Monitoring data processing method and device, equipment and storage medium

Abstract

The invention provides a monitoring data processing method, which comprises the steps of identifying a target person based on first monitoring data of a current building, and determining whether the target person is a registered person of the current building or not based on person registration information of the current building; if the target person is not the registered person of the current building, determining whether the target person is the registered person of other buildings based on the person registration information of other buildings; and if the target person is not the registered person of the other building, obtaining second monitoring data of the target person in the community, the second monitoring data being used for performing safety management on the community. According to the invention, big data tasks of monitoring comparison can be shunted from small-scale data comparison to large-scale data comparison, comparison calculation of most people and shunting operation are carried out, so that the amount of data required to be searched in the safety management process of the cell is reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a monitoring data processing method, device, equipment and storage medium. Background Art

[0002] In the prior art, community security management generally relies on community monitoring equipment for monitoring identification and post-investigation, such as installing cameras at the community gate, or multiple public cameras in the community park. However, when there are many people in the community, the amount of data comparison for monitoring identification will be quite large, which is not conducive to finding the monitoring target in time, and also puts higher requirements on the data calculation of the equipment. Even for post-investigation, it is easy to have the problem of difficulty in finding due to the large amount of data. Therefore, there is an urgent need for a community monitoring solution that reduces the amount of data search. Summary of the invention

[0003] The embodiment of the present invention provides a monitoring data processing method, which aims to provide a monitoring data processing method with low data search volume for community security management. The target person can be identified through the first monitoring data of the current building, and based on the personnel registration information of the current building, it is determined whether the target person is a registered person of the current building. When the target person is not a registered person of the current building, it is determined whether the target person is a registered person of other buildings based on the personnel registration information of other buildings. When the target person is not a registered person of other buildings, the second monitoring data of the target person in the community is obtained. The second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community, and the big data task of monitoring comparison can be diverted, first from small data comparison, and then reversed to big data comparison. For the comparison calculation of most personnel, the diversion operation is implemented, thereby reducing the amount of data required to be searched in the process of security management of the community.

[0004] In a first aspect, an embodiment of the present invention provides a monitoring data processing method for community security management, wherein the community includes multiple buildings, each of which corresponds to personnel registration information of the building, and the method includes:

[0005] Based on the first monitoring data of the current building, a target person is identified, and based on the personnel registration information of the current building, whether the target person is a registered person of the current building is determined;

[0006] If the target person is not a registered person in the current building, then based on the personnel registration information of other buildings, determine whether the target person is a registered person in the other buildings;

[0007] If the target person is not a registered person of the other buildings, the second monitoring data of the target person in the community is obtained, and the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

[0008] Optionally, the personnel registration information of the current building includes: personnel registration information corresponding to each floor in the current building; the first monitoring data is floor monitoring data or elevator monitoring data of the current building; the step of identifying a target person based on the first monitoring data of the current building, and determining whether the target person is a registered person of the current building based on the personnel registration information of the current building includes:

[0009] Based on the floor monitoring data or the elevator monitoring data, the target person is identified, and based on the personnel registration information of each of the floors, it is determined whether the target person in the current building is a registered person in each of the current buildings;

[0010] If the target person is a registered person on each of the floors, then the target person is determined to be a registered person in the current building;

[0011] If the target person is not a registered person on each of the floors, it is determined that the target person is not a registered person in the current building.

[0012] Optionally, the step of identifying the target person based on the floor monitoring data or the elevator monitoring data, and determining whether the target person in the current building is a registered person on each of the floors based on the personnel registration information on each of the floors includes:

[0013] Based on the floor monitoring data or the elevator monitoring data, the target person and the current floor corresponding to the target person are determined, where the current floor is the floor where the target person walks or stays for more than a preset time;

[0014] Based on the personnel registration information of the current floor, determining whether the target person is a registered person of the current floor;

[0015] If the target person is not a registered person on the current floor, then based on the registration information of the people on other floors, determine whether the target person is a registered person on other floors;

[0016] If the target person is not a registered person on the current floor and is not a registered person on other floors, it is determined that the target person is not a registered person in the current building; otherwise, it is determined that the target person is a registered person in the current building.

[0017] Optionally, the step of obtaining the second monitoring data of the target person in the community includes:

[0018] Extracting attribute features and facial features of the target person from the first monitoring data;

[0019] Based on the attribute features and the facial features, second monitoring data including the target person is determined from among all monitoring data of the community.

[0020] Optionally, the step of determining, based on the attribute feature and the facial feature, second monitoring data containing the target person from among all monitoring data of the cell comprises:

[0021] In the first monitoring data, determining the current date and the current time when the target person is identified;

[0022] Retrieving the monitoring data within the current date from among all the monitoring data of the cell;

[0023] From the monitoring data within the current date, retrieve the previous monitoring data before the current time and the subsequent monitoring data after the current time;

[0024] Based on the attribute features and the facial features, second monitoring data including the target person is determined in the previous monitoring data and the subsequent monitoring data.

[0025] Optionally, after the step of acquiring the second monitoring data of the target person in the community, the method further includes:

[0026] Based on the second monitoring data, obtaining behavior information and trajectory information of the target person;

[0027] Based on the behavior information and the trajectory information of the target person, security management is performed on the community.

[0028] Optionally, after the step of acquiring the second monitoring data of the target person in the community, the method further includes:

[0029] Splicing the preceding monitoring data with the following monitoring data in chronological order to obtain a spliced ​​video;

[0030] Deduplication processing is performed on overlapping frames in the spliced ​​video, and prompt processing is performed on the image of the target person in the spliced ​​video to obtain third monitoring data containing the target person;

[0031] Based on the third monitoring data, security management is performed on the cell.

[0032] In a second aspect, an embodiment of the present invention further provides a monitoring data processing device for community security management, wherein the community includes a plurality of buildings, each of the buildings corresponds to personnel registration information of the building, and the monitoring data processing device includes:

[0033] A first determination module, used to identify a target person based on first monitoring data of the current building, and determine whether the target person is a registered person of the current building based on the personnel registration information of the current building;

[0034] A second determination module is used to determine whether the target person is a registered person of the other building based on the personnel registration information of the other buildings if the target person is not a registered person of the current building;

[0035] An acquisition module is used to obtain second monitoring data of the target person in the community if the target person is not a registered person in the other buildings. The second monitoring data includes previous monitoring data before the target person is identified and subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the monitoring data processing method provided in the embodiment of the present invention when executing the computer program.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the monitoring data processing method provided in the embodiment of the invention are implemented.

[0038] In an embodiment of the present invention, based on the first monitoring data of the current building, the target person is identified, and based on the personnel registration information of the current building, it is determined whether the target person is a registered person of the current building; if the target person is not a registered person of the current building, based on the personnel registration information of other buildings, it is determined whether the target person is a registered person of other buildings; if the target person is not a registered person of other buildings, the second monitoring data of the target person in the community is obtained, and the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified, and the second monitoring data is used for security management of the community. The present invention can divert the big data task of monitoring comparison, first from small-scale data comparison, and then reverse to large-scale data comparison, and implement diversion operations for the comparison calculation of most personnel, thereby reducing the amount of data required to be searched in the process of security management of the community. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 is a flow chart of a monitoring data processing method provided by an embodiment of the present invention;

[0041] Figure 2 is a structural schematic diagram of a monitoring data processing device provided by an embodiment of the present invention;

[0042] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, Figure 1 1 is a method flow chart of a monitoring data processing method provided by an embodiment of the present invention. The monitoring data processing method comprises the following steps:

[0045] 101. Based on the first monitoring data of the current building, identify the target person, and based on the personnel registration information of the current building, determine whether the target person is a registered person of the current building.

[0046] In the embodiment of the present invention, the community includes multiple buildings, and each building corresponds to the personnel registration information of the building.

[0047] The first monitoring data of the current building may be the floor monitoring data or elevator monitoring data of the current building. The first monitoring data may be obtained through monitoring equipment, such as the camera monitoring equipment in the elevator or the monitoring equipment at the door of the building. The first monitoring data includes information such as the behavior and activity trajectory of the target person in the building.

[0048] The above-mentioned registered persons may be the owner of the current building, the owner's family, friends, residents, etc. It should be noted that the registered person information includes image information, identity information, voice information, etc.

[0049] The monitoring equipment of the current building can be used to extract images of the target person entering the current building, compare the owner's stored information, and extract voice information to identify whether the target person entering the current building is the owner of the current building, the owner's family, friends, etc. If there is no unified monitoring camera at the door of the building, the camera in the elevator can be used to extract the image of the person.

[0050] Furthermore, the facial features and voice information of the target person are identified through surveillance video images, and then compared with the facial information and voice information of the owners or residents in the building to see if there is a successful match, thereby determining whether the target person is a registered person in the building.

[0051] It should be noted that in the community, each building’s elevator is generally equipped with a camera. If there is no unified surveillance camera at the building entrance, the camera in the elevator can be used to extract person images and sound information, and compare it with the facial information and voice information of the owner or resident in the building to identify whether the target person entering the current building is a registered person of the current building.

[0052] 102. If the target person is not a registered person in the current building, determine whether the target person is a registered person in other buildings based on the registration information of the people in other buildings.

[0053] In the embodiment of the present invention, the above-mentioned other buildings correspond to the personnel registration information of their respective buildings.

[0054] Furthermore, if the target person is not in the list of registered persons in the current building, then it is necessary to compare the registration information with the personnel in other buildings to see whether the target person is a registered person in other buildings.

[0055] Specifically, the facial features of the target person can be compared with the images of registered persons in other buildings to see if there is a successful match, thereby determining whether the target person has registered in other buildings. Specifically, other information such as sound information can also be extracted to confirm whether the person has registered in other buildings.

[0056] It should be noted that if the target person is not on the list of registered persons in the current building, the target person can be temporarily marked, such as a "temporary stranger" mark, and then compared with the information of people in other buildings.

[0057] 103. If the target person is not a registered person in other buildings, obtain the second monitoring data of the target person in the community.

[0058] In an embodiment of the present invention, the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified. The previous monitoring data can be understood as the historical monitoring data before the current date and current time when the target person is identified. The subsequent monitoring data can be understood as the monitoring data after the current date and current time when the target person is identified.

[0059] In a possible embodiment, when the target person is not a registered person in the current building and other buildings, the current date and time are determined, and all historical monitoring data before the current time on the current date are retrieved from the entire community, and the target person is searched in reverse order to obtain the monitoring data on the target person before the current time, and the monitoring data includes the movement trajectory and behavior information corresponding to the target person. The above-mentioned behavior information includes walking, standing still to chat, making phone calls, etc. And retrieve all monitoring data after the current time on the current date.

[0060] Furthermore, by sequentially splicing the surveillance video images of the target person in the previous surveillance data and the subsequent surveillance data, spliced ​​video data is obtained, so that all activity tracks of the target person in the current community and the confirmed track range are determined in the spliced ​​video data.

[0061] Specifically, all monitoring data of the community can be retrieved, and a reverse search can be performed on the target person in the community to obtain monitoring data before the current date and current time of identifying the target person, as well as monitoring data about the target person after the current date and current time, and obtain the corresponding movement trajectory and behavior information of the target person.

[0062] It should be noted that after it is confirmed that the target person is not a registered person from other buildings, the target person can be marked again, such as "final stranger".

[0063] Specifically, when it is confirmed that the person does not belong to the current building, the owner information of other buildings in the community is compared to confirm whether the person belongs to the owner of other buildings (visiting). If so, the tracking and monitoring is cancelled. If the person is not an owner of the community, he can be considered a "final stranger".

[0064] After acquiring the second monitoring data, the second monitoring data can be used to analyze the behavior trajectory, activity range and other information of the target person, and the security management of the community can be carried out based on the behavior trajectory, activity range and other information of the target person.

[0065] In an embodiment of the present invention, the surveillance video of the target person can be sent to the monitoring room for prompt marking so as to confirm the information in time, and at the same time, store the relevant data. The monitoring room can confirm the information of the floor owner according to the specific building and floor where the target person moves. The mark can be whether there are 1, 2, 3 friends visiting, or whether there are any lost items. The monitoring room can also compare the clothing characteristics of the target person with the clothing characteristics of the stored platform staff according to the clothing behavior of the target person to determine whether it is a platform staff; if it is determined to be a platform staff, the identity information of the target person is marked. The clothing characteristics of the above-mentioned platform staff are pre-stored by the system, and can be the clothing characteristics of platform staff such as Meituan, Ele.me, and electrical appliance repair.

[0066] In an embodiment of the present invention, the present invention identifies personnel information through the current building, marks target personnel who do not belong to the current building, and then compares the personnel information of other buildings. After determining that the personnel do not belong to the community, the historical data of the entire community is retrieved to identify the route trajectory behavior of the target personnel, and the activity trajectory, residence time, frequently entered areas and other information of the target personnel are identified, thereby assisting the community property management department to perform security management, such as strengthening patrols in specific areas, adjusting access control strategies, or taking alarm measures when necessary, etc., in order to improve the security level of the entire community.

[0067] In an embodiment of the present invention, a target person is identified based on the first monitoring data of the current building, and based on the personnel registration information of the current building, it is determined whether the target person is a registered person of the current building; if the target person is not a registered person of the current building, then based on the personnel registration information of other buildings, it is determined whether the target person is a registered person of the other buildings; if the target person is not a registered person of other buildings, the second monitoring data of the target person in the community is obtained, the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified, and the second monitoring data is used for security management of the community. The present invention identifies the target person through the first monitoring data of the current building, and determines whether the target person is a registered person of the current building based on the personnel registration information of the current building. When the target person is not a registered person of the current building, it is determined whether the target person is a registered person of other buildings based on the personnel registration information of other buildings. When the target person is not a registered person of other buildings, the second monitoring data of the target person in the community is obtained. The second monitoring data is used for security management of the community. The present invention can divert the big data task of monitoring comparison, first from small-scale data comparison, and then reversely to large-scale data comparison. The comparison calculation of most personnel is diverted, thereby reducing the amount of data that needs to be searched in the process of security management of the community.

[0068] It is understandable that in the specific implementation of this application, related data such as personnel image data and personnel registration data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as model training, deployment and use, must comply with relevant laws, regulations and standards of relevant countries and regions.

[0069] Optionally, the personnel registration information of the current building includes: the personnel registration information corresponding to each floor in the current building; the first monitoring data is the floor monitoring data or the elevator monitoring data of the current building; in the step of identifying the target person based on the first monitoring data of the current building, and determining whether the target person is a registered person in the current building based on the personnel registration information of the current building, the target person can be identified based on the floor monitoring data or the elevator monitoring data, and based on the personnel registration information of each floor, it can be determined whether the target person in the current building is a registered person on each floor; if the target person is a registered person on each floor, it is determined that the target person is a registered person in the current building; if the target person is not a registered person on each floor, it is determined that the target person is not a registered person in the current building.

[0070] In an embodiment of the present invention, the personnel registration information of the current building includes: the personnel registration information corresponding to each floor in the current building, and the above-mentioned personnel registration information includes image information, identity information, voice information, etc.

[0071] The above-mentioned personnel registration information may be the owner information, which includes the householder information and temporary householder information, such as family members, friends, etc. The temporary householder information may be obtained by the householder uploading the temporary personnel information on the app or property management office.

[0072] Furthermore, it is possible to determine whether the target person is a registered person in the building by preferentially comparing the floor where the person appears in the monitoring data with the person information in the registration information of each floor in the building.

[0073] If the target person is in the registration information of one of the floors, then it can be determined that the target person is a person who has registered in the current building. Specifically, if the registration record of the target person can be found on one of the floors, then the target person can be identified as a registered person in the current building.

[0074] If the target person does not appear in the registration information of any floor, it is determined that the target person is not a registered person in the current building. In other words, if the registration record of the target person cannot be found on any floor, it can be determined that the target person is not a registered person in the current building.

[0075] Optionally, in the steps of identifying the target person based on the floor monitoring data or the elevator monitoring data, and determining whether the target person in the current building is a registered person on each floor based on the personnel registration information on each floor, the target person and the current floor corresponding to the target person can be determined based on the floor monitoring data or the elevator monitoring data; based on the personnel registration information on the current floor, determine whether the target person is a registered person on the current floor; if the target person is not a registered person on the current floor, then based on the personnel registration information on other floors, determine whether the target person is a registered person on other floors; if the target person is not a registered person on the current floor and is not a registered person on other floors, then determine that the target person is not a registered person on the current building, otherwise, determine that the target person is a registered person on the current building.

[0076] In the embodiment of the present invention, the current floor is a floor where the target person has walked or stayed for more than a preset time. The preset time may be greater than the average door opening time of the elevator or the default door opening time of the elevator, and the preset time may also be a time defined by the user, such as 1 minute, 2 minutes, etc.

[0077] The target person can be identified through floor monitoring data or elevator monitoring data, and the target person's current floor can be determined. The registration information of the person on the current floor can be compared with the target person to determine whether the target person is a registered person in the current building.

[0078] By querying the registration information database of the owners, residents, staff and other personnel on the floor, and comparing the target person's facial information and voice information, it can be determined whether the target person is a registered person on the current floor. If the target person has been registered on the floor, it can be considered that he is a legitimate person in the current building.

[0079] If the target person is not a registered person on the current floor, nor a registered person on other floors, then it can be determined that the target person is not a registered person in the current building. On the contrary, if the target person is a registered person on the current floor or other floors, then it can be determined that the target person is a registered person in the current building. Specifically, in the process of confirming and tracking the identity of the target person, it is necessary to first exclude his / her registration on the current floor and other floors. If none of them are satisfied, it means that the target person has no direct connection with the current building, so it is determined that he / she is not a registered person in the current building. On the contrary, if the target person is a registered person on the current floor or other floors, then it can be judged that he / she is a legitimate person in the current building.

[0080] Specifically, the floor where the target person is located can be determined based on the floor monitoring data or the elevator monitoring data, and it can be determined whether the target person is a registered person on the current floor. If the target person is not a registered person on the current floor, it can be further determined based on the registration information of other floors whether the target person is a registered person on other floors. If the target person is neither a registered person on the current floor nor a registered person on other floors, it can be determined that the target person is not a registered person in the current building. Otherwise, it can be determined that the target person is a registered person in the current building.

[0081] In a possible embodiment, when the target person presses the target floor on the elevator, the current floor will be identified and the door will be opened. Therefore, multiple target floors of the elevator can be obtained from the elevator, and the target person who gets off the elevator from each target floor is compared with the personnel registration information stored on the target floor to determine whether the target person who is currently leaving is a registered person on the floor. For example, when the target person presses the floor 3 on the elevator, the personnel registration information stored on the 3rd floor is compared with the target person to determine whether the target person is a registered person on the 3rd floor. If the target person is not a registered person on the 3rd floor, the registration information of the personnel on other floors can be compared to determine whether the target person is a registered person on other floors. If the target person is not a registered person on other floors, it is determined that the target person is not a registered person on the current building. If the target person is a registered person on other floors, it is determined that the target person is a registered person on the current building.

[0082] In another possible embodiment, when the target user moves across multiple floors (for example, moving across 2 floors, from the 1st floor to the 10th floor, or from the 3rd floor to the 10th floor, or from the 30th floor to the 20th floor, or from the 30th floor to the -1st floor), priority is given to comparing the personnel registration information of the relevant floors involved in the elevator movement trajectory, rather than directly comparing the personnel registration information of all floors in the building.

[0083] It should be noted that, considering that owners may visit each other, if it is determined that the target person does not belong to the owner of the current floor, the target person will be matched with the data of the owners of the entire building. If he is the owner of this building, the tracking and monitoring will be cancelled. If he is not the owner of this building, he can be marked as the person to be tracked.

[0084] Optionally, in the step of obtaining the second monitoring data of the target person in the community, the attribute characteristics and facial features of the target person can be extracted from the first monitoring data; based on the attribute characteristics and facial features, the second monitoring data containing the target person can be determined from all the monitoring data in the community.

[0085] In the embodiment of the present invention, the attribute characteristics of the target person can be understood as the clothing characteristics of the target person, such as clothing color and the logo of the work unit on the clothing. The facial characteristics of the target person include the facial appearance and expression of the target person.

[0086] The second monitoring data includes the preceding monitoring data before the target person is identified, and the following monitoring data after the target person is identified.

[0087] Specifically, the target person's clothing features, facial features and other information can be used to quickly fuzzily search for suspected target persons in all monitoring data of the current community based on the color of their clothing, and a detailed comparison of the facial appearance information of the acquired suspected target persons can be performed until the monitoring data of the target person is found in the historical camera data of the current community.

[0088] In a possible embodiment, the clothing features of the target person may also be compared with the clothing features of the stored platform staff (such as Meituan, Ele.me, and electrical appliance repair). If it is determined that the target person is a platform staff, the identity attribute information is further labeled for the target person.

[0089] Optionally, in the step of determining the second monitoring data containing the target person among all the monitoring data in the community based on attribute features and facial features, the current date and current time when the target person is identified can be determined in the first monitoring data; among all the monitoring data in the community, the previous monitoring data before the current time and the subsequent monitoring data after the current time can be retrieved; based on the attribute features and facial features, the second monitoring data containing the target person can be determined in the previous monitoring data and the subsequent monitoring data.

[0090] In an embodiment of the present invention, the above-mentioned attribute features include clothing features of the target person, such as clothing color and work unit logo on the clothing; the above-mentioned facial features of the target person include facial appearance, expression and other features of the target person.

[0091] Specifically, the current date and current time when the target person appears can be determined in the first monitoring data, and based on the identified current date and current time, the monitoring data of the previous monitoring data and the subsequent monitoring data at the current date and current time can be retrieved from all the monitoring data in the community. Then, based on the attribute characteristics and facial features of the target person, the historical monitoring data in the community before the current date and current time and the monitoring data after the current date and current time are compared and queried to determine the second monitoring data containing the target person.

[0092] Optionally, after the step of obtaining the second monitoring data of the target person in the community, the behavior information and trajectory information of the target person can be obtained based on the second monitoring data; and the community can be managed securely based on the behavior information and trajectory information of the target person.

[0093] In the embodiment of the present invention, the second monitoring data can be processed for behavior recognition to obtain the behavior information of the target person, and the second monitoring data can be processed for image tracking to obtain the trajectory information of the target person, and the above-mentioned behavior information includes walking, standing and chatting, making phone calls, etc. The above-mentioned trajectory information includes the walking trajectory of the target person, that is, the specific path from one place to another in the community.

[0094] It should be noted that by conducting security management of the community based on the behavior information and trajectory information of the target person, the security of the community can be improved and the safety of residents' lives can be ensured.

[0095] Optionally, after the step of obtaining the second monitoring data of the target person in the community, the previous monitoring data and the subsequent monitoring data can be spliced ​​in chronological order to obtain a spliced ​​video; the overlapping frames in the spliced ​​video can be deduplicated, and the image of the target person in the spliced ​​video can be prompted to obtain the third monitoring data containing the target person; based on the third monitoring data, the community is managed securely.

[0096] In an embodiment of the present invention, the previous monitoring data of the target person before the current time, the monitoring data of the current time (first monitoring data) and the subsequent monitoring data after the current time can be spliced ​​in chronological order to obtain a spliced ​​video of the target person. The above current time is the time when the first monitoring data identifies the target person.

[0097] The above-mentioned overlapping frames can be understood as overlapping images of the target person in the same time area in the stitched video.

[0098] In a possible embodiment, the monitoring data is spliced ​​in chronological order. When there are overlapping frames between the monitoring data of different video devices, the overlapping frames of the monitoring data are deduplicated. Because in the splicing process, some of the same pictures may be recorded multiple times, these repeated parts need to be removed to avoid redundant data affecting subsequent analysis.

[0099] The above prompt processing can be understood as the process of identifying the movement trajectory and behavior information of the target person, and marking the movement trajectory, behavior information, and time nodes of the target person on the two-dimensional map of the community. The purpose is to make the location and behavior of the target person in the video more obvious, which is convenient for subsequent security management.

[0100] In a possible embodiment, the previous monitoring data and the subsequent monitoring data can be spliced ​​in chronological order, so that a continuous monitoring data can be formed to show the activity trajectory of the target person in the community, and the overlapping frames are deduplicated, and the movement trajectory and behavior information of the image area corresponding to the target person are identified, and the movement trajectory, behavior information, and time nodes of the target person are marked on the two-dimensional map of the community to obtain the third monitoring data containing the target person. And according to the third monitoring data of the target person, the community is managed for safety, such as setting a warning area, adjusting the patrol route, issuing an early warning, etc., to improve the safety of the community.

[0101] In an embodiment of the present invention, the personnel registration information of each building can be identified by the building, and the target personnel who do not belong to the building can be marked, such as the mark of "temporary stranger", and then compared with the personnel of other buildings. When it is confirmed as the "final stranger" of this community, the route trajectory behavior of the stranger in the historical data of the entire community is reversely retrieved and stored for later viewing. The present invention implements a shunt operation for the comparison calculation of most personnel by diverting the big data task of monitoring comparison, first comparing small data, and then reversely comparing big data; at the same time, it also avoids unnecessary comparison operations of outsiders who are directly engaged in normal activities in the community; and when it is judged that there is a stranger, it is necessary to retrieve the historical trajectory data of the stranger in the community before being identified by the current building, and perform trajectory splicing, and the historical data, current data, and later data will be spliced ​​and stored, which is conducive to the overall investigation in the later stage. Overall, the optimization of monitoring and tracking is achieved, early warning, and early data storage facilitates later investigation.

[0102] like Figure 2 As shown, an embodiment of the present invention provides a monitoring data processing device for community security management, wherein the community includes multiple buildings, each of which corresponds to personnel registration information of the building, and the monitoring data processing device includes:

[0103] The first determination module 201 is used to identify a target person based on the first monitoring data of the current building, and determine whether the target person is a registered person of the current building based on the personnel registration information of the current building;

[0104] The second determination module 202 is used to determine whether the target person is a registered person of the other building based on the registration information of the personnel of the other building if the target person is not a registered person of the current building;

[0105] The acquisition module 203 is used to obtain the second monitoring data of the target person in the community if the target person is not a registered person of the other buildings. The second monitoring data includes the previous monitoring data before the target person is identified and the subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

[0106] Optionally, the first determining module 201 includes:

[0107] A first determination submodule is used to identify a target person based on the floor monitoring data or the elevator monitoring data, and determine whether the target person in the current building is a registered person on each of the floors based on the personnel registration information on each of the floors;

[0108] A second determination submodule is used to determine that the target person is a registered person of the current building if the target person is a registered person of each of the floors;

[0109] The third determination submodule is used to determine that the target person is not a registered person in the current building if the target person is not a registered person in each of the floors.

[0110] Optionally, the first determining submodule includes:

[0111] A first determining unit is used to determine the target person and the current floor corresponding to the target person based on the floor monitoring data or the elevator monitoring data, wherein the current floor is a floor where the target person walks or stays for more than a preset time;

[0112] A second determination unit, configured to determine whether the target person is a registered person on the current floor based on the registration information of the person on the current floor;

[0113] A third determining unit is used to determine whether the target person is a registered person on other floors based on the registration information of the persons on other floors if the target person is not a registered person on the current floor;

[0114] The fourth determination unit is used to determine that the target person is not a registered person of the current building if the target person is not a registered person of the current floor and is not a registered person of the other floors; otherwise, determine that the target person is a registered person of the current building.

[0115] Optionally, the acquisition module 203 includes:

[0116] An extraction submodule, used to extract attribute features and facial features of the target person from the first monitoring data;

[0117] The determination submodule is used to determine the second monitoring data containing the target person from among all the monitoring data of the community based on the attribute features and the facial features.

[0118] Optionally, the determining submodule includes:

[0119] a fifth determining unit, configured to determine, in the first monitoring data, a current date and a current time when the target person is identified;

[0120] A first retrieving unit, configured to retrieve the monitoring data within the current date from all the monitoring data of the cell;

[0121] A second retrieving unit, configured to retrieve, from the monitoring data within the current date, previous monitoring data before the current time and subsequent monitoring data after the current time;

[0122] The sixth determining unit is used to determine the second monitoring data containing the target person in the previous monitoring data and the subsequent monitoring data based on the attribute characteristics and the facial features.

[0123] Optionally, the device further includes a first security management module, and the first security management module includes:

[0124] An acquisition submodule, used for acquiring behavior information and trajectory information of the target person based on the second monitoring data;

[0125] The first security management submodule is used to perform security management on the cell based on the behavior information and the trajectory information of the target person.

[0126] Optionally, the device further includes a second security management module, and the second security management module includes:

[0127] A splicing submodule, used for splicing the preceding monitoring data with the following monitoring data in chronological order to obtain a spliced ​​video;

[0128] A processing submodule, used for performing deduplication processing on overlapping frames in the spliced ​​video and performing prompt processing on the image of the target person in the spliced ​​video to obtain third monitoring data containing the target person;

[0129] The second security management submodule is used to perform security management on the cell based on the third monitoring data.

[0130] The monitoring data processing device provided in the embodiment of the present invention can implement each process implemented by the monitoring data processing method in the above method embodiment and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0131] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a monitoring data processing method stored in the memory 302 and executable on the processor 301, wherein:

[0132] The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps:

[0133] Based on the first monitoring data of the current building, a target person is identified, and based on the personnel registration information of the current building, whether the target person is a registered person of the current building is determined;

[0134] If the target person is not a registered person in the current building, then based on the personnel registration information of other buildings, determine whether the target person is a registered person in the other buildings;

[0135] If the target person is not a registered person of the other buildings, the second monitoring data of the target person in the community is obtained, and the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

[0136] Optionally, the personnel registration information of the current building includes: personnel registration information corresponding to each floor in the current building; the first monitoring data is floor monitoring data or elevator monitoring data of the current building; the step of identifying a target person based on the first monitoring data of the current building and determining whether the target person is a registered person of the current building based on the personnel registration information of the current building executed by the processor 301 includes:

[0137] Based on the floor monitoring data or the elevator monitoring data, the target person is identified, and based on the personnel registration information of each of the floors, it is determined whether the target person in the current building is a registered person in each of the current buildings;

[0138] If the target person is a registered person on each of the floors, then the target person is determined to be a registered person in the current building;

[0139] If the target person is not a registered person on each of the floors, it is determined that the target person is not a registered person in the current building.

[0140] Optionally, the step of identifying the target person based on the floor monitoring data or the elevator monitoring data, and determining whether the target person in the current building is a registered person on each of the floors based on the personnel registration information on each of the floors, performed by the processor 301, includes:

[0141] Based on the floor monitoring data or the elevator monitoring data, the target person and the current floor corresponding to the target person are determined, where the current floor is the floor where the target person walks or stays for more than a preset time;

[0142] Based on the personnel registration information obtained on the current floor, determining whether the target person is a registered person on the current floor;

[0143] If the target person is not a registered person on the current floor, then based on the registration information of the people on other floors, determine whether the target person is a registered person on other floors;

[0144] If the target person is not a registered person on the current floor and is not a registered person on other floors, it is determined that the target person is not a registered person in the current building; otherwise, it is determined that the target person is a registered person in the current building.

[0145] Optionally, the step of obtaining the second monitoring data of the target person in the community performed by the processor 301 includes:

[0146] Extracting attribute features and facial features of the target person from the first monitoring data;

[0147] Based on the attribute features and the facial features, second monitoring data including the target person is determined from among all monitoring data of the community.

[0148] Optionally, the step of determining, based on the attribute feature and the facial feature, second monitoring data containing the target person from among all monitoring data of the cell, performed by the processor 301 includes:

[0149] In the first monitoring data, determining the current date and the current time when the target person is identified;

[0150] Retrieving the monitoring data within the current date from among all the monitoring data of the cell;

[0151] From the monitoring data within the current date, retrieve the previous monitoring data before the current time and the subsequent monitoring data after the current time;

[0152] Based on the attribute features and the facial features, second monitoring data including the target person is determined in the previous monitoring data and the subsequent monitoring data.

[0153] Optionally, after the step of acquiring the second monitoring data of the target person in the community, the method executed by the processor 301 further includes:

[0154] Based on the second monitoring data, obtaining behavior information and trajectory information of the target person;

[0155] Based on the behavior information and the trajectory information of the target person, security management is performed on the community.

[0156] Optionally, after the step of acquiring the second monitoring data of the target person in the community, the method executed by the processor 301 further includes:

[0157] Splicing the preceding monitoring data with the following monitoring data in chronological order to obtain a spliced ​​video;

[0158] Deduplication processing is performed on overlapping frames in the spliced ​​video, and prompt processing is performed on the image of the target person in the spliced ​​video to obtain third monitoring data containing the target person;

[0159] Based on the third monitoring data, security management is performed on the cell.

[0160] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to devices such as smart phones, tablets, computers, servers, etc. that can perform the monitoring data processing method.

[0161] The electronic device provided in the embodiment of the present invention can implement each process implemented by the monitoring data processing method in the above method embodiment and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0162] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the monitoring data processing method provided by the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0163] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0164] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A monitoring data processing method for residential security management, wherein the residential area includes a plurality of buildings, characterized in that: Each of the buildings corresponds to the personnel registration information of the building, and the method comprises the following steps: Based on the first monitoring data of the current building, a target person is identified, and based on the personnel registration information of the current building, whether the target person is a registered person of the current building is determined; If the target person is not a registered person in the current building, then based on the personnel registration information of other buildings, determine whether the target person is a registered person in the other buildings; If the target person is not a registered person of the other buildings, the second monitoring data of the target person in the community is obtained, and the second monitoring data includes the previous monitoring data before the target person is identified, and the subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

2. The monitoring data processing method according to claim 1, characterized in that: The personnel registration information of the current building includes: personnel registration information corresponding to each floor in the current building; the first monitoring data is floor monitoring data or elevator monitoring data of the current building; the step of identifying a target person based on the first monitoring data of the current building, and determining whether the target person is a registered person of the current building based on the personnel registration information of the current building includes: Based on the floor monitoring data or the elevator monitoring data, the target person is identified, and based on the personnel registration information of each of the floors, it is determined whether the target person in the current building is a registered person on each of the floors; If the target person is a registered person on each of the floors, then the target person is determined to be a registered person in the current building; If the target person is not a registered person on each of the floors, it is determined that the target person is not a registered person in the current building.

3. The monitoring data processing method according to claim 2, characterized in that: The step of identifying the target person based on the floor monitoring data or the elevator monitoring data, and determining whether the target person in the current building is a registered person on each of the floors based on the personnel registration information on each of the floors comprises: Based on the floor monitoring data or the elevator monitoring data, the target person and the current floor corresponding to the target person are determined, where the current floor is the floor where the target person walks or stays for more than a preset time; Based on the personnel registration information of the current floor, determining whether the target person is a registered person of the current floor; If the target person is not a registered person on the current floor, then based on the registration information of the people on other floors, determine whether the target person is a registered person on other floors; If the target person is not a registered person on the current floor and is not a registered person on other floors, it is determined that the target person is not a registered person in the current building; otherwise, it is determined that the target person is a registered person in the current building.

4. The monitoring data processing method according to any one of claims 1 to 3, characterized in that: The step of obtaining the second monitoring data of the target person in the community includes: Extracting attribute features and facial features of the target person from the first monitoring data; Based on the attribute features and the facial features, second monitoring data including the target person is determined from among all monitoring data of the community.

5. The monitoring data processing method according to claim 4, characterized in that: The step of determining, based on the attribute feature and the facial feature, second monitoring data containing the target person from among all monitoring data of the cell comprises: In the first monitoring data, determining the current date and the current time when the target person is identified; Retrieving the monitoring data within the current date from among all the monitoring data of the cell; From the monitoring data within the current date, retrieve the previous monitoring data before the current time and the subsequent monitoring data after the current time; Based on the attribute features and the facial features, second monitoring data including the target person is determined in the previous monitoring data and the subsequent monitoring data.

6. The monitoring data processing method according to any one of claims 1 to 5, characterized in that: After the step of acquiring the second monitoring data of the target person in the community, the method further includes: Based on the second monitoring data, obtaining behavior information and trajectory information of the target person; Based on the behavior information and the trajectory information of the target person, security management is performed on the community.

7. The monitoring data processing method according to any one of claims 1 to 5, characterized in that: After the step of acquiring the second monitoring data of the target person in the community, the method further includes: Splicing the preceding monitoring data with the following monitoring data in chronological order to obtain a spliced ​​video; Deduplication processing is performed on overlapping frames in the spliced ​​video, and prompt processing is performed on the image of the target person in the spliced ​​video to obtain third monitoring data containing the target person; Based on the third monitoring data, security management is performed on the cell.

8. A monitoring data processing device for residential security management, wherein the residential area includes a plurality of buildings, characterized in that: Each of the buildings corresponds to the personnel registration information of the building, and the monitoring data processing device includes: A first determination module, used to identify a target person based on first monitoring data of the current building, and determine whether the target person is a registered person of the current building based on the personnel registration information of the current building; A second determination module is used to determine whether the target person is a registered person of the other building based on the personnel registration information of the other buildings if the target person is not a registered person of the current building; An acquisition module is used to obtain second monitoring data of the target person in the community if the target person is not a registered person in the other buildings. The second monitoring data includes previous monitoring data before the target person is identified and subsequent monitoring data after the target person is identified. The second monitoring data is used for security management of the community.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the monitoring data processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the monitoring data processing method according to any one of claims 1 to 7 are implemented.

Images