CN118172698A

CN118172698A - Recognition method, device, equipment and medium for monitoring sentry abnormal behavior

Info

Publication number: CN118172698A
Application number: CN202410286834.7A
Authority: CN
Inventors: 刘红正
Original assignee: Beijing Shengzhe Science & Technology Co ltd
Current assignee: Beijing Shengzhe Science & Technology Co ltd
Priority date: 2024-03-13
Filing date: 2024-03-13
Publication date: 2024-06-11

Abstract

The invention relates to the technical field of computers and discloses a method, a device, equipment and a medium for identifying abnormal behaviors of a monitor post. The method comprises the following steps: acquiring a monitoring video, and extracting a monitoring image from the monitoring video; inputting the monitoring image into a pre-trained human body attribute identification model, and acquiring attribute data corresponding to the monitoring image output by the human body attribute identification model; and generating a monitor post abnormal alarm if the abnormal behavior of the monitor post is detected according to the attribute data corresponding to the monitoring image and the target alarm rule. According to the technical scheme, the recognition of the abnormal behavior of the monitor post is carried out by combining the pre-trained human attribute recognition model and the target warning rule, so that the recognition cost of the abnormal behavior of the monitor post can be reduced, and the warning accuracy of the abnormal behavior of the monitor post can be improved.

Description

Recognition method, device, equipment and medium for monitoring sentry abnormal behavior

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for identifying abnormal behavior of a monitor post.

Background

A monitoring post, referring to a place in a certain organization, organization or work environment that is responsible for monitoring, managing or guiding work, can also be understood as a post that serves as a regulatory responsibility, which plays a vital role in social operation. Whether an abnormal situation occurs on the monitor post is a matter of life production safety.

At present, the existing recognition method of abnormal behaviors of a monitor post generally adopts a machine learning model to directly recognize the abnormal behaviors according to a field monitoring image. However, in an actual scene, various different situations exist in the monitor post, a large amount of sample data is required for model training to accurately identify different types of abnormal behaviors, the identification cost is high, and effective identification of other abnormal behaviors which randomly occur cannot be realized, so that missing report or false report of the abnormal behaviors of the monitor post is easy to cause.

Disclosure of Invention

The invention provides a method, a device, equipment and a medium for identifying abnormal behaviors of a monitor post, which can reduce the identification cost of the abnormal behaviors of the monitor post, can realize the effective identification of other abnormal behaviors which randomly occur, and can improve the alarm accuracy of the abnormal behaviors of the monitor post.

According to one aspect of the invention, there is provided a method for identifying abnormal behavior of a monitor post, comprising:

Acquiring a monitoring video, and extracting a monitoring image from the monitoring video;

Inputting the monitoring image into a pre-trained human body attribute identification model, and acquiring attribute data corresponding to the monitoring image output by the human body attribute identification model;

And generating a monitor post abnormal alarm if detecting that the monitor post abnormal behavior exists according to the attribute data corresponding to the monitoring image and the target alarm rule.

According to another aspect of the present invention, there is provided an apparatus for identifying abnormal behavior of a monitor post, comprising:

The monitoring image acquisition module is used for acquiring a monitoring video and extracting a monitoring image from the monitoring video;

The attribute data acquisition module is used for inputting the monitoring image into a pre-trained human attribute identification model and acquiring attribute data corresponding to the monitoring image output by the human attribute identification model;

And the abnormal alarm generating module is used for generating abnormal alarm of the monitor post if abnormal behavior of the monitor post is detected according to the attribute data corresponding to the monitor image and the target alarm rule.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a guard box abnormal behavior according to any of the embodiments of the present invention.

According to another aspect of the invention, there is provided a computer readable storage medium storing a computer program for causing a processor to implement the method for identifying an abnormal behavior of a guard post according to any one of the embodiments of the invention when executed.

According to the technical scheme, the monitoring video is obtained, and the monitoring image is extracted from the monitoring video; then, inputting the monitoring image into a pre-trained human body attribute identification model, and acquiring attribute data corresponding to the monitoring image output by the human body attribute identification model; finally, according to the attribute data corresponding to the monitoring image and the target alarm rule, if abnormal behavior of the monitor post is detected, abnormal alarm of the monitor post is generated; by combining the pre-trained human attribute recognition model and the target alarm rule, the abnormal behavior recognition of the monitor post is carried out together, so that the recognition cost of the abnormal behavior of the monitor post can be reduced, and the alarm accuracy of the abnormal behavior of the monitor post can be improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1A is a flow chart of a method for identifying a guard abnormal behavior according to a first embodiment of the present invention;

FIG. 1B is a schematic diagram of a rule configuration page provided according to a first embodiment of the present invention;

FIG. 1C is a schematic diagram of a detection flow of abnormal behavior of a monitor post according to a first embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a device for identifying abnormal behavior of a monitor post according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of an electronic device implementing a method for identifying a guard abnormal behavior in accordance with an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1A is a flowchart of a method for identifying abnormal behavior of a monitor post according to an embodiment of the present invention, where the method may be implemented by a device for identifying abnormal behavior of a monitor post, and the device for identifying abnormal behavior of a monitor post may be implemented in hardware and/or software, and typically the device for identifying abnormal behavior of a monitor post may be configured in an electronic device, for example, a computer device or a server. As shown in fig. 1A, the method includes:

S110, acquiring a monitoring video, and extracting a monitoring image from the monitoring video.

In this embodiment, monitoring devices, such as a camera, a network video recorder, etc., may be deployed in advance at the location of the monitor post to capture images of the monitor post and the nearby area; then, the monitoring video can be pulled or pushed based on rtsp, rtmp, onvif, 28181 and other protocols so as to acquire real-time monitoring video. Furthermore, the monitoring video can be decoded and subjected to frame-by-frame algorithm analysis so as to extract and obtain the monitoring image.

S120, inputting the monitoring image into a pre-trained human body attribute identification model, and acquiring attribute data corresponding to the monitoring image output by the human body attribute identification model.

The human body attribute recognition model can comprise a human head detection model, a human body detection model, a motion recognition model, a tracking model and the like. In this embodiment, the trained detection models of different types can be obtained directly from the network. The type of the human attribute recognition model in this embodiment may not be particularly limited.

Specifically, after each frame of monitoring image is obtained, the monitoring images can be respectively input into different types of human attribute recognition models so as to obtain various attribute data corresponding to each frame of monitoring image. Wherein the attribute data may include at least one of a head position, a head direction, a clothing color, a person posture, whether a person is of special interest, a tracking mark, and a tracking trajectory.

S130, generating a monitor post abnormal alarm if the abnormal behavior of the monitor post is detected according to the attribute data corresponding to the monitor image and the target alarm rule.

The target alarm rule may be preset rule information for judging whether the attribute data is abnormal, for example, a head position of a person exceeds a delimited area frame, a detection target does not exist in the area frame, and the person is in a doze state. Typically, the target alert rules may include determine a post rules and inspection rules; determine a post rules, which can be rule information applicable to a scene that a monitor post needs personnel to be on duty at a fixed position; the patrol rule can be rule information applicable to a scene that a supervision guard needs personnel to patrol and duty.

Specifically, after the attribute data corresponding to the monitoring image is obtained, first, logic judgment can be performed on the attribute data based on the target alarm rule to determine whether the current attribute data accords with the target alarm rule. Then, if the abnormal behavior is determined to be met, the existence of the abnormal behavior of the monitor post can be determined, and the current abnormal behavior type can be determined according to the corresponding relation between the preset target alarm rule and the abnormal behavior type, for example, the existence of off-post, the invasion of the control personnel, the existence of sleepiness, the failure of inspection post according to the regulation and the like can be further generated, so that the abnormal alarm of the monitor post can be generated for real-time alarm. The monitoring post abnormal alarm can provide detailed alarm word description including occurrence time, abnormal behavior type, target personnel characteristics and the like, and can be sent to the appointed user in a mode of short message, mail, system notification and the like.

Optionally, when generating the monitor post abnormality alarm, firstly, abnormal data corresponding to the monitor post abnormal behavior, for example, a time period corresponding to the abnormal behavior, such as off-post time period, sleepy time period, etc., can be determined; then, the monitoring image with abnormal behavior of the monitor post can be formed into a monitoring video segment; and finally, respectively filling the abnormal data, the monitoring video segment and the judgment result of the abnormal behavior of the monitor post to the corresponding positions of a preset alarm template to generate a final abnormal alarm of the monitor post.

In the embodiment, when abnormal behavior of the monitor post is detected, the alarm is triggered in real time, so that the monitoring efficiency can be improved, and the real-time performance of the abnormal behavior alarm of the monitor post can be improved.

In an optional implementation manner of this embodiment, before detecting that there is abnormal behavior of the monitor post according to the attribute data and the target alarm rule corresponding to the monitor image, the method may further include:

And responding to rule editing operation of a user in a rule configuration page, acquiring rule base setting and a rule defense arrangement plan, and generating the target alarm rule according to the rule base setting and the rule defense arrangement plan.

The target alarm rule may include determine a post rules and guard rules, the rule base setting may include at least one of a rule name, a detection target, rule content, a region box, a judgment position, a duration, and an alarm interval, and the rule guard plan may include a guard time range. The duration time is set to be 1-1800 seconds, the default value is 5 seconds, and the duration time can be divided into sedentary early warning time and off-duty early warning time for the patrol rule. Rule contents, which are condition information conforming to the rule, for example, for determine a post rules, the corresponding rule contents may be that the detection target is not in the region frame; for the inspection rule, the corresponding rule content can be that the detection targets stay at the same position or the detection targets are in a doze state, and the like.

In the embodiment, by distinguishing determine a post rules from guard rules, the system can more accurately adapt to different supervision demands; secondly, the continuous time is set, so that the system is continuously monitored within a certain time range, and the stability and the accuracy of the system are improved.

In one specific example, the rule configuration page may be as shown in FIG. 1B. The alarm rule consists of a rule base setting part and a rule defense arrangement plan part, and a user performs operations such as new creation, editing, deletion, starting and stopping of the alarm rule in the rule configuration page. It will be appreciated that a user may configure multiple alert rules simultaneously to accommodate different alert scenarios. The user may manually draw a region of the post (including a region of the range of the movement post) as a region frame, and may further select a determination position in the region frame, for example, a center point of a lower edge of the frame, and the like. The detection target may be a clothing color of a person to be monitored, for example, a red waistcoat, huang Ma a, etc. The rule defense arrangement plan is used for setting the effective time of the alarm rule, and can be in long-term effect or be set by user definition. Optionally, when detecting that the user selects the custom setting time range, the time selection option may be displayed in the page, for example, a date selection button and a time selection slider may be included, and the user may manually select the date and time when the current alarm rule is effective.

Specifically, the user may edit the alarm rule on the rule configuration page to set each data item, and click the enable button after the editing is completed, so as to make the target alarm rule effective. The client can acquire rule base settings and rule defense arrangement plans configured by the user according to page editing operation of the user, and splice configuration contents to automatically generate current target alarm rules.

In another optional implementation manner of this embodiment, according to the attribute data and the target alarm rule corresponding to the monitoring image, if the abnormal behavior of the monitor post is detected, generating the abnormal alarm of the monitor post may include:

acquiring the monitoring time corresponding to the monitoring image, and judging whether the monitoring time is in a defense deployment time range or not;

If the monitoring time is determined to be in the defense setting time range, judging whether the target person is in the area frame or not according to the head position and the head direction of the target person corresponding to the monitoring image;

If the target person is determined to be positioned in the area frame, judging whether the target person is a detection target according to the clothing color of the target person;

if the target person is determined to be a detection target, judging whether the target person accords with the rule content according to the tracking track and the person posture of the target person;

if the target person accords with the rule content, determining that abnormal monitor post behaviors exist when the duration of the target person accords with the rule content reaches the duration, and generating the abnormal monitor post alarm based on the alarm interval.

In one specific example, the detection flow of the monitor post anomaly may be as shown in FIG. 1C. Firstly, filtering a defense setting time range, and directly ending a detection flow if the monitoring time corresponding to the current monitoring image is not in the defense setting time range; if the monitoring time is determined to be within the defense setting time range, if the target person exists in the determined area frame, further judging whether the target person is a detection target to be monitored, for example, whether the target person is a red waistcoat person, a yellow waistcoat person, a key person, a white list person and the like; if yes, further judging whether the tracking track and the personnel posture of the target personnel accord with the rule content of the target alarm rule; if the rule content conforming to the target alarm rule is determined and the duration (alarm trigger time length) is satisfied, the existence of abnormal monitor post behavior can be determined, and an alarm can be performed.

Optionally, determining whether the target person accords with the rule content according to the tracking track and the person gesture of the target person may include:

Judging whether the target person is separated from the area frame according to the tracking track of the target person;

If yes, determining rule contents of the target personnel conforming to the determine a post rule; if not, determining that the target person does not accord with the rule content of the determine a post rule.

In a specific example, when the target alarm rule is determine a post rules, the rule content may be that the detection target is separated from the region frame, and the detection target is a red waistcoat person; at this time, if the clothing color of the target person is detected to be the red waistcoat, the target person can be determined to be the detection target; further, if the tracking track of the target person is detected to deviate from the region frame, the rule content conforming to the determine a post rule can be determined, so that abnormal behavior of the monitor post can be determined. Further, the monitoring time corresponding to the monitoring image can be obtained as the occurrence time of the abnormal behavior, the duration of the abnormal behavior of the monitor post can be obtained, and finally, the text description of the abnormal behavior of the monitor post can be generated based on the information to be used as the abnormal alarm of the monitor post. For example, the abnormal alarm of the monitor post corresponding to determine a post rules may be that the abnormal behavior of the monitor post occurs (2023-06-06:16:43:48), determine a post (someone with red waistcoat) is separated from the designated area frame, off-post occurs, and the duration (5 minutes) is long.

Judging whether the target person stays at the same position and is in a doze state according to the tracking track and the person posture of the target person;

If the target personnel are determined to stay at the same position and are in a doze state, determining rule contents of the target personnel conforming to the guard rule;

and if the target personnel are determined not to stay at the same position and/or not to be in a doze state, determining that the target personnel do not accord with the rule content of the guard rule.

In a specific example, when the target alert rule is a patrol rule, the supervised guard abnormal behavior may include both sedentary and off guard conditions. For sedentary conditions, if the target person is detected to stay at the same position according to the tracking track and the target person is recognized to be in a doze state according to the person posture, abnormal behavior of sedentary monitoring sentry can be determined. For example, for sedentary such a monitor post anomaly, the monitor post anomaly alert may be that "(2023-06-06 16:43:48) the monitor post anomaly occurred, the patrol post (yellow waistcoat somebody) stays longer than the set period (5 minutes), and is suspected to be dozing.

Secondly, if the off-guard condition is detected, the abnormal behavior of off-guard can be determined, and the corresponding abnormal alarm of the off-guard can be "(2023-06-0616:43:48) that the abnormal behavior of the guard occurs, and the patrol (red waistcoat someone) is off the designated area frame, and the off-guard occurs for a duration (5 minutes)".

In the embodiment, the image captured by the monitoring camera is analyzed in real time by adopting a computer vision technology and a deep learning algorithm, and human body attribute identification is performed by utilizing a machine learning model, so that the system can automatically identify and classify various behaviors, thereby rapidly finding abnormal conditions and adapting to the continuously-changing environment and the newly-appearing abnormal behaviors. And secondly, by classifying and identifying different people and analyzing various actions and behaviors of different types of people, the rapid identification of whether the person who performs the supervision task leaves the guard, sleeps, leaves the guard and the like can be realized, the real-time performance of the identification of the abnormal behavior of the supervision guard is improved, and the supervision guard can react in the shortest time. Moreover, by retaining video clips or video shots, problem backtracking and evidence retention are facilitated.

The technical scheme of the embodiment of the invention can realize automatic monitoring and management of the supervision posts, can improve the supervision efficiency and lighten the manual burden, can strengthen the safety management of important posts in social operation, and can be applied to monitoring and safety management of various places including but not limited to enterprises and public institutions, public places, transportation hubs, strict management places and the like.

Example two

Fig. 2 is a schematic structural diagram of an apparatus for identifying abnormal behavior of a monitor post according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes: a monitoring image acquisition module 210, an attribute data acquisition module 220, and an abnormal alert generation module 230; wherein,

The monitoring image acquisition module 210 is configured to acquire a monitoring video, and extract a monitoring image from the monitoring video;

The attribute data acquisition module 220 is configured to input the monitoring image to a pre-trained human attribute identification model, and acquire attribute data corresponding to the monitoring image output by the human attribute identification model;

the abnormal alarm generating module 230 is configured to generate a monitor post abnormal alarm if the abnormal behavior of the monitor post is detected according to the attribute data corresponding to the monitor image and the target alarm rule.

Optionally, the device for identifying abnormal behavior of the monitor post further comprises:

And the alarm rule generation module is used for responding to rule editing operation of a user in a rule configuration page, acquiring rule base setting and a rule defense arrangement plan, and generating the target alarm rule according to the rule base setting and the rule defense arrangement plan.

Optionally, the target alarm rule includes determine a post rules and guard rules, the rule base setting includes at least one of a rule name, a detection target, rule content, a region box, a judgment position, a duration and an alarm interval, and the rule guard scheme includes a guard time range.

Optionally, the abnormal alarm generating module 230 is specifically configured to obtain a monitoring time corresponding to the monitoring image, and determine whether the monitoring time is within a time range of the arming;

Optionally, the abnormal alarm generating module 230 is specifically configured to determine whether the target person is separated from the area frame according to the tracking track of the target person;

Optionally, the abnormal alarm generating module 230 is specifically configured to determine, according to the tracking track and the person gesture of the target person, whether the target person stays at the same position and is in a doze state;

Optionally, the attribute data includes at least one of a head position, a head direction, a clothing color, a person pose, whether a person is of particular interest, a tracking identifier, and a tracking trajectory.

The device for identifying the abnormal behavior of the monitor post provided by the embodiment of the invention can execute the method for identifying the abnormal behavior of the monitor post provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

Example III

Fig. 3 shows a schematic diagram of an electronic device 30 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 30 includes at least one processor 31, and a memory, such as a Read Only Memory (ROM) 32, a Random Access Memory (RAM) 33, etc., communicatively connected to the at least one processor 31, wherein the memory stores a computer program executable by the at least one processor, and the processor 31 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 32 or the computer program loaded from the storage unit 38 into the Random Access Memory (RAM) 33. In the RAM 33, various programs and data required for the operation of the electronic device 30 may also be stored. The processor 31, the ROM 32 and the RAM 33 are connected to each other via a bus 34. An input/output (I/O) interface 35 is also connected to bus 34.

Various components in electronic device 30 are connected to I/O interface 35, including: an input unit 36 such as a keyboard, a mouse, etc.; an output unit 37 such as various types of displays, speakers, and the like; a storage unit 38 such as a magnetic disk, an optical disk, or the like; and a communication unit 39 such as a network card, modem, wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 31 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 31 performs the various methods and processes described above, such as the identification of the guard exception behavior.

In some embodiments, the method of identifying the guard abnormal behavior may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 30 via the ROM 32 and/or the communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the method of identifying a guard exception behavior described above may be performed. Alternatively, in other embodiments, processor 31 may be configured to perform the method of identifying the guard exception behavior in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method for identifying abnormal behavior of a monitor post, comprising:

2. The method of claim 1, further comprising, prior to detecting the presence of a post anomaly based on the attribute data corresponding to the monitored image and the target alert rule:

3. The method of claim 2, wherein the target alert rules comprise determine a post rules and inspection rules, the rule base settings comprise at least one of a rule name, a detection target, a rule content, a region box, a judgment location, a duration, and an alert interval, and the rule defense deployment plan comprises a defense deployment time range.

4. The method of claim 3, wherein generating a guard post anomaly alarm if the presence of a guard post anomaly behavior is detected based on the attribute data corresponding to the monitoring image and a target alarm rule, comprises:

5. The method of claim 4, wherein determining whether the target person meets the rule content based on the tracking trajectory and person pose of the target person comprises:

6. The method of claim 4, wherein determining whether the target person meets the rule content based on the tracking trajectory and person pose of the target person comprises:

7. The method of any of claims 1-6, wherein the attribute data includes at least one of a head position, a head direction, a clothing color, a person pose, whether a person is of particular interest, a tracking identifier, and a tracking trajectory.

8. An apparatus for identifying abnormal behavior of a monitor, comprising:

9. An electronic device, the electronic device comprising:

at least one processor, and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying the guard action anomaly of any one of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores a computer program for causing a processor to execute the method for identifying the guard post abnormal behavior of any one of claims 1-7.