CN115115997A

CN115115997A - Method and device for determining abnormal object and storage medium

Info

Publication number: CN115115997A
Application number: CN202110298315.9A
Authority: CN
Inventors: 陈晟; 程登峰; 梁安文; 邱雪川
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2021-03-19
Filing date: 2021-03-19
Publication date: 2022-09-27

Abstract

The application discloses a method, a device and a storage medium for determining an abnormal object, which relate to the technical field of data processing and can accurately analyze the behavior of people entering relevant places, so that the safety risk in the relevant places is reduced. The method comprises the following steps: acquiring the residence position of a target object in a preset scene in a preset time period and the residence time of the target object in each residence position; acquiring a monitoring rule corresponding to a preset scene, wherein the monitoring rule is used for representing the limitation of the behavior parameters of each object in the preset scene; determining behavior parameters of the target object according to the acquired residence position and residence time; and if the behavior parameters of the target object do not meet the monitoring rules corresponding to the preset scene, determining that the target object is an abnormal object. The method for determining the abnormal object can accurately analyze the behavior of the person entering the preset scene, and effectively reduces the safety risk of the preset scene.

Description

Method and device for determining abnormal object and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining an abnormal object, and a storage medium.

Background

In order to ensure the security of the relevant places (such as data centers, vaults, machine rooms, warehouses), it is common to perform behavioral analysis on persons who enter the relevant places. In the case of determining a person with abnormal behavior (such as long stay in a warehouse, large distance between different people in a vault, and irregular moving path in a machine room), an alarm is usually issued to warn the people in the relevant place or to inform the relevant people (such as security personnel) of the attention so that the relevant people can effectively take measures to avoid the occurrence of a potentially dangerous event.

In the prior art, behavior analysis can be performed by using images acquired by image acquisition devices located in various areas in a site. However, it is usually only determined in which area a person is located according to the images acquired by the image acquisition devices in each area, and the specific position of the person and/or the duration of the person at a certain position cannot be accurately determined. For example: if the person 1 moves back and forth between points a and B (the distance between points a and B is small) in the area, it may be determined that the person 1 is located in the area 1 only by the above method, and the time period during which the person 1 is located at point a and the time period during which the person 1 stays at point a/B may be regarded as the time period during which the person 1 stays at point a/B. In this case, the behavior analysis performed by the above method is not accurate enough.

Disclosure of Invention

The application provides a method, a device and a storage medium for determining an abnormal object, which can accurately analyze the behavior of people entering a relevant place, thereby reducing the safety risk in the relevant place.

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, the present application provides a method for determining an abnormal object, including: acquiring the residence position of a target object in a preset scene in a preset time period and the residence time of the target object in each residence position; acquiring a monitoring rule corresponding to the preset scene, wherein the monitoring rule is used for representing the limitation of the behavior parameters of each object in the preset scene; determining a behavior parameter of the target object according to the acquired residence position and residence time, wherein the behavior parameter comprises at least one of a distance between the target object and other objects, residence time of the target object in a preset area of the preset scene, or a movement track of the target object; and if the behavior parameters of the target object do not meet the monitoring rule corresponding to the preset scene, determining that the target object is an abnormal object.

According to the method for determining the abnormal object, the distance between the target object and other objects, the residence time of the target object in the preset area of the preset scene, the moving track of the target object and other behavior parameters can be accurately obtained according to the residence position and residence time of the target object, and the accuracy of the behavior parameters is high, so that whether the target object is the abnormal object can be accurately determined according to whether the behavior parameters meet the monitoring rule corresponding to the preset scene, and the safety risk in the preset scene is reduced. The scheme of this application can be accurate carry out behavioral analysis to the personnel who enter into in the scene of predetermineeing promptly, and the effectual safety risk that reduces the scene of predetermineeing.

With reference to the first aspect, in a possible implementation manner, the acquiring the dwell position of the target object in the preset scene in the preset time period and the dwell time of the target object in each dwell position includes: in a preset time period, acquiring at least one piece of identity information (the identity information is used for identifying an object entering the preset scene), the reporting time of each piece of identity information, and a residence position and residence time matched with the same object; determining target identity information, wherein the target identity information is used for representing the target object, and the target object is an object of which the residence position meets a preset condition in target reporting time (the time difference between the target reporting time and the obtained earliest residence time is less than a preset time length); and determining that the target object corresponds to the acquired resident position and resident time, and taking the acquired resident position and resident time as the resident position and resident time of the target object.

Based on the scheme, under the condition that the identity information is multiple, the target object and the target identity information corresponding to the target object are determined according to the reporting time of each identity information and the residence position of each object in the preset scene, so that when the target object is an abnormal object, related personnel can know the identity information of the abnormal object conveniently, and the safety risk of the preset scene is further reduced.

With reference to the first aspect and the foregoing possible implementation manners, in another possible implementation manner, the acquiring the residence position and the residence time that are both matched with the same object includes: and receiving a resident position and a resident time aiming at the same object from the image processing equipment within a preset time period. Or, the obtaining of the residence position and the residence time matched with the same object includes: receiving a residence position and residence time from the image processing equipment in the preset time period; and determining the residence position and residence time corresponding to each preset moment from the acquired residence position and residence time for the same object, and taking the determined residence position and residence time as the residence position and residence time matched with the same object.

Based on the scheme, the preset time and the residence position corresponding to the preset time can be acquired from the acquired residence time after all residence time and residence position are acquired, so that the operation amount for determining the behavior parameters of the target object can be reduced when the behavior parameters of the target object are determined according to the acquired preset time and the residence position corresponding to the preset time, and the efficiency for determining the abnormal object is improved.

With reference to the first aspect and the possible implementation manners, in another possible implementation manner, the determining, from the obtained residence position and residence time, a residence position and residence time corresponding to each preset time includes: if the acquired residence time does not have the preset time, determining the residence position corresponding to the preset time according to the residence position corresponding to the first target residence time and the residence position corresponding to the second target residence time; the first target residence time is the time which is before the preset time and is adjacent to the preset time in the obtained residence time; the second target residence time is a time which is after the preset time and is adjacent to the preset time in the obtained residence time.

Based on the scheme, when the preset time does not exist in the residence time, the residence position corresponding to the preset time is determined according to the residence positions corresponding to the two residence times adjacent to the preset time, and the residence position and the residence time corresponding to each preset time are determined, so that whether the target object is an abnormal object or not can be accurately determined, and the safety risk of the preset scene is further reduced.

With reference to the first aspect and the foregoing possible implementation manners, in another possible implementation manner, the method further includes: acquiring map parameters and scene parameters corresponding to a preset scene; determining the display position of the target object on the map according to the map parameters, the scene parameters and the resident position of the target object in a preset scene; and displaying the target object on the map in a preset mode according to the display position of the target object on the map.

Based on the scheme, the display position of the target object on the map can be determined, and the target object is displayed on the map, so that when the target object is an abnormal object, related personnel can conveniently determine the track of the abnormal object in the preset scene, and the safety risk of the preset scene is further reduced.

In a second aspect, the present application provides an apparatus for determining an abnormal object, the apparatus comprising: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the residence position of a target object in a preset scene in a preset time period and the residence time of the target object in each residence position; the obtaining unit is further configured to obtain a monitoring rule corresponding to the preset scene, where the monitoring rule is used to characterize a limitation on a behavior parameter of each object in the preset scene; a determining unit, configured to determine a behavior parameter of the target object according to the residence position and the residence time acquired by the acquiring unit, where the behavior parameter includes at least one of a distance between the target object and another object, a residence time of the target object in a preset area of the preset scene, or a movement trajectory of the target object; if the behavior parameter of the target object does not satisfy the monitoring rule corresponding to the preset scene, the determining unit is further configured to determine that the target object is an abnormal object, and the monitoring rule is used to represent the limitation on the behavior parameter of each object in the preset scene.

According to the method for determining the abnormal object, because the behavioral parameters such as the distance between the target object and other objects, the residence time of the target object in the preset area of the preset scene, the moving track of the target object and the like can be accurately obtained according to the residence position and residence time of the target object, and because the behavioral parameters are high in accuracy, whether the target object is the abnormal object can be accurately determined according to whether the behavioral parameters meet the monitoring rules corresponding to the preset scene, so that the safety risk in the preset scene is reduced. The scheme of this application can be accurate carry out behavioral analysis to the personnel who enter into in the scene of predetermineeing promptly, and the effectual safety risk that reduces the scene of predetermineeing.

With reference to the second aspect, in a possible implementation manner, the obtaining unit is specifically configured to: the above acquiring the residence position of the target object in the preset scene in the preset time period and the residence time of the target object in each residence position includes: acquiring at least one piece of identity information (the identity information is used for identifying an object entering the preset scene) and the reporting time of each piece of identity information, and the residence position and the residence time matched with the same object in a preset time period; determining target identity information, wherein the target identity information is used for representing the target object, and the target object is an object of which the residence position meets a preset condition within a target reporting time (the time difference between the target reporting time and the obtained earliest residence time is less than a preset time); and determining that the target object corresponds to the acquired resident position and resident time, and taking the acquired resident position and resident time as the resident position and resident time of the target object.

With reference to the second aspect and the possible implementation manner, in another possible implementation manner, the obtaining unit is specifically configured to: receiving a resident position and resident time aiming at the same object from image processing equipment in a preset time period; or, receiving the residence position and residence time from the image processing equipment in the preset time period; the determining unit is further configured to determine, for the same object, a residence position and residence time corresponding to each preset time from the obtained residence positions and residence times, and use the determined residence positions and residence times as residence positions and residence times matched with the same object; the determining unit is further configured to determine, if there is no preset time in the obtained residence time, a residence position corresponding to the preset time according to the residence position corresponding to the first target residence time and the residence position corresponding to the second target residence time; the first target residence time is a time which is before the preset time and is adjacent to the preset time in the obtained residence time; the second target residence time is a time which is after the preset time and is adjacent to the preset time in the obtained residence time.

Based on the scheme, after all the residence time and the residence position are obtained, the preset time and the residence position corresponding to the preset time are collected from the obtained residence time, so that when the behavior parameters of the target object are determined according to the collected preset time and the residence position corresponding to the preset time, the calculation amount for determining the behavior parameters of the target object can be reduced, the efficiency of determining the abnormal object is improved, when the preset time does not exist in the residence time, the residence position corresponding to the preset time is determined according to the residence positions corresponding to two residence times adjacent to the preset time, the residence position and the residence time corresponding to each preset time are determined, whether the target object is the abnormal object can be accurately determined, and the safety risk of the preset scene is further reduced.

In a third aspect, the present application provides an apparatus for determining an abnormal object, including a memory and a processor. The memory is coupled to the processor. The memory is for storing computer program code comprising computer instructions. When the processor executes the computer instructions, the determination device of the abnormal object performs the determination method of the abnormal object as described in the first aspect and any one of its possible design manners.

In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions that, when run on a device for determining an abnormal object, cause the device for determining an abnormal object to perform the method for determining an abnormal object according to the first aspect and any possible design thereof.

In a fifth aspect, the present application provides a computer program product, which includes computer instructions, when the computer instructions are run on an abnormal object determination apparatus, causing the abnormal object determination apparatus to execute the abnormal object determination method according to the first aspect and any possible design manner thereof.

For a detailed description of the second to fifth aspects and their various implementations in this application, reference may be made to the detailed description of the first aspect and its various implementations; moreover, the beneficial effects of the second aspect to the fifth aspect and the various implementation manners thereof may refer to the beneficial effect analysis of the first aspect and the various implementation manners thereof, and are not described herein again.

These and other aspects of the present application will be more readily apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a first schematic structural diagram of a system for determining an abnormal object according to an embodiment of the present application;

fig. 2 is a schematic diagram of an image capturing device covering a preset scene according to an embodiment of the present disclosure;

FIG. 3 is a schematic illustration of a park position provided by an embodiment of the present application;

fig. 4 is a schematic structural diagram of a system for determining an abnormal object according to an embodiment of the present application;

fig. 5 is a schematic diagram illustrating that an image acquisition device provided in the embodiment of the present application performs image acquisition on a preset range;

fig. 6 is a first flowchart illustrating a method for determining an abnormal object according to an embodiment of the present application;

fig. 7 is a flowchart illustrating a second method for determining an abnormal object according to an embodiment of the present application;

fig. 8 is a schematic flowchart of obtaining a parking location and a parking time according to an embodiment of the present disclosure;

fig. 9 is a schematic flowchart illustrating a processing of a residence position and residence time according to an embodiment of the present application;

fig. 10 is a schematic flowchart of determining a target object according to an embodiment of the present application;

fig. 11 is a schematic flowchart of determining whether a target object is an abnormal object according to an embodiment of the present application;

fig. 12 is a third schematic flowchart of a method for determining an abnormal object according to an embodiment of the present application;

FIG. 13 is a diagram illustrating a trajectory of a target object according to an embodiment of the present disclosure;

fig. 14 is a schematic hardware structure diagram of an apparatus for determining an abnormal object according to an embodiment of the present application;

fig. 15 is a schematic structural diagram of an apparatus for determining an abnormal object according to an embodiment of the present application.

Detailed Description

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 only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.

In order to solve the problems, the application provides a method for determining an abnormal object, which can accurately perform behavior analysis on personnel entering a preset scene, and effectively reduce the safety risk of the preset scene.

The method for determining the abnormal object is applied to a system for determining the abnormal object. The abnormal object determination system is used for determining whether an object entering a preset scene is an abnormal object.

As shown in fig. 1, the system for determining an abnormal object includes at least one image capturing apparatus 01, an image processing apparatus 02, and a server 03. At least one image acquisition device 01 and the server 03 are connected to the image processing device 02.

The image acquisition device 01 is configured to acquire an image of an object in a preset scene and send the acquired image to the image processing device 02.

Optionally, the image capturing device 01 may include one camera or may include a plurality of cameras. Illustratively, when the image capturing apparatus 01 includes a plurality of cameras, the image capturing apparatus 01 may include two cameras (i.e., a binocular camera) and may also include three cameras (i.e., a trinocular camera). This is not limited in the examples of the present application.

For example, a plurality of image capturing devices 01 may be disposed within the preset scene. When a plurality of image capturing devices 01 are set in a preset scene, the visual field ranges of the plurality of image capturing devices 01 may collectively cover most or all of the range in the preset scene. For example, as shown in fig. 2, taking an example that the system for determining an abnormal object includes 10 image capturing devices 01, when the 10 image capturing devices 01 are arranged as shown in fig. 2, the visual field ranges of the 10 image capturing devices 01 may collectively cover most or all of the range of the preset scene 04.

For example, the preset scenario in the embodiment of the present application may be a place with a high requirement on safety. For example, the preset scenario is a place such as a data center, a machine room, a warehouse, or a vault, which is related to production safety, data safety, resource safety, and the like.

One or more objects in the preset scene may be used, which is not limited in the embodiment of the present application.

The image processing device 02 is configured to receive the image acquired by the image acquisition device 01, determine a residence position of an object in a preset scene and a residence time at each residence position according to the image acquired by the image acquisition device 01, and send the residence position and the corresponding residence time to the server 03.

Optionally, when the image capturing device 01 is a multi-view image capturing device, because the multi-view image capturing device includes a plurality of cameras, the image processing device 02 may accurately determine the residence position of the object in the preset scene according to the image captured by the multi-view image capturing device 01.

Alternatively, the dwell position may be a position coordinate of an object in the preset scene within the preset scene. The origin of the coordinate system where the parking position is located may be a preset position, or may be determined according to actual conditions. The coordinate system in which the dwell position is located may be a world coordinate system.

For example, as shown in fig. 3, in the coordinate system of the parking position, the image processing device may determine the position coordinate of the object 05 entering the preset scene as (x, y, z) according to the image captured by the image capturing device. Since the position of the object 05 on the z-axis of the coordinate system is generally the same, the coordinates of the dwell position of the object into the preset scene may only include the coordinate position of the object 05 on the x-axis and the y-axis.

Optionally, when a plurality of objects enter the preset scene, the image processing device 03 may determine a residence position of each object in the preset scene and a residence time at each residence position. That is, in the case where there are a plurality of objects entering the preset scene, the image processing apparatus 03 may correspond each object to a plurality of resident positions thereof within the preset scene.

Optionally, the image processing device 02 may be integrated with the image capturing device 01, or may be separately and independently disposed, which is not limited in this embodiment of the application.

Optionally, the image processing apparatus 02 may send the dwell position of each object in the preset scene and the dwell time of each dwell position to the server 03 by means of kafka middleware, so as to ensure reliability of data transmission.

Optionally, in conjunction with fig. 1, as shown in fig. 4, the system for determining an abnormal object may further include an identity information obtaining device 06. The identity information acquisition device 06 is connected to the server 03.

The identity information acquiring device 06 is configured to acquire identity information of an object entering a preset scene, and send the identity information and an acquiring time of the identity information to the server 03. For example, the identity information obtaining device 06 may be an access control device, and may also be other devices, which is not limited in this embodiment of the present application.

Optionally, the image acquisition device 01 may perform image acquisition on a preset range, and the image processing device 02 determines whether an object enters a preset scene according to the acquired image. The preset range may be an area near the identity information acquisition device 06.

For example, as shown in fig. 5, the image capturing device 01 may capture an image of the periphery of the identity information acquiring device 06, and if the image processing device 02 determines that there is a parking position within one meter around the identity information acquiring device 06 based on the image captured by the image capturing device 01, it is determined that there is an object entering a preset scene.

The server 03 is configured to acquire a residence position of a target object in a preset scene in a preset time period and a residence time of the target object at each residence position, determine a behavior parameter of the target object, and determine whether the target object is an abnormal object according to the behavior parameter of the target object.

Optionally, when an object in the preset scene is an object, the object is the target object. When the objects in the preset scene are multiple objects, the server 03 may determine the target object from the multiple objects according to the identity information of the multiple objects.

The following describes a method for determining an abnormal object provided in an embodiment of the present application.

The execution subject of the method for determining the abnormal object provided by the embodiment of the application is a device for determining the abnormal object. The device for determining the abnormal object may be the server 03, a Central Processing Unit (CPU) in the server 03, a control module for identifying the abnormal object in the server 03, or a client for identifying the abnormal object in the server 03. The embodiment of the present application takes a method for determining an abnormal object executed by a server as an example, and describes a method for determining an abnormal object provided by the present application.

As shown in fig. 6, the method for determining an abnormal object of the object includes:

s601, the server acquires the residence position of the target object in the preset scene in the preset time period and the residence time of the target object in each residence position.

The dwell position is determined by the image processing device from the image captured by the image capturing device.

Alternatively, the dwell time may be in milliseconds. The dwell position may be a position coordinate of the object in a preset scene. The dwell position may be plural.

The duration of the preset time period may be determined according to actual conditions, and the embodiment is not limited in this application. For example, the duration of the preset time period may be several seconds, and the duration of the preset time period may also be several minutes.

Optionally, the preset time period may be a plurality of time periods, and the durations of the plurality of time periods may be the same or different. This is not limited in the examples of the present application.

One or more objects in the preset scene may be provided. And under the condition that one object enters the preset scene, the object is the target object. In the case that there are a plurality of objects in the preset scene, the server may determine the target object from the plurality of objects.

Optionally, with reference to fig. 6, as shown in fig. 7, the S601 includes S6011-S6013.

S6011, the server acquires at least one identity information, the reporting time of each identity information, and the residence position and the residence time matched with the same object in a preset time period.

The identity information is used to identify an object entering a preset scene.

Optionally, when there is one object in the preset scene, the acquired identity information is one. And under the condition that a plurality of objects enter the preset scene, the identity information is a plurality of identity information, and each identity information corresponds to one object.

Optionally, the server may obtain at least one identity information through the identity information obtaining device in the preset scenario. The reporting time of each identity information may be the time when the identity information obtaining device obtains the identity information.

For example, when the identity information acquiring device is an access control device, when an object opens the access control device, the access control device may acquire identity information of the object opening the access control device and time for opening the access control device, and send the identity information of the object opening the access control device and the time for opening the access control device to the server.

Optionally, the server may further obtain identity information of each object in the preset scene according to the image acquired by the image acquisition device.

In the following, a description is given of how the server acquires the residence position and the residence time both matching the same object in step S6011, respectively, when there are one or more objects in the preset scene.

In a first implementation manner, when there are multiple objects in a preset scene, as shown in fig. 8, the obtaining, by the server in S6011, the residence position and the residence time both matched with the same object may include S6011a-S6011 b.

S6011a, the server receives the resident position and the resident time from the image processing apparatus within the preset time period.

When there are a plurality of objects in the preset scene, the plurality of resident locations received by the server may include a plurality of resident locations of each object within the preset scene.

S6011b, the server determines the residence position and residence time corresponding to each preset time from the obtained residence positions and residence times for the same object, and takes the determined residence position and residence time as the residence position and residence time matched with the same object.

Optionally, the preset time may be the time of the whole second. The preset time may be a time between the earliest residence time and the latest residence time of each object within a preset time period. For example, taking the earliest residence time of the object within the preset time period as 9 points, 10 minutes, 1 second and 20 milliseconds, and the latest residence time as 9 points, 15 minutes, 1 second and 20 milliseconds as examples, the preset time may include 9 points, 10 minutes, 2 seconds, 9 points, 10 minutes, 3 seconds, 9 points, 10 minutes, 4 seconds, … …, 9 points, 15 minutes and 1 second.

Optionally, when a preset time exists in the obtained residence time, the residence position corresponding to the preset time is the residence position corresponding to the residence time that is the same as the preset time in the residence time.

Optionally, when the preset time does not exist in the obtained residence time, the server determines the residence position corresponding to the preset time according to the residence position corresponding to the first target residence time and the residence position corresponding to the second target residence time. The first target residence time is a time which is before the preset time and is adjacent to the preset time in the acquired residence time. The second target residence time is a time which is after the preset time and is adjacent to the preset time in the obtained residence time.

Illustratively, there is no preset time t in the acquired residence time ₁ Then find later than t in multiple dwell times ₁ Last dwell time of, i.e. dwell time t _high And earlier than t ₁ Last dwell time of, i.e. dwell time t _low . Dwell time t _high The corresponding dwell position in the coordinate system is (x) _high ，y _high ) Dwell time t _low The corresponding dwell position in the coordinate system is (x) _low ，y _low )。

For example, as shown in fig. 3, taking the moving speed of the object in a short time as a constant speed movement as an example, the moving speed Δ x of the object in the x axis and the moving speed Δ y of the object in the y axis can be obtained according to the following first and second formulas.

The formula I is as follows:

the formula II is as follows:

after the moving speeds of the object in the x axis and the y axis are obtained, the residence time t is obtained according to a formula three and a formula four ₁ Is (x) _1， y ₁ )。

The formula III is as follows: x is the number of ₁ ＝x _low +Δx×(t ₁ -t _low )；

The formula four is as follows: y is ₁ ＝y _low +Δy×(t ₁ -t _low )。

It can be seen that after all the residence time and the residence position are obtained, the preset time and the residence position corresponding to the preset time are collected from the obtained residence time, so that when the behavior parameters of the target object are determined according to the collected preset time and the residence position corresponding to the preset time, the calculation amount for determining the behavior parameters of the target object can be reduced, and the efficiency for determining the abnormal object is improved.

Optionally, the residence positions and residence times corresponding to the multiple preset times acquired in different preset time periods may be repeated, or the residence positions and residence times corresponding to some times may be lacked. In order to ensure that the safety of the preset scene is higher, whether the preset time within the preset time periods is repeated or not can be further determined according to the residence positions and the residence times corresponding to the preset times determined by the preset time periods. When there is a repetition moment at a preset moment in a plurality of preset time periods, the repetition residence time and the residence position corresponding to the repetition moment may be deleted, and only one temporal residence time corresponding to the repetition moment and the residence position corresponding to the repetition moment are reserved.

And simultaneously determining whether the residence position and residence time corresponding to some missing moments exist according to the residence positions and residence time corresponding to the preset moments determined by the preset time periods, and determining the residence position and residence time corresponding to the missing moments according to the mode of determining the residence position corresponding to the preset moments according to the residence position corresponding to the first target residence time and the residence position corresponding to the second target residence time when the residence position and residence time corresponding to some missing moments lack.

According to the method and the device, when the preset time does not exist in the residence time, the residence position corresponding to the preset time is determined according to the residence positions corresponding to the two residence times adjacent to the preset time, so that the residence position and the residence time corresponding to each preset time can be determined, whether the target object is an abnormal object or not can be accurately determined, and the safety risk of the preset scene is further reduced.

In a second implementation manner, when there is one object in the preset scene, the acquiring, by the server in S6011, the residence position and the residence time both matched with the same object may include: the server receives a resident position and a resident time for the same object from the image processing device within a preset time period.

Optionally, after the server receives the residence position and residence time for the same object from the image processing device within the preset time period, the server may also process the received residence position and residence time for the same object, that is, determine the residence position and residence time corresponding to each preset time, and use the determined residence position and residence time as the residence position and residence time both matched with the same object. In a case that there is one object in the preset scene, the specific method for the server to determine the residence position and the residence time corresponding to each preset time refers to the above S6011b, which is not described herein again.

For example, as shown in fig. 9, the obtaining, by the server, the residence position and the residence time that are both matched with the same object includes: 1. receiving a residence position and residence time from image acquisition equipment in a preset time period; 2. determining a residence position and residence time corresponding to each preset moment, namely deleting and selecting the received residence positions and determining the residence position corresponding to the whole second moment; 3. removing the duplication of the resident positions and the resident time corresponding to a plurality of preset moments acquired in different preset time periods; 4. and supplementing corresponding residence positions and residence time to missing moments in a plurality of preset moments acquired in different preset time periods.

S6012, the server determines the target identity information.

Optionally, in a case that one piece of identity information is acquired by the server, the identity information is target identity information. When a plurality of objects enter the preset scene, the number of the identity information is multiple, each identity information corresponds to one object, and the server can determine the target identity information corresponding to the target object from the identity information.

The target identity information is used for representing a target object, and the target object is an object of which the residence position meets the preset condition within the target reporting time. The time difference between the target reporting time and the obtained earliest residence time is less than the preset time.

Optionally, the preset time period may be 1 second.

Optionally, the preset condition may be that the object is located at the position where the object resides in the preset scene and is closest to the identity information acquiring device in the preset scene.

For example, when the object in the preset scene includes a first object and a second object, the time when the entrance guard of the preset scene reports the identity information of the first object is a first reporting time. If the earliest residence time and the first reporting time of the first object in the preset scene are within 1 second, and the distance between the residence position corresponding to the earliest residence time of the first object in the preset scene and the access control is less than the distance between the residence position corresponding to the earliest residence time of the second object in the preset scene and the access control, determining that the first object is a target object, the first reporting time is the target reporting time, and the identity information of the first object is the target identity information.

S6013, the server determines that the target object corresponds to the acquired residence position and residence time, and takes the acquired residence position and residence time as the residence position and residence time of the target object.

According to the scheme, under the condition that the identity information is multiple, the target object and the target identity information corresponding to the target object are determined according to the reporting time of each identity information and the residence position of each object in the preset scene, so that when the target object is an abnormal object, related personnel can know the identity information of the abnormal object conveniently, and the safety risk of the preset scene is further reduced.

For example, as shown in fig. 10, the obtaining, by the server, at least one piece of identity information and the reporting time of each piece of identity information within a preset time period, where the residence position and the residence time that are matched with the same object include: 1. and the entrance guard reports the door opening event. The door opening event reported by the door control comprises the time of the door opening action of the door control and the identity information of at least one object. 2. And acquiring the resident position of the door control within 1 meter away from the door control within one second before and after the time of the door control opening action. 3. The server queries the resident location that does not meet the condition. 4. And setting the data as abnormal data and recording an abnormal log. 5. When the server inquires the qualified resident position, whether the resident position is an object is determined. 6. And under the condition that the object is determined to be the target object, binding the identity information of the object reported by the access control with the resident position of the target object. 7. In the case where a plurality of objects are determined, the distance from each object to the gate is calculated. 8. And determining an object closest to the entrance guard as a target object. And after the target object is determined, binding the identity information of the object reported by the access control with the resident position of the target object, namely executing the step 6.

S602, the server acquires a monitoring rule corresponding to a preset scene.

The monitoring rules are used for characterizing the definition of the behavior parameters of each object in the preset scene.

Optionally, the monitoring rule may include at least one of that the distance between the target object and another object is smaller than a preset distance, the residence time of the target object in a preset region of the preset scene is greater than or equal to a preset time, or the deviation of the movement trajectory of the target object from the preset movement trajectory is within a preset range.

Further, the monitoring rule may further include a preset number of objects in the preset scene.

Optionally, the preset number of the objects, the preset distance between the target object and another object, the preset duration of the target object in the preset area of the preset scene, and the preset movement track of the target object may be set according to the safety requirements corresponding to different preset scenes.

Optionally, the monitoring rules corresponding to different preset scenarios may be the same or different. This is not limited in the embodiments of the present application.

Alternatively, the monitoring rules may be preset. For example, when setting the monitoring rule, the user may determine a preset scenario first, and when the preset scenario is different, the monitoring rule may be different. In the case that the preset scene is a vault, the monitoring rule may include that the number of objects entering the preset scene is greater than a preset number and the distance between the target object and other objects is less than a preset distance. In the case that the preset scene is a data center, the monitoring rule may include that a residence time of the target object in a preset area of the preset scene is greater than or equal to a preset time and a deviation of a movement trajectory of the target object from the preset movement trajectory is within a preset range.

S603, the server determines the behavior parameters of the target object according to the acquired residence position and residence time.

The behavior parameters are used for determining whether the object is an abnormal object in a preset scene.

Optionally, the behavior parameter includes at least one of a distance between the target object and another object, a residence time of the target object in a preset region of the preset scene, or a movement trajectory of the target object.

Alternatively, the distance between the target object and other objects may be determined by the dwell positions of different objects at the same dwell time.

Optionally, the residence time of the target object in the preset region of the preset scene may be determined by the number of the residence positions of the object in the preset region and the residence time corresponding to the residence position of the target object in the preset region.

The preset area may be an area in a preset scene that requires a dwell time of an object. The preset area may be a partial area in the preset scene, or may be a whole area of the preset scene. The number of the preset regions may be one or more.

For example, when the preset scene is, for example, a data center, the preset area may be an area in which the data center requires the object to stay for patrol inspection for more than a preset time.

Optionally, the moving track of the target object may be a moving track of the target object in a preset scene within a preset time period, which is determined according to the residence position and residence time of the target object, which are obtained within the preset time period.

Further, the behavior parameter may further include the number of objects in the preset scene.

Optionally, the number of the objects may be the number of the objects which are acquired by the image processing device according to the image acquisition device and sent to the server, or the number of the objects which are acquired by the server may be determined by the acquired resident position.

Alternatively, the behavior parameters may correspond to monitoring rules.

For example, when the preset scene is the data center, the monitoring rule may include that the residence time of the target object in the preset area of the preset scene is greater than or equal to the preset time and the deviation of the movement track of the target object from the preset movement track is within a preset range, and the corresponding behavior parameter may include the residence time of the target object in the preset area of the preset scene or the movement track of the target object.

For example, when the preset scene is a vault, the monitoring rule may include that, in the case that the number of objects entering the preset scene is greater than the preset number and the distance between the target object and other objects is less than the preset distance, the corresponding behavior parameter may include the number of objects and the distance between the target object and other objects.

S604, the server determines whether the behavior parameters of the object meet the monitoring rules corresponding to the preset scene.

For example, in a case that the monitoring rule includes a preset distance between the target object and another object, the behavior parameter includes a distance between the target object and the other object, and if the distance between the target object and the other object is greater than the preset distance, it is determined that the behavior parameter does not satisfy the monitoring rule.

Optionally, in the case that the behavior parameter includes a distance between the target object and another object, the server may determine whether the behavior parameter satisfies the monitoring rule in real time. That is, after the server determines the distances between the target object and the other objects, it may be determined whether the distances between the target object and the other objects satisfy the monitoring rule.

Optionally, in a case that the behavior parameter includes a residence time of the target object in a preset region of the preset scene or a movement trajectory of the target object, the server may determine whether the behavior parameter meets the monitoring rule after determining that the target object leaves the preset scene. The server may also determine whether the behavior parameter satisfies the monitoring rule when the server does not receive the residence position of the target object in the preset scene and the residence time of the target object at each residence position within the preset time.

Continuing to execute S605 when the behavior parameters of the object do not meet the monitoring rules corresponding to the preset scene; and continuing to execute the step S606 when the behavior parameter of the object meets the monitoring rule corresponding to the preset scene.

S605, the server determines that the target object is an abnormal object.

Optionally, after the server determines that the target object is an abnormal object, an abnormal log may be generated and stored.

Optionally, after step S605, the method may further include: the server generates alarm information. The alarm information is used for indicating that the target object is an abnormal object or a preset scene has a safety risk. Therefore, related personnel (such as security personnel) in the preset scene can take effective measures in time according to the alarm information, so that the occurrence of potential dangerous events in the preset scene is avoided, and the safety of the preset scene is ensured.

S606, the server determines that the target object is a normal object.

Optionally, after the server determines that the target object is a normal object, a normal log may be generated and stored.

For convenience of understanding, the following exemplary description is provided for a method for determining an abnormal object according to an embodiment of the present application.

For example, when the behavior parameters include the number of objects in the preset scene, distances between the target object and other objects, a residence time of the target object in a preset area of the preset scene, and a moving track of the target object, as shown in fig. 11, the method for determining an abnormal object provided in the embodiment of the present application includes: 1. and the image processing equipment reports the residence position of the object in the preset scene and the residence time of the object in each residence position. 2. And the server receives the resident positions of the objects in the preset scene and the resident time of each resident position reported by the image processing equipment. 3. The server analyzes data of the residence position of the object in the preset scene and the residence time of the object in each residence position, namely determining the residence position at the moment of a whole second. 4. And the server judges whether the image processing equipment continues to report. When the image processing device continues to report, the server may determine the number of objects in the preset scene in the behavior parameters and the distance between the target object and other objects. 5. The number of objects in the preset scene is determined. 6. Distances between the target object and other objects are determined. 7. When the image processing apparatus stops the report, the server determines that the object has left the preset area. When the server determines that the object has left the preset area, the server may determine a residence time of the target object in the preset area of the preset scene and a movement trajectory of the target object in the behavior parameters. 8. And determining the residence time of the target object in a preset area of a preset scene. 9. And determining the moving track of the target object. 10. It is determined whether the behavior parameter satisfies the monitoring rule. 11. And when the behavior parameters do not meet the monitoring rules, determining the target object as an abnormal object. 12. And when the behavior parameters meet the monitoring rules, determining the target object as a normal object.

According to the method for determining the abnormal object, the distance between the target object and other objects, the residence time of the target object in the preset area of the preset scene, the moving track of the target object and other behavior parameters can be accurately obtained according to the residence position and residence time of the target object, and the accuracy of the behavior parameters is high, so that whether the target object is the abnormal object can be accurately determined according to whether the behavior parameters meet the monitoring rule corresponding to the preset scene, and the safety risk in the preset scene is reduced. The scheme of the application can accurately conduct behavior analysis on the personnel entering the preset scene, and effectively reduces the safety risk of the preset scene.

Optionally, with reference to fig. 6, as shown in fig. 12, the method for determining an abnormal object provided in the embodiment of the present application further includes S607-S609.

S607, the server obtains the map parameters and the scene parameters corresponding to the preset scene.

Optionally, the scene parameters corresponding to the preset scene may include an actual length of the preset scene and an actual width of the preset scene.

Optionally, the map parameter corresponding to the preset scene may include a pixel value corresponding to a picture of the preset scene displayed on the map. For example, the picture of the preset scene displayed on the map may be a picture converted from a CAD map through interactive and visual design, and the picture itself has a pixel value.

And S608, the server determines the display position of the target object on the map according to the map parameter, the scene parameter and the resident position of the target object in the preset scene.

Alternatively, the display position of the target object on the map may be position coordinates of the target object on the map. And the coordinate system where the position coordinates of the target object on the map are located is a map coordinate system.

Since the coordinate system of the resident position of the target object is a world coordinate system and the coordinate system of the display position of the target object on the map is a map coordinate system, which may be different from the coordinate system (i.e., the world coordinate system) of the resident position, the server may convert the resident position of the target object into the display position of the target object on the map through the coordinate system conversion, so as to display the trajectory of the target object in the preset scene on the map. For example, the server may convert the position of the target object from a world coordinate system in which the resident position is located into a map coordinate system, and display the position of the target object after coordinate system conversion on the map.

Illustratively, the pixel value of the picture of the preset scene displayed on the map is α × β, that is, the picture of the preset scene displayed on the map includes α pixels in the direction of the x-axis in the map coordinate system, and the picture of the preset scene displayed on the map includes β pixels in the direction of the y-axis in the map coordinate system. Each pixel in the picture of the preset scene displayed on the map may correspond to one coordinate value in the map coordinate system. The origin of the world coordinate system where the target object resides is (x) ₀ ，y ₀ ) The position coordinate of the residence position in the world coordinate system is (x) ₁ ，y ₁ ). The actual length and width distances of the preset scene are L and W, that is, the actual length of the picture of the preset scene displayed on the map in the direction of the x axis in the map coordinate system is L, and the actual length of the picture of the preset scene displayed on the map in the direction of the y axis in the map coordinate system is W. The position coordinate (alpha) of the target object in the map coordinate system can be obtained according to the following formula five _x ，β _y ) Formula six.

The formula five is as follows:

formula six:

and S609, the server displays the target object on the map in a preset mode according to the display position of the target object on the map.

Optionally, after the server determines the display positions of the target objects on the map, the target objects are displayed on the preset scene picture displayed on the map according to the sequence of the residence time of the target objects corresponding to each display position, so that the track of the target objects in the preset scene can be displayed on the map.

For example, as shown in fig. 13, the picture setting of the preset scene displayed on the map may be in the fourth quadrant of the map coordinate system. According to the display position of the target object after the coordinate system conversion and the corresponding residence time of the target object at each display position, the trajectory route of the target object in the preset scene 04 is obtained as shown by a curve 07 in fig. 13, and the coordinate (x) in fig. 13 is obtained ₀ ，y ₀ ) And position coordinates in the map coordinate system representing an origin in the world coordinate system in which the dwell position is located.

The method and the device have the advantages that the resident position of the target object in the preset scene can be converted into the display position of the target object on the map, so that the target object can be displayed on the map, and further, when the target object is an abnormal object, related personnel can conveniently determine the track of the abnormal object in the preset scene, and the safety risk of the preset scene is further reduced.

The scheme provided by the embodiment of the application is mainly introduced from the perspective of a method. To implement the above functions, it includes hardware structures and/or software modules for performing the respective functions. Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed in hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

As shown in fig. 14, the present embodiment provides an apparatus 14 for determining an abnormal object of an object. The object-exception determination device 14 may include at least one processor 141, a communication link 142, a memory 143, and a communication interface 144.

In particular, processor 141 is configured to execute computer-executable instructions stored in memory 143 to implement steps or actions of the terminal.

The processor 141 may be a chip. For example, the Field Programmable Gate Array (FPGA) may be a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), a system on chip (SoC), a Central Processing Unit (CPU), a Network Processor (NP), a Digital Signal Processing (DSP), a Microcontroller (MCU), a Programmable Logic Device (PLD) or other integrated chips.

A communication line 142 for transmitting information between the processor 141 and the memory 143.

The memory 143 is used for storing and executing computer-executable instructions and is controlled by the processor 141 to execute.

Memory 143, which may be separate, is coupled to the processor via communication link 142. Memory 143 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM). It should be noted that the memory of the systems and devices described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

A communication interface 144 for communicating with other devices or a communication network. The communication network may be an ethernet, a Radio Access Network (RAN), or a Wireless Local Area Network (WLAN).

It is to be noted that the structure shown in fig. 14 does not constitute a limitation of the determination device of the abnormal object of the object, and the determination device of the abnormal object of the object may include more or less components than those shown in fig. 14, or a combination of some components, or a different arrangement of components, in addition to the components shown in fig. 14.

As shown in fig. 15, the present embodiment provides an abnormal object determination apparatus 15. The determination device 15 of the abnormal object may include an acquisition unit 151 and a determination unit 152.

The obtaining unit 151 is configured to obtain a residence position of a target object in a preset scene within a preset time period and a residence time of the target object at each residence position. For example, in conjunction with fig. 6, the obtaining unit 151 may be configured to perform S601.

The obtaining unit 151 is further configured to obtain a monitoring rule corresponding to a preset scene. For example, in conjunction with fig. 6, the obtaining unit 151 may be configured to execute S602.

And the determining unit 152 is configured to determine the behavior parameters of the target object according to the acquired residence position and residence time. For example, in connection with fig. 6, the determination unit 152 may be configured to perform step S603.

The determining unit 152 is further configured to determine that the target object is an abnormal object if the behavior parameter of the target object does not meet the monitoring rule corresponding to the preset scene. For example, in conjunction with fig. 6, the determination unit 152 may be configured to perform step S605.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In actual implementation, the obtaining unit 151 and the determining unit 152 may be implemented by the processor 141 shown in fig. 14 calling the program code in the memory 143. The specific implementation process may refer to the description of the method for determining an abnormal object shown in fig. 6 to 12, which is not described herein again.

Another embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are run on an abnormal object determination apparatus, the abnormal object determination apparatus is caused to perform the steps performed by the abnormal object determination apparatus in the method flow shown in the foregoing method embodiment.

In another embodiment of the present application, a computer program product is also provided, where the computer program product includes instructions that, when executed on an apparatus for determining an abnormal object of an object, cause the apparatus for determining an abnormal object of an object to perform the steps performed by the apparatus for determining an abnormal object of an object in the method flow shown in the above-mentioned method embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining an abnormal object, comprising:

the method comprises the steps of obtaining the residence position of a target object in a preset scene in a preset time period and the residence time of the target object in each residence position;

acquiring a monitoring rule corresponding to the preset scene, wherein the monitoring rule is used for representing the limitation of the behavior parameters of each object in the preset scene;

determining behavior parameters of the target object according to the obtained residence position and residence time, wherein the behavior parameters comprise at least one of the distance between the target object and other objects, the residence time of the target object in a preset area of the preset scene or the movement track of the target object;

and if the behavior parameters of the target object do not meet the monitoring rules corresponding to the preset scene, determining that the target object is an abnormal object.

2. The determination method according to claim 1, wherein the acquiring the dwell position of the target object in the preset scene within the preset time period and the dwell time of the target object at each dwell position comprises:

acquiring at least one identity information and the reporting time of each identity information, and the residence position and residence time matched with the same object in the preset time period; the identity information is used for identifying an object entering the preset scene;

determining target identity information, wherein the target identity information is used for representing the target object, and the target object is an object of which the resident position meets a preset condition within the target reporting time; the time difference between the target reporting time and the obtained earliest residence time is less than a preset time length;

and determining that the target object corresponds to the obtained resident position and resident time, and taking the obtained resident position and resident time as the resident position and resident time of the target object.

3. The method of claim 2, wherein the obtaining the dwell position and dwell time that match the same object comprises:

receiving a resident position and a resident time aiming at the same object from the image processing equipment in the preset time period;

or,

receiving a residence position and residence time from the image processing equipment in the preset time period; and determining the residence position and residence time corresponding to each preset moment from the acquired residence positions and residence times for the same object, and taking the determined residence positions and residence times as the residence positions and residence times matched with the same object.

4. The method according to claim 3, wherein the determining the residence position and the residence time corresponding to each preset time from the acquired residence positions and residence times includes:

if the preset time does not exist in the obtained residence time, determining a residence position corresponding to the preset time according to a residence position corresponding to the first target residence time and a residence position corresponding to the second target residence time; the first target residence time is the time which is before the preset time and is adjacent to the preset time in the obtained residence time; and the second target residence time is the time which is after the preset time and is adjacent to the preset time in the obtained residence time.

5. The determination method according to any one of claims 1-4, characterized in that the method further comprises:

acquiring map parameters and scene parameters corresponding to the preset scene;

determining the display position of the target object on the map according to the map parameters, the scene parameters and the resident position of the target object in the preset scene;

and displaying the target object on the map in a preset mode according to the display position of the target object on the map.

6. An apparatus for determining an abnormal object, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the residence position of a target object in a preset scene in a preset time period and the residence time of the target object in each residence position;

the acquiring unit is further configured to acquire a monitoring rule corresponding to the preset scene, where the monitoring rule is used to represent a limitation on a behavior parameter of each object in the preset scene;

a determining unit, configured to determine a behavior parameter of the target object according to the residence position and the residence time acquired by the acquiring unit, where the behavior parameter includes at least one of a distance between the target object and another object, a residence time of the target object in a preset region of the preset scene, or a movement trajectory of the target object;

if the behavior parameter of the target object does not meet the monitoring rule corresponding to the preset scene, the determining unit is further configured to determine that the target object is an abnormal object.

7. The determination apparatus according to claim 6, wherein the obtaining unit is specifically configured to:

the determining unit is further configured to determine target identity information, where the target identity information is used to represent the target object, and the target object is an object whose residence position meets a preset condition within a target reporting time; the time difference between the target reporting time and the obtained earliest residence time is less than a preset time length;

the determining unit is further configured to determine that the target object corresponds to both the acquired residence position and the acquired residence time, and use the acquired residence position and residence time as the residence position and residence time of the target object.

8. The apparatus according to claim 7, wherein the obtaining unit is specifically configured to:

or,

receiving a residence position and residence time from the image processing equipment in the preset time period;

the determining unit is further configured to determine, for the same object, a residence position and residence time corresponding to each preset time from the obtained residence positions and residence times, and use the determined residence positions and residence times as residence positions and residence times matched with the same object;

9. An abnormal object determination device, characterized in that the abnormal object determination device comprises a memory and a processor; the memory and the processor are coupled; the memory for storing computer program code, the computer program code comprising computer instructions; the determination device of the abnormal object performs the determination method of the abnormal object as claimed in any one of claims 1 to 5 when the processor executes the computer instructions.

10. A computer-readable storage medium having stored therein instructions that, when run on a determination device of an abnormal object, cause the determination device of the abnormal object to execute the determination method of the abnormal object according to any one of claims 1 to 5.