CN109005386A - Community Watch method, device and equipment based on image analysis - Google Patents

Abstract

The invention discloses a community monitoring method, device and equipment based on image analysis. The community monitoring method includes: obtaining the time when the face image of the monitored user was last collected within a first preset time period and the current time interval; wherein, the monitored user is any one of the registered users in the community; it is judged whether the time interval exceeds the preset value; when the time interval exceeds the preset value, it is confirmed that the monitored user is an abnormal user; The first monitoring image data in the time period is assumed; wherein, the last time the face image of the monitored user is collected is within the second preset time period, and according to the first monitoring image data, it is determined that the abnormal user is in the second preset time period. Behavior information within a time period, according to the behavior information, alarms and reminders can be made to let the outside world know in time when there is an emergency among community members, so as to avoid serious safety accidents.

Description

Community monitoring method, device and equipment based on image analysis

technical field

The invention relates to the technical field of intelligent communities, in particular to a community monitoring method, device and equipment based on image analysis.

Background technique

At present, the community is the basic unit carrying the social population and an important embodiment of urban development. However, due to various reasons, there are still many problems in community building, such as the lack of openness, compatibility and interconnection of technologies and products, unified technical standards have not yet been formed, and products have single functions and no perception functions. The current community services cannot be fully intelligent, and can no longer meet the requirements of human beings for the living environment. Smart communities have become an important direction for future community development.

There are a large number of people in the community, but there is no standardized system to manage the community population. For more and more intelligent modern technology, the access control of community members and the monitoring of strangers' access require a more convenient platform for monitoring. The current smart community system does not have a plan to monitor the travel behavior of the community population through face recognition technology, and now there are many residents who only live alone, so when there is an emergency in the community, it is difficult for the outside world to know the status of the community personnel in time , likely to cause serious safety accidents.

Contents of the invention

The main purpose of the present invention is to provide a community monitoring method, device and equipment based on image analysis, aiming at solving the problem that the outside world is difficult to know the status of the community personnel in time when there is an emergency in the community, and it is easy to cause serious safety accidents. The problem.

In order to achieve the above object, the present invention proposes a community monitoring method based on image analysis, including:

Obtain the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein the monitored user is any one of the registered users in the community;

judging whether the time interval exceeds a preset value;

When the time interval exceeds a preset value, confirming that the monitored user is an abnormal user;

Obtaining the first monitoring image data of the abnormal user within a second preset time period; wherein, the last time the face image of the monitored user was collected is within the second preset time period;

determining behavior information of the abnormal user within the second preset time period according to the first monitoring image data;

According to the behavior information, an alarm reminder is performed.

The present invention also provides a community monitoring device based on image analysis, including:

The first obtaining module is used to obtain the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein, the monitored user is any registered user in the community one;

A judging module, configured to judge whether the time interval exceeds a preset value, and trigger a first confirmation module when the time interval exceeds a preset value;

The first determining module is configured to confirm that the monitored user is an abnormal user according to the trigger of the judging module;

The second acquisition module is used to acquire the first monitoring image data of the abnormal user within the second preset time period; wherein, the time when the face image of the monitored user was last collected is at the second preset time within the paragraph;

A second determining module, configured to determine the behavior information of the abnormal user within the second preset time period according to the first monitoring image data;

The reminding module is used for giving an alarm and reminding according to the behavior information.

The present invention also provides a community monitoring device based on image analysis, including a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program Steps for realizing the above-mentioned community monitoring method.

The present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned community monitoring method are realized.

Above-mentioned scheme of the present invention comprises following beneficial effect at least:

By obtaining the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time, and judging whether the time interval exceeds the preset value, when the time interval exceeds the preset value, confirm The monitored user is an abnormal user, and the first monitoring image data of the abnormal user in the second preset time period is obtained, and finally the behavior information of the abnormal user in the second preset time period is determined according to the acquired first monitoring image data , and give alarm reminders based on behavior information, which can let the outside world know in time when community members have emergencies, so as to avoid serious safety accidents.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to the structures shown in these drawings without creative effort.

Fig. 1 is the network architecture diagram of the community monitoring system that the embodiment of the present invention provides;

Fig. 2 is a schematic flow chart of a community monitoring method provided by an embodiment of the present invention;

FIG. 3 is a schematic flowchart of step S60 in FIG. 2 provided by an embodiment of the present invention;

FIG. 4 is an interactive flowchart of a community monitoring method provided by an embodiment of the present invention;

5 is a schematic structural diagram of a community monitoring device provided by an embodiment of the present invention;

Fig. 6 is a schematic structural diagram of a community monitoring device provided by an embodiment of the present invention.

The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The terms "first", "second" and "third" in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. Furthermore, the term "comprise", as well as any variations thereof, is intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or apparatuses.

Firstly, a network architecture to which the solution of the embodiment of the present application may be applied is introduced by way of example with reference to related drawings.

As shown in Figure 1, the above-mentioned network architecture involves community servers, monitoring equipment deployed around the residences of registered users in each community in the community monitoring area, and monitors in the management center. In addition, the community server also communicates with the mobile communication terminals of registered users in each community and the police Server communication. Among them, the community server can be understood as a server that analyzes the time interval when the community registered user does not appear, and records information such as the face image and monitoring data of the monitored user; the monitoring equipment around the community registered user's residence is used to collect the community registered user's Surveillance image data around the residence (including at least the monitoring data of the doorway and corridor of the community registered user), and the monitoring equipment can specifically be a camera, a camera, etc.; the management center monitor and the mobile communication terminal of the community registered user are used to receive and display The reminder information pushed by the community server can let the outside world know in time when the monitored community personnel have an emergency, so as to avoid serious security accidents.

Among them, the community server stores the registration information of each registered user. The registration information includes the identity of the registered user, face image, contact information, residence information, etc., so that the identity of the registered user can be confirmed and the contact information of the registered user can be obtained based on the face image. In this way, the relevant information can be accurately sent to the mobile communication terminal of the corresponding registered user, and at the same time, it can also ensure that the community management personnel know the residence information of the registered user, so as to check the abnormality at home.

As shown in Figure 2, a specific embodiment of the present invention provides a community monitoring method based on image analysis, including:

Step S10, obtaining the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein, the monitored user is any one of the registered users in the community.

Among them, in the specific embodiment of the present invention, any one of the registered users in the community is the monitored object, and the community server can obtain the monitoring image of each registered user in the community in real time, and for each registered user in the community, it will obtain The time interval between the time when the face image of the community registered user was last collected and the current time within the first preset time period, and perform subsequent steps according to the time interval, so as to prevent emergencies of the community registered user as the monitored user Let the outside world know in time to avoid serious safety accidents.

Specifically, the above-mentioned first preset time period can be set according to monitoring needs, and can be a periodic time, such as from 0:00 to 24:00 every day from Monday to Sunday every week. Between 0:00 and 24:00 from Monday to Sunday, the last time the face image of the monitored user was collected was 3:30 on Monday, then by calculating the time difference between 3:30 and the current time, you can Get the time interval during which the monitored user does not appear. And the above-mentioned current time can be the end time of the first preset time period, of course, it can also be a certain time after the end time, such as half an hour after the end time, so as to prevent the community registered users from being in a dangerous state.

Step S20, judging whether the time interval exceeds a preset value.

Wherein, in a specific embodiment of the present invention, the above-mentioned preset value can be set according to actual monitoring requirements, specifically, it can be 5 days, 7 days, etc.

Step S30, when the time interval exceeds a preset value, confirm that the monitored user is an abnormal user.

In this embodiment, for example, when the community server calculates that the time interval between the appearance of the monitored user exceeds 7 days, the community server determines that the monitored user is an abnormal user. Of course, after the community server determines that the monitored user is an abnormal user, if the community manager communicates with the monitored user and there is no abnormality, then the time will be restarted and the community manager can make a note, which can avoid double counting , so as not to cause too much workload; and if the community manager cannot get in touch with the monitored user, then the community manager needs to conduct further investigation.

Step S40, acquiring the first monitoring image data of the abnormal user within the second preset time period; wherein, the last time the face image of the monitored user is collected is within the second preset time period.

Wherein, in a specific embodiment of the present invention, the above-mentioned first monitoring image data includes the last face image of the monitored user, so after confirming that the monitored user is an abnormal user, by collecting abnormal users in the second preset time The first monitoring image data within the period is conducive to subsequent analysis of the behavior information of the abnormal user within the second preset period of time.

As a preferred example, the step of obtaining the first surveillance image data of the abnormal user within the second preset time period in the above step S40 specifically includes: obtaining the abnormal user's first surveillance image data during the second preset time period through the monitoring equipment of the abnormal user's residence. The first surveillance image data within.

That is, the community server can obtain the first monitoring image data through the monitoring equipment around the residence of the abnormal user, so as to accurately analyze the behavior of the monitored user subsequently.

Step S50, according to the first surveillance image data, determine the behavior information of the abnormal user within the second preset time period.

Among them, in a specific embodiment of the present invention, the community server determines the behavior information of the abnormal user in the second time period according to the first monitoring image data, specifically, the community server can use the time difference method to perform Analyze and determine the behavior information of abnormal users. Among them, the time difference method mainly obtains the human body behavior information in the monitoring image data by comprehensively analyzing the difference between two consecutive frames or several frames of images in the monitoring image data.

Step S60, according to the behavior information, give an alarm reminder.

Among them, in a specific embodiment of the present invention, the community server analyzes whether the abnormal user has a sudden abnormal situation according to the behavior information of the above-mentioned abnormal user, so that when the monitored user has a sudden abnormal situation, it can promptly give an alarm reminder .

As a preferred example, in the above-mentioned step S60, according to the behavior information, the specific implementation of the alarm reminder includes the following steps: when the behavior information indicates that the abnormal user's behavior within the second preset time period is to leave the abnormal user's residence, send Community managers send reminder messages to remind abnormal users who have not returned for a long time.

It can be understood that, in the specific embodiment of the present invention, when the community server judges that the abnormal user is in the state of going out according to the behavior information of the abnormal user within the second time period, the community server needs to remind the community management personnel in time, and the community management personnel will You can view the first monitoring image data of abnormal users, so as to contact abnormal users and ask them why they did not return to their residences. In this way, abnormal users who have not returned for a long time can be monitored in time, and abnormal users can be prevented from dangerous incidents. people know.

For example, A is a user in a certain community. He leaves home to travel on Sunday. The monitoring equipment of A’s residence obtains the face image and surveillance video of A leaving home on Sunday. The community The server will obtain and store the specific monitoring information of A going out on Sunday. After A leaves home for 7 days, when the community server calculates the face image time of all community users, it determines that A is a resident who has exceeded 7 days. The server analyzes the first monitoring image data collected when A leaves, and the result determined after the analysis is that A leaves home, and the community server sends a reminder message to the community management personnel to inform the community management personnel that household A has been away for a long time. If you have not returned, you need the community management personnel to contact A to investigate whether A is safe, so as to avoid that no one will know because A has not returned for a long time. In one embodiment, the community server can also send the information that A has not returned for a long time to the police station server, so that the police can track and find A in time.

As shown in Figure 3, wherein, in a specific embodiment of the present invention, the above-mentioned steps also include the following steps after sending the reminder message for prompting the abnormal user to leave for a long time to the community manager:

Step S601, acquiring second surveillance image data collected around the abnormal user's residence after the abnormal user leaves the abnormal user's residence.

In the embodiment of the present invention, when it is determined through the first monitoring image data that the abnormal user is going out, the community server will start to obtain the second monitoring image data of the abnormal user after going out. The monitoring image data collected around the residence of the first and other abnormal users is analyzed according to the second monitoring image data, so as to help the community management personnel understand some situations happening around the residence of the abnormal user.

Step S602, analyzing the first surveillance image data and the second surveillance image data, and judging whether the first surveillance image data or the second surveillance image data contains preset dangerous images.

Wherein, the preset dangerous image is a preset image that poses a threat to abnormal users.

Step S603, when the first surveillance image data or the second surveillance image data contains a preset dangerous image, output an alarm message.

In the above-mentioned first monitoring image data and second monitoring image data, after the community server analyzes the preset dangerous images that pose a threat to abnormal users, it can send alarm information to the community management personnel in time, and send the preset alarm information in time For the community management personnel, the community management personnel can know in time that abnormal users are in a dangerous state in the first monitoring image data or the second monitoring image data. Wherein, the preset dangerous image includes at least one of non-registered users staying around the abnormal user's residence, non-registered users entering and leaving the abnormal user's residence, and lights of the abnormal user's residence being turned on.

Therefore, when the monitored first monitoring image data or the second monitoring image data include information of non-registered users (non-registered users may be users who do not match the face images of registered users stored in the community server), and it is determined If a non-registered user appears in an abnormal user's home or stays at the door, an alarm message will be sent further.

Wherein, the above-mentioned step of outputting the alarm information includes: sending the alarm information to the police or the community manager for prompting that there are suspicious persons around the residence of the abnormal user.

It can be understood that, in a specific embodiment of the present invention, when the community server obtains the monitoring image data of non-registered users appearing in the abnormal user's home or staying at the abnormal user's door, the community server determines the preset danger according to the monitoring image data. image, so as to send alarm information to the management center personnel. Similarly, the community server can also establish a connection with the police server, which is convenient for timely feedback of monitoring image data of abnormal users, so that the police can timely detect abnormal users in their homes or abnormal Suspicious people around the user's residence are arrested.

Further, after the above step of outputting the alarm information, it also includes sending reminder information to the terminal of the abnormal user for prompting that there are suspicious persons around the residence of the abnormal user.

Among them, in a specific embodiment of the present invention, the abnormal user can establish a connection with the community server with his mobile phone. After the user leaves home, if some preset dangerous images appear in the home, the community server can judge the preset dangerous images in time. The image thus reminds the abnormal user, so that the abnormal user can discover the abnormal situation in his home in time, so as to call the police in time.

For example, according to household A in the above example, when a certain illegal person H enters the home of household A to commit crimes after household A leaves home, the surveillance equipment obtains the monitoring image data of the illegal personnel H and transmits it to the community server. According to the monitoring image data, the community server analyzes that the illegal person H enters and exits A's home. The community server judges that the illegal person is a non-registered user and contains preset dangerous images in the preset image, and the community server immediately reports to the police server and community managers. Send alarm information and send reminder information to resident A.

Among them, in a specific embodiment of the present invention, in order to ensure that the information that the abnormal user has not gone out can be traced in time, the step of alarming and reminding in the above step S60 according to the behavior information further includes: when the behavior information indicates that the abnormal user is in the second preset The behavior within the time period is to send a warning message to the community manager to remind the community manager to check the abnormal user’s residence when entering the abnormal user’s residence, or a reminder message to remind the abnormal user that he has not gone out for a long time; Inquiry or reminder information can also be sent to abnormal users.

That is, in a specific embodiment of the present invention, the behavior information in the first monitoring image data of the abnormal user analyzed by the community server is that the abnormal user has entered the house and the abnormal user has not appeared for more than the preset time, then the community server judges that the abnormal user exceeds the preset time. If there is no time to go out, remind the community management staff that they need to come to check if there is any emergency, such as the user's sudden illness. For some users with sudden illnesses, community managers can make notes, and adjust the preset time interval judged by the community server to a smaller threshold, so as to prevent these users from being discovered in time due to sudden illnesses.

It can be seen that, in a specific embodiment of the present invention, the community server obtains the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time, and judges whether the time interval is Exceeding the preset value, when the time interval exceeds the preset value, confirm that the monitored user is an abnormal user, and obtain the first monitoring image data of the abnormal user within the second preset time period, and finally according to the acquired first monitoring image data Data, determine the behavior information of abnormal users within the second preset time period, and give an alarm and reminder based on the behavior information, so that when an emergency occurs in the community, the outside world can be informed in time to avoid serious safety accidents.

In addition, as shown in Figure 4, in one embodiment of the present invention, in order to facilitate the understanding of the above-mentioned community monitoring method, the community server, monitoring equipment, police station server, and mobile communication terminal of the monitored user are used to illustrate the above-mentioned community monitoring method. monitoring method.

As shown in Figure 4, based on the above-mentioned community monitoring method, wherein, the community server obtains the time interval between the time when the face image of the monitored user is collected for the last time and the current time, so that the community server judges the face image data collected for the last time Whether the time interval between the time of appearance and the current time exceeds the preset time interval. When the community server judges that the last time the face image of the monitored user was collected exceeds the preset time interval, the community server determines that the monitored user The user is an abnormal user, so the first monitoring image data of the user collected by the monitoring equipment is analyzed to analyze the behavior of the abnormal user in the first monitoring image data. If the user is going out, the community server will obtain the abnormal user leaving the residence Afterwards, the second surveillance image data collected around the abnormal user’s residence is used to judge whether the preset dangerous image is included, and if the preset dangerous image is included, an alarm message will be sent to the police station server. In addition, when the preset dangerous image is included, the Similarly, a reminder message is sent to the user's mobile communication terminal.

In addition, as shown in Figure 5, the present invention also provides a community monitoring device 2 based on image analysis, including a first acquisition module 21, a second acquisition module 24, a judgment module 22, a first determination module 23, a second determination module 25 and reminder module 26.

The first obtaining module 21 is used to obtain the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein, the monitored user is a registered user in the community either.

The judging module 22 is configured to judge whether the time interval exceeds a preset value, and trigger the first confirming module 23 when the time interval exceeds the preset value.

The first determining module 23 is configured to confirm that the monitored user is an abnormal user according to the trigger of the judging module.

The second obtaining module 24 is used to obtain the first monitoring image data of the abnormal user within the second preset time period; wherein, the last time the face image of the monitored user is collected is within the second preset time period Inside.

The second determination module 25 is configured to determine the behavior information of the abnormal user within the second preset time period according to the first surveillance image data.

The reminding module 26 is configured to give an alarm and remind according to the behavior information.

It should be noted that the community monitoring device 2 provided by the specific embodiment of the present invention is a device corresponding to the above-mentioned community monitoring method, and all the embodiments of the above-mentioned community monitoring method are applicable to the community monitoring device 2. The above-mentioned community monitoring device 2 embodiment There are corresponding modules corresponding to the steps in the above-mentioned community monitoring method, which can achieve the same or similar beneficial effects. In order to avoid too much repetition, we will not repeat too much about each module in the itinerary reminder device here.

As shown in Figure 6, the specific implementation of the present invention also provides a community monitoring device based on image analysis, including a memory 11, a processor 13 and a computer program 12 stored in the memory 11 and operable on the processor 13 When the processor 13 executes the computer program 12, it realizes the above-mentioned steps of the community monitoring method based on image analysis.

Specifically, in a specific embodiment of the present invention, the following steps are implemented when the processor 13 executes the computer program 12: Obtain the time when the face image of the monitored user was last collected within the first preset time period and the current time Time interval; wherein, the monitored user is any one of the registered users in the community; judge whether the time interval exceeds the preset value; when the time interval exceeds the preset value, confirm that the monitored user is an abnormal user; obtain the abnormal user in the second The first monitoring image data within the preset time period; wherein, the last time the face image of the monitored user was collected is within the second preset time period; according to the first monitoring image data, it is determined that the abnormal user is in the second preset time period Behavior information within a set time period; according to the behavior information, an alarm reminder will be issued.

Optionally, when the processor 13 executes the computer program 12, it also implements the following steps: when the behavior information indicates that the abnormal user’s behavior within the second preset time period is to leave the abnormal user’s residence, send a notification to the community management personnel for prompting the abnormal Reminder information for users who have not returned for a long time.

Optionally, when the processor 13 executes the computer program 12, it also implements the following steps: obtain the second surveillance image data corresponding to the residence of the abnormal user after the abnormal user leaves the residence of the abnormal user; Analyze the image data to determine whether the first monitoring image data or the second monitoring image data contains a preset dangerous image; when the first monitoring image data or the second monitoring image data contains a preset dangerous image, output an alarm message .

Optionally, when the processor 13 executes the computer program 12, it also implements the following steps: sending an alarm message to the police or a community management personnel for prompting that there are suspicious persons around the residence of the abnormal user.

Optionally, when the processor 13 executes the computer program 12, it also implements the following step: sending a reminder message to the terminal of the abnormal user for prompting that there is a suspicious person around the abnormal user's residence.

Optionally, when the processor 13 executes the computer program 12, it also implements the following steps: when the behavior information indicates that the abnormal user’s behavior within the second preset time period is to enter the abnormal user’s residence, send a message to the community management personnel to remind the community Warning information for management personnel to check the residence of abnormal users, or reminder information for reminding abnormal users that they have not gone out for a long time.

Optionally, when the processor 13 executes the computer program 12, it also implements the following steps: Obtain the first monitoring image data of the abnormal user within the second preset time period through the monitoring equipment installed around the residence of the abnormal user.

That is, in a specific embodiment of the present invention, when the processor 13 of the community monitoring device 1 executes the computer program 12, the steps of the above-mentioned community monitoring method based on image analysis are realized, so when a community member has an unexpected situation, the outside world is informed in time , to avoid serious safety accidents.

It should be noted that, since the processor 13 of the community monitoring device 1 executes the computer program 12 to implement the steps of the above-mentioned community monitoring method based on image analysis, all embodiments of the above-mentioned community monitoring method are applicable to the community monitoring device 1, and All can achieve the same or similar beneficial effects.

In addition, a specific embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned community monitoring method based on image analysis are realized.

Specifically, when the computer-readable storage medium is executed by the processor, the following steps are implemented: obtaining the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; The user is any one of the registered users in the community; it is judged whether the time interval exceeds the preset value; when the time interval exceeds the preset value, it is confirmed that the monitored user is an abnormal user; A monitoring image data; wherein, the last time the face image of the monitored user was collected is within the second preset time period; according to the first monitoring image data, the behavior information of the abnormal user within the second preset time period is determined ;According to the behavior information, an alarm reminder will be given.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: when the behavior information indicates that the behavior of the abnormal user within the second preset time period is to leave the residence of the abnormal user, send a reminder to the community management personnel Reminder information for abnormal users who have not returned for a long time.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: acquiring second surveillance image data corresponding to the residence of the abnormal user after the abnormal user leaves the residence of the abnormal user; The monitoring image data is analyzed to determine whether the first monitoring image data or the second monitoring image data contains a preset dangerous image; when the first monitoring image data or the second monitoring image data contains a preset dangerous image, an alarm is output information.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: sending an alarm message to the police or a community manager for prompting that there is a suspicious person around the residence of the abnormal user.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: sending a reminder message to the terminal of the abnormal user for prompting that there is a suspicious person around the abnormal user's residence.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: when the behavior information indicates that the behavior of the abnormal user within the second preset time period is to enter the residence of the abnormal user, send a reminder to the community management personnel A warning message for the community manager to check the abnormal user's residence, or a reminder message for the abnormal user who has not gone out for a long time.

Optionally, when the computer-readable storage medium is executed by the processor, the following steps are implemented: acquiring the first monitoring image data of the abnormal user within the second preset time period through the monitoring equipment arranged around the residence of the abnormal user.

That is, in a specific embodiment of the present invention, when the computer program is executed by the processor, the steps of the above-mentioned community monitoring method based on image analysis are implemented, so when a community member has an emergency situation, the outside world is informed in time to avoid serious safety hazards. ACCIDENT.

It should be noted that, since the computer program is executed by the processor to implement the steps of the above-mentioned community monitoring method based on image analysis, all embodiments of the above-mentioned community monitoring method are applicable to the computer-readable storage medium, and can achieve the same or similar beneficial effects.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to enable a terminal (which may be a smart speaker, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

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

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Under the conception of the present invention, the equivalent structural transformation made by using the description of the present invention and the contents of the accompanying drawings, or directly/indirectly used in Other relevant technical fields are included in the patent protection scope of the present invention.

Claims (10)

1. A community monitoring method based on image analysis, characterized in that, comprising: Obtain the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein the monitored user is any one of the registered users in the community; judging whether the time interval exceeds a preset value; When the time interval exceeds a preset value, confirming that the monitored user is an abnormal user; Obtaining the first monitoring image data of the abnormal user within a second preset time period; wherein, the last time the face image of the monitored user was collected is within the second preset time period; determining behavior information of the abnormal user within the second preset time period according to the first monitoring image data; According to the behavior information, an alarm reminder is performed. 2. The community monitoring method according to claim 1, wherein the step of alarming and reminding according to the behavior information includes: When the behavior information indicates that the behavior of the abnormal user within the second preset time period is to leave the residence of the abnormal user, send a reminder to the community manager to remind the abnormal user that he has not returned for a long time information. 3. The community monitoring method according to claim 2, characterized in that, after the step of sending the reminding information for prompting the abnormal resident not returning for a long time to the community management personnel, the community monitoring method also includes : acquiring second surveillance image data corresponding to the abnormal user's residence after the abnormal user leaves the abnormal user's residence; Analyzing the first surveillance image data and the second surveillance image data to determine whether the first surveillance image data or the second surveillance image data contains preset dangerous images; When the first monitoring image data or the second monitoring image data contains a preset dangerous image, an alarm message is output. 4. The community monitoring method according to claim 3, wherein the preset dangerous images include non-registered users staying around the abnormal user's residence, non-registered households entering and exiting the abnormal user's residence, all At least one of the lights of the residence of the abnormal user is turned on. 5. The community monitoring method according to claim 3, wherein the step of outputting alarm information includes: An alarm message for prompting suspicious persons around the abnormal user's residence is sent to the police or community management personnel. 6. The community monitoring method according to claim 3, wherein the step of outputting alarm information further comprises: Sending reminder information to the mobile communication terminal of the abnormal user for prompting that there are suspicious persons around the abnormal user's residence. 7. The community monitoring method according to claim 1, wherein the step of alarming and reminding according to the behavior information includes: When the behavior information indicates that the behavior of the abnormal user within the second preset time period is to enter the residence of the abnormal user, send a message to the community management personnel for prompting the community management personnel to the abnormal user The warning information for checking the residence of the user, or the reminder information for reminding the abnormal user that he has not gone out for a long time; or sending the information for asking the reason for not going out to the abnormal user. 8. A community monitoring device based on image analysis, characterized in that it comprises: The first obtaining module is used to obtain the time interval between the time when the face image of the monitored user was last collected within the first preset time period and the current time; wherein, the monitored user is any registered user in the community one; A judging module, configured to judge whether the time interval exceeds a preset value, and trigger a first confirmation module when the time interval exceeds a preset value; The first determining module is configured to confirm that the monitored user is an abnormal user according to the trigger of the judging module; The second acquisition module is used to acquire the first monitoring image data of the abnormal user within the second preset time period; wherein, the time when the face image of the monitored user was last collected is at the second preset time within the paragraph; A second determining module, configured to determine the behavior information of the abnormal user within the second preset time period according to the first monitoring image data; The reminding module is used for giving an alarm and reminding according to the behavior information. 9. A community monitoring device based on image analysis, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor executes the computer program When realizing the steps of the community monitoring method as described in any one of claims 1 to 7. 10. A computer-readable storage medium, the computer-readable storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, the community monitoring as described in any one of claims 1 to 7 is realized method steps.