CN113628404A

CN113628404A - Method and device for reducing invalid alarm

Info

Publication number: CN113628404A
Application number: CN202010383960.6A
Authority: CN
Inventors: 陶冶; 汪红星
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-05-08
Filing date: 2020-05-08
Publication date: 2021-11-09
Also published as: WO2021223665A1

Abstract

A method and a device for reducing invalid alarms are applied to a security monitoring system, and the method comprises the steps of obtaining first characteristic information of a first target when a camera or a server detects that the behavior of the first target is the behavior of triggering alarms, and then matching the first characteristic information with characteristic information in an invalid alarm database. Because the invalid alarm database stores the characteristic information of the target which triggers the invalid alarm before and/or the characteristic information of the target which is easy to trigger the invalid alarm and is stored in advance, when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is higher (such as greater than or equal to a first threshold), the alarm triggered by the first target is an invalid alarm, the alarm information triggered by the first target can be filtered, namely the alarm information is not output, the probability of generating the invalid alarm is reduced, the accuracy of the alarm is improved, and therefore the user experience is improved.

Description

Method and device for reducing invalid alarm

Technical Field

The present application relates to the field of image processing, and in particular, to a method and an apparatus for reducing invalid alarms.

Background

For safety, security measures are needed for special areas, such as railways, fences of zoos or display precious goods, and the traditional security measures are mainly manual patrol. The traditional security measures have the defects of high labor cost, low security efficiency, poor environmental adaptability and the like, and more intelligent abnormal intrusion detection technologies are introduced into the special areas, for example, an alarm is triggered when abnormal intrusion behaviors are detected.

Current abnormal intrusion detection is generally based on image processing techniques. In the abnormal intrusion detection technology based on the image processing technology, at least one camera is deployed around a security area, the camera can shoot in real time, and then image recognition is carried out on pictures shot by the at least one camera. And when the moving target in the security area is identified and determined and the behavior of the target is determined to be the preset behavior for triggering the alarm, and reporting the alarm information of the target to a worker for processing.

For example, the preset behavior triggering the alarm is the wandering behavior of the person, and due to the diversity of environments in which the security area is located, plants around the security area may shake back and forth under the blowing of wind, which may be mistakenly recognized as the wandering of the person, thereby triggering the alarm. But actually, the plant does not belong to the security target of the security area, so the staff can receive invalid warning information. Meanwhile, the plants generally stay in the pictures shot by the camera for a long time, multiple alarms can be triggered, and accordingly, workers can receive multiple invalid alarm information. Therefore, in the current abnormal intrusion detection technology, the probability of generating invalid alarms is higher, and the alarm accuracy is lower.

Disclosure of Invention

The embodiment of the application provides a method and a device for reducing invalid alarms, which can reduce the probability of generating the invalid alarms, improve the alarm accuracy and improve the user experience.

In a first aspect, an embodiment of the present application provides a method for reducing invalid alarms, where the method may be implemented by a camera, or a chip system in the camera, or may also be implemented by a server, or a chip system in the server, and the method includes: the method comprises the steps of firstly obtaining first characteristic information of a first target, then matching the first characteristic information with characteristic information in an invalid alarm database, and when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is smaller than a first threshold value, not outputting alarm information.

The alarm database comprises characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering invalid alarms. The behavior of the first target is a behavior of triggering an alarm. For example, if the above method is implemented by a camera, the behavior of the first object is a behavior that triggers an alarm of the camera. For another example, if the method is implemented by a server, the behavior of the first target may be a behavior triggering a camera alarm or a behavior triggering a server alarm.

In the above technical solution, when the camera or the server detects that the behavior of the first object is a behavior triggering a warning (such as crossing a line, regional intrusion, loitering, or the like), first feature information of the first object is obtained, and then the first feature information is matched with feature information in an invalid warning database. Because the invalid alarm database stores the characteristic information of the target which triggers the invalid alarm before and/or the characteristic information of the target which is easy to trigger the invalid alarm, when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is higher (such as greater than or equal to a first threshold), the alarm triggered by the first target is an invalid alarm, the alarm information triggered by the first target can be automatically filtered, namely the alarm information is not output, so that the manual detection link is saved, the probability of generating the invalid alarm is reduced, the accuracy of the alarm is improved, and the user experience is improved.

In other words, the device (e.g., the alarm server or the cloud service platform) executing the method of the present invention receives that the camera frequently sends an alarm, but after further confirmation of the alarm platform, if the matching degree with the feature information in the invalid alarm database is high, this means that the alarm is an error alarm (false alarm) that does not need to be concerned, and therefore, the alarm platform terminates the alarm and does not really output the alarm information to the user, thereby reducing the interference of the false alarm on the user.

In a possible design of the first aspect, when a matching degree between the first feature information and feature information in the invalid alarm database is smaller than a first threshold, receiving first information from the input interface, where the first information is used to indicate whether an alarm triggered by the first target is an invalid alarm; and when the first information is used for indicating that the alarm triggered by the first target is an invalid alarm, not outputting the alarm information, and adding the first characteristic information into an invalid alarm database, otherwise, outputting the alarm information.

For example, when the matching degree between the first feature information and the feature information in the invalid alarm database is low (e.g., smaller than the first threshold), the server may display a first image including the first target, so that the staff may determine whether the alarm triggered by the first target is an invalid alarm according to the first image, and input (e.g., mouse input, keyboard input, voice input, or the like) the determination result (marked as the first information) into the input interface. When the first information is used for indicating that the alarm triggered by the first target is an effective alarm, the server outputs alarm information; when the first information is used for indicating that the alarm triggered by the first target is an invalid alarm, the server filters the alarm information triggered by the first target, namely the alarm information is not output, and the first characteristic information is added into an invalid alarm database. The matching degree between the characteristic information in the current invalid alarm database and the first characteristic information is low, but the staff determines that the alarm triggered by the first target is an invalid alarm, and the server adds the first characteristic information into the invalid alarm database, so that the diversity of samples in the invalid alarm database can be increased. When the first target triggers the alarm again, the alarm information triggered by the first target can be automatically filtered, staff do not need to check the alarm information again, the expense of manual maintenance is reduced, and the user experience is improved.

In one possible design of the first aspect, adding the first characteristic information to an invalid alarm database includes: acquiring a first image, wherein the first image comprises a first target; determining the area of the first target in the first image, and then reducing and/or enlarging the area according to different sizes to obtain at least one sub-image; extracting feature information of the first target from each sub-image in at least one sub-image to obtain at least one piece of second feature information, wherein the at least one piece of second feature information comprises first feature information; the at least one second characteristic information is then added to an invalid alert database.

In the above design, since the feature information of the first target included in the images with different sizes may be different, the area including the first target is reduced according to different reduction sizes, enlarged according to different enlargement sizes, or respectively reduced and enlarged according to different reduction sizes and different enlargement sizes to obtain at least one sub-image, and then the feature information obtained based on each sub-image in the at least one sub-image is added to the invalid alarm database, so that the feature information of the first target can be enriched, the diversity of the feature information is increased, and the accuracy of automatically judging the invalid alarm can be improved.

In one possible design of the first aspect, obtaining first characteristic information of the first target includes: receiving multimedia information from a camera; when the fact that a first moving target exists in a shooting area of the camera and the behavior of the first target is a behavior triggering an alarm is detected, a first image is obtained from the multimedia information, and feature extraction is carried out on the first target in the first image to obtain first feature information.

In the above design, the server receives multimedia information from the camera, which may be video data or a plurality of images. The server detects the multimedia information, and when detecting that a moving first target exists in the area shot by the camera and the behavior of the first target is a behavior triggering alarm (such as area intrusion, border crossing or loitering), first feature information of the first target is extracted from a first image comprising the first target. That is, the behavior of triggering the alarm is identified by the server without the need of identifying by the camera, so that the load of the camera can be reduced.

In one possible design of the first aspect, obtaining first characteristic information of the first target includes: first characteristic information is received from a camera.

In the above design, the server receives the first feature information from the camera, where the first feature information is sent after extracting the first feature information of the first target from the first image including the first target when the camera detects that there is a moving first target in the shooting area of the camera, and the behavior of the first target is a behavior that triggers an alarm. That is, the behavior of triggering the alarm is identified by the camera without sending multimedia information to the server in real time to identify the behavior of triggering the alarm, so that the load of the server can be reduced and network resources can be saved.

In a possible design of the first aspect, when the type of the alarm triggered by the first target is the first alarm type, matching the first feature information with feature information in an invalid alarm database includes: determining third characteristic information in an invalid alarm database according to the first alarm type, wherein an invalid alarm triggered by a target corresponding to the third characteristic information is an invalid alarm of the first alarm type; and matching the first characteristic information with the third characteristic information.

In the above design, since the difference between the behaviors of the targets corresponding to different alarm types is large, the difference between the feature information corresponding to different alarm types is also large. Therefore, when determining whether to filter the alarm information of the first target, the first feature information does not need to be matched with all feature information included in the invalid alarm database one by one, but only the first feature information is matched with the third feature information corresponding to the first alarm type by taking the alarm type as a reference factor, so that invalid matching can be reduced, the calculated amount is reduced, and the matching efficiency is improved.

In a second aspect, the present application provides an apparatus for reducing invalid alarms, where the apparatus may be a camera, or a chip system in the camera, or may also be a server, or a chip system in the server, and the apparatus includes a processing unit and a transceiver unit. Wherein the content of the first and second substances,

the processing unit is used for acquiring first characteristic information of a first target, and the behavior of the first target is the behavior of triggering the camera to give an alarm; matching the first characteristic information with characteristic information in an invalid alarm database, wherein the invalid alarm database comprises the characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering an invalid alarm;

and the transceiving unit is used for not outputting the alarm information when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is greater than or equal to a first threshold value.

In a possible design of the second aspect, the transceiver unit is further configured to:

when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is smaller than a first threshold value, receiving first information from an input interface, wherein the first information is used for indicating whether an alarm triggered by the first target is an invalid alarm or not;

when the first information is used for indicating that the alarm triggered by the first target is an invalid alarm, not outputting alarm information, and the processing unit is further used for adding the first characteristic information to the invalid alarm database, otherwise, the transceiver unit is used for outputting alarm information.

In a possible design of the second aspect, the processing unit is specifically configured to:

acquiring a first image, wherein the first image comprises the first target;

determining a region of the first target in the first image;

reducing and/or enlarging the area according to different sizes to obtain at least one sub-image;

extracting feature information of the first target from each sub-image of the at least one sub-image to obtain at least one second feature information, wherein the at least one second feature information comprises the first feature information;

adding the at least one second characteristic information to the invalid alarm database.

receiving multimedia information from the camera;

the processing unit is specifically configured to:

when the fact that the first target moves in the shooting area of the camera and the behavior of the first target is the behavior triggering the alarm is detected, a first image is obtained from the multimedia information, and feature extraction is conducted on the first target in the first image to obtain first feature information.

receiving the first characteristic information from the camera.

In a possible design of the second aspect, when the type of the alarm triggered by the first target is a first alarm type, the processing unit is specifically configured to:

determining third characteristic information in the invalid alarm database according to the first alarm type, wherein an invalid alarm triggered by a target corresponding to the third characteristic information is an invalid alarm of the first alarm type;

and matching the first characteristic information with the third characteristic information.

In a third aspect, an embodiment of the present application provides an apparatus for reducing invalid alarms, where the apparatus for reducing invalid alarms includes at least one processor; the at least one processor is configured to execute a computer program or instructions to cause the apparatus to perform the method described in the first aspect.

In one possible design of the third aspect, the at least one processor, when executing the computer program or instructions, performs the steps of:

acquiring first characteristic information of a first target, wherein the behavior of the first target is a behavior of triggering a camera to give an alarm;

matching the first characteristic information with characteristic information in an invalid alarm database, wherein the invalid alarm database comprises the characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering an invalid alarm;

and when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is greater than or equal to a first threshold value, not outputting alarm information.

In one possible design of the third aspect, the apparatus for reducing invalid alarms further includes a memory for storing a computer program or instructions.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program comprising program instructions that, when executed by a computer, cause the computer to perform the method of any one of the first aspect or possible designs of the first aspect.

In a fifth aspect, the present application provides a computer program product, which stores a computer program, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the method of any one of the first aspect or possible designs of the first aspect.

In a sixth aspect, the present application provides a chip system comprising a processor configured to implement the method of any one of the first aspect or possible designs of the first aspect. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

In a seventh aspect, the present application provides an alert signal processing apparatus including an interface and a processor. The interface is configured to receive first feature information sent by the camera or a first image corresponding to the first feature information, and the processor is in communication with the interface and configured to implement the method according to any one of the first aspect or possible designs of the first aspect.

Advantageous effects of the second to seventh aspects and possible implementations thereof described above reference may be made to the description of advantageous effects of the first aspect and possible implementations thereof.

Drawings

Fig. 1 is a schematic diagram illustrating an architecture of a security monitoring system applied to the embodiment of the present application;

fig. 2 is a schematic flowchart illustrating a method for reducing invalid alarms according to an embodiment of the present application;

fig. 3 is a schematic diagram of a display interface provided in an embodiment of the present application;

FIG. 4 is a flow chart illustrating another method for reducing invalid alarms according to an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram illustrating an apparatus for reducing invalid alarms according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an alarm signal processing device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

For the skilled person to understand, technical terms related to the embodiments of the present application will be described first.

(1) The security area can be an area needing security precaution, such as a railway in an unmanned area, a fence in a garden, a display cabinet in which an anti-theft object is located, and the like. If the abnormal invasion condition of a security area needs to be detected, one or more acquisition devices, such as cameras and the like, can be arranged around the security area. The acquisition range of the one or more acquisition devices may cover the security area, for example, the security area may be a part of the acquisition area covered by the one or more acquisition devices, or may also be the whole acquisition area covered by the one or more acquisition devices.

(2) The security target can refer to an object needing precaution (or needing monitoring), such as a person, an animal or a vehicle. If the security target enters the security area, an alarm can be triggered. The corresponding security targets may be different in different security scenarios. For example, the purpose of security protection of a railway in an unmanned area is mainly to avoid accidents such as sudden braking or derailment of a train caused by wandering of surrounding wild animals on the railway, and therefore security protection targets in the security protection scene can be the wild animals. For another example, the security protection purpose of an enclosure in a zoo is mainly to prevent the guest from being injured by the animal in the enclosure crossing the enclosure and entering the enclosure illegally, so that the security protection target in the security protection scene can be human and animal.

(3) In the embodiments of the present application, "a plurality" means two or more, and in view of this, the "plurality" may also be understood as "at least two". "at least one" is to be understood as meaning one or more, for example one, two or more. For example, including at least one means including one, two, or more, and does not limit which ones are included, for example, including at least one of A, B and C, then including may be A, B, C, A and B, A and C, B and C, or a and B and C. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" generally indicates that the preceding and following related objects are in an "or" relationship, unless otherwise specified.

Unless stated to the contrary, the embodiments of the present application refer to the ordinal numbers "first", "second", etc., for distinguishing between a plurality of objects, and do not limit the sequence, timing, priority, or importance of the plurality of objects.

Next, technical features according to embodiments of the present application will be described.

In the traditional security measures, a plurality of workers generally monitor a security area in a patrol mode, and the cost of manual maintenance is high. Some security scenes with harsh environmental conditions are not friendly to human health or life, so that the traditional security measures are not applicable in the security scenes, such as security scenes with high environmental temperature or security of railways in unmanned areas. With the rapid development of image processing technology, especially the development of image recognition technology, the abnormal intrusion detection technology based on the image processing technology gradually replaces the transmitted security measures due to the advantages of automation, low requirements on environmental conditions and the like.

In the current abnormal intrusion detection technology, at least one camera needs to be deployed around a security area, so that all or part of the area needing security falls into a shooting area of the at least one camera. And then, image recognition is carried out on the pictures shot by the at least one camera so as to detect whether the security area is abnormally invaded or not in real time. When a moving target in the security area is identified and the behavior of the target is a preset behavior for triggering the alarm, the alarm is triggered, and the alarm information of the target is reported to the staff for processing. The alert information may include an image of the target. After receiving the alarm information, the staff can judge whether the alarm triggered by the target is an invalid alarm according to the image. If the staff judges that the alarm triggered by the target is an invalid alarm, deleting the alarm information; and responding the alarm information if the staff judges that the alarm triggered by the target is an effective alarm.

Due to the fact that the environment of the security area is diverse, reporting of invalid alarms may be triggered. For example, the preset behavior triggering the alarm is that the person wanders, plants around the security area shake back and forth under the action of wind, and are mistakenly identified as the person wandering, so that the alarm is triggered. Meanwhile, the plants generally stay in the pictures shot by the camera for a long time, the alarm is triggered repeatedly in windy weather, and accordingly, the workers receive multiple invalid alarms, and the workers have to discriminate the alarm every time and confirm whether the alarm is a wrong alarm (the alarm caused by shaking of the plants) or a correct alarm (the alarm caused by a security target), so that the manual maintenance cost is increased, and the user experience is poor. In addition, when the targets are all in the shot pictures of the multiple cameras deployed around the security area, each camera can give an alarm to the staff independently, so that the staff can receive the invalid alarm from each camera in the multiple cameras, the staff needs to confirm and delete each invalid alarm one by one, the manual maintenance cost is increased, and the user experience is poor.

In view of this, the embodiment of the present application provides a method for reducing invalid alarms, in which feature information of a target triggering an alarm is matched with feature information in an invalid alarm database, and when a matching degree between the two is greater than or equal to a first threshold, the alarm information triggered by the target is filtered, so that overhead of manual maintenance can be reduced, and user experience is improved.

The method provided by the embodiment of the application is explained below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating a possible security monitoring system adapted to an embodiment of the present application. As shown in fig. 1, the security monitoring system 100 may include a plurality of image capturing devices 110 (2 image capturing devices are included in fig. 1) and a server 120. The image capturing device 110 is deployed around the security area, and is configured to capture a picture of the security area in real time and send the captured picture to the server 120. The server 120 is configured to receive a picture taken by the image capturing device, and identify the taken picture to determine whether to trigger an alarm. The plurality of image acquisition devices 110 may be deployed around the same security area or in different security areas, which is not limited in the embodiments of the present application.

The image capturing device 110 includes, but is not limited to, a camera, a video camera, or a smart mobile terminal (e.g., a mobile phone, a tablet computer, a laptop computer) with a camera function, and the like, and the specific implementation form of the image capturing device 110 is not limited herein. Hereinafter, the image capturing device 110 will be described as an example of the camera 110. The server 120 includes, but is not limited to, an independent server, a server cluster, or a cloud server, and the like, and the specific implementation form of the server 120 is not limited herein.

Optionally, the security monitoring system 100 may further include a display 130, and the display 130 is configured to display an image including an object triggering an alarm to the staff. The staff member can also perform input operations on the input interface (or called display interface) of the display 130, such as deleting invalid alarm information.

In one possible implementation, the server 120 includes a processor 121, and the processor 121 may identify the image to determine whether there is an abnormal intrusion into the security area. Optionally, the processor 121 may further extract feature information of an object triggering an alarm from the image. For example, the processor 121 may be implemented in one or more of the following forms: a general purpose processor, a Central Processing Unit (CPU), an Image Signal Processor (ISP), a microprocessor, a Digital Signal Processor (DSP), a field-programmable gate array (FPGA), or the like.

Illustratively, the server 120 may also include a memory 122. The Memory 122 may be a Read-Only Memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by the apparatus, but is not limited to such. The memory 122 may be a separate device and is connected to the processor 121 through a bus. The memory 122 may also be integrated with the processor 121.

The memory 122 may be configured to store an application program code for executing the scheme of the present application, and the processor 121 controls the execution, that is, the processor 121 is configured to execute the application program code stored in the memory 122 to implement the method for reducing invalid alarms in the embodiment of the present application. In some embodiments, the processor 121 may also have the capability to store code therein, which may be executed without the aid of the memory 122.

In another possible implementation, the camera 110 may recognize the captured image to determine whether to send the warning message to the server 120. In this embodiment, the camera 110 may include the aforementioned processor 120, and optionally, the camera 110 may further include the aforementioned memory 122. For a detailed implementation of the processor 121 and the memory 122, please refer to the foregoing description, which is not repeated herein.

The embodiment of the application can be applied to scenes and the like needing security protection, such as an indoor video monitoring scene, an outdoor video monitoring scene, a night video monitoring scene or a security protection monitoring scene, or can be applied to a common image shooting scene and the like, which are not exemplified herein. A method for reducing invalid alarms according to an embodiment of the present application is described below with reference to the security monitoring system 100 shown in fig. 1. Referring to fig. 2, fig. 2 is a flow chart of the method.

S201: the server 120 receives the multimedia information from the camera 110.

The camera 110 captures a picture in its shooting area to obtain multimedia information, and transmits the multimedia information to the server 120. The server 120 receives multimedia information. The multimedia information may be video data, for example, the video camera 110 compresses the pictures taken by the video camera within a set time period into video data in h.264/h.265 format, and then transmits the video data to the server 120. Alternatively, the multimedia information may be image data, for example, the camera 110 extracts a plurality of images from a picture taken by the camera 110 within a set time period, compresses the plurality of images into image data in JPEG format, and transmits the image data to the server 120. In addition, a part or all of the shooting area of the camera 110 is a security area. For example, all areas in a room in an indoor monitoring scene are security areas, and the camera 110 needs to be deployed in the room, so that the shooting area of the camera 110 is all or part of the area in the room, that is, all the areas in the shooting area of the camera 110 are security areas. For another example, an enclosure of the campus in the campus monitoring scene is a security area, and the camera 110 needs to be deployed around the enclosure, so that a part of the image in the shooting area of the camera 110 is an image of the enclosure, that is, a part of the image in the shooting area of the camera 110 is a security area.

S202: the server 120 detects the media information, and if it is detected that a moving first target exists in the shooting area of the camera 110 and the behavior of the first target is a behavior triggering an alarm, S203 is performed, otherwise, S201 is performed.

For example, after the server 120 receives the multimedia information from the camera 110, the multimedia information needs to be detected to determine whether there is an abnormal intrusion in the shooting area of the camera 110. Specifically, the server 120 may first determine whether a moving object (the detected moving object is referred to as a first object) exists in the shooting area according to the multimedia information, and then determine whether the behavior of the first object is a behavior for triggering an alarm. For example, if the multimedia information is video data, the server 120 may decompress the video data and extract at least one image from the decompressed video data, and then detect the at least one image through a moving object detection method to determine whether a moving first object exists in the photographing region. For another example, if the multimedia information is image data, the server 120 may decompress the image data to obtain at least one image, and then detect the at least one image through a moving object detection method to determine whether a moving first object exists in the photographing region. The moving target detection method is a target detection method, and a machine learning algorithm can be adopted.

If the server 120 determines that there is no moving object in the photographing region, the server 120 performs the step of S201 of receiving multimedia information for the next set time period. If the server 120 determines that there is a moving first object within the photographing region, the server 120 needs to determine whether the behavior of the first object is a behavior that triggers an alarm. Alternatively, the server 120 may determine whether the behavior of the first target is the behavior that triggers an alarm through an alarm recognition model. For example, the server 120 may extract first feature information of a first object from an image including the first object, and input the first feature information into an alarm recognition model to obtain a recognition result. For another example, the server 120 may reduce the area of the image where the first target is located according to different reduction sizes, enlarge the area of the image according to different enlargement sizes, or respectively reduce and enlarge the area of the image according to different reduction sizes and different enlargement sizes to obtain at least one sub-image, extract the feature information of the first target from each sub-image in the at least one sub-image to obtain at least one piece of second feature information, and then input the at least one piece of second feature information into the alarm recognition model to obtain the recognition result. If the recognition result is greater than or equal to a preset second threshold, the server 120 determines that the behavior of the first target is the behavior of triggering the alarm, otherwise, the behavior of the first target is not the behavior of triggering the alarm. The behavior for triggering the alarm may be a behavior preset according to different security scenes, for example, a behavior for triggering the alarm when a wild animal wanders on a railway in an unmanned area, a behavior for triggering the alarm when a person turns over a wall in security in a campus area, and the like. The alarm recognition model is obtained by performing model training on feature information corresponding to a preset alarm triggering behavior by the server 120, and the corresponding model training process may refer to the prior art, which is not limited in the embodiment of the present application.

The method for extracting feature information of an object from an image may include, but is not limited to, a feature extraction method based on Histogram of Oriented Gradient (HOG), a feature extraction method based on Local Binary Pattern (LBP), a feature extraction method based on Deep Neural Network (DNN), a feature extraction method based on Convolutional Neural Network (CNN), and the like.

It should be understood that there may be multiple moving objects within the capture area. When a plurality of moving objects exist in the shooting area, the server 120 may determine, one by one, whether the behavior of each of the plurality of running objects is a behavior that triggers an alarm through the alarm recognition model. If the behavior of one of the plurality of running targets is a behavior that triggers an alarm, the server 120 performs S203. The following description will be given taking as an example a first object, which is a first moving object, in the shooting area.

If the server 120 determines that the behavior of the first target is not the behavior of triggering the alarm, the server 120 performs the step S201 of receiving the multimedia information within the next set duration. If the server 120 determines that the behavior of the first object is the behavior of triggering the alarm, the server 120 performs S203, i.e., acquires a first image including the first object.

It should be noted that the abnormal intrusion detection in step S202 may be implemented by using the method of performing moving object detection first and then performing object behavior identification, or may be implemented by using the prior art, which is not limited in this embodiment of the present application.

S203: the server 120 obtains a first image from the multimedia information, the first image including a first target.

The multimedia message may include a plurality of images, each of the plurality of images including the first target, and the server 120 may select one of the plurality of images as the first image. For example, the server 120 may select, as the first image, an image with the most characteristic information of the first target in the plurality of images, or select, as the first image, an image with the earliest shooting time in the plurality of images, or select, as the first image, an image with the highest resolution in the plurality of images, and the like, which is not limited in this embodiment of the application.

S204: the server 120 performs feature extraction on the first target in the first image to obtain first feature information.

In one possible implementation, if the server 120 has already extracted the feature information of the first target in step S202, the server 120 may not perform step S204, that is, the feature information extracted by the server 120 in step S202 may be used as the first feature information, and the amount of calculation may be reduced. Otherwise, the server 120 extracts the first feature information of the first object from the first image. It should be understood that the server 120 may perform step S204 even if the server 120 has extracted the feature information of the first object in step S202. For example, the server 120 may extract feature information of the first target according to the HOG-based feature extraction method in step S202, and the server 120 may extract feature information of the first target according to the CNN-based feature extraction method in step S204.

In another possible embodiment, the server 120 may determine an area of the first object in the first image, reduce, enlarge, or reduce and enlarge the area according to different sizes to obtain at least one sub-image, and then extract feature information of the first object from each of the at least one sub-image to obtain at least one second feature information, where the at least one second feature information may include the first feature information. Since the feature information of the first target included in the images with different sizes may be different, at least one sub-image is obtained by reducing the area including the first target with different reduction sizes, enlarging the area including the first target with different enlargement sizes, or respectively reducing and enlarging the area including the first target with different reduction sizes and different enlargement sizes, and then the feature information of the first target is extracted from each sub-image in the at least one sub-image, so that the feature information of the first target can be enriched, and the diversity of the feature information is increased.

S205: the server 120 matches the first characteristic information with characteristic information in an invalid alarm database. If the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is greater than or equal to a first threshold value, executing S206; if the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is less than the first threshold, S207 is executed.

The invalid alarm database stores the characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering the invalid alarm. For example, the feature information in the invalid alarm database may include feature information of an object which is easy to trigger an invalid alarm and is acquired in advance according to a security scene, or the feature information in the invalid alarm database may include feature information of an object which historically triggers an invalid alarm, or the feature information in the invalid alarm database includes feature information of an object which is easy to trigger an invalid alarm and feature information of an object which historically triggers an invalid alarm and is acquired in advance according to a security scene. Optionally, the invalid alarm database may further include at least one of information such as an alarm type, a security target, a security area, or an Identity (ID) of a camera. Wherein, the alarm types may include, but are not limited to, a human border crossing behavior, a human loitering behavior, a human wall turning behavior, an animal border crossing behavior, or a vehicle border crossing behavior. Optionally, the feature information of a target in the invalid alarm database may be obtained by performing feature extraction on sub-images obtained by performing reduction, or amplification, or reduction and amplification of different sizes on an area in an image where the target is located, so as to increase diversity of the feature information in the invalid alarm database, and a specific extraction process may refer to the foregoing description and is not described herein again.

The server 120 may match the first characteristic information with characteristic information in an invalid alarm database, or match at least one second characteristic information with characteristic information in an invalid alarm database, to determine whether the behavior of the first target is a behavior that triggers an invalid alarm. Taking the example of matching the first feature information with the feature information in the invalid alarm database, the server 120 may match the first feature information with all the feature information in the invalid alarm database one by one, so that although the accuracy of the matching result may be ensured, when there is more feature information in the invalid alarm database, the calculation amount of the server 120 may be greatly increased. Optionally, the server 120 may match the alarm type, the security area, the security scene, or the like as consideration factors to eliminate part of invalid matches, reduce the amount of calculation, and improve the matching efficiency. For example, the type of the alarm triggered by the first target is a first alarm type (e.g., a human wall-turning behavior), the server 120 may obtain third feature information from an invalid alarm database according to the first alarm type, where the invalid alarm triggered by the target with fine and smooth third features is an invalid alarm of the first alarm type, and then match the first feature information with the third feature information.

When the server 120 determines that the matching degree between the first feature information and one feature information in the invalid alarm data is greater than or equal to the first threshold, the server 120 may determine that the alarm triggered by the first target is an invalid alarm, that is, execute step S206; or when the server 120 determines that the average matching degree between the first feature information and the set number (e.g., 3) of feature information in the invalid alarm data is greater than or equal to the first threshold, the server 120 may determine that the alarm triggered by the first target is an invalid alarm, i.e., execute step S206. When the server 120 determines that the matching degree between the first feature information and any feature information in the invalid warning data is smaller than the first threshold, the server 120 may send the first image to the display 130 for displaying, that is, execute step S207.

S206: the server 120 determines that the alarm triggered by the first target is an invalid alarm and does not output alarm information.

Since the invalid alarm database stores the characteristic information of the object that previously triggered the invalid alarm and/or the characteristic information of the object that easily triggered the invalid alarm, when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is high (e.g., greater than or equal to the first threshold), it indicates that the alarm triggered by the first object is an invalid alarm. Therefore, the alarm information triggered by the first target can be automatically filtered, namely the alarm information is not output, so that the manual detection link is saved, the manual maintenance overhead is reduced, and the working efficiency and the user experience of the alarm process can be improved.

S207: server 120 sends the first image to display 130 for display.

When the matching degree between the first feature information and the feature information in the invalid alarm database is low (e.g., smaller than a first threshold), the server 120 sends the first image to the display 130 for displaying, and the display 130 displays the first image in a display interface (or referred to as an input interface), so that the worker can determine whether the alarm triggered by the first target is an invalid alarm according to the first image. In order to improve the efficiency of the warning process, the server 120 may send the first image to the display 130 for display, and may also remind the staff to determine the first image displayed on the current display interface in a manner of voice, warning light, animation, or the like.

For example, fig. 3 is a schematic diagram of a display interface, and as shown in fig. 3, the display interface 300 may include a first image 310, an invalid alarm option 320, an valid alarm option 330, a second information area 340, and the like. Wherein the first image 310 includes a first object 311. Alternatively, the area of the first object 311 in the first image 310 may be specified in the form of a focus frame. The second information area 340 is used for displaying second information, where the second information is used for assisting a worker to determine whether an alarm triggered by the first target in the first image is an invalid alarm, and the second information may include, but is not limited to, an ID of a camera, address information of a security area, an alarm type or time, and the like. It should be understood that the position of each option in the display interface shown in fig. 3 is only an example, and the embodiment of the present application does not limit this. For example, the second information area 340 is located to the left of the first image 310 in fig. 3, but in practice the second information area 340 may be located above, below, to the left of, etc. the first image 310. When the worker determines that the alarm triggered by the first target is a valid alarm, the worker may select the valid alarm option 330 through an input method such as a keyboard input, a mouse input, or a voice input, so as to perform step 210. When the staff determines that the alarm triggered by the first target is an invalid alarm, the staff may select the invalid alarm option 320 through an input manner such as a keyboard input, a mouse input, or a voice input, so as to execute the content executed in step S209.

S208: the server 120 receives first information from the touch screen display 130 indicating whether the alarm triggered by the first target is an invalid alarm.

Of course, the first information may come from other input devices such as a keyboard and a mouse, besides the display 130.

For example, the first information may be information triggered by the invalid alert option 320 or information triggered by the valid alert option 330. When the first information is the information triggered by the invalid alarm option 320, the first information is used to indicate that the alarm triggered by the first target is an invalid alarm. When the first information is the information triggered by the valid alarm option 330, the first information is used to indicate that the alarm triggered by the first target is a valid alarm.

S209: when the first information indicates that the alarm triggered by the first target is an invalid alarm, the server 120 does not output the alarm information and adds the first feature information to an invalid alarm database.

When the first information indicates that the alarm triggered by the first target is an invalid alarm, the server 120 filters the alarm information of the first target, namely, the alarm information is not output, and meanwhile, the server 120 can also add the first characteristic information to an invalid alarm database, so that repeated alarms triggered by the first target can be filtered, a manual detection link is omitted, the cost of manual maintenance can be reduced, and the user embodiment is improved.

Optionally, if in step S202 or step S204, the server 120 obtains at least one second feature information of the first target, in step S209, the server 120 may add the at least one second feature information to the invalid alarm database to enrich the feature information of the first target and increase the diversity of the invalid alarm database, so as to improve the accuracy of determining the invalid alarm. If the server 120 does not obtain the at least one second feature information of the first object in step S202 or step S204, in step S209, the server 120 may reduce, enlarge, or reduce and enlarge the area of the first object in the first image according to different sizes to obtain at least one sub-image, obtain the at least one second feature information of the first object from each sub-image in the at least one sub-image, and then add the at least one second feature information to the invalid alarm database to enrich the feature information of the first object and increase the diversity of the invalid alarm database, so as to improve the accuracy of determining the invalid alarm.

S210: when the first information indicates that the alarm triggered by the first target is a valid alarm, the server 120 outputs alarm information.

When the first information indicates that the alarm triggered by the first target is an invalid alarm, the server 120 outputs alarm information. The form, content, form, content and the like of the alarm information output in different security scenes may be different, and the way of dealing with the alarm information may also be different. For example, when it is determined that an animal loiters on a railway in an unmanned area, the warning information may include, but is not limited to, a warning type, location information triggering a warning, a warning level, a number of security targets or security targets, and the like, and the server 120 may send the warning information to a train located at a set distance from the warning location while outputting the warning information, so as to prompt the train to decelerate in advance, whistle, or the like. The alarm level is used for indicating the emergency degree corresponding to the alarm triggered by the target, and in general, the higher the alarm level is, the higher the emergency degree is. For another example, when it is determined that a person enters a security area by way of a border crossing, the alarm information may include, but is not limited to, an alarm type, location information triggering an alarm, an alarm level, and the like, and while the server 120 outputs the alarm information, the server may perform voice alarm through a speaker near the alarm location, or notify related security personnel to perform manual alarm.

In the above embodiment of the present application, the server 120 receives the multimedia information from the camera 110, where the multimedia information may be video data or a plurality of images. The server 120 detects the multimedia information, and when it is detected that a moving first object exists in the shooting area of the camera 110 and the behavior of the first object is a behavior triggering an alarm (such as area intrusion, border crossing, or loitering), first feature information of the first object is extracted from the first image including the first object, that is, the behavior triggering the alarm is identified by the server 120 without the camera 110, so that the calculation amount of the camera 110 can be reduced. Further, the server 120 matches the first characteristic information with characteristic information in an invalid alarm database. When the matching degree between the two is high (for example, greater than or equal to the first threshold), it indicates that the alarm triggered by the first target is an invalid alarm, and the server 120 may automatically filter the alarm information triggered by the first target, that is, not output the alarm information, thereby saving a manual detection link, reducing the overhead of manual maintenance, and improving the working efficiency of the alarm process and the user experience. When the matching degree between the two is low (e.g., smaller than the first threshold), the server 120 may display the first image including the first target, so that the staff member determines whether the alarm triggered by the first target is an invalid alarm according to the first image. When the staff judges that the alarm triggered by the first target is an invalid alarm according to the first image, the server 120 does not output alarm information, and simultaneously adds the first characteristic information to an invalid alarm database to increase the diversity of samples in the invalid alarm database. When the first target triggers the alarm again, the server 120 may automatically filter the alarm information triggered by the first target without the need of the staff to check again, which may reduce the probability of generating an invalid alarm and improve the accuracy of the alarm, thereby improving the user experience.

In the embodiments provided in the present application, in order to implement the functions in the methods provided in the embodiments of the present application, the server 120 may include a hardware structure and/or a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether any of the above-described functions is implemented as a hardware structure, a software module, or a hardware structure plus a software module depends upon the particular application and design constraints imposed on the technical solution.

Another method for reducing invalid alarms according to the embodiment of the present application is described below with reference to the security monitoring system 100 shown in fig. 1. Referring to fig. 4, fig. 4 is a flowchart illustrating another method for reducing invalid alarms according to an embodiment of the present application.

S401: the server 120 receives an alert request from the camera 110, the alert request including the first image and the first feature information.

The first image comprises a first target, the behavior of the first target is the behavior of triggering an alarm, and the first characteristic information is the characteristic information of the first target.

The camera 110 photographs a picture in its photographing area while detecting the picture in its photographing area to determine whether a moving object (the detected moving object is referred to herein as a first object) exists in its photographing area, and the behavior of the first object is a behavior that triggers an alarm. Specifically, the camera 110 may extract at least one image from the shooting picture of the set duration, and detect the at least one image by a moving object detection method to determine whether a moving first object exists in the shooting area. Wherein, part or all of the shooting areas of the camera 110 are security areas. For example, all areas in a room in an indoor monitoring scene are security areas, and the camera 110 needs to be deployed in the room, so that the shooting area of the camera 110 is all or part of the area in the room, that is, all the areas in the shooting area of the camera 110 are security areas. For another example, an enclosure of the campus in the campus monitoring scene is a security area, and the camera 110 needs to be deployed around the enclosure, so that a part of the image in the shooting area of the camera 110 is an image of the enclosure, that is, a part of the image in the shooting area of the camera 110 is a security area. The moving target detection method is a target detection method, and a machine learning algorithm can be adopted.

When the camera 110 detects that there is a moving first object in its shooting area, the camera 110 determines again whether the behavior of the first object is a behavior that triggers an alarm. Alternatively, the camera 110 may determine whether the behavior of the first target is the behavior that triggers an alert through an alert recognition model. For example, the camera 110 may extract first feature information of a first target from an image including the first target, and input the first feature information into an alarm recognition model to obtain a recognition result. For another example, the camera 100 may reduce the area of the image where the first target is located according to different reduction sizes, enlarge the area according to different enlargement sizes, or respectively reduce and enlarge the area according to different reduction sizes and different enlargement sizes to obtain at least one sub-image, extract the feature information of the first target from each sub-image in the at least one sub-image to obtain at least one piece of second feature information, and then input the at least one piece of second feature information into the alarm recognition model to obtain the recognition result. If the recognition result is greater than or equal to a preset second threshold, the camera 110 determines that the behavior of the first target is a behavior of triggering an alarm, otherwise, the behavior of the first target is not a behavior of triggering an alarm. The behavior for triggering the alarm may be a behavior preset according to different security scenes, for example, a behavior for triggering the alarm when a wild animal wanders on a railway in an unmanned area, a behavior for triggering the alarm when a person turns over a wall in security in a campus area, and the like. The alarm recognition model is obtained by performing model training on feature information corresponding to a preset alarm triggering behavior by the camera 110, and the corresponding model training process may refer to the prior art, which is not limited in the embodiment of the present application.

When the camera 110 detects that there is a moving first object in its shooting area and the behavior of the first object triggers the behavior of the alarm, the camera 110 may send first characteristic information of the first object or at least one second characteristic information of the first object to the server 120. The server 120 receives the first characteristic information or the at least one second characteristic information. Optionally, the camera 110 may also send a first image including the first target to the server 120. For example, the camera 110 may select an image with the most characteristic information of the first target in the plurality of images as the first image to be sent to the server 120, select an image with the earliest shooting time in the plurality of images as the first image to be sent to the server 120, select an image with the highest resolution in the plurality of images as the first image to be sent to the server 120, and the like, which is not limited in the embodiment of the present application.

S402: the server 120 matches the first characteristic information with characteristic information in an invalid alarm database. If the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is greater than or equal to a first threshold value, executing S403; if the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is less than the first threshold, S404 is executed.

The invalid alarm database stores the characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering the invalid alarm. For example, the feature information in the invalid alarm database may include feature information of an object which is easy to trigger an invalid alarm and is acquired in advance according to a security scene, or the feature information in the invalid alarm database may include feature information of an object which historically triggers an invalid alarm, or the feature information in the invalid alarm database includes feature information of an object which is easy to trigger an invalid alarm and feature information of an object which historically triggers an invalid alarm and is acquired in advance according to a security scene. Optionally, the invalid alarm database may further include at least one of information such as an alarm type, a security target, a security area, or an identity of a camera. Wherein, the alarm types may include, but are not limited to, a human border crossing behavior, a human loitering behavior, a human wall turning behavior, an animal border crossing behavior, or a vehicle border crossing behavior. Optionally, the feature information of a target in the invalid alarm database may be obtained by performing feature extraction on sub-images obtained by performing reduction, or amplification, or reduction and amplification of different sizes on an area in an image where the target is located, so as to increase diversity of the feature information in the invalid alarm database, and a specific extraction process may refer to the foregoing description and is not described herein again.

When the server 120 determines that the matching degree between the first feature information and one feature information in the invalid alarm data is greater than or equal to the first threshold, the server 120 may determine that the alarm triggered by the first target is an invalid alarm, that is, execute step S403; or when the server 120 determines that the average matching degree between the first feature information and the set number (e.g., 3) of feature information in the invalid alarm data is greater than or equal to the first threshold, the server 120 may determine that the alarm triggered by the first target is an invalid alarm, i.e., execute step S403. When the server 120 determines that the matching degree between the first feature information and any feature information in the invalid warning data is smaller than the first threshold, the server 120 may send the first image to the display 130 for displaying, that is, execute step S404.

S403: the server 120 determines that the alarm triggered by the first target is an invalid alarm and does not output alarm information. This step may also be understood as terminating the alarm request issued by the camera.

Since the invalid alarm database stores the characteristic information of the object that previously triggered the invalid alarm and/or the characteristic information of the object that easily triggered the invalid alarm, when the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is high (e.g., greater than or equal to the first threshold), it indicates that the alarm triggered by the first object is an invalid alarm. Therefore, the warning request sent by the camera can be automatically filtered, and the warning information is not output, so that the manual detection link is saved, the manual maintenance overhead is reduced, and the working efficiency and the user experience of the warning process can be improved.

S404: server 120 sends the first image to display 130 for display.

When the matching degree between the first feature information and the feature information in the invalid alarm database is low (e.g., smaller than a first threshold), the server 120 sends the first image to the display 130 for displaying, and the display 130 displays the first image in a display interface (or referred to as an input interface), so that the worker can determine whether the alarm triggered by the first target is an invalid alarm according to the first image. In order to improve the efficiency of the warning process, the server 120 may send the first image to the display 130 for display, and may also remind the staff to determine the first image displayed on the current display interface in a manner of voice, warning light, animation, or the like. The display interface can be seen in fig. 3, and is not described in detail here.

S405: the server 120 receives first information from the touch screen display 130 indicating whether the alarm triggered by the first target is an invalid alarm.

S406: when the first information indicates that the alarm triggered by the first target is an invalid alarm, the server 120 does not output the alarm information and adds the first feature information to an invalid alarm database.

When the first information indicates that the alarm triggered by the first target is an invalid alarm, the server 120 filters the alarm request from the camera, does not output the alarm information, and meanwhile, the server 120 can also add the first characteristic information to an invalid alarm database, so that repeated alarms triggered by the first target can be filtered, a manual detection link is omitted, the cost of manual maintenance can be reduced, and the user embodiment is improved.

Optionally, if in step S401, the server 120 obtains at least one second feature information of the first target, in step S406, the server 120 may add the at least one second feature information to the invalid alarm database to enrich the feature information of the first target and increase the diversity of the invalid alarm database, so as to improve the accuracy of determining the invalid alarm. If the server 120 does not obtain the at least one second feature information of the first object in step S401, in step S406, the server 120 may reduce, enlarge, or reduce and enlarge the region of the first object in the first image according to different sizes to obtain at least one sub-image, obtain the feature information of the first object from each sub-image in the at least one sub-image to obtain the at least one second feature information, and then add the at least one second feature information to the invalid alarm database to enrich the feature information of the first object and increase the diversity of the invalid alarm database, so that the accuracy of determining the invalid alarm may be improved.

S407: when the first information indicates that the alarm triggered by the first target is a valid alarm, the server 120 outputs alarm information.

In the above embodiment of the present application, the server 120 receives the first feature information from the camera 110, where the first feature information is sent after extracting the first feature information of the first object from the first image including the first object when the camera 110 detects that there is a moving first object in its shooting area, and the behavior of the first object is a behavior that triggers an alarm. That is, the behavior of triggering the alarm is identified by the camera 110 without transmitting multimedia information to the server 120 in real time to identify the behavior of triggering the alarm, so that the load of the server 120 can be reduced and network resources can be saved.

Based on the same technical concept, the embodiment of the application also provides a device for reducing invalid alarms.

Fig. 5 shows a schematic diagram of an apparatus 500 for reducing invalid alarms. The apparatus 500 for reducing invalid alarms may be used to implement the functions of the server 120 in the embodiment shown in fig. 2 or fig. 4, that is, the functions of the server 120 in the embodiment shown in fig. 1. The means for reducing invalid alarms 500 may be a hardware structure, a software module, or a hardware structure plus a software module. The means 500 for reducing invalid alarms may be implemented by a chip or a system of chips. In the embodiment of the present application, the chip system may be composed of a chip, and may also include a chip and other discrete devices.

The apparatus 500 for reducing invalid alarms may comprise a processing unit 501 and a transceiving unit 502.

Among other things, the processing unit 501 may perform steps S202 to S206, S209, and S210 in the embodiment shown in fig. 2, and/or other processes for supporting the techniques described herein. In one possible implementation, the processing unit 501 may be used to communicate with the receiving unit 502, or the processing unit 501 may communicate with other modules of the security system 100, which may be circuits, devices, interfaces, buses, software modules, transceivers, or any other devices that can implement communication. Receiving unit 502 may perform steps S201, S207, and S208 in the embodiment shown in fig. 2, and/or other processes for supporting the techniques described herein. In one possible implementation, the receiving unit 502 may be used to communicate with the processing unit 501, or may communicate with other modules of the security system 100, which may be circuits, devices, interfaces, buses, software modules, transceivers, or any other devices that can implement communication.

Alternatively, processing unit 501 may perform, among other things, steps S402, S403, S406, and S407 in the embodiment shown in fig. 4, and/or other processes for supporting the techniques described herein. In one possible implementation, the processing unit 501 may be used to communicate with the receiving unit 502, or the processing unit 501 may communicate with other modules of the security system 100, which may be circuits, devices, interfaces, buses, software modules, transceivers, or any other devices that can implement communication. The receiving unit 502 may perform step S401, step S404, and step S407 in the embodiment shown in fig. 4, and/or other processes for supporting the techniques described herein. In one possible implementation, the receiving unit 502 may be used to communicate with the processing unit 501, or may communicate with other modules of the security system 100, which may be circuits, devices, interfaces, buses, software modules, transceivers, or any other devices that can implement communication.

All relevant contents of each step related to the above method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again.

The division of the modules in the embodiment shown in fig. 5 is schematic, and only one logical function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, may also exist alone physically, or may be integrated in one module by two or more modules. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

Fig. 6 illustrates an alarm signal processing device 600 according to an embodiment of the present application, where the alarm signal processing device 600 may be used to implement the functions of the server 120 in the embodiments illustrated in fig. 2 and/or fig. 4. The processor 601 in the alarm signal processing device 600 may be a chip or a chip system. In the embodiment of the present application, the chip system may be composed of a chip, and may also include a chip and other discrete devices. The alarm signal processing device 600 is, for example, a stand-alone server, a calculator, a server cluster, a cloud server.

The alert signal processing apparatus 600 comprises at least one processor 601 for implementing or for the alert signal processing apparatus 600 to implement the functions of the server 120 in the embodiments shown in fig. 2 and/or fig. 4. Illustratively, the processor 601 may obtain first characteristic information of a first target, the behavior of the first target being a behavior of triggering a camera alarm; matching the first characteristic information with characteristic information in an invalid alarm database, wherein the invalid alarm database comprises the characteristic information of at least one target, and the behavior of each target in the at least one target is the behavior of triggering an invalid alarm; and if the matching degree between the first characteristic information and the characteristic information in the invalid alarm database is greater than or equal to a first threshold value, not outputting the alarm information. For details, reference is made to the detailed description in the method example, which is not repeated herein.

The alert signal processing apparatus 600 may also include at least one memory 602 for storing program instructions and/or data. The memory 602 is coupled to the processor 601. The coupling in the embodiments of the present application is an indirect coupling or a communication connection between devices, units or modules, and may be an electrical, mechanical or other form for information interaction between the devices, units or modules. The processor 601 may cooperate with the memory 602. Processor 601 may execute program instructions stored in memory 602. At least one of the at least one memory may be included in the processor. The memory 602 may be integrated within the processor 601.

The alert signal processing apparatus 600 may also include an interface 603 for communicating with the processor 601 or for communicating with other devices over a transmission medium so that the alert signal processing apparatus 600 may communicate with other devices. Illustratively, the other device may be a computing module. The processor 601 may send and receive data using the interface 603, for example, receive multimedia information sent by a camera or an alarm request, where the alarm request includes the first feature information and a first image corresponding to the first feature information.

The embodiment of the present application does not limit the specific connection medium among the interface 603, the processor 601, and the memory 602. In the embodiment of the present application, the memory 602, the processor 601 and the interface 603 are connected by the bus 604 in fig. 6, the bus is represented by a thick line in fig. 6, and the connection manner between other components is merely illustrative and not limited thereto. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.

In the embodiments of the present application, the processor 601 may be a general-purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor.

In the embodiment of the present application, the memory 602 may be a nonvolatile memory, such as a Hard Disk Drive (HDD) or a solid-state drive (SSD), and may also be a volatile memory, such as a Random Access Memory (RAM). The memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 602 in the embodiments of the present application may also be circuitry or any other device capable of performing a storage function for storing program instructions and/or data.

Also provided in embodiments of the present application is a computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the method performed by the server 120 in the embodiments shown in fig. 2 and/or fig. 4.

The embodiment of the present application provides a chip system, which includes a processor and may further include a memory, and is used to implement the function of the server 120 in the foregoing method. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

The embodiment of the present application provides an apparatus for reducing invalid alarms, and the apparatus includes the server 120 in the embodiment shown in fig. 2 and/or fig. 4.

The method provided by the embodiment of the present application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a network appliance, a user device, or other programmable apparatus. The computer instructions may be stored in, or transmitted from, a computer-readable storage medium to another computer-readable storage medium, e.g., from one website, computer, server, or data center, over a wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), for short) or wireless (e.g., infrared, wireless, microwave, etc.) network, the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more integrated servers, data centers, etc., the available medium may be magnetic medium (e.g., floppy disk, hard disk, magnetic tape), optical medium (e.g., digital video disc (digital video disc, DVD for short), or a semiconductor medium (e.g., SSD).

Claims

1. A method for reducing invalid alarms, comprising:

2. The method of claim 1, wherein the method further comprises:

and when the first information is used for indicating that the alarm triggered by the first target is an invalid alarm, not outputting alarm information, and adding the first characteristic information into the invalid alarm database, otherwise, outputting the alarm information.

3. The method of claim 2, wherein adding the first characteristic information to the invalid alert database comprises:

acquiring a first image, wherein the first image comprises the first target;

determining a region of the first target in the first image;

4. The method according to any one of claims 1 to 3, wherein the obtaining of the first characteristic information of the first target comprises:

receiving multimedia information from the camera;

5. The method of any one of claims 1 to 3, wherein the obtaining of the first characteristic information of the first target comprises:

receiving the first characteristic information from the camera.

6. The method according to any one of claims 1 to 5, wherein when the type of the alarm triggered by the first target is a first alarm type, matching the first feature information with feature information in an invalid alarm database comprises:

7. An apparatus for reducing invalid alarms, comprising:

8. The apparatus of claim 7, wherein the transceiver unit is further configured to:

9. The apparatus as claimed in claim 8, wherein said processing unit is specifically configured to:

acquiring a first image, wherein the first image comprises the first target;

determining a region of the first target in the first image;

10. The apparatus of any of claims 7-9, wherein the transceiver unit is further configured to:

receiving multimedia information from the camera;

the processing unit is specifically configured to:

11. The apparatus of any of claims 7-9, wherein the transceiver unit is further configured to:

receiving the first characteristic information from the camera.

12. The apparatus according to any one of claims 7 to 11, wherein when the type of the alarm triggered by the first target is a first alarm type, the processing unit is specifically configured to:

13. A computer-readable storage medium, having stored thereon a computer program or instructions, which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 6.

14. An alarm signal processing device characterized by comprising:

the interface is used for receiving first characteristic information sent by the camera or a first image corresponding to the first characteristic information;

a processor, in communication with the interface, for performing the method of any of claims 1 to 6.