CN115965913A

CN115965913A - Security monitoring method, device and system and computer readable storage medium

Info

Publication number: CN115965913A
Application number: CN202310119844.7A
Authority: CN
Inventors: 张锦玉
Original assignee: Shanxi Economic Control Technology Co ltd
Current assignee: Shanxi Economic Control Technology Co ltd
Priority date: 2023-02-16
Filing date: 2023-02-16
Publication date: 2023-04-14

Abstract

The application relates to a security monitoring method, a security monitoring device, a security monitoring system and a computer readable storage medium, and relates to the technical field of security monitoring. The method comprises the following steps: the method comprises the steps of obtaining a first face image corresponding to an entering person at an entrance and collected by image collection equipment, judging whether the entering person belongs to an inside person or not based on the first face image and preset person information, if the entering person belongs to the inside person, obtaining walking images corresponding to the entering person at all times respectively, judging whether the entering person is a first abnormal person or not based on the walking images, the first face image and the preset person information, if the entering person is the first abnormal person, outputting first abnormal early warning information, if the entering person does not belong to the inside person, obtaining access information corresponding to the entering person, judging whether the entering person is a second abnormal person or not based on the access information, and if the entering person is the second abnormal person, outputting second abnormal early warning information, thereby improving the safety of a monitored area.

Description

Security monitoring method, device and system and computer readable storage medium

Technical Field

The present application relates to the field of security monitoring technologies, and in particular, to a method, an apparatus, a system, and a computer-readable storage medium for security monitoring.

Background

With the development of science and technology, people have higher and higher requirements on safety, more and more places are applied to a security monitoring system, the security monitoring system usually identifies faces of people entering a monitored area to determine external people and internal people, and registers information of the external people to ensure the safety of the monitored area.

The security monitoring system monitors the external personnel to judge whether the external personnel have abnormal personnel with security threats or not, and the internal personnel may also have security threats.

Disclosure of Invention

In order to improve the security of a monitored area, the application provides a security monitoring method, a security monitoring device, a security monitoring system and a computer readable storage medium.

The above object of the present invention is achieved by the following technical solutions:

in a first aspect, a method for security monitoring is provided, where the method includes:

acquiring a first face image, which is acquired by image acquisition equipment and corresponds to an entrance of an entering person;

based on first face image and preset personnel information, judge whether the entering personnel belong to inside personnel, preset personnel information and include: presetting a face image and presetting position information corresponding to the preset face image;

if the entering person belongs to an internal person, acquiring walking images which are acquired by image acquisition equipment and respectively correspond to the entering person at each moment, and judging whether the entering person is a first abnormal person or not based on each walking image, the first face image and the preset person information, wherein the walking images are images of the entering person when the entering person walks in a monitored area;

if the entering person is a first abnormal person, outputting first abnormal early warning information;

if the entering person does not belong to the internal person, access information corresponding to the entering person is obtained, whether the entering person is a second abnormal person or not is judged based on the access information, and the access information comprises: the method comprises the steps of accessing position information and an integral image of an accessing person, wherein the integral image is an image acquired by image acquisition equipment for an entering person;

and if the entering person is a second abnormal person, outputting second abnormal early warning information.

In a possible implementation manner, the determining whether the entering person belongs to an inside person based on the first face image and preset person information includes:

determining image matching values corresponding to the preset face images respectively based on the first face image and the preset face image corresponding to the entering person;

if the image matching value larger than a preset image matching threshold value exists, the entering person belongs to an internal person;

and if the image matching value larger than the preset image matching threshold value does not exist, the entering person does not belong to the internal person.

In another possible implementation manner, the determining whether the entering person is a first abnormal person based on each walking image, the first face image, and the preset person information includes:

determining a matched face image based on the first face image and a preset face image;

determining target position information corresponding to the entering person based on preset position information corresponding to the preset face image and the matched face image;

determining walking positions corresponding to the walking images respectively based on the walking images;

determining a distance change value corresponding to an entering person based on each walking position and the target position information;

and if the distance change value is larger than a preset walking change threshold value, the entering person is a first abnormal person.

In another possible implementation manner, if the distance variation value is greater than a preset walking variation threshold, the entering person is a first abnormal person, and then the method further includes:

acquiring terminal position information of the first abnormal person, wherein the terminal position information is used for representing a terminal of the first abnormal person in the actual walking process;

determining a position distance based on the end point position information and the destination position information;

if the position distance is larger than a preset distance threshold, acquiring a behavior image of the first abnormal person acquired by the image acquisition equipment at the end point position;

extracting behavior characteristics of a first abnormal person based on the behavior image;

a security level is determined based on the behavioral characteristics.

In another possible implementation manner, the determining, based on the access information, whether the entering person is a second abnormal person includes:

if the access position information is different from the preset access position information, extracting clothing features corresponding to the access personnel based on the integral image of the access personnel;

and if the clothing feature does not belong to the preset clothing feature, determining the entering person as a second abnormal person.

In another possible implementation manner, the method further includes:

if the clothing feature belongs to a preset clothing feature, determining the access time length of the entering person based on the clothing feature, the preset time length and the corresponding relation between the preset time length and the preset clothing feature;

and if the leaving information of the entering personnel is not detected within the access duration, outputting access early warning information.

In another possible implementation manner, the method further includes:

acquiring a region position and a region time length corresponding to a region person, wherein the region person is a person in a public region, and the region time length is the time length of the region person in the region position;

if the area time length is greater than a preset time length threshold value, determining a first area matching value based on the area position and a preset activity area position;

if the first area matching value is smaller than a first preset matching threshold value, acquiring a second face image corresponding to the area position of the area personnel acquired by the image acquisition equipment;

determining the region target position corresponding to region personnel based on the second face image and the preset personnel information;

determining a second region matching value based on the region location and the region destination location;

and if the second region matching value is smaller than a second preset matching threshold value, determining the region personnel as the observers.

In a second aspect, a security monitoring device is provided, the device comprising:

the first acquisition module is used for acquiring a first face image which is acquired by image acquisition equipment and corresponds to an entrance of an entering person;

the first judgment module is used for judging whether the entering personnel belong to the internal personnel or not based on the first face image and preset personnel information, and the preset personnel information comprises: presetting a face image and presetting position information corresponding to the preset face image;

the second judging module is used for acquiring walking images which are acquired by image acquisition equipment and respectively correspond to the entering personnel at each moment when the entering personnel belong to the internal personnel, and judging whether the entering personnel are first abnormal personnel or not based on each walking image, the first face image and the preset personnel information, wherein the walking images are images of the entering personnel walking in the monitored area;

the first output module is used for outputting first abnormal early warning information when the entering person is a first abnormal person;

a third determining module, configured to, when the entering person does not belong to an inside person, obtain access information corresponding to the entering person, and determine, based on the access information, whether the entering person is a second abnormal person, where the access information includes: the method comprises the steps of accessing position information and an integral image of an accessing person, wherein the integral image is an image acquired by image acquisition equipment for an entering person;

and the second output module is used for outputting second abnormal early warning information when the entering person is a second abnormal person.

In a possible implementation manner, the first determining module is specifically configured to, when determining whether the entering person belongs to an inside person based on the first face image and preset person information:

determining image matching values corresponding to the preset face images respectively based on a first face image and the preset face images corresponding to the entering people;

In another possible implementation manner, the second determining module is specifically configured to, when determining whether the entering person is a first abnormal person based on each walking image, the first face image, and the preset person information:

and when the distance change value is larger than a preset walking change threshold value, the entering person is a first abnormal person.

In another possible implementation manner, the apparatus further includes: a second obtaining module, a first determining module, a third obtaining module, an extracting module and a second determining module, wherein,

the second obtaining module is used for obtaining the terminal point position information of the first abnormal person, and the terminal point position information is used for representing the terminal point of the first abnormal person in the actual walking process;

the first determining module is configured to determine a position distance based on the end point position information and the destination position information;

the third obtaining module is used for obtaining the behavior image of the first abnormal person, which is collected by the image collecting device at the end point position, when the position distance is greater than a preset distance threshold;

the extraction module is used for extracting the behavior characteristics of the first abnormal person based on the behavior image;

the second determination module is configured to determine a security level based on the behavior feature.

In another possible implementation manner, when determining, based on the access information, whether the entering person is a second abnormal person, the third determining module is specifically configured to:

when the access position information is different from the preset access position information, extracting clothing features corresponding to the access personnel based on the integral image of the access personnel;

and when the clothing feature does not belong to the preset clothing feature, determining the entering person as a second abnormal person.

In another possible implementation manner, the apparatus further includes: a third determining module and a third outputting module, wherein,

the third determining module is used for determining the access time length of the entering person based on the clothing feature, the preset time length and the corresponding relation between the preset time length and the preset clothing feature when the clothing feature belongs to the preset clothing feature;

and the third output module is used for outputting access early warning information when the leaving information of the entering personnel is not detected in the access duration.

In another possible implementation manner, the apparatus further includes: a fourth obtaining module, a fourth determining module, a fifth obtaining module, a fifth determining module, a sixth determining module, and a seventh determining module, wherein,

the fourth acquisition module is used for acquiring the region position and the region duration corresponding to the region personnel, wherein the region personnel are the personnel in the public region, and the region duration is the duration of the region personnel at the region position;

the fourth determining module is configured to determine a first region matching value based on the region position and a preset activity region position when the region duration is greater than a preset duration threshold;

the fifth obtaining module is used for obtaining a second face image corresponding to the region position of the regional personnel collected by the image collecting equipment when the first region matching value is smaller than a first preset matching threshold value;

the fifth determining module is configured to determine, based on the second face image and the preset person information, a region destination position corresponding to a region person;

the sixth determining module is configured to determine a second region matching value based on the region location and the region destination location;

and the seventh determining module is used for determining the region personnel as the observers when the second region matching value is smaller than a second preset matching threshold.

In a third aspect, a security monitoring system is provided, which includes:

at least three image acquisition devices capable of acquiring a face image of an entering person at an entrance, an entire image of the entering person, and a walking image of the entering person

Still include electronic equipment, electronic equipment includes: the electronic equipment and the image acquisition equipment can carry out information interaction;

a memory;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: and executing the operation corresponding to the security monitoring method shown in any possible implementation manner in the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a set of codes, or a set of instructions is stored, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by a processor to implement the method for security monitoring as shown in any one of the possible implementations of the first aspect.

In summary, the present application includes at least one of the following beneficial technical effects:

the application provides a security monitoring method, a security monitoring device, a security monitoring system and a computer readable storage medium, compared with the related art, in the application, through acquiring a first face image corresponding to an entering person at an entrance acquired by an image acquisition device, judging whether the entering person belongs to an inside person or not based on the first face image and preset person information, if the entering person belongs to the inside person, acquiring walking images corresponding to the entering person acquired by the image acquisition device at all times respectively, and judging whether the entering person is a first abnormal person or not based on the walking images, the first abnormal warning information is output if the entering person belongs to the inside person, when the entering person belongs to the inside person, judging whether the entering person is a second abnormal person based on the access information, when the access information is not accurate, the entering person belongs to a second abnormal person, outputting the second abnormal warning information, when the entering person belongs to the inside person, when the monitoring system determines that the access information of the outside person and the security monitoring system is output the first abnormal warning information, and the security warning information of the outside person is output, and the security warning information of the outside person is improved.

Drawings

Fig. 1 is a schematic flowchart of a security monitoring method provided in an embodiment of the present application.

Fig. 2 is a schematic structural diagram of a security monitoring device provided in an embodiment of the present application.

Fig. 3 is a schematic structural diagram of a security monitoring system provided in an embodiment of the present application.

Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to figures 1-4.

The present embodiment is only for explaining the present application, and it is not limited to the present application, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present application.

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship, unless otherwise specified.

The embodiments of the present application will be described in further detail with reference to the drawings.

The embodiment of the application provides a security monitoring method, which is executed by an electronic device, wherein the electronic device can be a server or a terminal device, the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server providing cloud computing service. The terminal device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like, but is not limited thereto, the terminal device and the server may be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application is not limited thereto, where as shown in fig. 1, the method may include:

and S101, acquiring a first face image, which is acquired by image acquisition equipment and corresponds to an entrance of an entering person.

For this application embodiment, first face image is the face image of entering personnel, and image acquisition equipment can acquire the first face image that enters personnel and correspond at the entry in real time, also can acquire the first face image that enters personnel and correspond when detecting that entering personnel get into, does not do the restriction in this application embodiment.

For the embodiment of the application, the electronic device can acquire the first face image corresponding to the entering person from the image acquisition device in real time, also can acquire the first face image corresponding to the entering person at the entrance from the image acquisition device at intervals of preset time, and also can acquire the first face image corresponding to the entering person at the entrance when an acquisition instruction triggered by the user is detected, and no limitation is made in the embodiment of the application. In the above application embodiment, after acquiring the first face image corresponding to the entry of the entering person acquired by the image acquisition device, the display device may display the first face image corresponding to the entry of the entering person in real time, or display the first face image corresponding to the entry of the entering person when detecting that the user triggers the display instruction, so that the user can master the condition of the entering person.

And S102, judging whether the entering person belongs to the inside person or not based on the first face image and the preset person information.

Wherein, predetermine personnel information and include: the method comprises the steps of presetting a face image and presetting position information corresponding to the face image.

For the embodiment of the present application, the preset staff information is internal staff information stored in advance, for example, information of all residents in the cell a. The method includes the steps that a first face image corresponding to an entering person is matched with preset person information, if the information matched with the first face image can be found in the preset person information, the entering person belongs to an inside person, and if the information matched with the first face image is not found in the preset person information, the entering person does not belong to the inside person, namely, an outside person.

Step S103, if the entering person belongs to the internal person, acquiring walking images which are acquired by the image acquisition equipment and respectively correspond to the entering person at each moment, and judging whether the entering person is a first abnormal person or not based on each walking image, the first face image and preset person information.

The walking image is an image of the entering person walking in the monitored area.

For the embodiment of the application, the electronic device can acquire the walking image corresponding to the entering person in real time, also can acquire the walking image corresponding to the entering person at intervals of preset time, and also can acquire the walking image corresponding to the entering person when a trigger instruction of a user is detected, which is not limited in the embodiment of the application.

For the embodiment of the application, when the entering person belongs to the insider, in order to determine whether the entering person has security threat, the walking images corresponding to the entering person at all times are obtained, and whether the walking images of the entering person are abnormal is judged based on the walking images, the first face images and the preset person information so as to judge whether the entering person is the first abnormal person.

In the above application embodiment, after determining whether the entering person is a first abnormal person based on each walking image, the first face image and the preset person information, if the entering person is the first abnormal person, the display device may display the walking images corresponding to the first abnormal person and the first abnormal person at each moment in real time, or when detecting a display instruction triggered by the user, the display device may display the walking images corresponding to the first abnormal person and the first abnormal person at each moment, so that the user can master the walking condition corresponding to the first abnormal person.

And step S104, if the entering person is a first abnormal person, outputting first abnormal early warning information.

For the embodiment of the application, when it is determined that the entering person is a first abnormal person, first abnormal early warning information is output, and the first abnormal early warning information may include: and entering the walking image of the person, so that the user can master the walking condition of the first abnormal person and timely process the first abnormal person.

And S105, if the entering person does not belong to the internal person, acquiring access information of the entering person, and judging whether the entering person is a second abnormal person or not based on the access information.

Wherein the access information comprises: and accessing the position information and the whole image of the access personnel, wherein the whole image is the image acquired by the image acquisition equipment for the access personnel.

For the embodiment of the application, when the entering person does not belong to the inside person, the access information of the entering person is obtained, and based on the access information and the abnormality evaluation criterion, when the entering person does not belong to the inside person, whether the entering person is the second abnormal person is determined.

In the above application embodiment, after determining whether the entering person is the second abnormal person based on the access information, if the entering person is the second abnormal person, the display device may display the second abnormal person and the access information corresponding to the second abnormal person in real time, and may also display the access information corresponding to the second abnormal person and the second abnormal person when a display instruction triggered by the user is detected, so that the user can master the abnormal condition of the second abnormal person.

And S106, if the entering person is a second abnormal person, outputting second abnormal early warning information.

For the embodiment of the application, after the entering person is determined to be the second abnormal person, that is, the second abnormal person may have potential safety hazard, the second abnormal early warning information is output, and the second abnormal early warning information may include the first face image of the second abnormal person, so that the user can process the second abnormal person in time.

The embodiment of the application provides a security monitoring method, compared with the related art, in the embodiment of the application, a first face image corresponding to an entrance of an entering person collected by an image collecting device is obtained, whether the entering person belongs to an insider or not is judged based on the first face image and preset person information, if the entering person belongs to the insider, walking images corresponding to the entering person collected by the image collecting device at all times are obtained, and whether the entering person is a first abnormal person or not is judged based on the first face image and the preset person information.

A possible implementation manner of the embodiment of the application is that whether the entering personnel belong to the internal personnel is judged based on the first face image and the preset personnel information, and the possible implementation manner specifically comprises the following steps: determining image matching values corresponding to the preset face images respectively based on a first face image and the preset face images corresponding to the entering people; if the image matching value greater than the preset image matching threshold value exists, the entering person belongs to the internal person; and if the image matching value larger than the preset image matching threshold value does not exist, the entering personnel do not belong to the internal personnel. In this embodiment of the application, the preset person information is person information stored in a database, the preset person information includes preset face images, the first face image and the preset face images may be compared through a hash algorithm, and image matching values obtained by comparing each preset face image with the first face image respectively are determined, for example, the image matching values of the preset face image a1 and the first face image a and the matching values of the preset face image a2 and the first face image a. When the image matching value larger than the preset image matching threshold value exists, the entering person is indicated to be an internal person, and when the image matching value larger than the preset image matching threshold value does not exist, namely all the image matching values are smaller than the preset image matching threshold value, the entering person does not belong to an external person.

Whether an entering person belongs to an inside person or not is accurately determined by calculating matching values of the first face image and the preset face images and based on the matching values of the preset face images and the first face image.

Another possible implementation manner of the embodiment of the application, based on the walking image, the first face image and the preset personnel information, determines whether the entering personnel is a first abnormal personnel, and specifically may include: determining a matched face image based on the first face image and a preset face image; determining target position information corresponding to the entering person based on preset position information corresponding to the preset face image and the matched face image; determining walking positions corresponding to the walking images respectively based on the walking images; determining a distance change value corresponding to an entering person based on the walking position and the target position information; and if the distance change value is smaller than the preset walking change threshold value, the entering person is the first abnormal person. In this embodiment of the application, based on the first face image and the preset face image, the step of determining the matching face image may be performed before the step of determining the walking position corresponding to each walking image based on each walking image, may also be performed after the step of determining the walking position corresponding to each walking image based on each walking image, and may also be performed simultaneously with the step of determining the walking position corresponding to each walking image based on each walking image, which is not limited in this embodiment of the application.

For the embodiment of the application, when an entering person belongs to an inside person, the entering person may also have a problem when entering the area monitored by the security monitoring system, a matching face image matched with the first face image may be determined based on the first face image and the preset face image through a hash algorithm, the preset position information corresponding to the matching face image, that is, the destination position information corresponding to the entering person, is determined based on the preset position information corresponding to the preset face image, that is, the position where the entering person is located is the position where the person corresponding to the preset face image is located, that is, the face image and the position information corresponding to the inside person in the area are stored in the database, in the security of the residential area, when the entering person is an inside person, when the entering person is not walking to the destination position information corresponding to the entering person, the entering person may have an abnormality, for example, the residential quarter burglary. The method comprises the steps of determining walking positions corresponding to walking images respectively at each moment based on the walking images corresponding to entering personnel respectively, determining difference values between the walking positions and target positions respectively, determining a distance change value based on each difference value to determine the distance change condition corresponding to the walking positions and the target positions, and when the distance change value is larger than a preset walking change threshold value, when entering personnel walk to the corresponding target positions, the difference values between the walking positions and the target positions in a walking track are continuously reduced, the entering personnel belong to normal walking personnel, and when the entering personnel do not walk to the corresponding target positions, the difference values between the walking positions and the target positions in the walking track are unstable, and the entering personnel belong to first abnormal personnel.

For the embodiment of the application, the walking position corresponding to the walking image is determined based on the walking image of the entering person, whether the entering person walks to the target position or not is determined according to the walking position, the distance change value of the walking position and the target position information is determined, and when the entering person is determined to be an internal person based on the distance change value, the abnormal condition of the entering person is determined, when the entering person belongs to the internal person, the supervision on the entering person is improved, and then the safety of monitoring the entering person is improved.

In another possible implementation manner of the embodiment of the application, if the distance variation value is greater than the preset walking variation threshold, the entering person is a first abnormal person, and then the method may further include: acquiring destination position information of a first abnormal person; determining a position distance based on the end point position information and the destination position information; if the position distance is larger than a preset distance threshold, acquiring a behavior image of a first abnormal person acquired by the image acquisition equipment at the end point position; extracting behavior characteristics of the first abnormal person based on the behavior image; a security level is determined based on the behavioral characteristics. In this embodiment of the present application, when it is detected that the duration of the first abnormal person at a certain position exceeds the preset waiting duration, the end point position information of the first abnormal person may be obtained, when an obtaining instruction triggered by a user is detected, the end point position information of the first abnormal person may also be obtained, when it is detected that the first abnormal person is about to leave the monitoring range, the end point position information of the first abnormal person may also be obtained, which is not limited in this embodiment of the present application.

And the terminal position information is used for representing the terminal of the first abnormal person in the actual walking process.

For the embodiment of the application, based on the end point position and the destination position information, the position distance between the position of the first abnormal person and the destination position in the actual walking process is determined, when the distance difference between the end point position and the destination position is too large, the behavior image of the first abnormal person at the end point position is obtained, the behavior characteristics of the first abnormal person can be extracted based on the behavior image through a trained behavior characteristic recognition model, and the behavior characteristics comprise: the loitering behavior characteristic and the visiting behavior characteristic are obtained, and the safety level corresponding to the behavior characteristic is determined based on the preset safety level corresponding to the behavior characteristic. For example, the end position is a. The target position is B, the position distance between the end position A and the target position B is 810m, the preset distance threshold is 200m, the behavior characteristic of the first abnormal person is loitering, and the safety level corresponding to the behavior characteristic is level 3.

And the trained behavior feature recognition model is obtained by training based on preset behavior image data. Further, when the safety level is smaller than the preset safety level, safety level early warning information is output to remind a user, and the occurrence rate of potential safety hazards is reduced.

In another possible implementation manner of the embodiment of the present application, the accessing information includes: accessing personnel information;

judging whether the entering person is a second abnormal person based on the access information may specifically include: if the access personnel information is different from the preset access information, acquiring an integral image of the access personnel acquired by the image acquisition equipment; extracting clothing features corresponding to the entering personnel based on the whole image; and if the clothing feature does not belong to the preset clothing feature, determining the entering person as a second abnormal person. In the embodiment of the present application, the preset access information may be selected or input by a user, and the preset access information is backup information of an external person to verify the identity of the external person.

For the embodiment of the application, when an external person visits residents in an area, the visitor information and the preset visit information are compared, if the visitor information is the same as the preset visit information, the external person is safe, the visit information is different from the preset visit information, and can be partially or completely different, and when the visit information is different from the preset visit information, whether the external person is a second abnormal person or not is judged according to clothing characteristics of the external person, such as a salesman and a maintenance person, wherein the external person belongs to a temporary person and leaves the monitored area soon after entering the monitored area, and the security of the monitored area is not threatened. By acquiring a whole image of the entering person and extracting clothing features of the entering person based on the whole image, the clothing features may include: the color and style of the garment are obvious, and when the garment features of the entering personnel do not belong to the preset garment features, the entering personnel do not belong to the personnel with the backup information or the personnel who do not form the security threat, and the entering personnel are the second abnormal personnel.

For the embodiment of the application, when the entering personnel do not belong to the inside personnel, the entering personnel are verified, when the verification fails, the clothing characteristics of the entering personnel are judged by acquiring the whole image of the entering personnel, the entering personnel not belonging to the preset clothing characteristics are determined as the second abnormal personnel, the second abnormal personnel are accurately determined, and the safety of the monitored area is improved.

Further, when the entering person is a second abnormal person, the second abnormal person can be monitored in a key mode, warning information can be output to the second abnormal person, a no-pass instruction can be output, the no-pass instruction is used for controlling the passing equipment to be closed, the second abnormal person is prevented from entering, and the safety of the monitored area is further improved.

For the embodiment of the application, when the entering person is not an abnormal person, a passing permission instruction can be output, and the passing permission instruction is used for controlling the characteristic equipment to be opened so as to enable the entering person to enter.

In another possible implementation manner of the embodiment of the present application, the method may further include: if the clothing feature belongs to the preset clothing feature, determining the access time length of the entering person based on the clothing feature, the preset access time length and the corresponding relation between the preset access time length and the preset clothing feature; and if the leaving information of the entering personnel is not detected within the access duration, outputting access early warning information. In this embodiment of the application, in order to further improve the security of a monitored area, the access duration of an access person may be limited, when a clothing feature of an entering person belongs to a preset clothing feature, a matching clothing feature matched with the clothing feature is determined based on the preset clothing feature, an access duration corresponding to the matching clothing feature is determined based on a corresponding relationship between the preset duration and the preset clothing feature, and when departure information of the entering person is not detected within the access duration, access warning information is output to provide a user to supervise the entering person, where the departure information of the entering person may include: the exit image of the entering person, accessing the pre-warning information may include: access to the clothing features of the person.

For the embodiment of the application, when the entering personnel belong to temporary personnel entering the monitoring area, the access duration of the entering personnel is determined through the clothing characteristics of the entering personnel, and when the time of the entering personnel in the monitoring area exceeds the access duration, the entering personnel may have abnormity and output early warning information so as to improve the safety of the monitored area.

In another possible implementation manner of the embodiment of the present application, the method may further include: acquiring the region position and the region duration corresponding to the region personnel; if the area duration is greater than a preset duration threshold, determining a first area matching value based on the area position and a preset activity area position; if the first area matching value is smaller than a first preset matching threshold value, acquiring a second face image corresponding to the area position of the area personnel acquired by the image acquisition equipment; determining a region target position corresponding to the region personnel based on the second face image and preset personnel information; determining a second region matching value based on the region position and the region destination position; and if the second region matching value is smaller than a second preset matching threshold value, determining the region personnel as the observers. In the embodiment of the application, the electronic device may acquire the area position and the area duration corresponding to the area person in real time, may also acquire the area position and the area duration corresponding to the area person at intervals of a specific time, and may also acquire the area position and the area duration corresponding to the area person when a trigger instruction of a user is detected, which is not limited in the embodiment of the application.

The regional personnel are personnel in a public region, and the regional duration is the duration of the regional personnel at the regional position.

For the present embodiment, when a person in a monitored area is in an inactive area for a long time, the person may have an abnormality, such as a squat point. When the area duration corresponding to the area personnel is greater than a preset duration threshold value, the area personnel may be abnormal, whether the area personnel is abnormal is judged by judging the position of the area personnel, a preset activity area is an area where the area personnel are allowed to be located for a long time, the area position and the preset activity area position can be represented by coordinates, the ratio of the overlapping area of the area position and the preset activity area to the area position is determined as a first area matching value based on the area position and the preset activity area position, when the first area matching value is smaller than the first preset matching threshold value, the time of the area personnel at the area position is longer, and the area position does not belong to the preset activity area position, the area personnel may be abnormal, the electronic equipment obtains a second face image corresponding to the area personnel at the area position acquired by the image acquisition equipment, matches the second face image with the preset face image to obtain a face image matched with the second face image, determines the preset position information corresponding to the face image matched with the second face image as an area target position based on the area position and the area target position, determines that the area position of the area personnel is not smaller than the preset activity area target position, and the abnormal area personnel may exist in the observation area, and the observation target area personnel.

For the embodiment of the application, the region positions of the region personnel are respectively matched with the preset activity region position and the region target position, the abnormal conditions of the region personnel are judged, and the safety of the monitored region is further improved.

The above embodiment introduces a security monitoring method from the perspective of a method flow, and the following embodiment introduces a security monitoring device from the perspective of a virtual module or a virtual unit, which is described in detail in the following embodiment.

The embodiment of the application provides a security monitoring device, as shown in fig. 2, this security monitoring device 20 specifically can include: a first obtaining module 21, a first judging module 22, a second judging module 23, a first output module 24, a third judging module 25 and a second output module 26, wherein,

the first acquisition module 21 is configured to acquire a first face image, which is acquired by the image acquisition device and corresponds to an entrance of an entering person;

the first judging module 22 is configured to judge whether the entering person belongs to the inside person or not based on the first face image and preset person information, where the preset person information includes: presetting a face image and presetting position information corresponding to the face image;

the second judging module 23 is configured to, when an entering person belongs to an inside person, obtain walking images, which are acquired by the image acquisition device and correspond to the entering person at each time, and judge whether the entering person is a first abnormal person or not based on each walking image, the first face image and preset person information, where the walking image is an image of the entering person when the entering person walks in the monitored area;

the first output module 24 is configured to output first abnormal early warning information when the entering person is a first abnormal person;

the third judging module 25 is configured to, when the entering person does not belong to an inside person, obtain access information corresponding to the entering person, and judge whether the entering person is a second abnormal person based on the access information, where the access information includes: accessing position information and an integral image of an accessing person, wherein the integral image is an image acquired by image acquisition equipment for an entering person;

and a second output module 26, configured to output second abnormal early warning information when the entering person is a second abnormal person.

In a possible implementation manner of the embodiment of the application, the first determining module 22 is specifically configured to determine whether the entering person belongs to the inside person based on the first face image and the preset person information:

if the image matching value greater than the preset image matching threshold value exists, the entering person belongs to the inside person;

and if the image matching value larger than the preset image matching threshold value does not exist, the entering personnel do not belong to the internal personnel.

In another possible implementation manner of the embodiment of the present application, when determining whether the entering person is a first abnormal person based on each walking image, the first face image, and the preset person information, the second determining module 23 is specifically configured to:

and when the distance change value is greater than the preset walking change threshold value, the entering person is a first abnormal person.

In another possible implementation manner of the embodiment of the present application, the apparatus 20 further includes: a second obtaining module, a first determining module, a third obtaining module, an extracting module and a second determining module, wherein,

the second acquisition module is used for acquiring the terminal position information of the first abnormal person, and the terminal position information is used for representing the terminal of the first abnormal person in the actual walking process;

the first determining module is used for determining a position distance based on the end point position information and the target position information;

the third acquisition module is used for acquiring a behavior image of the first abnormal person acquired by the image acquisition equipment at the end point position when the position distance is greater than a preset distance threshold;

a second determination module to determine a security level based on the behavioral characteristics.

In another possible implementation manner of the embodiment of the application, when determining, based on the access information, whether the entering person is a second abnormal person, the third determining module 25 is specifically configured to:

when the access position information is different from the preset access position information, extracting clothing features corresponding to the access personnel based on the whole image of the access personnel;

In another possible implementation manner of the embodiment of the present application, the apparatus 20 further includes: a third determination module and a third output module, wherein,

the third determining module is used for determining the access time length of the entering personnel based on the clothing characteristics, the preset time length and the corresponding relation between the preset time length and the preset clothing characteristics when the clothing characteristics belong to the preset clothing characteristics;

and the third output module is used for outputting the visit early warning information when the leaving information of the entering personnel is not detected in the visit duration.

In another possible implementation manner of the embodiment of the present application, the apparatus 20 further includes: a fourth obtaining module, a fourth determining module, a fifth obtaining module, a fifth determining module, a sixth determining module, and a seventh determining module, wherein,

the fourth determination module is used for determining a first area matching value based on the area position and the preset activity area position when the area duration is greater than the preset duration threshold;

the fifth acquisition module is used for acquiring a second face image corresponding to the region position of the region personnel acquired by the image acquisition equipment when the first region matching value is smaller than a first preset matching threshold value;

the fifth determining module is used for determining the region target position corresponding to the region personnel based on the second face image and the preset personnel information;

a sixth determining module, configured to determine a second region matching value based on the region location and the region destination location;

The embodiment of the application provides a security monitoring device, compared with the related art, in the embodiment of the application, a first face image corresponding to an entrance of an entering person collected by an image collecting device is obtained, whether the entering person belongs to an insider or not is judged based on the first face image and preset person information, if the entering person belongs to the insider, walking images corresponding to the entering person collected by the image collecting device at all times are obtained, and based on the walking images, the first face image and the preset person information, whether the entering person is a first abnormal person or not is judged, when the entering person belongs to the insider, abnormal conditions of the entering person are judged through the walking images of the entering person, if the entering person is the first abnormal person, first abnormal early warning information is output, if the entering person does not belong to the insider, namely, the entering person belongs to an outsider, access information of the entering person is obtained, whether the entering person is a second abnormal person is judged based on the access information, when the access information is inaccurate, the entering person belongs to the second abnormal person, second abnormal early warning information is output, the inside person and the monitoring system analyzes the insider and determines whether the inside person and the abnormal conditions of the outsiders appear, and the safety of the entering person is improved, and the abnormal conditions of the first abnormal conditions are output when the outsiders are output, the safety early warning information.

As can be clearly understood by those skilled in the art, for convenience and simplicity of description, reference may be made to the corresponding process in the foregoing method embodiment for a specific working process of the security monitoring apparatus described above, which is not described herein again.

The embodiment of the application provides a security monitoring system, as shown in fig. 3, the security monitoring system 30 shown in fig. 3 includes: an image capturing device 301, an image capturing device 302, an image capturing device 303, and an electronic device 304. The image acquisition device 301 can acquire a face image of an entering person at an entrance, the image acquisition device 302 can acquire an overall image of the entering person, the image acquisition device 303 can acquire a walking image of the entering person, and the image acquisition device 301, the image acquisition device 302 and the image acquisition device 303 can perform information interaction with the electronic device 304.

The security monitoring system shown in fig. 3 is only an example, and should not bring any limitation to the functions and the application range of the embodiment of the present application.

Electronic device, as shown in fig. 4, the electronic device 304 shown in fig. 4 includes: a processor 3041, and a memory 3043. Processor 3041 and memory 3043 are coupled together, such as by bus 3042. Optionally, the electronic device 304 may also include a transceiver 3044. It should be noted that the transceiver 3044 is not limited to one in practical applications, and the structure of the electronic device 304 is not limited to the embodiment of the present application.

The processor 3041 may be a CPU (central processing unit), a general-purpose processor, a DSP (digital signal processor), an ASIC (application specific integrated circuit), an FPGA (field programmable gate array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 3041 may also be a combination of computing functions, e.g., a combination comprising one or more microprocessors, DSPs, and microprocessors, etc.

Bus 3042 may include a path that carries information between the above components. The bus 3042 may be a PCI (peripheral component interconnect) bus, an EISA (extended industry standard architecture) bus, or the like. The bus 3042 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 4, but this does not represent only one bus or one type of bus.

The memory 3043 may be a ROM (read only memory) or other type of static storage device that can store static information and instructions, a RAM (random access memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (electrically erasable programmable read only memory), a CD-ROM (compact disc read only memory) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), a magnetic disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.

The memory 3043 is used for storing application codes for implementing the present application and is controlled by the processor 3041. The processor 3041 is configured to execute the application program code stored in the memory 3043 to implement the contents of the foregoing method embodiments.

Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. But also a server, etc. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments. Compared with the prior art, in the embodiment of the application, whether an entering person belongs to an internal person or not is judged based on the first face image and preset person information by acquiring the first face image corresponding to the entering person at an entrance acquired by the image acquisition device, if the entering person belongs to the internal person, walking images corresponding to the entering person acquired by the image acquisition device at all times are acquired, whether the entering person is a first abnormal person or not is judged based on the walking images, the abnormal condition of the entering person is judged through the walking images of the entering person when the entering person belongs to the internal person, if the entering person is the first abnormal person, first abnormal early warning information is output, if the entering person does not belong to the internal person, namely, the entering person belongs to the external person, access information of the entering person is acquired, if the entering person is the second abnormal person is judged based on the access information, when the access information is not accurate, the entering person belongs to the second abnormal person, second abnormal early warning information is output, the monitoring system analyzes the internal person and the external person and monitors abnormal condition of the first abnormal early warning information when the access information is not accurate, and the abnormal information is output, and the abnormal early warning information is output.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

The foregoing is only a few embodiments of the present application and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present application, and that these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A security monitoring method is characterized by comprising the following steps:

if the entering person does not belong to the internal person, access information corresponding to the entering person is obtained, whether the entering person is a second abnormal person is judged based on the access information, and the access information comprises: accessing position information and an integral image of an accessing person, wherein the integral image is an image acquired by an image acquisition device for an entering person;

2. The method according to claim 1, wherein the determining whether the entering person belongs to an inside person based on the first face image and preset person information comprises:

3. The method according to claim 1, wherein the determining whether the entering person is a first abnormal person based on each walking image, the first face image and the preset person information includes:

4. The method according to claim 3, wherein if the distance variation value is greater than a preset walking variation threshold, the entering person is a first abnormal person, and thereafter:

a security level is determined based on the behavioral characteristics.

5. The method of claim 1, wherein the determining whether the entering person is a second abnormal person based on the access information comprises:

6. The method of claim 5, further comprising:

7. The method of claim 1, further comprising:

if the first region matching value is smaller than a first preset matching threshold value, acquiring a second face image corresponding to a region position of a regional person acquired by image acquisition equipment;

determining the region target position corresponding to the region personnel based on the second face image and the preset personnel information;

determining a second region match value based on the region location and the region destination location;

8. A security monitoring device, comprising:

a third determining module, configured to, when the entering person does not belong to an inside person, obtain access information corresponding to the entering person, and determine whether the entering person is a second abnormal person based on the access information, where the access information includes: accessing position information and an integral image of an accessing person, wherein the integral image is an image acquired by an image acquisition device for an entering person;

9. A security monitoring system, comprising:

the system comprises at least three image acquisition devices, wherein the image acquisition devices can acquire a face image of an entering person at an entrance, an integral image of the entering person and a walking image of the entering person;

still include electronic equipment, electronic equipment includes: the image acquisition equipment can perform information interaction with the electronic equipment;

a memory;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: a method of performing security monitoring according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of security monitoring according to any one of claims 1 to 7.