CN116343420A - Alarm processing method and device, storage medium and electronic device - Google Patents

Abstract

The application discloses an alarm processing method, an alarm processing device, a storage medium and an electronic device, and relates to the technical field of intelligent home/intelligent families, wherein the alarm processing method comprises the following steps: acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object; judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment. The method and the device can carry out alarm reminding aiming at the behavior of a certain target monitoring object, avoid generalization of alarm reminding and improve experience and satisfaction of users in the using process.

Description

Alarm processing method and device, storage medium and electronic device

Technical Field

The application relates to the technical field of smart home, in particular to an alarm processing method, an alarm processing device, a storage medium and an electronic device.

Background

With the popularization of intelligent monitoring devices and the importance of users on security, more and more families are configured with intelligent monitoring devices indoors and outdoors.

As known from the related art, the intelligent monitoring device has a video review or real-time review function, and in the aspect of alarm notification, although the mobile detection and alarm capabilities already exist, the alarm notification is still in a generalized stage, and an alarm prompt can be sent only by a person or an object to move, so that the intelligent monitoring device has no pertinence, and the experience of a user in the use process is poor. Currently, finding a method for carrying out alarm reminding aiming at the behavior of a certain target individual becomes a research hotspot.

Disclosure of Invention

The application provides an alarm processing method, an alarm processing device, a storage medium and an electronic device, which realize that a first alarm prompt is generated under the condition that a target monitoring object is monitored in a monitoring video segment, so that the alarm prompt can be carried out aiming at the behavior of a certain target monitoring object, the generalization of the alarm prompt is avoided, and the experience and satisfaction of a user in the use process are improved.

The application provides an alarm processing method, which comprises the following steps: acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object; judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

According to the alarm processing method provided by the application, after the first alarm reminder is generated, the alarm processing method further comprises the following steps: extracting a target monitoring video sub-segment from the monitoring video segment, wherein the target monitoring video sub-segment is a video segment containing the target monitoring object; performing voice extraction on the target monitoring video sub-segment to obtain a voice segment corresponding to the target monitoring video sub-segment; performing voice recognition on the voice fragments to obtain text fragments corresponding to the voice fragments; and generating a second alarm prompt under the condition that the text segment contains the target vocabulary, wherein the second alarm prompt is used for prompting a user that the target monitoring object generates a first preset behavior.

According to the alarm processing method provided by the application, after the target monitoring video sub-segment is extracted from the monitoring video segment, the alarm processing method further comprises the following steps: judging whether a second preset behavior occurs to the target monitoring object or not based on the target monitoring video sub-segment; and generating a third alarm prompt under the condition that the second preset behavior of the target monitoring object occurs, wherein the third alarm prompt is used for prompting a user that the second preset behavior of the target monitoring object occurs.

According to the alarm processing method provided by the application, after the third alarm reminder is generated, the alarm processing method further includes: establishing connection with a first preset platform, and reporting a video clip corresponding to a first target scene to the first preset platform, wherein the first target scene is a scene of the target monitoring object in which the second preset behavior occurs, and the first preset platform is a platform for processing the second preset behavior.

According to the alarm processing method provided by the application, after the monitoring video clip is acquired, the alarm processing method further comprises the following steps: extracting a monitoring video sub-segment from the monitoring video segment, wherein each video frame in the monitoring video sub-segment comprises the monitoring object; judging whether the monitored object is one of a pre-marked monitored object set or not based on the biological characteristics of the monitored object of the monitored video sub-segment; and generating a fourth alarm prompt under the condition that the judgment result is negative, wherein the fourth alarm prompt is used for prompting a user that the monitoring video segment comprises a strange object, and the strange object is other objects except the pre-marked monitoring object set.

According to the alarm processing method provided by the application, after the monitoring video clip is acquired, the alarm processing method further comprises the following steps: judging whether a preset event occurs in a monitoring scene corresponding to the monitoring video segment based on the monitoring video segment; and generating a fifth alarm reminding under the condition that the monitoring scene has a preset event, wherein the fifth alarm reminding is used for reminding a user that the monitoring scene has the preset event.

According to the alarm processing method provided by the application, after the fifth alarm reminder is generated, the alarm processing method further includes: establishing connection with a second preset platform, and reporting video clips corresponding to a second target scene to the second preset platform, wherein the second target scene is a scene of the monitoring scene where the preset event occurs, and the second preset platform is a platform for processing the preset event.

According to the alarm processing method provided by the application, the biological characteristics comprise image characteristics, and the determination that the monitored object is the target monitored object is realized in the following manner: acquiring a monitoring video frame image comprising a monitoring object based on the monitoring video segment; determining image characteristics of the monitoring object based on the monitoring video frame image; acquiring a preset target monitoring object image feature library, wherein the target monitoring object image feature library comprises target image features of each target monitoring object; comparing the image features with the target image features, and determining the monitoring object as the target monitoring object when the target image features matched with the image features exist.

According to the alarm processing method provided by the application, the biological characteristics comprise voiceprint characteristics, and the determination that the monitored object is the target monitored object is realized in the following manner: based on the monitoring video segment, acquiring continuous multi-frame monitoring video frames comprising a monitoring object; extracting voiceprint features corresponding to the monitored object based on the continuous multi-frame monitored video frames; acquiring a preset target monitoring object voiceprint feature library, wherein the target monitoring object voiceprint feature library comprises target voiceprint features of each target monitoring object; comparing the voiceprint features with the target voiceprint features, and determining that the monitored object is the target monitored object when the target voiceprint features matched with the voiceprint features exist.

The application also provides an alarm processing device, which comprises: the first module is used for acquiring a monitoring video clip, wherein the monitoring video clip at least comprises a monitoring object; the second module is used for judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and the third module is used for generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

The present application also provides an electronic device comprising a memory in which a computer program is stored and a processor arranged to implement an alarm processing method as described in any of the above by execution of the computer program.

The present application also provides a computer-readable storage medium including a stored program, wherein the program when run performs a method of implementing any one of the alarm processing methods described above.

The present application also provides a computer program product comprising a computer program which when executed by a processor implements a method of alarm processing as described in any of the above.

According to the alarm processing method, the device, the storage medium and the electronic device, whether the monitored object is the target monitored object is judged through the monitoring video segment, and the first alarm reminding is generated under the condition that the monitored object is the target monitored object, so that the alarm reminding can be carried out aiming at the behavior of a certain target monitored object, the generalization of the alarm reminding is avoided, and the experience and the satisfaction of a user in the using process are improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a schematic diagram of a hardware environment of an alarm processing method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of an alarm processing method provided in the present application;

FIG. 3 is a second flow chart of the alarm processing method provided in the present application;

FIG. 4 is a third flow chart of the alarm processing method provided in the present application;

FIG. 5 is a flow chart of an alarm processing method provided in the present application;

FIG. 6 is a fifth flow chart of the alarm processing method provided in the present application;

FIG. 7 is a flowchart of an alarm processing method provided in the present application;

FIG. 8 is a flow chart of an alarm processing method provided in the present application;

FIG. 9 is a schematic diagram of the structure of the alarm processing device provided in the present application;

fig. 10 is a schematic structural diagram of an electronic device provided in the present application.

Detailed Description

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and 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 embodiments of the present application 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.

According to one aspect of the embodiment of the application, the alarm processing method is widely applied to full-house intelligent digital control application scenes such as Smart Home (Smart Home), intelligent Home equipment ecology, intelligent Home (Intelligence House) ecology and the like. Alternatively, in the present embodiment, the above-described alarm processing method may be applied to a hardware environment constituted by the terminal device 102 and the server 104 as shown in fig. 1. As shown in fig. 1, the server 104 is connected to the terminal device 102 through a network, and may be used to provide services (such as application services and the like) for a terminal or a client installed on the terminal, a database may be set on the server or independent of the server, for providing data storage services for the server 104, and cloud computing and/or edge computing services may be configured on the server or independent of the server, for providing data computing services for the server 104.

The network may include, but is not limited to, at least one of: wired network, wireless network. The wired network may include, but is not limited to, at least one of: a wide area network, a metropolitan area network, a local area network, and the wireless network may include, but is not limited to, at least one of: WIFI (Wireless Fidelity ), bluetooth. The terminal device 102 may not be limited to a PC, a mobile phone, a tablet computer, an intelligent air conditioner, an intelligent smoke machine, an intelligent refrigerator, an intelligent oven, an intelligent cooking range, an intelligent washing machine, an intelligent water heater, an intelligent washing device, an intelligent dish washer, an intelligent projection device, an intelligent television, an intelligent clothes hanger, an intelligent curtain, an intelligent video, an intelligent socket, an intelligent sound box, an intelligent fresh air device, an intelligent kitchen and toilet device, an intelligent bathroom device, an intelligent sweeping robot, an intelligent window cleaning robot, an intelligent mopping robot, an intelligent air purifying device, an intelligent steam box, an intelligent microwave oven, an intelligent kitchen appliance, an intelligent purifier, an intelligent water dispenser, an intelligent door lock, and the like.

In yet another embodiment, the alarm processing method provided by the application can be applied to an image pickup device in an intelligent household appliance. The intelligent household appliance is a household appliance product formed by introducing a microprocessor, a sensor technology and a network communication technology into household appliances, has the functions of automatically sensing the space state of a house, the state of the household appliance and the service state of the household appliance, and can automatically control and receive control instructions of a house user in the house or remotely. It is understood that the smart home appliance is an integral part of the smart home.

The alarm processing method provided by the application can be applied to a cloud processing system, wherein the cloud processing system can be connected with monitoring equipment, and can acquire monitoring video clips collected by the monitoring equipment. The monitoring equipment can be an independent monitoring camera or a monitoring module arranged on other intelligent household equipment. The alarm processing method provided by the application can distinguish and mark different target monitoring objects, for example, the alarm processing method can be a preset family member including old people, children or caretakers and the like. By the method and the device, misjudgment and harassment brought to the user by non-targeted identification and frequent alarm can be avoided, alarm reminding can be realized aiming at the behavior of a certain target monitoring object, generalization of alarm reminding is avoided, and experience and satisfaction of the user in the use process are improved.

In order to further describe the alarm processing method provided in the present application, the following description will be made with reference to fig. 2.

Fig. 2 is a schematic flow chart of an alarm processing method provided in the present application.

In an exemplary embodiment of the present application, as can be seen in connection with fig. 2, the alarm processing method may include steps 210 to 230, and each step will be described below.

In step 210, a surveillance video clip is obtained, where the surveillance video clip includes at least a surveillance object.

In one embodiment, a surveillance video clip may be acquired. The monitoring video clips can be acquired by monitoring equipment, wherein the monitoring equipment can be an independent monitoring camera or a monitoring module arranged on other intelligent household equipment. In the application process, at least the monitoring object can be included in the monitoring video segment. Wherein the monitored object may be a person appearing in the monitored video clip.

In step 220, it is determined whether the monitored object is a target monitored object based on the biological characteristics of the monitored object in the monitored video clip.

In step 230, a first alert is generated when the monitored object is a target monitored object, where the first alert is used to prompt the user to monitor the video clip for the presence of the target monitored object.

In one embodiment, whether the monitored object is a target monitored object may be determined based on the biological characteristics of the monitored object in the monitored video clip. And generating a first alarm reminder under the condition that the monitoring object is a target monitoring object. By the method and the device, the alarm reminding is carried out aiming at the behavior of a certain target monitoring object, and generalization of the alarm reminding is avoided.

In an exemplary embodiment of the present application, the biometric feature may include an image feature, and the monitoring object may be determined as the target monitoring object in the following manner:

acquiring a monitoring video frame image comprising a monitoring object based on the monitoring video segment;

determining image characteristics of a monitoring object based on the monitoring video frame image;

acquiring a preset target monitoring object image feature library, wherein the target monitoring object image feature library comprises target image features of each target monitoring object;

comparing the image features with the target image features, and determining the monitoring object as the target monitoring object when the target image features matched with the image features exist.

In one embodiment, a surveillance video frame image may be extracted from a surveillance video clip, where the surveillance video frame image may be understood as an image corresponding to each frame of video frame that forms a surveillance video band. The monitoring video frame image comprises a monitoring object. Further, the image characteristics of the monitoring object can be determined based on the monitoring video frame image. In the application process, a target monitoring object image feature library can be preset, wherein the target monitoring object image feature library can be composed of target image features of all target monitoring objects. In an example, the image features are compared with each target image feature one by one, and when there is a match between the image features and the target image features, the monitoring object can be determined to be the target monitoring object.

In an exemplary embodiment of the present application, the biometric feature may include a voiceprint feature, and the monitoring object may be determined to be the target monitoring object in the following manner:

based on the monitoring video segment, acquiring continuous multi-frame monitoring video frames comprising a monitoring object;

extracting voiceprint features corresponding to the monitored object based on the continuous multi-frame monitored video frames;

acquiring a preset target monitoring object voiceprint feature library, wherein the target monitoring object voiceprint feature library comprises target voiceprint features of each target monitoring object;

and comparing the voiceprint characteristics with each target voiceprint characteristic, and determining the monitoring object as a target monitoring object when the target voiceprint characteristics matched with the voiceprint characteristics exist.

In one embodiment, consecutive multi-frame surveillance video frames comprising a surveillance object may be extracted from a surveillance video clip, where a surveillance video frame may be understood as each frame of video frame that constitutes a surveillance video band. Further, voiceprint features corresponding to the monitored object may be extracted based on consecutive multi-frame monitored video frames. In the application process, a target monitoring target voiceprint feature library can be preset, wherein the target monitoring target voiceprint feature library can be composed of target voiceprint features of all target monitoring targets. In an example, the voiceprint features are compared with each target voiceprint feature one by one, and when there is a match between the voiceprint features and the target voiceprint features, the monitored object can be determined to be the target monitored object.

According to the alarm processing method, whether the monitored object is the target monitored object is judged through the monitoring video segment, and the first alarm reminding is generated under the condition that the monitored object is the target monitored object, so that the alarm reminding can be carried out aiming at the behavior of a certain target monitored object, the generalization of the alarm reminding is avoided, and the experience and satisfaction of a user in the using process are improved.

FIG. 3 is a second flow chart of the alarm processing method provided in the present application.

In order to further describe the alarm processing method provided in the present application, the following description will be made with reference to fig. 3.

In an exemplary embodiment of the present application, as can be seen in fig. 3, the alarm processing method may include steps 310 to 370, wherein steps 310 to 330 are the same as or similar to steps 210 to 230, and the detailed description and the beneficial effects thereof are referred to above, and in this embodiment, the details are not repeated, and steps 340 to 370 will be respectively described below.

In step 340, a target surveillance video sub-segment is extracted from the surveillance video segment, where the target surveillance video sub-segment is a video segment containing a target surveillance object.

In step 350, the target surveillance video sub-segment is extracted by voice, so as to obtain a voice segment corresponding to the target surveillance video sub-segment.

In step 360, the speech segment is subjected to speech recognition, and a text segment corresponding to the speech segment is obtained.

In one embodiment, the target surveillance video sub-segment may be subjected to voice extraction to obtain a voice segment, where the voice segment is voice information about the target surveillance video sub-segment. In the application process, a specific method of voice extraction is not limited. Further, the speech segments may be speech recognized to obtain text segments corresponding to the audio segments. The text segment may be understood as a text corresponding to the words that the target monitoring object speaks in the target monitoring video sub-segment.

In step 370, a second alert reminder is generated when it is detected that the text segment includes the target vocabulary, where the second alert reminder is used to prompt the user that the target monitored object has the first preset behavior.

In one embodiment, when it is detected that the target vocabulary exists in the text segment, the target monitoring object may be considered to have a first preset behavior that needs to be monitored and alerted. The target vocabulary may correspond to the first preset behavior, in this embodiment, the target vocabulary may be adjusted according to an actual situation, and the first preset behavior may also be adjusted according to an actual situation, in this embodiment, the target vocabulary and the first preset behavior are not specifically limited.

In yet another example, the target vocabulary may be an abusive vocabulary and the first predetermined behavior may be a behavior of an abusive other person. In the embodiment, the target monitoring object can be accurately marked by combining face recognition and voiceprint recognition, further, by setting target words, such as target words possibly triggering dangerous scenes, such as abuse, calling for help and the like, in the application process, the text segments are obtained by carrying out voice recognition on the voice segments corresponding to the target monitoring video sub-segments, and the warning prompt is generated under the condition that the text segments are monitored to contain the target words, so that generalization of the warning prompt can be avoided, and experience and satisfaction of users in the use process are improved.

FIG. 4 is a third flow chart of the alarm processing method provided in the present application.

The procedure of another alarm processing method provided in the present application will be described with reference to fig. 4.

In an exemplary embodiment of the present application, as can be seen in fig. 4, the alarm processing method may include steps 410 to 460, wherein steps 410 to 440 are the same as or similar to steps 310 to 340, and the detailed description and the beneficial effects thereof are referred to above, and in this embodiment, the details are not repeated, and steps 450 and 460 will be respectively described below.

In step 450, it is determined whether the second preset behavior occurs in the target monitoring object based on the target monitoring video sub-segment.

In step 460, a third alert reminder is generated in case the second preset behavior occurs in the target monitoring object, where the third alert reminder is used to prompt the user that the second preset behavior occurs in the target monitoring object.

In one embodiment, behavior information of a target monitored object is extracted and analyzed based on a target detection video sub-segment. Further, when the behavior of the target monitoring object is monitored to be the second preset behavior, a third alarm prompt can be generated, wherein the third alarm prompt is used for prompting the user that the target monitoring object generates the second preset behavior. It should be noted that, the second preset behavior may be adjusted according to actual situations, for example, falling, getting a person, climbing, etc., and in this embodiment, the second preset behavior is not specifically limited.

FIG. 5 is a flow chart of an alarm processing method provided in the present application.

In an exemplary embodiment of the present application, as can be seen in fig. 5, the alarm processing method may further include steps 510 to 570, wherein steps 510 to 560 are the same as or similar to steps 410 to 460, and the detailed description and the beneficial effects thereof may be referred to the foregoing description, which is omitted in this embodiment, and the step 570 will be described below.

In step 570, a connection is established with a first preset platform, and a video clip corresponding to a first target scene is reported to the first preset platform, where the first target scene is a scene where the target monitoring object generates the second preset behavior.

In one embodiment, a connection may be established with a first preset platform, and a video clip corresponding to a first target scene may be reported to the first preset platform. The first preset platform may be a platform for processing the second preset behavior. The first preset platform can be a platform for restraining a scene with second preset behaviors, and can correspond to the second preset behaviors, wherein the first preset platform is a platform for supervising the second preset behaviors. In an example, the first preset platform may be a supervision department, the second preset behavior may be a behavior of typing, and when the target monitoring individual is monitored to generate the behavior of typing, a video clip corresponding to a scene where the target monitoring object generates the second preset behavior (behavior of typing) may be reported to the supervision department to alarm and be used as relevant evidence of the alarm. By the embodiment, the scene generated in the monitoring video clip can be intelligently monitored and related alarms can be carried out, so that the experience and satisfaction of a user in the using process can be improved.

Fig. 6 is a flowchart of an alarm processing method provided in the present application.

In an exemplary embodiment of the present application, as can be seen in fig. 6, the alarm processing method may further include steps 610 to 640, wherein step 610 is the same as or similar to step 210, and the detailed description and the beneficial effects thereof are as follows, and in this embodiment, steps 620 to 640 will be described separately.

In step 620, a surveillance video sub-segment is extracted from the surveillance video segment, where each video frame in the surveillance video sub-segment includes a surveillance object.

In step 630, it is determined whether the monitored object is one of a pre-labeled set of monitored objects based on the biological characteristics of the monitored object of the monitored video sub-segment.

In step 640, if the determination result is no, a fourth alert is generated, where the fourth alert is used to prompt the user to monitor that the video clip includes a strange object, and the strange object is another object except for the pre-marked monitoring object set.

In one embodiment, the monitoring video sub-segment is extracted from the monitoring video segment, so that the monitoring object can be obtained quickly and accurately, and a foundation is laid for further quickly and accurately judging whether the monitoring object is one of the pre-marked monitoring object sets.

In an example, a fourth alert reminder may be generated when it is detected that the monitored object is not one of the pre-labeled set of monitored objects, such that the user may be prompted to include a strange object in the monitored video clip. Furthermore, the user can make role type labeling on the strange object, so that the behavior information of the strange object can be monitored in a targeted manner.

It should be noted that the pre-labeled monitoring object set may include a plurality of target monitoring objects. In an example, the pre-labeled collection of monitoring objects may also include a plurality of monitoring objects that the user wants to focus on, e.g., may be a plurality of family members.

The pre-marked monitoring object set is a monitoring object or family member which is marked by image recognition or voiceprint recognition and is focused by a user. The manner of the pre-marking may also be other manners, and is not particularly limited in this embodiment.

Fig. 7 is a flowchart illustrating a method of alarm processing provided in the present application.

In an exemplary embodiment of the present application, as can be seen in fig. 7, the alarm processing method may include steps 710 to 730, wherein step 710 is the same as or similar to step 210, and the detailed description and the beneficial effects thereof are described above, and in this embodiment, step 720 and step 730 will be described below.

In step 720, based on the monitoring video clip, determining whether a preset event occurs in a monitoring scene corresponding to the monitoring video clip;

in step 730, a fifth alert reminder is generated in the event of the monitoring scenario having the preset event, where the fifth alert reminder is used to prompt the user for the monitoring scenario having the preset event.

In one embodiment, when it is determined that the preset event occurs in the monitoring scene corresponding to the monitoring video segment, a fifth alert may be generated to prompt the user that the preset event occurs in the monitoring scene. The preset event may be adjusted according to the actual situation, for example, a fire event may occur, and in this embodiment, the preset event is not specifically limited.

Fig. 8 is a flow chart of an alarm processing method provided in the present application.

In an exemplary embodiment of the present application, as can be seen in fig. 8, the alarm processing method may include steps 810 to 840, wherein steps 810 to 830 are the same as or similar to steps 710 to 730, and the detailed description and the beneficial effects are shown in the foregoing, which are not repeated in this embodiment, and the step 840 will be described below.

In step 840, a connection is established with a second preset platform, and a video clip corresponding to a second target scene is reported to the second preset platform, where the second target scene is a scene where a preset event occurs in the monitoring scene.

In one embodiment, a connection may be established with a second preset platform, and a video clip corresponding to the second target scene may be reported to the second preset platform, where the second preset platform may be a platform for processing a preset event. The second preset platform can process and solve the scene with the preset event, and can correspond to the preset event, wherein the second preset platform is a platform for solving the preset event. In an example, the second preset platform may be a fire department, the preset event may be an event of a fire, when a fire event is detected, a connection may be established with the fire department and an alarm may be given, and further, a video clip corresponding to the fire event may be uploaded to the second preset platform. By the embodiment, the events occurring in the monitoring video clips can be intelligently monitored and correlated, so that the experience and satisfaction of users in the using process can be improved.

According to the foregoing description, the alarm processing method provided by the application judges whether the monitored object is the target monitored object or not through the monitoring video segment, and generates the first alarm reminding only when the monitored object is the target monitored object, so that the alarm reminding can be carried out on the behavior of a certain target monitored object, the generalization of the alarm reminding is avoided, and the experience and satisfaction of a user in the using process are improved.

The alarm processing device provided in the present application is described below, and the alarm processing device described below and the alarm processing method described above may be referred to correspondingly to each other.

Fig. 9 is a schematic structural diagram of an alarm processing device provided in the present application.

In an exemplary embodiment of the present application, as can be seen in connection with fig. 9, the alarm processing device may include a first module 910 to a third module 930, and each module will be described below.

A first module 910, configured to obtain a surveillance video segment, where the surveillance video segment includes at least a surveillance object;

a second module 920, configured to determine whether the monitored object is a target monitored object based on the biological characteristics of the monitored object in the monitored video clip;

the third module 930 may be configured to generate a first alert reminder for prompting the user to present the target monitoring object to the monitoring video clip if the monitoring object is the target monitoring object.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

extracting a target monitoring video sub-segment from the monitoring video segment, wherein the target monitoring video sub-segment is a video segment containing a target monitoring object;

Performing voice extraction on the target monitoring video sub-segment to obtain a voice segment corresponding to the target monitoring video sub-segment;

performing voice recognition on the voice fragments to obtain text fragments corresponding to the voice fragments;

and generating a second alarm prompt under the condition that the text segment contains the target vocabulary, wherein the second alarm prompt is used for prompting the user that the target monitoring object has a first preset behavior.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

judging whether a second preset behavior occurs to the target monitoring object or not based on the target monitoring video sub-segment;

and generating a third alarm prompt under the condition that the target monitoring object has the second preset behavior, wherein the third alarm prompt is used for prompting the user that the target monitoring object has the second preset behavior.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

establishing connection with a first preset platform, and reporting a video clip corresponding to a first target scene to the first preset platform, wherein the first target scene is a scene of a target monitoring object with second preset behaviors, and the first preset platform is a platform for processing the second preset behaviors.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

extracting a monitoring video sub-segment from the monitoring video segment, wherein each video frame in the monitoring video sub-segment comprises a monitoring object;

judging whether the monitored object is one of a pre-marked monitored object set or not based on the biological characteristics of the monitored object of the monitored video sub-segment;

and generating a fourth alarm prompt under the condition that the judgment result is negative, wherein the fourth alarm prompt is used for prompting a user to monitor strange objects in the video clip, and the strange objects are other objects except the pre-marked monitoring object set.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

judging whether a preset event occurs in a monitoring scene corresponding to the monitoring video clip or not based on the monitoring video clip;

and generating a fifth alarm reminding under the condition that the monitoring scene has the preset event, wherein the fifth alarm reminding is used for reminding a user of the preset event of the monitoring scene.

In an exemplary embodiment of the present application, the third module 930 may be further configured to:

and establishing connection with a second preset platform, and reporting video clips corresponding to a second target scene to the second preset platform, wherein the second target scene is a scene of the monitoring scene, in which the preset event occurs, and the second preset platform is a platform for processing the preset event.

In an exemplary embodiment of the present application, the biometric feature includes an image feature, and the second module 920 may implement determining the monitoring object as the target monitoring object in the following manner:

acquiring a monitoring video frame image comprising a monitoring object based on the monitoring video segment;

determining image characteristics of a monitoring object based on the monitoring video frame image;

acquiring a preset target monitoring object image feature library, wherein the target monitoring object image feature library comprises target image features of each target monitoring object;

comparing the image features with the target image features, and determining the monitoring object as the target monitoring object when the target image features matched with the image features exist.

In an exemplary embodiment of the present application, the biometric feature includes a voiceprint feature, and the second module 920 may implement determining the monitoring object as the target monitoring object in the following manner:

based on the monitoring video segment, acquiring continuous multi-frame monitoring video frames comprising a monitoring object;

extracting voiceprint features corresponding to the monitored object based on the continuous multi-frame monitored video frames;

acquiring a preset target monitoring object voiceprint feature library, wherein the target monitoring object voiceprint feature library comprises target voiceprint features of each target monitoring object;

And comparing the voiceprint characteristics with each target voiceprint characteristic, and determining the monitoring object as a target monitoring object when the target voiceprint characteristics matched with the voiceprint characteristics exist.

Fig. 10 illustrates a physical schematic diagram of an electronic device, as shown in fig. 10, which may include: a processor 1010, a communication interface (Communications Interface) 1020, a memory 1030, and a communication bus 1040, wherein the processor 1010, the communication interface 1020, and the memory 1030 communicate with each other via the communication bus 1040. Processor 1010 may invoke logic instructions in memory 1030 to perform an alarm processing method comprising: acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object; judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

Further, the logic instructions in the memory 1030 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In another aspect, the present application further provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a computer readable storage medium, where the computer program, when executed by a processor, can perform the alarm processing method provided by the above methods, and the method includes: acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object; judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

In still another aspect, the present application further provides a computer readable storage medium, where the computer readable storage medium includes a stored program, where the program executes an alarm processing method provided by the above methods, and the method includes: acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object; judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment; and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims (12)

1. An alarm processing method, characterized in that the alarm processing method comprises:

acquiring a monitoring video segment, wherein the monitoring video segment at least comprises a monitoring object;

judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment;

and generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

2. The alert processing method of claim 1, wherein after the generating the first alert reminder, the alert processing method further comprises:

Extracting a target monitoring video sub-segment from the monitoring video segment, wherein the target monitoring video sub-segment is a video segment containing the target monitoring object;

performing voice extraction on the target monitoring video sub-segment to obtain a voice segment corresponding to the target monitoring video sub-segment;

performing voice recognition on the voice fragments to obtain text fragments corresponding to the voice fragments;

and generating a second alarm prompt under the condition that the text segment contains the target vocabulary, wherein the second alarm prompt is used for prompting a user that the target monitoring object generates a first preset behavior.

3. The alert processing method according to claim 2, wherein after the extracting the target surveillance video sub-segment from the surveillance video segment, the alert processing method further comprises:

judging whether a second preset behavior occurs to the target monitoring object or not based on the target monitoring video sub-segment;

and generating a third alarm prompt under the condition that the second preset behavior of the target monitoring object occurs, wherein the third alarm prompt is used for prompting a user that the second preset behavior of the target monitoring object occurs.

4. The alert processing method of claim 3, wherein after the generating the third alert reminder, the alert processing method further comprises:

establishing connection with a first preset platform, and reporting a video clip corresponding to a first target scene to the first preset platform, wherein the first target scene is a scene of the target monitoring object in which the second preset behavior occurs, and the first preset platform is a platform for processing the second preset behavior.

5. The alert processing method according to claim 1, wherein after the acquisition of the monitoring video clip, the alert processing method further comprises:

extracting a monitoring video sub-segment from the monitoring video segment, wherein each video frame in the monitoring video sub-segment comprises the monitoring object;

judging whether the monitored object is one of a pre-marked monitored object set or not based on the biological characteristics of the monitored object of the monitored video sub-segment;

and generating a fourth alarm prompt under the condition that the judgment result is negative, wherein the fourth alarm prompt is used for prompting a user that the monitoring video segment comprises a strange object, and the strange object is other objects except the pre-marked monitoring object set.

6. The alert processing method according to claim 1, wherein after the acquisition of the monitoring video clip, the alert processing method further comprises:

judging whether a preset event occurs in a monitoring scene corresponding to the monitoring video segment based on the monitoring video segment;

and generating a fifth alarm reminding under the condition that the monitoring scene has a preset event, wherein the fifth alarm reminding is used for reminding a user that the monitoring scene has the preset event.

7. The alert processing method according to claim 6, wherein after the generating the fifth alert reminder, the alert processing method further comprises:

establishing connection with a second preset platform, and reporting video clips corresponding to a second target scene to the second preset platform, wherein the second target scene is a scene of the monitoring scene where the preset event occurs, and the second preset platform is a platform for processing the preset event.

8. The alert processing method according to claim 1, wherein the biometric feature comprises an image feature, and determining that the monitored object is the target monitored object is implemented by:

Acquiring a monitoring video frame image comprising a monitoring object based on the monitoring video segment;

determining image characteristics of the monitoring object based on the monitoring video frame image;

acquiring a preset target monitoring object image feature library, wherein the target monitoring object image feature library comprises target image features of each target monitoring object;

comparing the image features with the target image features, and determining the monitoring object as the target monitoring object when the target image features matched with the image features exist.

9. The alert processing method according to claim 1, wherein the biometric feature comprises a voiceprint feature, and determining that the monitored object is the target monitored object is implemented by:

based on the monitoring video segment, acquiring continuous multi-frame monitoring video frames comprising a monitoring object;

extracting voiceprint features corresponding to the monitored object based on the continuous multi-frame monitored video frames;

acquiring a preset target monitoring object voiceprint feature library, wherein the target monitoring object voiceprint feature library comprises target voiceprint features of each target monitoring object;

Comparing the voiceprint features with the target voiceprint features, and determining that the monitored object is the target monitored object when the target voiceprint features matched with the voiceprint features exist.

10. An alarm processing apparatus, characterized in that the alarm processing apparatus comprises:

the first module is used for acquiring a monitoring video clip, wherein the monitoring video clip at least comprises a monitoring object;

the second module is used for judging whether the monitoring object is a target monitoring object or not based on the biological characteristics of the monitoring object in the monitoring video segment;

and the third module is used for generating a first alarm prompt under the condition that the monitoring object is the target monitoring object, wherein the first alarm prompt is used for prompting a user that the target monitoring object appears in the monitoring video segment.

11. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program when run performs the alarm processing method of any one of claims 1 to 9.

12. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the alarm processing method according to any of claims 1 to 9 by means of the computer program.

Images