CN114049587A

CN114049587A - Event detection method, server and system

Info

Publication number: CN114049587A
Application number: CN202111320334.3A
Authority: CN
Inventors: 杨晓英; 张呈宇; 张勋; 李董
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2021-11-09
Filing date: 2021-11-09
Publication date: 2022-02-15

Abstract

The application discloses an event detection method, a server and a system, and belongs to the technical field of image processing. The method comprises the following steps: receiving video data sent by a video acquisition terminal; identifying whether a target event occurs according to the video data; under the condition that a target event is identified, sending an event rechecking request to a preset control terminal; under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event to obtain a target event classification result; and determining an emergency plan matched with the target event classification result, and starting the emergency plan. Video data are acquired by means of a video acquisition terminal, all-dimensional inspection is realized, and more comprehensive and accurate video data are acquired; the edge server and the control terminal jointly determine whether the target event occurs, so that the identification accuracy of the target event can be effectively improved; after the target event is determined to occur, the target event is classified in time, a more targeted emergency plan is started, and the emergency processing capability is improved.

Description

Event detection method, server and system

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an event detection method, a server, and a system.

Background

Subway is an important public transport means, and during the commuting peak period, events such as passengers quarreling or trampling can occur due to the fact that the flow of people is too large, and the safety of public transport is threatened. Therefore, it is necessary to find out similar events in time and to start the corresponding emergency plan to avoid serious consequences.

At present, the inspection personnel inside the carriage mainly find and process the events through inspection. However, in peak hours, as passengers are more in the carriages, inspection personnel cannot walk through each carriage for inspection, the visual angle can be blocked by the passengers, the inspection cannot be carried out in all directions, and events cannot be found in time.

Disclosure of Invention

Therefore, the application provides an event detection method, a server and a system, so as to solve the problem that target events cannot be found in time due to the fact that inspection personnel cannot carry out all-dimensional inspection.

In order to achieve the above object, a first aspect of the present application provides an event detection method, including:

receiving video data sent by a video acquisition terminal;

identifying whether a target event occurs according to the video data;

under the condition that the target event is identified to occur, sending an event rechecking request to a preset control terminal, wherein the event rechecking request comprises video data corresponding to the target event, and the event rechecking request is used for enabling the control terminal to determine whether the target event occurs according to the video data corresponding to the target event;

under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event to obtain a target event classification result, wherein the event rechecking confirmation message is a message sent by the control terminal under the condition of confirming that the target event occurs;

and determining an emergency plan matched with the target event classification result, and starting the emergency plan.

Further, the video acquisition terminal operates in a designated space according to a preset track;

the receiving of the video data sent by the video acquisition terminal includes:

receiving video data sent by the video acquisition terminal according to a preset reporting requirement;

the preset reporting requirement comprises at least one of a period requirement, a real-time requirement and a video quality requirement.

Further, the identifying whether a target event occurs according to the video data includes:

identifying the video data through a preset target event identification model, and determining whether the target event occurs;

the target event recognition model is a model which is obtained through training and has the capability of recognizing the target event.

Further, after the identifying whether the target event occurs according to the video data, the method further includes:

under the condition that the target event is identified to occur, determining the occurrence position of the target event according to video data corresponding to the target event;

after sending an event rechecking request to a preset control terminal under the condition that the target event is identified to occur, the method further comprises the following steps:

under the condition of receiving an event rechecking confirmation message returned by the control terminal, sending an alarm instruction to the video acquisition equipment, so that the video acquisition equipment moves to the occurrence position of the target event according to the alarm instruction and sends an alarm signal;

wherein the alert indication includes a location of occurrence of the target event.

Further, the classifying the target event to obtain a target event classification result when receiving the event rechecking confirmation message returned by the control terminal includes:

under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event through a preset target event classification model to obtain a target event classification result;

the target event classification model is a model which is obtained through training and has the capability of classifying the target events.

Further, in the case of receiving the event rechecking confirmation message returned by the control terminal, after classifying the target event and obtaining a target event classification result, the method further includes:

sending a classification rechecking request to the control terminal, wherein the classification rechecking request is used for enabling the control terminal to confirm whether the target event classification result is accurate or not;

under the condition that the control terminal returns a classification rechecking confirmation message, executing the step of determining an emergency plan matched with the target event classification result and starting the emergency plan;

and the classification rechecking confirmation message is a message sent by the control terminal under the condition of confirming that the target event classification result is accurate.

Further, after the sending the classification rechecking request to the control terminal, the method further includes:

determining that the target event classification result is inaccurate under the condition that a preset specified condition is met;

the preset specified condition includes that a classification rechecking denial message returned by the control terminal is received and/or a classification rechecking confirmation message is not received in a preset time period, the preset specified condition indicates that the control terminal classifies the target event, a new target event classification result is obtained, and an emergency plan matched with the new target event classification result is started.

In order to achieve the above object, a second aspect of the present application provides an edge server, including: the receiving module is configured to receive video data sent by a video acquisition terminal;

the identification module is configured to identify whether a target event occurs according to the video data;

the sending module is configured to send an event rechecking request to a preset control terminal under the condition that the target event is identified to occur, wherein the event rechecking request comprises video data corresponding to the target event, and the event rechecking request is used for enabling the control terminal to determine whether the target event occurs according to the video data corresponding to the target event;

the classification module is configured to classify the target event to obtain a target event classification result under the condition that an event rechecking confirmation message returned by the control terminal is received, wherein the event rechecking confirmation message is a message sent by the control terminal under the condition that the target event is confirmed to occur;

and the starting module is configured to determine an emergency plan matched with the target event classification result and start the emergency plan.

Further, the edge server further includes: the device comprises a position determining module and an alarm module;

the position determining module is configured to determine an occurrence position of the target event according to video data corresponding to the target event under the condition that the target event is identified to occur;

the alarm module is configured to send an alarm instruction to the video acquisition device under the condition that an event rechecking confirmation message returned by the control terminal is received, so that the video acquisition device moves to the occurrence position of the target event according to the alarm instruction and sends an alarm signal; wherein the alert indication includes a location of occurrence of the target event.

In order to achieve the above object, a third aspect of the present application provides an event detection system, including: the system comprises a video acquisition terminal, an edge server and a control terminal;

the video acquisition terminal is used for acquiring video data and sending the video data to the edge server;

the edge server adopts the edge server of claim 8 or 9;

the control terminal is used for responding to an event rechecking request sent by the edge server, confirming whether the target event occurs according to video data corresponding to the target event in the event rechecking request, and returning an event rechecking confirmation message to the edge server under the condition that the target event is confirmed to occur.

This application has following advantage:

the event detection method, the server and the system receive video data sent by a video acquisition terminal; identifying whether a target event occurs according to the video data; under the condition that a target event is identified, sending an event rechecking request to a preset control terminal; under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event to obtain a target event classification result; and determining an emergency plan matched with the target event classification result, and starting the emergency plan. The method obtains video data by means of the video acquisition terminal, is not influenced by passenger flow, and can carry out all-dimensional inspection, thereby obtaining more comprehensive and accurate video data; in addition, based on the video data, the edge server and the control terminal jointly determine whether the target event occurs, so that the target event can be effectively prevented from being recognized by mistake, and the recognition accuracy of the target event is improved; and after the target event is determined to occur, the target event is classified in time so as to start a more targeted emergency plan and improve the processing capacity of the target event.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application and not to limit the application.

Fig. 1 is a flowchart of an event detection method according to an embodiment of the present application;

FIG. 2 is a flowchart of an event detection method according to another embodiment of the present application;

FIG. 3 is a flowchart of an event detection method according to another embodiment of the present application;

fig. 4 is a block diagram illustrating an edge server according to an embodiment of the present application;

fig. 5 is a block diagram illustrating an edge server according to another embodiment of the present application;

FIG. 6 is a block diagram illustrating components of an event detection system according to an embodiment of the present application;

FIG. 7 is a flowchart of an event detection method provided in an exemplary embodiment of the present application;

fig. 8 is a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

The following detailed description of embodiments of the present application will be made with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present application, are given by way of illustration and explanation only, and are not intended to limit the present application.

The subway is used as a common public transport means and has large pedestrian flow. Especially during peak periods, where the number of passengers is suddenly increased, excessive congestion may lead to various emergencies. Such as passengers quarreling, passengers falling down, etc., which are generally unpredictable and have a large impact range. Therefore, the emergency event needs to be discovered and processed in time, and a corresponding emergency plan is started, so as to avoid the occurrence of a secondary event caused by the fact that the discovery and the processing are not timely.

At present, the patrol personnel in the carriage mainly find and process emergencies through patrol. When the passengers in the carriage are fewer, the inspection personnel can smoothly walk inside the carriage or among the carriages for inspection. However, in the peak period, because the passengers are more, the carriage is crowded, the patrol personnel are difficult to walk inside the carriage and between the carriages for patrol, and the sight line can be shielded by the passengers, so that the omnibearing patrol can not be realized. Moreover, the working state of the patrol personnel is easily affected by the working duration, emotion, environment and the like, which may cause that the patrol personnel identify and process the emergency in time or are inaccurate.

In view of this, embodiments of the present application provide an event detection method, server, and system, where video data is acquired by means of a video acquisition terminal, and the method is not affected by passenger traffic and can perform all-around inspection, so as to obtain more comprehensive and accurate video data; in addition, based on the video data, the edge server and the control terminal jointly determine whether the target event occurs, so that the target event can be effectively prevented from being recognized by mistake, and the recognition accuracy of the target event is improved; and after the target event is determined to occur, the target event is classified in time so as to start a more targeted emergency plan and improve the processing capacity of the target event.

The first aspect of the embodiments of the present application provides an event detection method. Fig. 1 is a flowchart of an event detection method according to an embodiment of the present application, where the method is applicable to a Mobile Edge Computing (MEC) server (Edge server for short). As shown in fig. 1, the event detection method includes the following steps:

and S101, receiving video data sent by a video acquisition terminal.

The video acquisition terminal comprises various terminals with video acquisition functions. In some specific implementations, the video capture terminal operates in a designated space according to a preset trajectory, so that video data of a wider range and more viewing angles can be captured.

In some embodiments, receiving video data sent by a video capture terminal includes: and receiving video data sent by the video acquisition terminal according to a preset reporting requirement, wherein the preset reporting requirement comprises at least one of a period requirement, a real-time requirement and a video quality requirement. The period requirement refers to a requirement for a video data period reported by a video acquisition terminal, the real-time requirement refers to a requirement for a time difference between video data shooting of a video acquisition device and video data acquisition of an edge server, and the video quality requirement includes requirements for definition, resolution, frame rate and the like of a video. In practical application, the reporting requirements can be set according to the event detection place, the detection time, the detection accuracy requirements and the like, and the application is not limited to this.

For example, in an event detection scenario for a subway car, an annular track is installed on the top of the car, a Video capture terminal can move along the track and capture Video in the car during movement, and the Video is transmitted to an edge server through a fifth Generation Mobile Communication Technology (5th Generation Mobile Communication Technology, 5G) network in a Video Streaming (Video Streaming) manner according to a resolution of 360P (Progressive, meaning Progressive scanning), a frame rate of 30fps (frames per second), and a quasi-real-time requirement (time difference is less than 0.5 seconds).

And step S102, identifying whether a target event occurs according to the video data.

Wherein, the target event refers to the event which may affect the public safety and the public order, and includes but is not limited to the treading of people, the noise of people, the sudden illness of people, the fire, the waterlogging. In the case of occurrence of a target event, a human reaction, an external environment, and the like may be changed as compared with a normal case, and therefore, it is determined whether the human reaction and the environment are different from the normal case through video data, and when it is determined that the difference exists, occurrence of the target event is recognized.

In some embodiments, video data is identified through a preset target event identification model, and whether a target event occurs is determined; the target event recognition model is a model which is obtained through training and has the capability of recognizing the target event.

For example, an initial target event recognition model is constructed, pre-acquired training data is input into the model to obtain an output result, the output result and the input data are compared, model parameters are adjusted according to the comparison result until a preset termination condition is met, training is stopped, and a final target event recognition model is obtained. The training data includes video data of various target events and video data of normal situations. Specifically, in the training process, the target event recognition model extracts features from the video data and learns the difference between the features of the normal case and the features of the target event, thereby acquiring the ability to recognize the target event from the video data. When event detection is carried out, video data to be detected are input into a target event recognition model, the model processes the input data, whether a target event occurs is recognized, and a recognition result is output, so that whether the target event occurs is determined.

It should be noted that the features extracted from the video data by the target event recognition model include, but are not limited to, human body posture features, expression features, crowd gathering features, sound features, light features, and the like, and the features are not limited in this application.

And step S103, sending an event rechecking request to a preset control terminal under the condition that the target event is identified to occur.

The event rechecking request comprises video data corresponding to a target event, and is used for enabling the control terminal to determine whether the target event occurs according to the video data corresponding to the target event.

The control terminal is a preset terminal for realizing the rechecking function. And under the condition that the edge server identifies that the target event occurs, in order to avoid the target event from being detected by mistake, initiating an event rechecking request to the control terminal so that the control terminal rechecks and further determines whether the target event occurs.

In some embodiments, the edge server sends an event review request to a preset control terminal when recognizing that a target event occurs, where the event review request includes video data corresponding to the target event. And the control terminal receives and responds to the event rechecking request, identifies whether the target event occurs according to the video data corresponding to the target event, and returns a corresponding response message to the edge server according to the identification result so that the edge server can obtain the identification result of the control terminal.

It should be noted that the control terminal may review whether the target event occurs based on the same target event identification method as the edge server, may also review whether the target event occurs by using a different target event identification method (for example, perform target event identification by using a model with higher identification accuracy), and may also manually review whether the target event occurs based on the control terminal by a related person, which is not limited in this application.

And step S104, classifying the target events under the condition of receiving the event rechecking confirmation message returned by the control terminal, and obtaining a target event classification result.

The event rechecking confirmation message is a message sent by the control terminal under the condition of confirming the occurrence of the target event. Because different types of target events, personnel reactions, environmental expressions and the like are correspondingly different, the type of the target event can be determined according to the video data.

In some embodiments, under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event through a preset target event classification model to obtain a target event classification result; the target event classification model is a model which is obtained through training and has the capability of classifying the target events.

For example, an initial target event classification model is constructed, pre-acquired training data is input into the model to obtain an output result, the output result and the input data are compared, model parameters are adjusted according to the comparison result until a preset termination condition is met, training is stopped, and a final target event classification model is obtained. The training data includes video data of various types of target events. Specifically, in the training process, the target event classification model extracts features from video data, obtains features of different types of target events, and learns differences between the features of the different types of target events, thereby obtaining the ability to classify the target events according to the video data. When the target event is classified, the video data of the target event to be classified is input into a target event classification model, the model processes the input data, the type of the target event is determined, and the classification result is output, so that the classification result of the target event is obtained.

It should be noted that the essence of the target event recognition model and the essence of the target event classification model are both classification models, and the two models can be constructed by algorithms such as a decision tree, a neural network, a K-Nearest Neighbors (KNN) algorithm, a Support Vector Machine (SVM), and naive bayes. The algorithm for constructing the target event recognition model and the target event classification model is not limited in the application.

And step S105, determining an emergency plan matched with the target event classification result, and starting the emergency plan.

The emergency plan is a working scheme which is pre-made for dealing with the emergency in an legal, rapid, scientific and orderly manner and reducing the emergency and the damage caused by the emergency to the maximum extent. Aiming at different target events, the emergency work emphasis is different, so that an emergency work scheme can be formulated adaptively according to the types of the target events, and a corresponding emergency plan is formed.

In some embodiments, respective emergency protocols are pre-established for different types of target events. After the type of the target event is determined, the emergency plan matched with the type of the target event can be determined, and the emergency plan is started, so that the target event can be processed more specifically, and the influence range and the influence degree of the target event are reduced.

For example, when the target event is classified as a fire, the emergency plan includes: checking the condition of the fire passage, starting the fire fighting equipment, stopping the operation of the elevator equipment, etc.

For another example, when the target event is classified as a human being stepping on, the emergency plan includes: starting evacuation lighting indicating equipment, checking the smoothness of an evacuation channel, starting evacuation guide broadcasting and the like.

In this embodiment, video data sent by a video acquisition terminal is received; identifying whether a target event occurs according to the video data; under the condition that a target event is identified, sending an event rechecking request to a preset control terminal; under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event to obtain a target event classification result; and determining an emergency plan matched with the target event classification result, and starting the emergency plan. The method obtains video data by means of the video acquisition terminal, is not influenced by passenger flow, and can carry out all-dimensional inspection, thereby obtaining more comprehensive and accurate video data; in addition, based on the video data, the edge server and the control terminal jointly determine whether the target event occurs, so that the target event can be effectively prevented from being recognized by mistake, and the recognition accuracy of the target event is improved; and after the target event is determined to occur, the target event is classified in time so as to start a more targeted emergency plan and improve the processing capacity of the target event.

Fig. 2 is a flowchart of an event detection method according to another embodiment of the present application.

As shown in fig. 2, the event detection method includes the following steps:

step S201, receiving video data sent by a video acquisition terminal.

Step S202, whether a target event occurs is identified according to the video data.

Steps S201 to S202 in this embodiment are the same as steps S101 to S102 in this embodiment, and are not described herein again.

In step S203, when the occurrence of the target event is recognized, the occurrence position of the target event is determined based on the video data corresponding to the target event.

The occurrence position of the target event includes an area range where the target event occurs, and may be represented in the form of latitude and longitude, GPS (Global Positioning System) coordinates, address name, and the like. For example, the occurrence position of the target event is (116.328135, 39.90238); for another example, the occurrence position of the target event is the middle area of the carriage No. 5; for another example, the target event occurs in the west region of the south square of the train station.

In some embodiments, first, a position of a video capture device capturing video data is determined based on the video data corresponding to the target event; secondly, according to the position of the video acquisition device, the occurrence position of the target event can be determined.

In other embodiments, first, according to video data corresponding to a target event, a region corresponding to the video data is identified; and secondly, determining the occurrence position of the target event according to the area corresponding to the video data.

For example, the video data corresponding to the target event includes the number "X" of the video capture device₁X₂X₃X₄According to the preset corresponding relation between the number of the video acquisition device and the installation position and the number of the video acquisition device, the installation position of the video acquisition device can be determined, so that the shooting area of the video acquisition device is determined, and the occurrence position of the target event is determined according to the shooting area.

As another example, the video data corresponding to the target event includes a plurality of image frames from which it can be determined that it belongs to the video data inside the vehicle compartment, and a part of the image frames captures the area above both ends of the vehicle compartment including the compartment number "Y₁Y₂Y₃Y₄Y₅Y₆". Since the carriage number is similar to the 'ID card number' of the carriage, the carriage can be determined according to the carriage number, and the target event can be determined to be located at the approximate position of the carriage (for example, located in the head area of the carriage) by further combining the information such as the shooting angle and the shooting position corresponding to the image frame, so that the occurrence position of the target event can be determined.

It should be noted that the above method for determining the occurrence position of the target event is only an example, and in practical applications, the occurrence position of the target event can be flexibly determined according to needs, which is not limited in the present application.

Step S204, an event rechecking request is sent to a preset control terminal.

Step S205, under the condition of receiving the event recheck confirmation message returned by the control terminal, sending an alarm instruction to the video acquisition equipment, so that the video acquisition equipment can move to the occurrence position of the target event according to the alarm instruction and send an alarm signal.

The event review confirmation message is a message returned to the edge server by the control terminal when the control terminal confirms that the target event occurs. The alert indication includes the location of occurrence of the target event.

The edge server receives the event rechecking confirmation message, can further determine that the target event occurs, and can send an alarm instruction to the video acquisition device based on the event rechecking confirmation message so that the video acquisition device can give an alarm in time.

In some embodiments, in the case of receiving an event review confirmation message returned by the control terminal, the edge server generates an alarm indication based on the occurrence position of the target event and sends the alarm indication to the video capture device, and the video capture terminal receives the alarm indication. However, since the video capture terminal may operate in the designated space according to the preset trajectory, the position where the video capture device receives the alarm indication may not be the occurrence position of the target event, and therefore, the video capture device needs to move to the occurrence position of the target event in the alarm indication and send an alarm signal at the occurrence position.

The alarm signal may include one or more of a light signal and a sound signal, which may be set according to the occurrence location of the target event or other requirements.

For example, if the target event occurs inside the vehicle cabin, the warning signal may be set to a flashing light signal.

In another example, if the occurrence position of the target event is a train station south square, the alarm signal may be set as a sound signal.

And step S206, classifying the target events to obtain a target event classification result.

And step S207, determining an emergency plan matched with the target event classification result, and starting the emergency plan.

Steps S206 to S207 in this embodiment are the same as steps S104 to S105 in this embodiment, and are not described herein again.

It should be noted that, the order of step S203 and step S204 may be adjusted, that is, when the target event is identified, the occurrence position of the target event may be determined first, and then the event review request is sent to the control terminal, or the event review request is sent to the control terminal first, and then the occurrence position of the target event is determined, or the operation of determining the occurrence position of the target event and sending the time review request to the control terminal may be performed at the same time, which is not limited in the present application.

Similarly, the sequence of step S205 and step S206 may also be adjusted, that is, in the case of receiving the event recheck confirmation message returned by the control terminal, the alarm instruction may be sent to the video capture device first, and then the target event is classified, or the target event may be classified first, and then the alarm instruction is sent to the video capture device, and the operation of sending the alarm instruction to the video capture device and classifying the target event may also be performed at the same time, which is not limited in this application.

In this embodiment, after the edge server identifies the target event, the occurrence position of the target event is further determined, and after the control terminal rechecks and confirms the occurrence of the target event, the video acquisition device is instructed to move to the occurrence position of the target event to send out an alarm signal, so that the attention of workers near the occurrence position of the target event can be timely and conveniently brought, and the workers are instructed to rush to the occurrence position of the target event for emergency treatment, so that the response time of the target event is shortened, and the processing efficiency of the target event is improved.

Fig. 3 is a flowchart of an event detection method according to yet another embodiment of the present application.

As shown in fig. 3, the event detection method includes the steps of:

step S301, receiving video data sent by a video acquisition terminal.

Step S302, according to the video data, whether a target event occurs is identified.

Step S303, sending an event rechecking request to a preset control terminal when the target event is identified to occur.

And step S304, under the condition that the event rechecking confirmation message returned by the control terminal is received, classifying the target event to obtain a target event classification result.

Steps S301 to S304 in this embodiment are the same as steps S101 to S104 in this embodiment, and are not described herein again.

Step S305, sending a request for checking the classification to the control terminal.

The classification rechecking request is used for enabling the control terminal to confirm whether the target event classification result is accurate or not.

And step S306, under the condition that the control terminal returns the classification rechecking confirmation message, determining an emergency plan matched with the classification result of the target event, and starting the emergency plan.

In some embodiments, after obtaining the target event classification result, the edge server sends a classification rechecking request to the control terminal, where the classification rechecking request includes the target event classification result. And the control terminal receives a classification rechecking request sent by the edge server, classifies the target event according to the video data corresponding to the target event, and determines whether the classification of the target event is consistent with the classification result of the target event obtained by the edge server. And under the condition that the two are consistent, the control terminal sends a classification rechecking confirmation message to the edge server. After the edge server receives the classification rechecking confirmation message returned by the control terminal, the target event classification result can be determined to be accurate, based on the result, an emergency plan matched with the target event classification result is determined, and the emergency plan is started.

It should be noted that the control terminal may recheck whether the target event classification is accurate based on the same target event classification method as the edge server, may also determine the classification of the target event by using a different target event classification method (for example, perform the classification of the target event by using a model with higher classification accuracy), and may also manually classify the target event by a relevant person based on the control terminal, which is not limited in this application.

It should be further noted that, in some embodiments, after sending the classification rechecking request to the control terminal, the method further includes: and under the condition that a preset specified condition is met, determining that the target event classification result is inaccurate. The preset specified condition comprises that a classification rechecking denial message returned by the control terminal is received and/or a classification rechecking confirmation message is not received in a preset time period, the preset specified condition indicates that the control terminal classifies the target event, a new target event classification result is obtained, and an emergency plan matched with the new target event classification result is started.

For example, the preset specified condition is that a classification rechecking denial message returned by the control terminal is received, and/or a classification rechecking confirmation message is not received within 30 seconds. And if the preset specified conditions are met, the edge server determines that the obtained target event classification result is inaccurate. Based on the method, the control terminal classifies the target events, obtains a new target event classification result, determines an emergency plan matched with the new target event classification result, and starts the emergency plan.

It should be noted that, in some other embodiments, in the case that the preset specified condition is met, the edge server classifies the target event again, and sends the classification rechecking request to the control terminal again until the control terminal returns a classification rechecking confirmation message to the edge server. Through the process, the current target event classification result can be determined to be an accurate classification result, the edge server determines an emergency plan matched with the current target event classification result, and the emergency plan is started.

In this embodiment, after the edge server obtains the target event classification result, the control terminal rechecks the target event classification result to ensure that the target event is correctly classified, thereby ensuring to start an accurate and reasonable emergency plan.

The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps into multiple steps, which are all within the protection scope of the present application as long as the same logical relationship is included; it is within the scope of the present application to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.

A second aspect of the embodiments of the present application provides an edge server. Fig. 4 is a block diagram illustrating an edge server according to an embodiment of the present application. As shown in fig. 4, the edge server 400 includes the following modules:

the receiving module 401 is configured to receive video data sent by a video capture terminal.

An identifying module 402 configured to identify whether a target event occurs according to the video data.

A sending module 403, configured to send an event review request to a preset control terminal in case that the occurrence of the target event is recognized.

And the classifying module 404 is configured to classify the target event to obtain a target event classification result when receiving the event rechecking confirmation message returned by the control terminal.

The event rechecking confirmation message is a message sent by the control terminal under the condition of confirming the occurrence of the target event.

And the starting module 405 is configured to determine an emergency plan matched with the target event classification result, and start the emergency plan.

In some embodiments, the sending module 403 is further configured to send a classification review request to the control terminal after obtaining the target event classification result, so that the control terminal confirms whether the target event classification result obtained by the edge server is accurate.

In the embodiment, video data sent by a video acquisition terminal is received through a receiving module; the identification module identifies whether a target event occurs according to the video data; under the condition that a target event is identified, an event rechecking request is sent to a preset control terminal through a sending module; under the condition of receiving an event rechecking confirmation message returned by the control terminal, classifying the target event by a classification module to obtain a target event classification result; and the starting module determines an emergency plan matched with the target event classification result and starts the emergency plan. The device acquires video data by means of the video acquisition terminal, is not influenced by passenger flow, and can carry out all-dimensional inspection, so that more comprehensive and accurate video data can be acquired; in addition, based on the video data, the edge server and the control terminal jointly determine whether the target event occurs, so that the target event can be effectively prevented from being recognized by mistake, and the recognition accuracy of the target event is improved; and after the target event is determined to occur, the target event is classified in time so as to start a more targeted emergency plan and improve the processing capacity of the target event.

Fig. 5 is a block diagram of an edge server according to another embodiment of the present application. As shown in fig. 5, the edge server 500 includes the following modules:

the receiving module 501 is configured to receive video data sent by a video capture terminal.

An identifying module 502 configured to identify whether a target event occurs according to the video data.

A sending module 503, configured to send an event review request to a preset control terminal in case that the occurrence of the target event is recognized.

And the classification module 504 is configured to classify the target event to obtain a target event classification result when receiving the event rechecking confirmation message returned by the control terminal.

And the starting module 505 is configured to determine an emergency plan matched with the target event classification result, and start the emergency plan.

And a position determining module 506 configured to determine an occurrence position of the target event according to the video data corresponding to the target event in case that the occurrence of the target event is identified.

And the alarm module 507 is configured to send an alarm instruction to the video acquisition device when receiving the event rechecking confirmation message returned by the control terminal, so that the video acquisition device moves to the occurrence position of the target event according to the alarm instruction and sends an alarm signal.

Wherein the alert indication includes the location of occurrence of the target event.

In this embodiment, after the identification module identifies the target event, the position determination module determines the occurrence position of the target event, and after the control terminal rechecks and confirms the occurrence of the target event, the alarm module instructs the video acquisition device to move to the occurrence position of the target event to send an alarm signal, so that the attention of workers near the occurrence position of the target event can be timely and conveniently brought, and the workers are directed to rush to the occurrence position of the target event for emergency treatment, thereby shortening the response time of the target event and improving the processing efficiency of the target event.

A third aspect of the embodiments of the present application provides an event detection system. Fig. 6 is a block diagram illustrating an event detection system according to an embodiment of the present disclosure. As shown in fig. 6, the event detection system 600 includes: a video capture terminal 601, an edge server 602, and a control terminal 603.

The video acquisition terminal 601 is configured to acquire video data and send the video data to the edge server 602; the edge server 602 is any one of the edge servers in the embodiments of the present application; the control terminal 603 is configured to respond to the event review request sent by the edge server 602, determine whether a target event occurs according to the video data corresponding to the target event in the event review request, and return an event review confirmation message to the edge server 602 when the target event is determined to occur.

In some embodiments, the event detection system further comprises an event detection platform and a staff handheld terminal. The event detection platform is a platform for providing operation service, can receive relevant information of a target event, and is used for carrying out statistical analysis by a worker based on the information; the handheld terminal of the staff can also receive the relevant information of the target event and can also view the statistical analysis information about the target event generated by the event detection platform.

In some implementations, the video capture terminal 601 can slide along a track attached to the top of the car to capture video data at different positions and at different viewing angles. Moreover, the video capture terminal 601 accesses a communication network (e.g., a cellular mobile network of various network systems, a WIFI network, etc.), and transmits video data to the edge server 602 through the communication network.

Fig. 7 is a flowchart of an event detection method according to an exemplary embodiment of the present application, where the event detection method is applicable to the event detection system shown in fig. 6. As shown in fig. 7, the event detection method includes:

in step S701, the video capture terminal 601 slides along a preset track, captures video data in a car, and sends the video data to the edge server 602 through the 5G network.

In step S702, the edge server 602 receives the video data, identifies the video data through the target event identification model, and determines whether a target event occurs.

In step S703, when recognizing that the target event has occurred, the edge server 602 determines the occurrence position of the target event.

In step S704, the edge server 602 sends an event review request to the preset control terminal 603.

Wherein the event review request includes video data corresponding to the target event.

In step S705, the control terminal 603 determines whether a target event occurs according to the video data corresponding to the target event.

In step S706, in the case where it is determined that the target event is to be transmitted, the control terminal 603 returns an event review confirmation message to the edge server 602.

In step S707, the edge server 602 receives the event review confirmation message, and sends an alarm instruction to the video capture device.

In step S708, the video capture device moves to the occurrence position of the target event according to the alarm indication, and sends an alarm signal.

In step S709, the edge server 602 classifies the target event to obtain a target event classification result.

Step S710, the edge server 602 sends a request for checking the classification to the control terminal 603

In step S711, the control terminal 603 receives the classification rechecking request sent by the edge server 602, and determines whether the target event classification result is accurate.

In step S712, if the target event classification result is determined to be accurate, a classification rechecking confirmation message is returned to the edge server 602.

In step S713, the edge server 602 receives the classification rechecking confirmation message returned by the control terminal 603, determines an emergency plan matched with the target event classification result, and starts the emergency plan.

FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments 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, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the event detection method. For example, in some embodiments, the event detection method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM802 and/or communications unit 809. When the computer program is loaded into RAM803 and executed by the computing unit 801, one or more steps of the event detection method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the event detection method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one 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 codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, a unit that is not so closely related to solving the technical problem proposed by the present application is not introduced in the present embodiment, but it does not indicate that no other unit exists in the present embodiment.

It is to be understood that the above embodiments are merely exemplary embodiments that are employed to illustrate the principles of the present application, and that the present application is not limited thereto. It will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the application, and these changes and modifications are to be considered as the scope of the application.

Claims

1. An event detection method applied to an edge server includes:

receiving video data sent by a video acquisition terminal;

identifying whether a target event occurs according to the video data;

2. The event detection method according to claim 1, wherein the video capture terminal operates in a designated space according to a preset trajectory;

3. The event detection method according to claim 1, wherein the identifying whether a target event occurs according to the video data comprises:

4. The event detection method according to claim 1, wherein said identifying whether a target event occurs according to the video data further comprises:

5. The event detection method according to claim 1, wherein the classifying the target event to obtain a target event classification result when receiving an event review confirmation message returned by the control terminal includes:

6. The event detection method according to claim 1 or 5, wherein, in a case of receiving the event review confirmation message returned by the control terminal, classifying the target event and obtaining a target event classification result, further comprising:

7. The event detection method according to claim 6, wherein after the sending the request for checking classification to the control terminal, further comprising:

8. An edge server, comprising:

the receiving module is configured to receive video data sent by a video acquisition terminal;

9. The edge server of claim 8, wherein the edge server further comprises: the device comprises a position determining module and an alarm module;

10. An event detection system, comprising: the system comprises a video acquisition terminal, an edge server and a control terminal;

the edge server adopts the edge server of claim 8 or 9;