JP2023502816A - On-site monitoring method and device, electronic device, storage medium and program - Google Patents

Abstract

Embodiments of the present disclosure provide a field surveillance method and apparatus, an electronic device, a storage medium, and a program, the method comprising acquiring surveillance video collected by surveillance equipment installed at at least one surveillance point; determining, based on the surveillance video, whether a surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point; and if the surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point. obtaining people monitoring data matching the monitoring event within a preset time period; and determining people flow status data for the at least one monitoring device based on the people monitoring data. Thus, in the embodiments of the present disclosure, the determined crowd flow status data represents the status of the surveillance event and provides surveillance for surveillance video. [Selection drawing] Fig. 1

Description

(Cross reference to related applications)
This patent application is filed on October 30, 2020, Chinese Patent Application No. 202011190695.6, Applicant Shenzhen Shangyu Technology Co., Ltd. , the entire content of which is incorporated herein by reference.

TECHNICAL FIELD The present disclosure relates to the technical field of computer vision, and specifically to field monitoring methods and devices, electronic devices, storage media, and programs.

BACKGROUND ART With the improvement of people's living standards, more and more large-scale events are being held in various places and places. When a large-scale event is held, the flow of people is dense, so accidents such as crowd accidents and traffic accidents are likely to occur at the point or place where the large-scale event is held. Therefore, effective monitoring of people flow is becoming more and more important in order to increase the security of each point and each location.

In view of the above, embodiments of the present disclosure provide at least an on-site monitoring method and apparatus, an electronic device, a storage medium, and a program.

An embodiment of the present disclosure provides a field monitoring method, the method being performed by an electronic device, the method comprising:
obtaining surveillance video collected by surveillance equipment installed at at least one surveillance point;
determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point based on the surveillance video;
when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point, obtaining population monitoring data matching the monitoring event within a preset time period;
determining people flow status data for the at least one monitoring device based on the people monitoring data.

Thus, when the surveillance video collected by the surveillance equipment is acquired and a surveillance event is detected to occur in a surveillance area corresponding to at least one surveillance point based on the surveillance video acquired, a preset Obtaining people monitoring data matching a monitoring event within a time period, and determining people flow status data of at least one monitoring device based on the people monitoring data matching a monitoring event within a preset time period, and determining The collected people flow status data represents the status of the surveillance event, thereby realizing the surveillance of the surveillance video.

In some embodiments of the present disclosure, further comprising, after determining the people flow status data of the at least one monitoring device, generating people flow status alert information if the people flow status data satisfies an alarm condition. In this way, when the determined crowd flow status data satisfies the alarm conditions, the crowd flow status warning information is generated, and based on the generated crowd flow status warning information, the target monitoring area is controlled to reduce the safety accident rate. , it is possible to increase the safety of the flow of people in the target surveillance area.

In some embodiments of the present disclosure, if the surveillance event is a line crossing event, determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point based on the surveillance video. determining, based on the surveillance video, whether there is a target object within a surveillance area corresponding to the at least one surveillance point that straddles a target location that matches a pre-drawn entry/exit boundary. and determining that the line crossing event occurred in a surveillance area corresponding to the at least one surveillance point if the target object is present. Thus, when it is determined based on the surveillance video that there is a target object straddling the target location matching the entry/exit boundary within the surveillance area corresponding to the at least one surveillance point, the It is determined that a line-crossing event occurs in the monitoring area, thereby realizing real-time monitoring of the line-crossing event and enhancing the accuracy of monitoring the line-crossing event.

In some embodiments of the present disclosure, when the monitoring event is a line crossing event, obtaining people monitoring data matching the monitoring event within a preset time period includes: Obtaining the number of inflows and the number of outflows of people at different collection points in the zone, wherein the number of inflows is the direction in which a pre-drawn entrance/exit boundary line is drawn in advance at the different collection points. The number of people crossing along the pre-drawn exit direction includes that the number of people crossing the pre-drawn entrance/exit boundary line along the pre-drawn exit direction at the different collection time points. In this way, when the monitored event is a line-crossing event, the number of incoming people and the number of outgoing people at different collection points within a preset time period are acquired, and then the people-flow state data corresponding to the line-crossing event is obtained. Data support can be provided for the determination.

In some embodiments of the present disclosure, when the monitoring point is one, determining the people flow status data of the at least one monitoring device based on the people monitoring data includes: the number of people flowing in and the number of people flowing out. determining the total number of inflows and the total number of outflows within the preset time period in the monitoring area corresponding to the monitoring point, if the people flow status data satisfies an alarm condition; , generating the people flow status warning information includes the condition that the total number of incoming people is greater than a predetermined first people flow threshold and the total number of outgoing people is greater than a predetermined second people flow threshold; generating the people flow status warning information when either the total number of people flow is greater than the first people flow threshold or the total number of exiting people is greater than the second people flow threshold. . In this way, when there is one monitoring point, based on the number of inflows and outflows at different collection times within the preset time period, the preset time period in the monitoring area corresponding to the monitoring point is calculated. Determine the total number of inflows and the total number of outflows. A case where the total number of incoming people in a preset time zone is greater than a predetermined first threshold for the flow of people, and a case where the total number of outgoing people for a preset time zone is greater than a predetermined second threshold for people flow. In at least one case, the people flow status warning information is generated, so that early warning of the number of incoming people and the number of outgoing people in the surveillance video can be realized, so that the generated people flow status warning information includes: The flow of people is guided based on the basis, and the occurrence rate of safety accidents caused by a large number of people entering or exiting in a short time is reduced.

In some embodiments of the present disclosure, when the monitoring point is one, determining the people flow status data of the at least one monitoring device based on the people monitoring data includes: the number of people flowing in and the number of people flowing out. determining the velocity of incoming and outgoing people in the monitoring area corresponding to the monitoring point based on the. In this way, it is possible to determine the speed of the inflow of people and the speed of the outflow of people in the monitoring area corresponding to the monitoring point based on the number of inflows and the number of outflows at different collection points in a preset time period. Therefore, it is possible to monitor the velocity of incoming and outgoing people, and reduce the safety accident rate caused by high velocity of incoming or outgoing people.

In some embodiments of the present disclosure, when the monitoring points are multiple, determining people flow status data of the at least one monitoring device based on the people monitoring data includes: for each of the monitoring points, the inbound people flow determining the total number of inflows and the total number of outflows within the preset time period in the monitoring areas corresponding to each of the monitoring points based on the number and the number of outflows; Based on the historical number of people in the target monitoring area within the specified time period, and the total number of incoming and outgoing people within the preset time period corresponding to each of the monitoring points, said target monitoring area and, if the crowd status data satisfies an alarm condition, generating crowd status warning information includes: if the current population is greater than a predetermined current population threshold, generating the crowd flow status alert information. In this way, after determining the total number of inflows of people and the total number of outflows of people within a preset time period in the monitoring area corresponding to each monitoring point, the history of the target monitoring area within the preset time period is calculated. Based on the number of people and the total number of inflows and outflows within a preset time period corresponding to each monitoring point, determine the number of people present in the target monitoring area, and determine the number of people present in the target monitoring area. is greater than a predetermined threshold for the current population, it is possible to generate crowd flow status warning information, thereby realizing early warning for the current population in the target monitoring area, thereby When there are many people present, guide the people according to the generated people flow status warning information to reduce the occurrence rate of safety accidents caused by too many people in the target monitoring area.

In some embodiments of the present disclosure, if the surveillance event is a congestion event, determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point based on the surveillance video. determining, based on the surveillance video, whether a number of target objects within a surveillance area corresponding to the at least one surveillance point exceeds an overcrowding threshold; if so, determining that a congestion event has occurred in a monitoring area corresponding to the at least one monitoring point. Thus, when it is determined based on the surveillance video that the number of target objects in the surveillance area corresponding to the at least one surveillance point exceeds the congestion threshold, an overcrowding event occurs in the surveillance area corresponding to the at least one surveillance point. has occurred, thereby enabling real-time monitoring of congestion events and increasing the accuracy of congestion event monitoring.

In some embodiments of the present disclosure, when the surveillance event is an overcrowded event, obtaining people monitoring data matching the surveillance event within a preset time slot includes: statistically counting the number of said target objects at different collection time points within. In this way, if the monitoring event is a congestion event, the number of target objects at different collection times within a preset time period can be statistically determined, thereby subsequently determining the crowd flow conditions corresponding to the congestion event. Data support can be provided for determining data.

In some embodiments of the present disclosure, when the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes: determining an average number of people within the preset time period of the monitoring area corresponding to the monitoring point; generating the people flow status alert information when the number of people is greater than a predetermined first people threshold. Thus, when there is one monitoring point, the average of the monitoring area corresponding to the monitoring point within the preset time period is based on the number of target objects at different collection points within the preset time period. determining the number of people, and if the average number of people within a preset time period of the monitoring area corresponding to the monitoring point is greater than a predetermined first people threshold, generating people flow status warning information, thereby displaying the monitoring video; It is possible to monitor the average number of people in the detection area, thereby guiding the flow of people to the detection area based on the generated people flow status warning information, and preventing safety accidents due to the crowding of people in the detection area. Reduce incidence.

In some embodiments of the present disclosure, when the monitoring points are multiple, determining people flow status data of the at least one monitoring device based on the people monitoring data includes: for each of the monitoring points, the target object; determining the average number of people within the preset time period in the monitoring area corresponding to the monitoring point based on the number of; and determining the real-time total number of people in the target monitoring area based on the average number of people. and generating the people flow condition warning information when the people flow condition data satisfies an alarm condition, and generating the people flow condition alarm information when the real-time total number of people is greater than a predetermined second people threshold. ,including. In this way, after determining the average number of people in the monitoring area corresponding to each monitoring point within a preset time period, real-time monitoring in the target monitoring area is performed based on the average number of people corresponding to each of the plurality of monitoring points. Determining the total number of people, and if it is determined that the real-time total number of people in the target monitoring area is greater than a predetermined second people threshold, generating people flow status alert information, thereby indicating the real-time total number of people in the target monitoring area. It is possible to realize early warning of the number of people, so that when the real-time total number of people is large, the people in the target monitoring area will be guided according to the generated people flow status warning information, and the real-time total number in the target monitoring area will be guided. Reduce the incidence of safety accidents due to large numbers of people.

In some embodiments of the present disclosure, the method includes averaging people flow status data at the same collection time point within a plurality of recent historical dates to obtain people flow forecast data corresponding to each collection time point; further comprising constructing forecast data of people flow status data at a future date based on the forecast people flow status data, wherein the forecast data is used to generate a people flow guidance plan. In this way, it is possible to generate a people flow guidance plan based on forecast data of people flow state data for future dates.

For the explanation of the effects of the following devices, electronic devices, etc., refer to the explanation of the above method, and duplicate explanations will be omitted here.

Embodiments of the present disclosure further provide an on-site monitoring device, comprising:
a first acquisition module configured to acquire surveillance video acquired by surveillance equipment installed at at least one surveillance point;
a detection module configured to determine, based on the surveillance video, whether a surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point;
a second acquisition module configured to acquire population monitoring data matching the monitoring event within a preset time period when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point; ,
a determination module configured to determine people flow status data for the at least one monitoring device based on the people monitoring data.

In some embodiments of the present disclosure, after determining people flow status data of the at least one monitoring device, the site monitoring device generates people flow status alert information if the people flow status data satisfies an alarm condition. an alarm module configured in a.

In some embodiments of the present disclosure, if the surveillance event is a line crossing event, the detection module detects a pre-drawn entry/exit within a surveillance area corresponding to the at least one surveillance point based on the surveillance video. Determining whether there is a target object that straddles a target location matching a boundary line, and if so, the line-crossing event has occurred in a surveillance area corresponding to the at least one surveillance point. and is configured to perform:

In some embodiments of the present disclosure, if the monitoring event is a line-crossing event, the second obtaining module obtains the number of inflows and outflows at different collection time points within the preset time period. In this case, the number of people flowing in is the number of people who straddle a pre-drawn entrance/exit boundary line along the entrance direction drawn in advance at the different collection time points, and the number of people flowing in is the different At the time of collection, the number of people crossing the pre-drawn entry/exit boundary line along the pre-drawn exit direction.

In some embodiments of the present disclosure, if there is one monitoring point, the determination module determines the preset time period in the monitoring area corresponding to the monitoring point based on the number of inflows and the number of outflows. configured to determine the total number of inflows and the total number of outflows within the
The alarm module sets the condition that the total number of incoming people flow is greater than a predetermined first human flow threshold and the total number of outgoing human flow is greater than a predetermined second human flow threshold; The crowd flow status warning information is generated when either the condition that the number of people flowing out is greater than the threshold of one flow or the total number of people flowing out is greater than the threshold of the second crowd flow.

In some embodiments of the present disclosure, if there is one monitoring point, the decision module determines the velocity of incoming and outgoing people in a monitoring area corresponding to the monitoring point based on the number of incoming people and the number of outgoing people. is configured to determine the velocity of

In some embodiments of the present disclosure, if there are multiple monitoring points, the determining module determines, for each of the monitoring points, monitoring corresponding to each of the monitoring points based on the number of inflows and the number of outflows. Determining the total number of inflows and the total number of outflows in the area within the preset time period, and the historical number of people in the target monitoring area within the preset time period and each of the monitoring points. Determining the current number of people in the target monitoring area based on the total number of inflows and the total number of outflows within the preset time period respectively corresponding to
The alert module is configured to generate the crowd flow status alert information when the current population is greater than a predetermined current population threshold.

In some embodiments of the present disclosure, if the surveillance event is an overcrowding event, the detection module determines, based on the surveillance video, that the number of target objects within a surveillance region corresponding to the at least one surveillance point exceeds a congestion threshold. and if the number of target objects exceeds the congestion threshold, then determining that a congestion event has occurred in the surveillance region corresponding to the at least one surveillance point. configured to

In some embodiments of the present disclosure, if the monitoring event is an overcrowding event, the second acquisition module is configured to statistically count the number of target objects at different collection time points within the preset time period. Configured.

In some embodiments of the present disclosure, if the monitoring point is one, the determination module calculates the average number of people in the monitoring area corresponding to the monitoring point within the preset time period based on the number of target objects. configured to determine the
The alert module is configured to generate the people flow status alert information when the average number of people is greater than a predetermined first people threshold.

In some embodiments of the present disclosure, if there are multiple monitoring points, the determination module determines, for each monitoring point, the preset monitoring region corresponding to the monitoring point based on the number of target objects. determining an average number of people in a time period; and determining a real-time total number of people in a target monitoring area based on the average number of people;
The alert module is configured to generate the people flow status alert information when the real-time total number of people is greater than a second predetermined threshold number of people.

In some embodiments of the present disclosure, the site monitoring device averages people flow status data at the same collection time point within the most recent historical dates to obtain people flow status prediction data corresponding to each collection time point. and constructing prediction data of people flow state data at a future date based on said people flow state prediction data, wherein said prediction data is used to generate a people flow guidance plan. an early warning module configured to:

Embodiments of the present disclosure further provide an electronic device comprising a processor, a memory and a bus, wherein machine-readable instructions executable by the processor are stored in the memory and the electronic device operates. The processor and the memory then communicate over a bus and the machine-readable instructions, when executed by the processor, perform the method of site monitoring described in any of the above embodiments.

An embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs any of the above embodiments. Perform the site monitoring method described in .

Embodiments of the present disclosure further provide a computer program product, the computer program product comprising computer readable code, wherein when the computer readable code is executed in an electronic device, the processor of the electronic device performs any of the above. Perform the site monitoring method described in the example of .

Embodiments of the present disclosure provide at least a site monitoring method and apparatus, an electronic device, a storage medium, and a program for acquiring surveillance video collected by a surveillance device, and determining at least one monitoring point based on the collected surveillance video. obtaining people monitoring data corresponding to the monitoring event within a preset time period when a monitoring event occurs in the monitoring area corresponding to the monitoring area; Determining people flow status data and characterizing the status of the surveillance event by the determined people flow status data, thereby realizing surveillance for surveillance video.

In order to make the above objects, features and advantages of the present disclosure more comprehensible, particularly preferred embodiments will be described in detail below with reference to the accompanying drawings.

4 is a schematic flow chart of a site monitoring method provided by an embodiment of the present disclosure; 1 is a schematic diagram of a system architecture to which an on-site monitoring method of an embodiment of the present disclosure can be applied; FIG. 1 is a schematic diagram of an interface displaying a video screen screenshot depicting surveillance signs provided by an embodiment of the present disclosure; FIG. FIG. 4 is a schematic diagram of an interface displaying another video screen screenshot depicting surveillance signs provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface of early warning information corresponding to people flow data shown in an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface displaying detailed information of people flow condition alert provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface displaying detailed information of people flow condition alert provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of another interface displaying detailed information of people flow condition alert provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface for displaying alarm details provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface displaying detailed information of people flow condition alert provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface displaying detailed information of people flow condition alert provided by an embodiment of the present disclosure; FIG. 4 is a schematic diagram of an interface for displaying alarm details provided by an embodiment of the present disclosure; FIG. 3 is a schematic diagram of an interface in which real-time headcount and crowd flow headcount changes over time provided by embodiments of the present disclosure; 1 is a schematic diagram of an interface for forecasting people flow data in future time periods provided by embodiments of the present disclosure; FIG. 9 is a schematic diagram of the architecture of a field monitoring device 900 provided by embodiments of the present disclosure; FIG. 19 is a structural schematic diagram of an electronic device 1900 provided by an embodiment of the present disclosure; FIG.

In order to describe the technical solutions of the embodiments of the present disclosure more clearly, the following briefly introduces the drawings required for the embodiments, and the drawings here are incorporated into the specification to These drawings show embodiments consistent with the present disclosure and are used together with the specification to describe the technical solutions of the embodiments of the present disclosure. The following drawings merely illustrate some embodiments of the present disclosure and are therefore not to be considered limiting in scope, and those skilled in the art will be able to adapt these drawings without creative effort. It should be understood that other related drawings may also be obtained based on.

In order to make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the following clearly and completely describes the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. It should be understood that the described implementations are only some, but not all implementations of the present disclosure. In general, the components of the embodiments of the disclosure described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Accordingly, the detailed descriptions of embodiments of the present disclosure provided in the following drawings are not intended to limit the scope of the claimed disclosure, but are intended to illustrate particular embodiments of the disclosure. Not too much. Based on the embodiments of the present disclosure, all other embodiments obtained by persons skilled in the art without creative efforts are within the protection scope of the present disclosure.

BACKGROUND ART With the improvement of people's living standards, more and more large-scale events are being held in various places and places. When a large-scale event is held, the flow of people is concentrated, so accidents are likely to occur at the point or place where the large-scale event is held. There is a growing demand for predicting the number of people present. Crowd analysis has important applications in many areas of daily life. Crowd analysis can grasp the real-time number of people in an area in real time, reduce serious accidents such as crowds, and ensure people's safety. , can also be applied to commercial sites, and is useful for corporate customer behavior analysis.

However, the related applications of existing crowd analysis are more focused on people estimation in the video area and early warning for actions such as area intrusion. Predictions cannot be made to prevent safety problems, and data analysis cannot be performed to further summarize people flow discipline.

In order to solve the above problems and improve the safety of points and places, the embodiments of the present disclosure provide field monitoring methods and devices, electronic devices, storage media, and programs.

In order to facilitate understanding of the embodiments of the present disclosure, first, the site monitoring method disclosed in the embodiments of the present disclosure will be described in detail. The execution body of the site monitoring method provided by the embodiments of the present disclosure is generally a computing device with a certain computing power, which includes, for example, a terminal device, a server or other processing device, and a terminal device User equipment (abbreviated as UE), mobile device, user terminal, terminal, cellular telephone, cordless telephone, personal digital assistant (abbreviated as PDA), portable device, computing device, vehicle-mounted device , a wearable device, or the like. In some embodiments of the present disclosure, the site monitoring method may be implemented by a processor invoking computer readable instructions stored in memory.

FIG. 1 is a schematic flowchart of a site monitoring method provided by an embodiment of the present disclosure, which method includes S101-S104 as follows.

At S101, surveillance videos collected by surveillance equipment installed at at least one surveillance point are obtained.

At S102, it is determined whether a surveillance event has occurred in a surveillance area corresponding to at least one surveillance point based on the surveillance video.

In S103, when a monitoring event occurs in a monitoring area corresponding to at least one monitoring point, the number monitoring data matching the monitoring event within a preset time period is acquired.

At S104, determine people flow status data of at least one monitoring device based on the people monitoring data.

In the above method, by acquiring the surveillance video collected by the surveillance equipment, if it is detected that a surveillance event has occurred in the surveillance area corresponding to at least one surveillance point based on the gathered surveillance video, the preset obtaining people monitoring data matching the monitoring event within the determined time period; determining people flow status data of at least one monitoring device based on the people monitoring data; determining the status of the monitoring event based on the determined people flow status data; For example, the crowd flow status data can be the total number of incoming traffic, and when the total number of incoming traffic is large, it is characterized by the frequent occurrence of surveillance events.

FIG. 2 is a schematic diagram of a system architecture to which the field monitoring method of the embodiment of the present disclosure can be applied. As shown in FIG. 2, the system architecture includes a surveillance video acquisition terminal 201 , a network 202 and a field monitoring terminal 203 . To provide support for one exemplary application, the surveillance video acquisition terminal 201 and the scene monitoring terminal 203 establish a communication connection via the network 202, and the surveillance video acquisition terminal 201 communicates with the scene monitoring terminal 201 via the network 202. reporting the surveillance video to the terminal 203, the field surveillance terminal 203 responding to the surveillance video, and based on the surveillance video, determining whether a surveillance event occurred in the surveillance area corresponding to the at least one surveillance point; When a monitoring event occurs in a monitoring area corresponding to one monitoring point, people monitoring data matching the monitoring event within a preset time period is obtained, and based on the people monitoring data, at least one monitoring device is operated. Determine crowd flow data. Finally, the site monitoring terminal 203 uploads the monitoring video crowd flow data to the network 202 and transmits it to the monitoring video acquisition terminal 201 via the network 202 .

By way of example, surveillance video acquisition terminal 201 may include a video gathering device, and site monitoring terminal 203 may include a visual processing device or remote server having visual information processing capabilities. Network 202 may employ wired or wireless connectivity schemes. If the field monitoring terminal 203 is a visual processing device, the monitoring video acquisition terminal 201 can be connected to the visual processing device via a wired connection. is a remote server, the surveillance video acquisition terminal 201 can perform data interaction with the remote server through a wireless network.

Alternatively, in some sites, the surveillance video acquisition terminal 201 may be a vision processing device with a video acquisition module, specifically implemented as a host with a camera. In this case, the site monitoring method of the embodiments of the present disclosure may be performed by the surveillance video acquisition terminal 201 and the above system architecture may not include the network 202 and the site monitoring terminal 203 .

S101 to S104 will be described below.

About S101,
In some embodiments of the present disclosure, the method can detect a target monitoring region, and the target monitoring region can be any region in a real scene, for example, the target monitoring region is , department stores, beaches, parks and subway stations.

Illustratively, a plurality of monitoring points are installed in the target monitoring area, and one monitoring device is attached to each monitoring point so that the monitoring device can monitor the corresponding monitoring area and realize monitoring of the target monitoring area. can be done. The installation of monitoring points can be determined according to actual requirements. For example, if the target monitoring area is a department store, each door of the department store should have a monitoring point, and each elevator door should have a monitoring point. One monitoring point can be installed in at least one location, and the like.

In some embodiments of the present disclosure, the surveillance equipment may be a device such as a surveillance camera. By installing one monitoring device at each monitoring point and collecting the monitoring video in the corresponding monitoring area by the monitoring device, the monitoring video collected by each monitoring device can be obtained, that is, at least one Surveillance videos collected by surveillance equipment installed at surveillance points can be obtained.

Regarding S102,
Here, for the monitoring video collected by each monitoring device, it is possible to determine whether a monitoring event has occurred in the monitoring area corresponding to the monitoring point based on the monitoring video; It can be determined whether a surveillance event has occurred in a surveillance area corresponding to each surveillance point of the points. The monitoring event may include at least one of an overcrowding event and a line-crossing event, and the overcrowding event means that the density of people in the area is greater than a predetermined value, that is, the density of people in the area is high, Line-crossing means that there is a pedestrian crossing a predetermined reference line in the area.

To explain the line-crossing event and the overcrowded event in terms of a specific site, for example, for the line-crossing event, on the platform in the subway station, a reference line is placed at a predetermined distance (for example, 1 meter) from the subway. can be set to monitor whether there is a person crossing the reference line (that is, whether there is a person crossing the reference line to get on or off the subway), and if so, a crossing event occurs bottom. For example, for an overcrowding event, a target monitoring area can be set at a beach, and when the number of people in the target monitoring area is greater than a predetermined number of people, it is determined that the overcrowding event has occurred.

In some embodiments of the present disclosure, a function button can be set for each surveillance video, and the trigger of the function button can determine the execution of surveillance event surveillance for the surveillance area of the surveillance point. For example, if a first function button corresponding to a line-crossing event (monitoring a single surveillance video for a line-crossing event) is set, and the first function button corresponding to surveillance video A is triggered, then the surveillance You may decide to monitor for line crossing events for video A, or you may press the second function button corresponding to line crossing events (monitor video group for line crossing events). so that when a second function button corresponding to a surveillance video group A consisting of surveillance video A, surveillance video B, etc. is triggered, the surveillance video group A is determined to monitor for line crossing events. may

In some embodiments of the present disclosure, a third function button corresponding to the congestion event is configured (congestion event monitoring for a single surveillance video), and the third function button corresponding to surveillance video A is set to When triggered, it may be determined to monitor congestion events for Surveillance Video A, or the fourth function button corresponding to Congestion Events (Monitor Congestion Events for Surveillance Video Group ) so that when the fourth function button corresponding to a surveillance video group A consisting of Surveillance Video A, Surveillance Video B, etc. is triggered, the Surveillance Video Group A is determined to monitor congestion events. can be

In some embodiments of the present disclosure, prior to determining whether a surveillance event has occurred in a surveillance area corresponding to at least one surveillance point based on the surveillance video, rendering surveillance signs corresponding to the surveillance video. can do. For a line-crossing event, the surveillance markers may be pre-drawn entry/exit boundaries, entry directions, and exit directions. For congestion events, the watchdog may be any pre-drawn polygon, or for congestion events, no corresponding watchdog may be set. The surveillance signs corresponding to different surveillance videos are different, that is, the surveillance signs corresponding to the surveillance videos (at least one of the surveillance signs corresponding to the line crossing event and the surveillance sign corresponding to the overcrowding event) are drawn for each surveillance video. can do.

In some embodiments of the present disclosure, for each surveillance video, a one-frame video screen screenshot can be collected from the surveillance video, and the video screen screenshot can be displayed so that the user can see the actual request. Depending on the video screen screenshot can be drawn surveillance signs. Further, by taking a video screen screenshot with a pre-rendered surveillance sign, it is also possible to determine location information in the video screen screenshot of the surveillance sign in the video screen screenshot, wherein the location information is displayed on the video screen screenshot. It may be a set of coordinates of surveillance signs in a pixel coordinate system corresponding to the shot, or, for example, positional information of entry/exit boundaries. In addition, target location information matching surveillance signs in the video screen of the surveillance video can be determined. If the mounting information such as the position, orientation, etc. of the surveillance equipment does not change, the position information of the surveillance sign in the video screen screenshot may be the target position information of the surveillance sign in the video screen of the surveillance video. Further, based on the surveillance video collected by the surveillance equipment and the determined target location information, it can be determined whether a surveillance event has occurred in the surveillance area corresponding to the surveillance point.

In some embodiments of the present disclosure, if the surveillance signs include surveillance signs corresponding to a line crossing event, referring to the schematic diagram of an interface displaying a video screen screenshot depicting surveillance signs shown in FIG. 3A, This FIG. 3A includes a pre-drawn surveillance sign 31, which includes a drawn entry/exit boundary and an arrow sign indicating the entry/exit direction. When drawing the surveillance sign, it is also possible to set at least one of the threshold for entering the flow of people (i.e. the first threshold of people flow) and the threshold for the threshold of exiting the flow of people (i.e. the second threshold of people flow) in the displayed interface, which monitors the surveillance video based on at least one of predetermined thresholds of incoming and outgoing traffic. This FIG. 3A also includes guide information for setting the line-crossing event above the video screen screenshot, so that the user can draw a surveillance sign according to the guide information for setting the line-crossing event displayed. can. When drawing a watchdog, it is also possible to trigger a "redraw" button to delete the drawn watchdog and redraw a new watchdog.

In some embodiments of the present disclosure, if the surveillance signs include surveillance signs corresponding to congestion events, refer to the schematic diagram of the interface of another video screen screenshot depicting the surveillance signs shown in FIG. FIG. 3B includes a pre-drawn surveillance marker 32, the surveillance marker including polygons indicating detection areas, which may be multiple in number. When drawing monitoring signs, the number of people by level of early warning is displayed on the interface, that is, the number of early warnings corresponding to general risks, the number of early warnings corresponding to major risks, and the early warnings corresponding to serious risks. By setting the number of people, you can also monitor the surveillance video based on the number of people for each level of early warning you have set. This FIG. 3B also includes hint information for setting the overcrowding event above the video screen screenshot, so that the user can follow the displayed guide information for setting the line crossing event to set the surveillance sign indicating the detection area. can be drawn. When drawing a watchdog, a "redraw" button can also be triggered to delete the drawn watchdog and redraw a new watchdog. After drawing the surveillance signs corresponding to the surveillance video, the drawn surveillance signs can be stored in the multiplexing area, so that the next time the surveillance signs are determined, the function buttons in the multiplexing area can be directly pressed. It can be triggered and reuse of surveillance signs can be realized.

The human body mark function button in FIG. 3B is used to display the setting information of the human body mark. The size of the area of the human body on the monitoring video screen is related to the height and angle of the monitoring equipment, and even for the same human body, the size of the area on the monitoring video screen varies depending on the distance from the monitoring equipment, That is, when the distance to the monitoring equipment is short, the area of the human body is large, and considering this fact, the human body mark is the basic setting for the line-crossing event and the overcrowded event.

In some embodiments of the present disclosure, in the video screen screenshots shown in FIGS. 3A and 3B, multiple pedestrian body frames are marked at different depth positions, and the area and position of each pedestrian body frame are depth information can be estimated, so that an algorithm (e.g., an image recognition algorithm for recognizing a human body) can use the results of the human body mark to perform human body recognition for different monitoring devices in different cases. to improve the recognition accuracy, where the more human body frames, the higher the accuracy, and in some embodiments of the present disclosure, the number of marked pedestrian frames is set according to needs. For example, the number of marked pedestrian frames can range from 3 to 10. Furthermore, by using the area of the body frame of multiple pedestrians and the depth information of each pedestrian's position, it is possible to detect the real-time number of people included in the detection area of the video screen per second of the surveillance video. .

In the overcrowding event, after drawing the detection area (surveillance sign), based on the human body sample marked with the human body mark, the predicted area of the drawing area in the real scene is calculated, and the predicted area is the "Region Area Prediction", and can also calculate the population density within the detection area in subsequent point congestion alarms, video group congestion alarms, etc. Also included in this FIG. 3B is a "Correct Area" function button, after which the "Correct Area" function button is triggered, the predicted area displayed in "Region Area Prediction" can be corrected.

In some embodiments of the present disclosure, if the surveillance markings on the video screen include both surveillance markings corresponding to congestion events and monitoring markings corresponding to line crossing events, please refer to FIG. Figure 3C is a schematic diagram of an interface for early warning information corresponding to people flow data in the example, including early warning levels and numbers corresponding to each of the overcrowding event and the line crossing event; That is, for congestion events, the number of early warnings corresponding to general risks, the number of early warnings corresponding to large risks and the number of early warnings corresponding to severe risks, and the number of early warnings corresponding to the increase in the number of people present for crossing events. It includes the number of people, the number of people with early warning corresponding to the number of people present, and the number of people with early warning corresponding to overcrowding, so that the surveillance video can be monitored based on the number of people at each level of early warning set. can. Also included in this FIG. 3C are two buttons for validity periods, namely "Long Term Valid" and "User Defined", which initiate congestion and line crossing events on the video screen, allowing the user to set the relevant monitoring parameters. and time information can be flexibly set.

In some embodiments of the present disclosure, if the surveillance event is a line crossing event, then based on the surveillance video, determining whether the surveillance event occurred in the surveillance area corresponding to the at least one surveillance point includes: determining, based on the surveillance video, whether there is a target object within the surveillance area corresponding to the at least one surveillance point that straddles the target location matching the pre-drawn entry/exit boundary; If so, determining that a line crossing event has occurred in a surveillance area corresponding to the at least one surveillance point.

In some embodiments of the present disclosure, if the surveillance event is a line-crossing event, for the surveillance video collected at each surveillance point, an entry/exit boundary line is added to the surveillance area corresponding to the surveillance point based on the surveillance video. For example, in a surveillance video, it can detect whether there is a pedestrian straddling a drawn entry/exit boundary, and the existence If so, it is determined that a line-crossing event has occurred in the monitoring area corresponding to the monitoring point, and if not, it is determined that a line-crossing event has not occurred in the monitoring area corresponding to the monitoring point.

The monitoring area corresponding to the monitoring point may be a detection area that can be monitored by the monitoring equipment installed at the monitoring point, and the monitoring area corresponding to the monitoring point is related to the mounting position and mounting angle of the monitoring equipment. , different mounting positions and mounting angles correspond to different monitoring areas.

In some embodiments of the present disclosure, at least one It is determined that a line-crossing event has occurred in a monitoring area corresponding to one monitoring point, thereby realizing real-time monitoring of the line-crossing event and increasing the accuracy of monitoring the line-crossing event.

In some embodiments of the present disclosure, if the surveillance event is a congestion event, determining based on the surveillance video whether the surveillance event has occurred in the surveillance area corresponding to the at least one surveillance point is the surveillance event. determining, based on the video, whether a target number of objects within a surveillance area corresponding to at least one surveillance point exceeds an overcrowding threshold; determining that a congestion event has occurred in the corresponding monitored area.

In some embodiments of the present disclosure, if the surveillance event is a congestion event, for the surveillance video collected at each surveillance point, based on the surveillance video, the number of target objects in the surveillance area corresponding to the surveillance point is: determining whether the overcrowding threshold is exceeded, for example, determining the number of people in the surveillance area in the surveillance video, determining whether the number of people is greater than the preset overcrowding threshold; If so, it is determined that a congestion event has occurred in the monitoring area corresponding to the monitoring point; otherwise, it is determined that no congestion event has occurred in the monitoring area corresponding to the monitoring point. If the surveillance event is an overcrowding event, the surveillance area corresponding to the surveillance point may be the detection area matching the drawn polygon, and if no surveillance sign is drawn, the surveillance area corresponding to the surveillance point is It is the detection area that can be monitored by the monitoring equipment installed at the monitoring point (that is, the area corresponding to the monitoring interface of the monitoring video is all the monitoring area).

In the above method, when it is determined based on the surveillance video that the target number of objects in the surveillance area corresponding to the at least one surveillance point exceeds the congestion threshold, an overcrowding event occurs in the surveillance area corresponding to the at least one surveillance point. This makes it possible to implement real-time monitoring of congestion events and increase the accuracy of congestion event monitoring.

Regarding S103 and S104,
In some embodiments of the present disclosure, when it is determined that a monitoring event has occurred in a monitoring area corresponding to at least one monitoring point, obtaining people monitoring data matching the monitoring event within a preset time period. and the people monitoring data includes at least one of people monitoring data corresponding to a line crossing event and people monitoring data corresponding to an overcrowded event. Further, the people flow state data of at least one monitoring device is determined based on the people monitoring data matching the monitoring event within the preset time period, and the people flow state data and the people flow state data corresponding to the line crossing event are congested. At least one of crowd flow status data corresponding to the event is included. The preset time period can be set as needed, for example, the preset time period may be a time period from the time when it is determined that the monitoring event occurred to one hour later, If the time at which the monitoring event is determined to have occurred is 13:10:00, the preset time period is from 13:10:00 to 14:10:00. As another example, the preset time period may be a time period from the time when it is determined that the monitoring event has occurred until one minute later, and the time when it is determined that the monitoring event has occurred is 13:10. If it is 00 seconds, the preset time period is from 13:10:00 to 13:11:00.

For the line-crossing event, obtaining people-monitoring data matching the line-crossing event within a preset time period; and obtaining at least one people-monitoring data matching the line-crossing event within the preset time period. People flow status data for monitoring equipment consistent with a line crossing event can be determined.

For the overcrowding event, obtaining people monitoring data matching the overcrowding event within a preset time period, and operating at least one monitoring device based on the people monitoring data matching the overcrowding event within the preset time period. , people flow status data that matches the congestion event can be determined.

Some embodiments of the present disclosure further include, after determining the people flow status data of the at least one monitoring device, generating people flow status alert information if the people flow status data satisfies an alert condition.

Here, it is determined whether the crowd flow status data of at least one monitoring device satisfies the alarm condition, and if it satisfies, the crowd flow status alarm information is generated, so that the user can make a guidance plan based on the crowd flow status alarm information. can be generated, thus reducing the probability of accidents such as crowds and traffic jams in the target monitoring area.

Here, if the determined people flow state data satisfies the alarm conditions, the people flow state warning information is generated, and based on the generated people flow state warning information, the target monitoring area is controlled, the safety incident rate is reduced, and the target monitoring area is reduced. It is possible to improve the safety of the flow of people in the surveillance area.

In the following, the line crossing event warning process and the congestion event warning process will be described in detail respectively.

First, the warning process for a line-crossing event will be described.

If the monitoring event is a line-crossing event, obtaining the people monitoring data matching the monitoring event within the preset time period means the number of people flowing in and the number of people leaving at different collection points within the preset time period. It is to acquire the number of people flow, and the number of people flow is the number of people who cross the pre-drawn entrance/exit boundary line along the pre-drawn entry direction at different collection points, and the number of people flow is different. At the time of collection, the number of people crossing the pre-drawn entry/exit boundary line along the pre-drawn exit direction.

Here, the monitoring sign corresponding to the line-crossing event includes a preset entry/exit boundary line and an entry/exit direction (at least one of an entry direction and an exit direction, and the exit direction is the opposite direction of the entry direction). , the monitoring area corresponding to the surveillance video may be divided into an entrance area and an exit area by the entrance/exit boundary line, and the entrance direction of the entrance/exit directions may be the direction from the entrance area to the entrance area. Of the directions, the exit direction may be the direction from the entrance area to the exit area.

Further, based on the set entry/exit boundary line, entry/exit direction and surveillance video, determine the number of inflows (that is, the number of inflows) and the number of outflows at each collection point within the preset time period in the surveillance video. The number of inflows at different collection points is the number of people crossing the entrance/exit boundary along the direction of entry at different points of collection, and the number of outflows at different points of collection is , is the number of people crossing the entrance/exit boundary along the exit direction.

In some embodiments of the present disclosure, a trained target tracking algorithm is utilized to detect surveillance video based on set surveillance signs, and within a preset time period, at preset time intervals. The detection result can be output once in a preset time period, and the multiple detection results within the preset time period may be the number of inflows and the number of outflows at different collection points within the preset time period. , each detection result is associated with an output time (the output time is the time of collection), and furthermore, the number of inflows and the number of outflows at different collection times within a preset time period can be obtained.

In the above method, if the monitoring event is a line-crossing event, it is possible to obtain the number of incoming people and the number of outgoing people at different collection times within a preset time period, and then obtain the number of people-flowing people corresponding to the line-crossing event. Data support can be provided for determining state data.

In some embodiments of the present disclosure, when there is one monitoring point, determining the people flow status data of at least one monitoring device based on the people monitoring data is based on the number of people entering and leaving the monitoring point. determining the total number of inflows and the total number of outflows within a preset time period in the monitoring area corresponding to .

If the crowd flow status data satisfies the alarm condition, generating crowd status warning information means that the total number of incoming crowds is greater than a predetermined first crowd flow threshold, and the total number of outgoing crowds is greater than a predetermined second crowd flow threshold. and the total number of incoming people is greater than a first predetermined threshold of people flow, or the total number of outgoing people is greater than a second predetermined threshold of people flow, people flow status alarm. generating information.

After acquiring the monitoring data of the number of people matching the monitoring event (line-crossing event) within the preset time zone, that is, the number of people entering the line-crossing event at different collection points within the preset time zone and After obtaining the number of outflows, based on the number of inflows at different collection points in the preset time period and the number of outflows, the flow of inflows within the preset time period in the monitoring area corresponding to the monitoring point is determined. A total number and a total number of outflows can be determined.

Continuing with the above example, the trained target tracking algorithm may output a detection result once every 3 seconds (determines one collection time point every 3 seconds), and the detection result is: The number of inflows and the number of outflows of people within these three seconds may also be used. The number of inflows of people is 20, the number of outflows is 50, and the associated output time (collection time) may be 08:10:03. A plurality of detection results can be obtained, that is, the number of inflows and the number of outflows at different collection times within a preset time period can be obtained.

After obtaining the number of inflows and outflows at different collection times within the preset time period, add the number of inflows at different collection times to obtain the number of inflows within the preset time period. The total number of people can be obtained, and the number of people flowing at different collection times can be added to obtain the total number of people flowing within a preset time period.

Here, the first crowd flow threshold and the second crowd flow threshold are preset, and the first crowd flow threshold and the second crowd flow threshold can be set according to actual requirements. After obtaining the total number of inflows and the total number of outflows in the preset time period, determine whether the total number of inflows in the preset time period is greater than a first predetermined threshold for the flow of people. and/or determine whether the total number of outflows within the preset time period is greater than a predetermined second flow threshold.
The total number of incoming people in the preset time period is greater than a predetermined first people flow threshold, and the total number of outgoing people in the preset time period is greater than a second predetermined people flow threshold. When determining whether or not the total number of inflows of people within the preset time period is greater than a predetermined first threshold for the flow of people, and/or the total number of outflows of people within the preset time period is If it is greater than a predetermined second crowd flow threshold, generate crowd flow status warning information. The generated people flow state warning information may be information in the form of text, voice, video, etc. good. In this case, the type of alarm event in the people flow condition alarm information is the line crossing alarm at the point.

In some embodiments of the present disclosure, after the generated people flow condition alarm information is triggered, the detailed information of the people flow condition alarm may be displayed, and the detailed information may indicate the alarm point (i.e., the alarm point). name of the monitoring equipment emitting), alarm time, type of alarm event, but not limited to these, if the type of alarm event is a line crossing alarm at a point, the detailed information will include the number of incoming people in the unit time It further includes number, turnout, etc.

Here, if there is one monitoring point, based on the number of inflows and outflows at different collection points within the preset time period, determine the total number of inflows and the total number of outflows. When the total number of incoming people in a preset time period is greater than a first predetermined threshold of people flow and/or the total number of outgoing people in a preset time period is greater than a second predetermined threshold of people flow In this case, the people flow status warning information is generated, so that early warning of the number of incoming people and the number of outgoing people in the surveillance video can be realized, so that the people flow can be controlled based on the generated people flow status warning information. Reduce the occurrence rate of safety accidents caused by a large number of people entering or exiting in a short time.

In some embodiments of the present disclosure, when there is one monitoring point, determining the people flow status data of at least one monitoring device based on the people monitoring data is based on the number of people entering and leaving the monitoring point. determining the velocity of incoming and outgoing people flow in the monitored area corresponding to .

In some embodiments of the present disclosure, the speed of inflow and outflow of people in the monitoring area corresponding to the monitoring point is based on the number of inflows and outflows at different collection times within a preset time period. can also be determined.

In some embodiments of the present disclosure, after obtaining the number of inflows and outflows at different collection times within a preset time period, the multiple detection results are classified according to the output time (collection time). to obtain the number of inflows and the number of outflows within a unit time (for example, within one minute), thereby obtaining the velocity of inflows and outflows.

For example, classify and organize the output results for the output time from 08:10:00 to 08:11:00 (excluding 08:10:00 but including 08:11:00), , 08:10:03, 08:10:06, ..., 08:10:57, and 08:11:00 are classified into category 1. By arranging the detection results of 08:10:00 to 08:11:00, it is possible to obtain the number of inflows and outflows within one minute (within the unit time). We obtained the inflow velocity (unit: person/min) and the outflow velocity (unit: person/min) corresponding to .

In the above method, the speed of the inflow of people and the speed of the outflow of people in the monitoring area corresponding to the monitoring point can be determined based on the number of inflows and the number of outflows at different collection points in a preset time period. Therefore, it is possible to monitor the velocity of incoming and outgoing people, and reduce the safety accident rate caused by high velocity of incoming or outgoing people.

Please refer to the schematic diagram of the interface that displays the detailed information of the crowd flow status warning shown in FIG. 4. This FIG. Current line-crossing event time zone statistics, including event type, alarm time, duration (duration of line-crossing event), peak inflow, peak outflow, etc. to the current point in the statistic, including line crossing event alerts. This figure also includes a video screen screenshot, in which the outflow information (the number of outflows and the speed of the outflow) and the inflow information (the number of inflows and the speed of the inflow) corresponding to the current time. speed) is displayed, and multiple frames of alarm images are displayed below the video screen screenshot, and the number of alarm images is related to the duration of the alarm, e.g., the duration of a line crossing event is 17 minutes. In this case, one frame of alarm image may be extracted as alarm record every minute, that is, 17 frames of alarm image may be displayed below the video screen screenshot.

In some embodiments of the present disclosure, point information such as the name of surveillance equipment, installation location, and collected surveillance video, and the number of people flowing in and out per unit time, the number of people flowing in, etc. for subsequent search queries. Information may be permanently stored on a search server (eg, elasticsearch).

In some embodiments of the present disclosure, for multiple monitoring points, determining people flow status data for at least one monitoring device based on people monitoring data includes:
A step 1 of determining the total number of incoming and outgoing people in a monitoring area corresponding to each monitoring point for each monitoring point based on the number of incoming and outgoing people within a preset time period. When,
Within the target monitoring area based on the historical number of people in the target monitoring area within a preset time period and the total number of people entering and exiting within the preset time period corresponding to each monitoring point and step 2 of determining the current number of people in the .

Generating people flow status alert information if the people flow status data satisfies the alert condition includes generating people flow status alert information if the presence population is greater than a predetermined current presence threshold.

Here, considering that a plurality of monitoring devices can be installed in one site or place, people flow analysis is performed on the surveillance videos collected by each of the plurality of monitoring devices, and people flow state data from the plurality of monitoring videos is obtained. can be obtained. Surveillance videos collected by each of a plurality of surveillance devices form a video group, that is, people flow analysis can be performed on a video group to obtain people flow status data corresponding to the video group. In some embodiments of the present disclosure, triggering an enable line-cross event button corresponding to the video group configured in the display interface turns on the line-cross analysis feature for each surveillance video in the video group. be able to. In addition, it is also possible to set the specific information of the early warning by level of the total number of people present in the display interface. A level 2 early warning headcount and a level 3 early warning headcount corresponding to overcrowding can be entered.

In some embodiments of the present disclosure, for each monitoring point, after obtaining the number of inflows and outflows at different collection time points within a preset time period corresponding to the monitoring point, can be added to obtain the total number of inflows within a preset time period corresponding to the monitoring point, and the number of outflows at different collection points can be added to obtain the It is possible to obtain the total number of outflows within a preset time period corresponding to the monitoring point. In some embodiments of the present disclosure, the total number of inflows and the total number of outflows within a preset time period corresponding to each of the monitoring points can be obtained.

In some embodiments of the present disclosure, it is possible to obtain the total number of inflows and the total number of outflows from 08:11:00 to 08:12:00 corresponding to each monitoring device. The time period from 08:11:00 to 08:12:00 is a preset time period.

In some embodiments of the present disclosure, the historical number of people in the target monitoring area within a preset time period, and the total number of incoming and outgoing flows within a preset time period respectively corresponding to each of the monitoring points Based on the total number of numbers, determine the number of people currently present in the target surveillance area. For example, for each surveillance video in the video group, subtract the total number of outflows from the total number of inflows in a preset time slot corresponding to each of the surveillance videos, and The amount of change in people flow in the surveillance videos is obtained, the amount of change in people flow within a preset time period corresponding to each surveillance video is added, and the total change in people flow corresponding to the video group (that is, the site corresponding to the video group and place), then add the total change in people flow corresponding to the video group and the historical number of people in the target monitoring area within the preset time period to obtain the total number of people in the target monitoring area Obtaining the current population (ie, obtaining the current current population corresponding to the site or location corresponding to the video group).

In some embodiments of the present disclosure, the preset time period may be the time period from 08:11:00 to 08:12:00; It can obtain the current number of people corresponding to the time of the second (that is, the historical number of people in the target surveillance area within the preset time period), and from 08:11:00 corresponding to each surveillance video in the video group It is possible to obtain the total number of inflows of people and the total number of outflows until 08:12:00 (preset time period), and furthermore, the historical number of people ( That is, the number of people present at 08:11:00 obtained), and the total number of people flowing in from 08:11:00 to 08:12:00 corresponding to each surveillance video in the video group Based on the total number of people flowing out, the number of people present in the target monitoring area at 08:12:00 is determined.

After obtaining the number of people present in the target monitoring area, monitoring the number of people present in the target monitoring area, and when the number of people present in the target monitoring area is monitored as being greater than the preset threshold number of people present, Generate people flow status warning information. For example, the generated people flow status warning information may be "please note that there are currently many people in site xx". In this case, the type of alarm event in the crowd condition alarm information is the line crossing alarm of the video group.

In some embodiments of the present disclosure, multiple levels of warning risks can be set for video group crossing warnings, for example, multiple levels of warning risks include population increase, population warning, overpopulation set different thresholds for the number of people present for different warning risks, for example, the number threshold for the number of people present is set to 100, the number threshold for the number of people present is 200, and the number threshold for the number of people present is 200; The corresponding current population threshold may be set to 500. Different people flow status warning information can be set for different warning risks. For example, the people flow state warning information corresponding to an increase in the number of people present is made into text format warning information, the people flow state warning information corresponding to the number of people present warning is made into voice format warning information, and the people flow state warning information corresponding to an excessive number of people is made into a video format. It is also possible to use a form of alarm information.

In some embodiments of the present disclosure, after the generated people flow condition alarm information is triggered, the detailed information of the people flow condition alarm may be displayed, and the detailed information may indicate the alarm point (i.e., the alarm point). name of monitoring equipment emitting), alarm time, type of alarm event, and if the type of alarm event is a video group crossover alarm, the detailed information may also include the current number of people present. may contain.

Here, after determining the total number of inflows of people and the total number of outflows within a preset time period in the monitoring area corresponding to each monitoring point, , and the total number of inflows and outflows within a preset time period corresponding to each of the plurality of monitoring points, determine the current number of people in the target monitoring area, and If the current population is greater than the set current population threshold, the crowd flow status warning information can be generated, so that early warning of the current population in the target monitoring area can be realized. Therefore, when there are many people present, the people are guided based on the generated people flow state warning information, and the occurrence rate of safety accidents caused by many people in the target monitoring area is reduced.

Please refer to FIGS. 5A and 5B, FIG. 5A is a schematic diagram of an interface for displaying detailed information of people flow state warning, and in FIG. 5A, displaying detailed information of people flow state warning in the form of a map. FIG. 5B is a schematic diagram of another interface for displaying detailed information of people flow state alerts, in FIG. Includes events and line crossing events. In some embodiments of the present disclosure, after the line crossing event information displayed in FIG. 5A is triggered, or after the line crossing event information displayed in FIG. 5B is triggered, the display in FIG. 5C The alarm details displayed in FIG. 5C include the group name (i.e., the name corresponding to the video group), the type of event, the alarm time, the duration, and the total number of people present in the crowd. including the peak value of , and the statistics of the total number of people present in the day's flow.

Next, the congestion event alert process will be described in detail.

In some embodiments of the present disclosure, if the surveillance event is an overcrowding event, obtaining people monitoring data matching the surveillance event within the preset time period may be performed at different people within the preset time period. Statistically counting the number of target subjects at the time of collection.

Here, if there is a surveillance sign corresponding to the congestion event in the surveillance video, the target object (person) in the detection area corresponding to the surveillance sign is detected based on the surveillance sign corresponding to the congestion event and the surveillance video, and each The number of target objects in the detection area at the time of collection can be obtained. If there is no surveillance sign corresponding to the overcrowding event in the surveillance video, the entire surveillance screen of the surveillance video is regarded as the detection area, the surveillance video is detected, and the number of target objects in the detection area at each collection time is calculated. Obtainable.

In some embodiments of the present disclosure, a trained deep learning algorithm for target object recognition may be used to detect the detection area in the surveillance video and output the detection result in real time; The detection result may be the number of people in the detection area at each collection point in the surveillance video. The deep learning algorithm may output the detection result periodically, for example, the deep learning algorithm may output the detection result once every second, or may output the detection result every two seconds. For example, the result may be output once. For example, the detection result shows that the number of people in the detection area is 50 at 08:10:00 (at the time of collection), and the number of people in the detection area is 54 at 08:10:01. good too.

In some embodiments of the present disclosure, the number of target objects at different collection time points within a preset time period can be statisticated, for example, the preset time period is from 08:10:00 It is a time period until 08:11:00, and each second within the preset time period is set as one collection time point, that is, the number of target objects at 08:10:00 (collection time 1), The number of target objects at 08:10:01 (collection time 2), .

In the above method, if the monitoring event is an overcrowding event, the number of target objects at different collection time points within a preset time period can be statistically obtained, thereby subsequently obtaining crowd flow status data corresponding to the overcrowding event. Data support can be provided for determining

In some embodiments of the present disclosure, when there is one monitoring point, determining people flow status data of at least one monitoring device based on people monitoring data corresponds to the monitoring point based on the number of target objects. Determining the average number of people within a preset time period of the monitored area.

If the crowd flow condition data satisfies the alarm condition, generating crowd flow condition warning information includes generating crowd flow condition warning information if the average number of people is greater than a set first crowd threshold.

In some embodiments of the present disclosure, the number of target subjects at different collection times within a preset time period is averaged, and the average number of people within the preset time period of the monitoring area corresponding to the monitoring point is Obtainable. Then, the average number of people within the preset time period is monitored, and when the average number of people is greater than a first threshold number of people, crowd flow status warning information is generated. The length of the preset time period can be set according to requirements, for example, the length of the preset time period may be 5 seconds, 10 seconds, 60 seconds, 5 minutes, etc. . The preset time period corresponding to the line-crossing event and the preset time period corresponding to the overcrowding event may be the same or different in length.

In some embodiments of the present disclosure, the number of target objects at different collection time points within a preset time period, for example, the number of target objects at 08:10:01 is 50, and the number of target objects at 08:00 The number of target objects at 10:02 is 53, the number of target objects at 08:10:03 is 52, the number of target objects at 08:10:04 is 51, and the number of target objects is 08 One such target target count at 08:10:05 is 54, in which case the five detections are averaged to get an average value of 52, and By 10:05, it can be determined that the average number of people in the surveillance area corresponding to the surveillance point is 52.

In some embodiments of the present disclosure, monitoring the average number of people within a preset time period of the monitoring area corresponding to the monitoring point, and if the average number of people is greater than a first threshold of people, the state of people flow You may make it generate|occur|produce warning information. For example, the generated people flow state warning information may be "please note that there are many people in the xx area at this time". In this case, the type of alarm event of the crowd condition alarm information is overcrowding alarm at the point.

In some embodiments of the present disclosure, after the generated people flow condition alarm information is triggered, the detailed information of the people flow condition alarm may be displayed, and the detailed information may indicate the alarm point (i.e., the alarm point). name of the monitoring equipment emitting), alarm time, type of alarm event, and if the type of alarm event is overcrowding alarm at the point, detailed information will be available in real-time within the current detection area. It may further include the number of people.

Please refer to the schematic diagram of the interface for displaying the detailed information of the people flow status warning shown in FIG. Including event type, warning time, overcrowding duration, number of people peak value, density peak value, etc. Current overcrowding event hourly statistics, including overcrowding event warnings from the zero point of the day to the present time of statistics . Also included in this FIG. 6 is a video screen screenshot, and multiple frames of alarm images are displayed below the video screen screenshot, the number of alarm images being related to the duration of the congestion event, e.g. If the duration length is 17 minutes, one frame of alarm image may be extracted as the alarm record every minute, i.e. 17 frames of alarm image are displayed below the video screen screenshot. may

In some embodiments of the present disclosure, point information such as surveillance equipment name, mounting location, surveillance video collected, and real-time count of the surveillance equipment per minute, real-time for subsequent search queries. Information such as the maximum number of people in real time and the minimum number of people in real time may be associated and permanently stored in a search server (for example, elasticsearch).

In the above method, if there is one monitoring point, the average of the monitoring area corresponding to the monitoring point within the preset time period is based on the number of target objects at different collection times within the preset time period. determining the number of people, and if the average number of people in a preset time period of the monitoring area corresponding to the monitoring point is greater than a first threshold of people, generating people flow status warning information, thereby displaying the monitoring video; This makes it possible to monitor the average number of people in the detection area, thereby guiding the flow of people to the detection area based on the generated people flow status warning information, and preventing safety accidents due to the crowding of people in the detection area. reduce the incidence of

In some embodiments of the present disclosure, for multiple monitoring points, determining people flow status data for at least one monitoring device based on people monitoring data includes:
Step 1 of determining, for each monitoring point, the average number of people within a preset time period in the monitoring area corresponding to the monitoring point based on the number of target objects;
and determining the real-time total number of people in the target surveillance area based on the average number of people.

If the crowd flow status data satisfies the warning condition, generating crowd flow status warning information includes: generating crowd flow status warning information if the real-time total number of people is greater than a set second crowd threshold.

Here, for each monitoring point, based on the number of target objects at different collection points within the preset time period, the average number of people within the preset time period of the monitoring area corresponding to the monitoring point is determined. Furthermore, the average number of people corresponding to each of the plurality of monitoring points can be added to determine the real-time total number of people in the target monitoring area.

After determining the real-time total number of people in the target monitoring area, monitor the real-time total number of people, and if it is determined that the real-time total number of people in the target monitoring area is greater than the second set threshold of people, the people flow status warning information is generated. may be generated.

In some embodiments of the present disclosure, the crowd congestion analysis feature for each surveillance video in a video group may be turned on by triggering the start congestion event button corresponding to the video group configured in the display interface. can. In addition, it is possible to set the specific information of the real-time early warning of the total number of people on the display interface. The number of early warnings and the number of level 3 early warnings corresponding to critical risks can be entered. Here, when there are multiple monitoring devices, the monitoring videos collected by each of the multiple monitoring devices form a video group. For each surveillance video collected by each surveillance device (i.e., each surveillance video in a video group), a deep learning algorithm trained to recognize target objects is used to determine the detection area indicated by the surveillance signs in the surveillance video. It may be detected and the detection result may be output in real time, and the detection result may be the number of target objects in the detection area at the time of acquisition in the surveillance video. In some embodiments of the present disclosure, based on periodically obtained detection results, the average number of people within a preset time period in the monitoring area corresponding to the monitoring point can be determined.

After obtaining the average number of people corresponding to each surveillance video in the video group, the average number of people corresponding to each surveillance video included in the video group can be added to determine the real-time total number of people in the target surveillance area. Further, the real-time total number of people in the target monitoring area can be monitored, and when the real-time total number of people in the target monitoring area is greater than a set second threshold, crowd flow status warning information can be generated. For example, the generated people flow status warning information may be "please note that the total number of people at the xx site is large at this time". In this case, the type of alarm event in the crowd alert information is video group congestion alert.

In some embodiments of the present disclosure, multiple levels of alert risk can be set for video group congestion alerts, e.g., multiple levels of alert risk include level 1 risk, high risk, and critical risk. , set different second population thresholds for different warning risks, for example, the second population threshold corresponding to level 1 risk is 100, the second population threshold corresponding to level 2 risk is 200, and the second population threshold is 200 to correspond to serious risk. 500 may be set as the second number-of-persons threshold. Different people flow state warning information may be set for different warning risks. For example, the people flow state warning information corresponding to the level 1 risk is made into text format warning information, the people flow state warning information corresponding to the level 2 risk is made into voice format warning information, and the people flow state warning information corresponding to the level 3 risk is used. The information may be alarm information in video format.

In some embodiments of the present disclosure, after the generated people flow condition alarm information is triggered, the detailed information of the people flow condition alarm may be displayed, and the detailed information may indicate the alarm point (i.e., the alarm point). name of monitoring equipment emitting), alarm time, type of alarm event, and if the type of alarm event is video group overcrowding alarm, the detailed information may include real-time aggregates of the actual site. It may further include the number of people.

Please refer to FIGS. 7A and 5B, FIG. 7A is a schematic diagram of an interface for displaying detailed information of people flow state warning, and FIG. 7A displays detailed information of people flow state warning in the form of a map. FIG. 5B is a schematic diagram of another interface for displaying detailed information of people flow state alerts, in FIG. Includes events and line crossing events. In some embodiments of the present disclosure, after the congestion event information displayed in FIG. 7A is triggered or after the congestion event information displayed in FIG. 5B is triggered, the Alarm details can be displayed, and the alarm details displayed in FIG. 7B include group name (i.e., the name corresponding to the video group), event type, alarm time, duration, people peak value, density peak value. , real-time total headcount statistics for the day, and video source statistics.

Here, based on the surveillance video collected by at least one surveillance device and the surveillance signs that match the target positions in the pre-drawn video screen, after determining the people flow status data in the actual site, the people flow of the day It is also possible to generate a schematic diagram of changes over time in people flow state data so as to intuitively display the state data. In some embodiments of the present disclosure, the schematic diagram of the temporal change of the people flow state data is the first of the temporal change of the real-time total number of people, which includes the time-dependent change relationship of the peak value of the number of people and the time-dependent change relationship of the bottom value of the number of people. Schematic diagram of change and/or time-dependent change in total number of people inflow, including time-dependent change in total outflow, time-dependent change in total inflow, and time-dependent change in total number of people inflow Schematic diagram of change. The time interval between the first change chart and the second change chart can be set to 5 minutes, 10 minutes, 30 minutes, 1 hour, and the like.

Also, FIG. 8A shows a schematic diagram of an interface in which the real-time total number of people and the total number of people present in a people flow provided by an embodiment of the present disclosure change over time, and FIG. and a schematic diagram of an interface in which the total number of people present in the flow of people changes over time. Also, from FIG. 8A, it is possible to confirm the peak number of people and the bottom number of people of the overcrowded event. , the real-time minimum number of people in a certain time period, etc., can be implemented to monitor the surveillance video, so that the user can monitor the crowd flow status data in real-time.

FIG. 8B also shows a schematic diagram of an interface for predicting people flow data in future time periods provided by an embodiment of the present disclosure, FIG. The total inflow of people, the total amount of outflow of people, and the total number of people present in the flow of people per hour for the time zone up to 11:00 on the 16th of the month are shown, and the total amount of inflow of people, the total amount of outflow of people, and the total number of people in the flow of people for each hour are shown. Based on the total number of people present, construct the people flow state data in the future time zone, that is, the prediction area in FIG. can do.

In the above method, after determining the average number of people in the monitoring area corresponding to each monitoring point within a preset time period, the real-time total number of people in the target monitoring area is based on the average number of people corresponding to each of the plurality of monitoring points. and if it is determined that the real-time total number of people in the target monitoring area is greater than a predetermined second people threshold, the people flow status warning information can be generated, thereby increasing the real-time total number of people in the target monitoring area It is possible to realize early warning, so that when the real-time total number of people is large, the people in the target monitoring area are guided according to the generated people flow status warning information, and the real-time total number of people in the target monitoring area is guided. Reduce the incidence of safety accidents caused by too many things.

In some embodiments of the present disclosure, the method includes: averaging people flow status data at the same collection time point within a plurality of recent historical dates to obtain people flow forecast data corresponding to each collection time; Further comprising, based on the condition forecast data, constructing forecast data of the people flow condition data at a future date, the forecast data being used to generate a people flow guidance plan.

Here, multiple history cycles can be set according to requirements, for example, multiple history cycles can be human flow status data within the last seven days (one history cycle corresponds to one day), that is, At 00:00 on October 8th, the people flow state data from October 1st to October 7th (7 historical cycles) is acquired, and the people flow state data at the same collection point within the latest 7 historical dates is obtained. The people flow state prediction data corresponding to each collection time may be obtained by averaging, and the people flow state prediction data corresponding to each collection time constitutes the prediction data of the people flow state data at a future date.

For example, the people flow state data at the same collection time from October 1 to October 7 may be averaged to obtain an average value at each collection time, and the average value is the people flow corresponding to the collection time. The people flow state prediction data, which are state prediction data and correspond to each collection time, constitute prediction data of people flow state data at a future date. For example, generate prediction data for the total number of people flowing in at a future date (one day in the future), generate prediction data for the total number of people flowing out at a future date (one day in the future), Generate prediction data of the number of people present on a future date (one day in the future).

Furthermore, a people flow guidance plan can be generated based on forecast data of crowd flow state data on a future date. The number of people flowing into the target monitoring area at a time may be controlled.

In practical application sites, the method can be applied to sites such as department stores and halls. In the following, we will take a department store as an example to describe a single surveillance video line-crossing event and a video group line-crossing event, respectively. The monitoring devices can be installed, namely, monitoring device 1 (monitoring device 1 installed at monitoring point 1) collecting the monitoring video of door A, and monitoring device 2 (monitoring point 1) collecting the monitoring video of door B. 2) can be installed, and the monitoring device 1 and the monitoring device 2 can monitor pedestrians entering and exiting the door.

In some embodiments of the present disclosure, surveillance video 1 collected by surveillance device 1 and surveillance video 2 collected by surveillance device 2 may be obtained. For surveillance video 1, draw the entry/exit boundary line and entry/exit direction on the video screen screenshot of surveillance video 1, and the total number of inflows of people within a preset time period in the surveillance area corresponding to the surveillance point in surveillance video 1 and the total number of outflows is determined, and if the total number of inflows in the preset time period is greater than a predetermined first flow threshold, and if the total number of outflows in the preset time period is determined is greater than a predetermined second crowd flow threshold, and/or crowd flow status warning information is generated. Then, for surveillance video 2, the entry/exit boundaries and entry/exit directions are set in the video screen shot of surveillance video 2, and the number of people entering and exiting the surveillance area corresponding to the surveillance point in surveillance video 2 within a preset time zone is calculated. and the total number of outflows, and furthermore, if the total number of inflows in the preset time period is greater than a predetermined first flow threshold, and if the total number of outflows within the preset time period is greater than a predetermined second crowd flow threshold, and/or crowd flow state warning information is generated.

Surveillance video 1 and surveillance video 2 form a video group, and the video group may be analyzed to determine crowd flow state data in target surveillance areas corresponding to surveillance equipment 1 and surveillance equipment 2. . In some embodiments of the present disclosure, for surveillance video 1, determine the total number of inflows and the total number of outflows within a preset time period in the surveillance area corresponding to surveillance point 1; , the total number of inflows and the total number of outflows within a preset time zone in the monitoring area corresponding to the monitoring point 2 are determined. Furthermore, based on the historical number of people in the target monitoring area within a preset time period, and the total number of inflows and outflows within a preset time period corresponding to each of the plurality of monitoring points, the target Determine the number of people present in the monitored area. That is, the number of people present in the department store was determined. To generate people flow state warning information when the number of people present is greater than a predetermined current people threshold, thereby controlling pedestrians in the department store after receiving the people flow state warning information to reduce the occurrence rate of traffic accidents. can be done. You can also get a curve graph of the number of people present at each time of the day at the current location and the real-time total number of people, so that the discipline can be dynamically summarized to rationally control the number of department store staff. It is possible to adjust the operating hours, the number of staff in different time zones, and the like.

In the following, the congestion event of a single surveillance video and the congestion event of a video group are described respectively by taking a hall as an example. Assume that the four corners of the hall (four monitoring points) are respectively installed with monitoring equipment, i.e., the four monitoring equipment detect the four detection areas of the hall, and the monitoring video collected by each of the four monitoring equipment is form a video group.

In some embodiments of the present disclosure, for each surveillance video in a video group, preset surveillance areas corresponding to surveillance points are determined based on the number of target objects at different collection times within a preset time period. determining the average number of people in the time period, and generating people flow status warning information corresponding to the surveillance video if the average number of people corresponding to the surveillance video is greater than a predetermined first people threshold. This makes it possible to implement monitoring for congestion events for each surveillance video in the video group.

Also, the surveillance signs may be drawn on the video screen screenshot, ie the area corresponding to the surveillance signs is the detection area. It is also possible to not draw surveillance markers in the video screen screenshot, i.e. there is no corresponding reference plane marker in the surveillance video, in which case the entire video screen is the default detection area.

A video group may also be monitored for congestion events to determine the real-time total number of people in the target monitoring area corresponding to the video group. In some embodiments of the present disclosure, for each surveillance video in the video group, determine the average number of people within a preset time period of the surveillance area corresponding to the surveillance point, and corresponding to each of the four surveillance points Determine the real-time total number of people in the target monitoring area based on the average number of people. That is, the real-time total number of people in multiple detection areas in the hall was determined. when the real-time total number of people in the target monitoring area is greater than a second predetermined threshold of people, generate people flow status warning information, so that after receiving the people flow status warning information, guide people flow to the crowded area in the hall; By doing so, it is possible to reduce the incidence of accidents due to crowding.

In the above method provided by the embodiments of the present disclosure, the description order of each step implies a strict execution order and does not constitute any limitation to the implementation process, and the specific execution order of each step is not limited to its function and possible Those skilled in the art will understand that this should be determined by the underlying logic.

Based on the same idea, the embodiment of the present disclosure further provides a site monitoring device, FIG. 9 is a schematic architecture diagram of the site monitoring device 900 provided by the embodiment of the present disclosure, the first acquisition module 901, a detection module 902, a second acquisition module 903 and a determination module 904, specifically:
a first acquisition module 901 configured to acquire surveillance videos collected by surveillance equipment installed at at least one surveillance point;
a detection module 902 configured to determine whether a surveillance event has occurred in a surveillance area corresponding to at least one surveillance point based on the surveillance video;
a second acquisition module 903 configured to acquire people monitoring data matching a monitoring event within a preset time period when a monitoring event occurs in a monitoring area corresponding to at least one monitoring point;
a determining module 904 configured to determine people flow status data for at least one monitoring device based on the people monitoring data.

In some embodiments of the present disclosure, after determining the people flow status data of at least one monitoring device, the scene monitoring device 900 is configured to generate people flow status alert information if the people flow status data satisfies an alarm condition. further includes an alert module 905 that is triggered.

In some embodiments of the present disclosure, if the surveillance event is a line crossing event, the detection module 902 draws pre-drawn entry/exit boundaries within the surveillance area corresponding to at least one surveillance point based on the surveillance video. determining whether there is a target object that straddles the target location that matches with , and if there is a target object, determining that a line-crossing event has occurred in a surveillance region corresponding to at least one surveillance point; , is configured to run

In some embodiments of the present disclosure, if the monitoring event is a line crossing event, the second acquisition module 903 acquires the number of incoming people and the number of outgoing people at different collection time points within a preset time period. In other words, the number of inflows of people is the number of people crossing the pre-drawn entrance/exit boundary line along the pre-drawn entry direction at different collection times, and the number of outflows is the number of people at different collection times. , which is the number of people crossing the pre-drawn entrance/exit boundary line along the pre-drawn exit direction.

In some embodiments of the present disclosure, if there is one monitoring point, the determining module 904 determines the number of incoming people in the monitoring area corresponding to the monitoring point within a preset time period based on the number of incoming people and the number of outgoing people. configured to determine the total number and the total number of migrants,
The alarm module 905 sets the condition that the total number of incoming people is greater than a predetermined first people flow threshold and the total number of outgoing people is greater than a second predetermined people flow threshold, and the total number of incoming people is greater than the first people flow threshold. or the total number of outflows is greater than the second threshold in crowd flow, generating crowd flow status warning information.

In some embodiments of the present disclosure, if there is one monitoring point, the determination module 904 determines the velocity of incoming and outgoing people in the monitoring area corresponding to the monitoring point based on the number of incoming people and the number of outgoing people. configured to determine.

In some embodiments of the present disclosure, when there are multiple monitoring points, the determination module 904 preconfigures a monitoring area corresponding to each of the monitoring points based on the number of inflows and the number of outflows for each monitoring point. Determining the total number of inflows of people and the total number of outflows of people in the predetermined time period determining the number of people present in the target monitoring area based on the total number of inflows and the total number of outflows in the time slot; and
The alert module 905 is configured to generate people flow status alert information when the presence population is greater than a predetermined current presence threshold.

In some embodiments of the present disclosure, if the surveillance event is a congestion event, the detection module 902 determines, based on the surveillance video, that the number of target objects within the surveillance region corresponding to at least one surveillance point exceeds a congestion threshold. and determining that a congestion event has occurred in a monitoring region corresponding to at least one monitoring point if the number of target subjects exceeds a congestion threshold. be.

In some embodiments of the present disclosure, if the monitoring event is a congestion event, the second acquisition module 903 is configured to statistically count the number of target objects at different collection time points within a preset time period. be.

In some embodiments of the present disclosure, if there is one monitoring point, the determination module 904 determines the average number of people within a preset time period of the monitoring area corresponding to the monitoring point based on the number of target subjects. configured as
The alert module 905 is configured to generate people flow status alert information when the average number of people is greater than a set first people threshold.

In some embodiments of the present disclosure, if there are multiple monitoring points, the determining module 904 determines, for each monitoring point, based on the number of target targets, configured to perform: determining an average headcount; and based on the average headcount, determining a real-time total headcount in a target monitoring area;
The alert module 905 is configured to generate people flow status alert information when the real-time total number of people is greater than a set second people threshold.

In some embodiments of the present disclosure, the scene monitoring device 900 averages the people flow status data at the same collection time point within the most recent historical dates to obtain the people flow forecast data corresponding to each collection time point. and, based on the people flow state prediction data, constructing prediction data of the people flow state data at a future date, the prediction data being used to generate a people flow guidance plan. and an early warning module 906, which

In some embodiments of the present disclosure, the functions or modules provided by the apparatus provided by the embodiments of the present disclosure may be configured to perform the methods described in the above method embodiments, and the specific implementation thereof. may refer to the description of the above method embodiment, and for the sake of simplification, the duplicate description is omitted here.

Based on the same technical idea, the embodiment of the present disclosure further provides an electronic device 1900. FIG. FIG. 10 is a structural schematic diagram of an electronic device 1900 provided by an embodiment of the present disclosure, including a processor 1901, a memory 1902, and a bus 1903. Memory 1902 is used to store execution instructions and includes internal memory 1921 and external memory 1922 . The internal memory 1921 here is also called an internal storage device, and is used to temporarily store operation data in the processor 1901 and data to be exchanged with an external memory 1922 such as a hard disk. In data exchange with memory 1922, when electronic device 1900 operates, processor 1901 and memory 1902 communicate via bus 1903 to provide processor 1901 with monitoring collected by monitoring equipment located at at least one monitoring point. obtaining a video;
determining whether a surveillance event occurred in a surveillance area corresponding to at least one surveillance point based on the surveillance video;
when a monitoring event occurs in a monitoring area corresponding to at least one monitoring point, obtaining people monitoring data matching the monitoring event within a preset time period;
determining people flow status data for at least one monitoring device based on the people monitoring data.

In addition, embodiments of the present disclosure further provide a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the above method. The site monitoring method described in the examples is carried out.

Embodiments of the present disclosure further provide a computer program product, the computer program product comprising computer readable code, wherein when the computer readable code is executed in the electronic device, a processor in the electronic device performs any of the above. Execute to realize the on-site monitoring method described in item 1.

Embodiments of the present disclosure further provide another computer program product, including a computer-readable storage medium having program code stored thereon, instructions contained in the program code for executing on-site monitoring according to the above method embodiments. It can be used to implement the method, please refer specifically to the above method embodiments, and the duplicate description is omitted here.

An apparatus according to embodiments of the present disclosure may be a system, method and/or computer program product. The computer program product may include a computer readable storage medium loaded with computer readable program instructions for causing a processor to implement aspects of the present disclosure.

A computer-readable storage medium may be a tangible device capable of storing and storing instructions for use by an instruction-executing device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include portable computer disks, hard disks, Random Access Memory (abbreviated as RAM), Read-Only Memory: ROM), Erasable Programmable Read Only Memory (EPROM) or flash memory, Static Random-Access Memory (SRAM), portable compact disc read-only Memory (Compact Disc Read-Only Memory, abbreviated as CD-ROM), Digital Video Disc, abbreviated as DVD, memory sticks, floppy disks, and mechanical encoding devices, such as instructions Including memorized punch cards or in-slot projection structures, as well as any suitable combination of the above. Computer readable storage media, as used herein, refers to instantaneous signals themselves, such as radio waves or other freely propagating electromagnetic waves, or electromagnetic waves propagated through waveguides or other transmission media (e.g., passing through fiber optic cables). light pulses), or electrical signals transmitted over wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to each computing/processing device, or may be downloaded via networks such as the Internet, local area networks, wide area networks and/or wireless networks. It may be downloaded to an external computer or external storage device. A network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface within each computing/processing device receives computer-readable program instructions from the network for storage on a computer-readable storage medium within each computing/processing device. Transfer program instructions.

Computer program instructions for performing the operations of the present disclosure may be assembler instructions, Industry Standard Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or Smalltalk, Source or target code written in any combination of one or more programming languages, including object-oriented programming languages such as C++, and common procedural programming languages such as "C" or similar programming languages; There may be. The computer-readable program instructions may be executed entirely on the user's computer, partially executed on the user's computer, executed as a separate software package, or partially executed on the user's computer. and partially on a remote computer, or entirely on a remote computer or server. When referring to a remote computer, the remote computer is connected to the user's computer via any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN). or may be connected to an external computer (eg, via the Internet using an Internet service provider). In some embodiments, state information in computer readable program instructions is used to personalize electronic circuits, such as programmable logic circuits, FPGAs or Programmable Logic Arrays (PLAs), such that: The electronic circuitry executes computer readable program instructions, thereby enabling aspects of the present disclosure to be implemented.

It is clear to those skilled in the art that for the sake of simplicity and brevity of explanation, the specific working processes of the systems and devices described above may refer to the corresponding processes in the method embodiments. understood and will not be described here. It should be understood that in some of the examples provided by the present disclosure, the disclosed systems, devices and methods may be embodied in other forms. The embodiments of the apparatus described above are only exemplary, for example, the division of the units is only the division of logical functions, and other division forms are possible in actual implementation, and for example, , multiple units or components may be combined or integrated into another system, or some features may be ignored or not performed. It should be noted that any mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, electrical, mechanical or other can be in the form

Said units described as separate members may or may not be physically separated, and members indicated as units may or may not be physical units, and may or may not be located in one place. or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, may physically exist independently, or may be integrated into one unit by two or more. may

When the functions are implemented in the form of software functional units and sold or used as stand-alone products, they may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present disclosure can be realized in the form of a software product substantially or the part contributing to the prior art or the part of the technical solution can be realized in the form of a computer software product. is stored on a storage medium and causes a computer device (which may be a personal computer, server, network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. including. The storage medium includes various media capable of storing program code, such as USB flash disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk.

The above are only specific embodiments of the present disclosure, and the protection scope of the present disclosure is not limited thereto. , are all included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Embodiments of the present disclosure provide field surveillance methods and apparatus, electronic devices, storage media, and programs for acquiring surveillance video collected by surveillance equipment installed at at least one surveillance point. determining, based on the surveillance video, whether a surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point; and wherein the surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point. obtaining people monitoring data that matches the monitoring event within a preset time period; and determining people flow status data of the at least one monitoring device based on the people monitoring data. include.

Embodiments of the present disclosure provide at least a site monitoring method and apparatus, an electronic device, a storage medium, and a program for acquiring surveillance video collected by a surveillance device, and determining at least one monitoring point based on the collected surveillance video. obtaining people monitoring data corresponding to the monitoring event within a preset time period when a monitoring event occurs in the monitoring area corresponding to the monitoring area; Determining people flow status data and characterizing the status of the surveillance event by the determined people flow status data, thereby realizing surveillance for surveillance video.
For example, the present application provides the following items.
(Item 1)
A field monitoring method implemented by an electronic device, comprising:
obtaining surveillance video collected by surveillance equipment installed at at least one surveillance point;
determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point based on the surveillance video;
when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point, obtaining population monitoring data matching the monitoring event within a preset time period;
determining people flow status data for the at least one monitoring device based on the people monitoring data.
(Item 2)
After determining people flow status data for the at least one monitoring device,
further comprising generating people flow status alert information if the people flow status data satisfies an alert condition.
The method of item 1.
(Item 3)
If the surveillance event is a line crossing event, then based on the surveillance video, determining whether the surveillance event occurred in a surveillance area corresponding to the at least one surveillance point includes:
determining, based on the surveillance video, whether there is a target object within a surveillance area corresponding to the at least one surveillance point that straddles a target location matching a pre-drawn entry/exit boundary;
determining that the line crossing event occurred in a surveillance area corresponding to the at least one surveillance point if the target object is present.
3. The method of item 1 or 2.
(Item 4)
When the monitoring event is a line-crossing event, obtaining the number-of-persons monitoring data matching the monitoring event within a preset time period includes:
Obtaining the number of inflows and the number of outflows at different collection times within the preset time period, wherein the number of inflows is the number of people entering and exiting at the different collection times It is the number of people who cross the boundary line along the pre-drawn entrance direction, and the number of people who go out is the number of people who cross the pre-drawn entrance/exit boundary line along the pre-drawn exit direction at the different collection points. to be, including
The method of item 2.
(Item 5)
When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
Determining the total number of inflows and the total number of outflows within the preset time period in the monitoring area corresponding to the monitoring point based on the number of inflows and the number of outflows;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
a condition that the total number of inflows of people is greater than a predetermined first person flow threshold and the total number of outflows is greater than a predetermined second person flow threshold;
The condition that the total number of inflows of people is greater than the first threshold of people flow, or that the total number of outflows of people is greater than the second threshold of people flow
generating the people flow status alert information if any of
The method of item 4.
(Item 6)
When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
Determining an inflow velocity and an outflow velocity in a monitoring area corresponding to the monitoring point based on the inflow rate and the outflow rate.
The method of item 4.
(Item 7)
Determining people flow status data of the at least one monitoring device based on the people monitoring data when the monitoring points are plural;
For each monitoring point, based on the number of inflows and the number of outflows, the total number of inflows and the total number of outflows within the preset time zone in the monitoring area corresponding to each of the monitoring points and
Based on the historical number of people in the target monitoring area within the preset time period, and the total number of inflows of people and the total number of outflows of people within the preset time period corresponding to each of the monitoring points, determining the current population within the target monitoring area;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
generating the crowd flow status alert information when the current population is greater than a predetermined current population threshold.
The method of item 4.
(Item 8)
If the surveillance event is a congestion event, then based on the surveillance video, determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point;
determining whether a number of target objects within a surveillance area corresponding to the at least one surveillance point exceeds an overcrowding threshold based on the surveillance video;
determining that an overcrowding event has occurred in a monitoring region corresponding to the at least one monitoring point when the number of target objects exceeds the overcrowding threshold.
3. The method of item 1 or 2.
(Item 9)
When the monitoring event is an overcrowding event, obtaining the number-of-people monitoring data matching the monitoring event within a preset time period includes:
counting the number of target objects at different collection time points within the preset time period.
The method of item 2.
(Item 10)
When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
determining an average number of people within the preset time period in the monitoring area corresponding to the monitoring point based on the number of target subjects;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
generating the people flow status alert information when the average number of people is greater than a predetermined first people threshold.
The method of item 9.
(Item 11)
Determining people flow status data of the at least one monitoring device based on the people monitoring data when the monitoring points are plural;
determining, for each of the monitoring points, an average number of people within the preset time period in the monitoring area corresponding to the monitoring point based on the number of target targets;
determining a real-time total number of people in a target surveillance area based on the average number of people;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
generating the crowd flow status alert information when the real-time total population is greater than a second predetermined population threshold.
The method of item 9.
(Item 12)
The method includes:
averaging people flow status data at the same collection time point within the most recent historical dates to obtain people flow status prediction data corresponding to each collection time point;
constructing forecast data of people flow status data at a future date based on the forecast people flow status data, wherein the forecast data is used to generate a people flow guidance plan.
12. The method of any one of items 1-11.
(Item 13)
a first acquisition module configured to acquire surveillance video acquired by surveillance equipment installed at at least one surveillance point;
a detection module configured to determine, based on the surveillance video, whether a surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point;
a second acquisition module configured to acquire population monitoring data matching the monitoring event within a preset time period when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point; ,
a determination module configured to determine people flow status data for the at least one monitoring device based on the people monitoring data.
(Item 14)
An electronic device comprising a processor, memory and a bus,
The memory stores machine-readable instructions executable by the processor, and when the electronic device operates, the processor and the memory communicate over a bus, and the machine-readable instructions are 13. The electronic device, which, when executed by the processor, performs the site monitoring method of any one of items 1 to 12.
(Item 15)
13. A computer readable storage medium storing a computer program that, when executed by a processor, performs the site monitoring method according to any one of items 1 to 12.
(Item 16)
A computer program comprising computer readable code,
13. Computer program product, executed by a processor of the electronic device to implement the site monitoring method according to any one of items 1 to 12, when the computer readable code is executed in an electronic device.

Claims (16)

A field monitoring method implemented by an electronic device, comprising:
obtaining surveillance video collected by surveillance equipment installed at at least one surveillance point;
determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point based on the surveillance video;
when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point, obtaining population monitoring data matching the monitoring event within a preset time period;
determining people flow status data for the at least one monitoring device based on the people monitoring data. After determining people flow status data for the at least one monitoring device,
2. The method of claim 1, further comprising generating people flow status alert information if the people flow status data satisfies an alert condition. If the surveillance event is a line crossing event, then based on the surveillance video, determining whether the surveillance event occurred in a surveillance area corresponding to the at least one surveillance point includes:
determining, based on the surveillance video, whether there is a target object within a surveillance area corresponding to the at least one surveillance point that straddles a target location matching a pre-drawn entry/exit boundary;
3. The method of claim 1 or 2, comprising determining that the line crossing event has occurred in a surveillance area corresponding to the at least one surveillance point if the target object is present. When the monitoring event is a line-crossing event, obtaining the number-of-persons monitoring data matching the monitoring event within a preset time period includes:
Obtaining the number of inflows and the number of outflows at different collection times within the preset time period, wherein the number of inflows is the number of people entering and exiting at the different collection times It is the number of people who cross the boundary line along the pre-drawn entrance direction, and the number of people who go out is the number of people who cross the pre-drawn entrance/exit boundary line along the pre-drawn exit direction at the different collection points. 3. The method of claim 2, comprising being. When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
Determining the total number of inflows and the total number of outflows within the preset time period in the monitoring area corresponding to the monitoring point based on the number of inflows and the number of outflows;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
a condition that the total number of inflows of people is greater than a predetermined first person flow threshold and the total number of outflows is greater than a predetermined second person flow threshold;
generating the people flow status warning information when either the total number of incoming people flows is greater than the first people flow threshold or the total number of outgoing people flows is greater than the second people flow threshold; 5. The method of claim 4, comprising: When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
5. The method of claim 4, comprising determining a velocity of incoming and outgoing people in a monitoring area corresponding to said monitoring point based on said number of incoming people and said number of outgoing people. Determining people flow status data of the at least one monitoring device based on the people monitoring data when the monitoring points are plural;
For each monitoring point, based on the number of inflows and the number of outflows, the total number of inflows and the total number of outflows within the preset time zone in the monitoring area corresponding to each of the monitoring points and
Based on the historical number of people in the target monitoring area within the preset time period, and the total number of inflows of people and the total number of outflows of people within the preset time period corresponding to each of the monitoring points, determining the current population within the target monitoring area;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
5. The method of claim 4, comprising generating the crowd status alert information if the current population is greater than a predetermined current population threshold. If the surveillance event is a congestion event, then based on the surveillance video, determining whether a surveillance event occurred in a surveillance area corresponding to the at least one surveillance point;
determining whether a number of target objects within a surveillance area corresponding to the at least one surveillance point exceeds an overcrowding threshold based on the surveillance video;
3. The method of claim 1 or 2, comprising determining that a congestion event has occurred in a surveillance area corresponding to the at least one surveillance point when the number of target objects exceeds the congestion threshold. When the monitoring event is an overcrowding event, obtaining the number-of-people monitoring data matching the monitoring event within a preset time period includes:
3. The method of claim 2, comprising statistically counting the number of target objects at different collection times within the preset time window. When the number of monitoring points is one, determining people flow status data of the at least one monitoring device based on the people monitoring data includes:
determining an average number of people within the preset time period in the monitoring area corresponding to the monitoring point based on the number of target subjects;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
10. The method of claim 9, comprising generating the crowd status alert information if the average population is greater than a predetermined first population threshold. Determining people flow status data of the at least one monitoring device based on the people monitoring data when the monitoring points are plural;
determining, for each of the monitoring points, an average number of people within the preset time period in the monitoring area corresponding to the monitoring point based on the number of target targets;
determining a real-time total number of people in a target surveillance area based on the average number of people;
Generating people flow state warning information if the people flow state data satisfies an alarm condition includes:
10. The method of claim 9, comprising generating the crowd status alert information if the real-time total population is greater than a second predetermined population threshold. The method includes:
averaging people flow status data at the same collection time point within the most recent historical dates to obtain people flow status prediction data corresponding to each collection time point;
2. The method of claim 1, further comprising: constructing forecast data of people flow status data at a future date based on the forecast people flow status data, wherein the forecast data is used to generate a people flow guidance plan. 12. The method of any one of 11 to 11. a first acquisition module configured to acquire surveillance video acquired by surveillance equipment installed at at least one surveillance point;
a detection module configured to determine, based on the surveillance video, whether a surveillance event has occurred in a surveillance area corresponding to the at least one surveillance point;
a second acquisition module configured to acquire population monitoring data matching the monitoring event within a preset time period when the monitoring event occurs in the monitoring area corresponding to the at least one monitoring point; ,
a determination module configured to determine people flow status data for the at least one monitoring device based on the people monitoring data. An electronic device comprising a processor, memory and a bus,
The memory stores machine-readable instructions executable by the processor, and when the electronic device operates, the processor and the memory communicate over a bus, and the machine-readable instructions are 13. The electronic equipment, which, when executed by the processor, performs the site monitoring method according to any one of claims 1 to 12. 13. A computer readable storage medium storing a computer program which, when executed by a processor, performs the site monitoring method according to any one of claims 1 to 12. A computer program comprising computer readable code,
A computer program product which, when the computer readable code is executed in an electronic device, is executed by a processor of the electronic device to implement the site monitoring method according to any one of claims 1 to 12.

Images