As shown in FIG. 4 , the device 400 for event detection in this embodiment includes:

Obtaining unit 401, configured to obtain image data, and identify the urban scene of the image data;

A determination unit 402, configured to determine a target to be detected and an event to be detected corresponding to the urban scene;

A detection unit 403, configured to detect the to-be-detected target in the image data to obtain the detection state of the to-be-detected event;

The processing unit 404 is configured to obtain an event detection result of the image data according to the detection state of the to-be-detected event.

The image data acquired by the acquiring unit 401 may be extracted from video stream data captured in real time by a camera in a certain monitoring area of the city; the acquired image data includes at least one city image, and the The city image may correspond to at least one of city scenes such as roads, squares, schools, and the like.

When acquiring the image data, the acquiring unit 401 may adopt an optional implementation manner as follows: acquiring the video stream data of the city; extracting at least one key frame image from the acquired video stream data as the image data.

After acquiring the image data, the acquiring unit 401 identifies the urban scene of the acquired image data. Under normal circumstances, the urban scene identified by the acquiring unit 401 is only one of a road, a square, a school, etc., but there are cases where multiple urban scenes can be obtained by identifying image data.

When recognizing the urban scene of the image data, the obtaining unit 401 may adopt an optional implementation manner as follows: input the acquired image data into the first recognition model, and obtain the urban scene of the image data according to the output result of the first recognition model.

In addition, when recognizing the urban scene of the image data, the obtaining unit 401 may also use the urban scene corresponding to the standard image most similar to the image data as the all the urban scenes by calculating the similarity between the image data and different standard images. Acquire the image data of the city scene.

In this embodiment, after the acquisition unit 401 identifies the city scene of the acquired image data, the determination unit 402 determines the target to be detected and the event to be detected corresponding to the identified city scene. Wherein, the target to be detected determined by the determining unit 402 may be one or multiple; the determined event to be detected may be one or multiple.

When determining the target to be detected and the event to be detected corresponding to the urban scene, the determining unit 402 may determine it according to a preset corresponding relationship, and the preset corresponding relationship includes each urban scene and the target to be detected corresponding to each urban scene. and the event to be detected.

In this embodiment, after the determination unit 402 determines the object to be detected and the event to be detected corresponding to the urban scene, the detection unit 403 detects the object to be detected in the image data to obtain the detection state of the event to be detected. The detection state of the to-be-detected event obtained by the detection unit 403 is one of a normal state and an abnormal state.

It can be understood that, if the determination unit 402 determines a plurality of events to be detected, the detection unit 403 can obtain the detection status corresponding to each event to be detected, respectively.

Specifically, when the detection unit 403 detects the object to be detected in the image data and obtains the detection state of the event to be detected, an optional implementation method that can be adopted is: inputting the acquired image data and the determined object to be detected The second recognition model obtains the detection state of the to-be-detected event according to the output result of the second recognition model.

In addition, when the detection unit 403 detects the object to be detected in the image data and obtains the detection state of the event to be detected, it can also obtain the detection state of the event to be detected according to whether there is a detection result of the object to be detected in the image data, For example, if there is stagnant water in the image data of the corresponding road, it is determined that the stagnant water event is in an abnormal state.

In this embodiment, after the detection unit 403 obtains the detection state of the event to be detected, the processing unit 404 obtains the event detection result of the image data according to the obtained detection state of the event to be detected.

The processing unit 404 may directly use the detection state of the event to be detected obtained by the detection unit 403 as the event detection result of the image data.

Since there may be errors in the detection state of the event to be detected acquired by the detection unit 403, in order to improve the accuracy of the obtained event detection result, the processing unit 404 obtains the event detection result of the image data according to the detection state of the event to be detected. , the optional implementation method that can be adopted is: sending the obtained image data and the obtained event status of the event to be detected to the user, so that the user can confirm the event status of the event to be detected; according to the confirmation result returned by the user , to get the event detection result of the image data.

That is, the processing unit 404 can also check the obtained event state of the event to be detected by the user, so as to remove the wrong event state of the event to be detected as much as possible, and further improve the accuracy of the obtained event detection result. The processing unit 404 can also use the confirmation result returned by the user to optimize the second recognition model, that is, the image data, the target to be detected and the confirmation result of the image data are used as training data, and continue to update the second recognition model, so that the second recognition model is updated. The recognition model can output a more accurate detection state of the event to be detected.

In addition, the device 400 for event detection in this embodiment may further include an alarm unit 405, configured to perform: after obtaining the event detection result of the acquired image data, determine whether there is an abnormal state in the obtained event detection result When it is determined that there is an event to be detected in an abnormal state in the event detection result, an alarm message is sent, and the sent alarm message includes the abnormal state of the event to be detected and the location of the event to be detected in an abnormal state information.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

As shown in FIG. 5 , it is a block diagram of an electronic device of the method for event detection according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 5 , the device 500 includes a computing unit 501 that can be executed according to a computer program stored in a read only memory (ROM) 502 or loaded from a storage unit 508 into a random access memory (RAM) 503 Various appropriate actions and handling. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501 , the ROM 502 and the RAM 503 are connected to each other through a bus 504 . An input/output (I/O) interface 505 is also connected to bus 504 .

Various components in the device 500 are connected to the I/O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 505, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc. ; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 501 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 501 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the method of event detection. For example, in some embodiments, the method of event detection may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 508 .

In some embodiments, part or all of the computer program may be loaded and/or installed on device 500 via ROM 502 and/or communication unit 509 . When a computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the method of event detection described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the method of event detection by any other suitable means (eg, by means of firmware).

Various implementations of the systems and techniques described herein may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip System (SOC), Load Programmable Logic Device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the traditional physical host and VPS service ("Virtual Private Server", or "VPS" for short) , there are the defects of difficult management and weak business expansion. The server can also be a server of a distributed system, or a server combined with a blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.

Claims

A method of event detection, comprising:

acquiring image data, and identifying the urban scene of the image data;

determining the target to be detected and the event to be detected corresponding to the urban scene;

Detecting the object to be detected in the image data to obtain the detection state of the event to be detected;

According to the detection state of the to-be-detected event, an event detection result of the image data is obtained.
The method of claim 1, wherein said acquiring image data comprises:

Get the video stream data of the city;

Extract at least one key frame image from the video stream data as the image data.
The method according to claim 1, wherein the determining the target to be detected and the event to be detected corresponding to the urban scene comprises:

According to the preset correspondence, the target to be detected and the event to be detected corresponding to the urban scene are determined.
The method according to claim 1, wherein the detecting the object to be detected in the image data to obtain the detection state of the event to be detected comprises:

The image data and the target to be detected are input into a second recognition model, and the detection state of the event to be detected is obtained according to the output result of the second recognition model.
The method according to claim 1, wherein the obtaining the event detection result of the image data according to the detection state of the to-be-detected event comprises:

sending the image data and the event status of the to-be-detected event to the user;

According to the confirmation result returned by the user, the event detection result of the image data is obtained.
The method of claim 1, further comprising:

After obtaining the event detection result of the image data, determine whether there is an event to be detected in an abnormal state in the event detection result;

When it is determined that there is an event to be detected in an abnormal state in the event detection result, alarm information is issued.
A device for event detection, comprising:

an acquisition unit for acquiring image data and identifying the urban scene of the image data;

a determining unit, configured to determine the target to be detected and the event to be detected corresponding to the urban scene;

a detection unit, configured to detect the to-be-detected object in the image data to obtain the detection state of the to-be-detected event;

A processing unit, configured to obtain an event detection result of the image data according to the detection state of the to-be-detected event.
The device according to claim 7, wherein, when the acquiring unit acquires the image data, specifically:

Get the video stream data of the city;

Extract at least one key frame image from the video stream data as the image data.
The device according to claim 7, wherein, when the determining unit determines the target to be detected and the event to be detected corresponding to the urban scene, specifically:

According to the preset correspondence, the target to be detected and the event to be detected corresponding to the urban scene are determined.
The device according to claim 7, wherein, when the detection unit detects the to-be-detected object in the image data and obtains the detection state of the to-be-detected event, the detection unit specifically executes:

The image data and the target to be detected are input into a second recognition model, and the detection state of the event to be detected is obtained according to the output result of the second recognition model.
The device according to claim 7, wherein, when the processing unit obtains the event detection result of the image data according to the detection state of the to-be-detected event, the processing unit specifically executes:

sending the image data and the event status of the to-be-detected event to the user;

According to the confirmation result returned by the user, the event detection result of the image data is obtained.
The apparatus of claim 7, further comprising an alarm unit for performing:

After the processing unit obtains the event detection result of the image data, determine whether there is an event to be detected in an abnormal state in the event detection result;

When it is determined that there is an event to be detected in an abnormal state in the event detection result, alarm information is issued.
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 one of claims 1 to 6 Methods.
A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-6.
A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.