Video monitoring and warning method and television

文档序号：1159431 发布日期：2020-09-15 浏览：8次中文

阅读说明：本技术 一种视频监控告警方法和电视机 (Video monitoring and warning method and television ) 是由王凯超于 2020-06-23 设计创作，主要内容包括：本申请提供了一种视频监控告警方法和电视机,其中该视频监控告警方法应用于电视机,包括：采集所述电视机所在环境的图像；确认所述图像中用于监控用户动作的检测区域；检测所述检测区域中呈现的所述用户动作是否与预设的告警触发动作相匹配；若所述用户动作与所述告警触发动作相匹配,则向用户发送告警信息。本发明能够通过电视机实现家庭环境中安全高效的视频监控告警,以便用户能够及时处理摔倒、跌落等意外情况。(The application provides a video monitoring and alarming method and a television, wherein the video monitoring and alarming method is applied to the television and comprises the following steps: collecting an image of an environment where the television is located; confirming a detection area for monitoring user action in the image; detecting whether the user action presented in the detection area is matched with a preset alarm triggering action; and if the user action is matched with the alarm triggering action, sending alarm information to the user. The invention can realize safe and efficient video monitoring and alarming in the home environment through the television, so that the user can timely handle the accident conditions of falling, falling and the like.)

1. A video monitoring and alarming method is applied to a television and is characterized by comprising the following steps:

collecting an image of an environment where the television is located;

confirming a detection area for monitoring user action in the image;

detecting whether the user action presented in the detection area is matched with a preset alarm triggering action;

and if the user action is matched with the alarm triggering action, sending alarm information to the user.

2. The video surveillance alarm method according to claim 1, further comprising, before said capturing the image of the environment in which the television is located:

determining monitoring on time and monitoring off time;

the collecting the image of the environment where the television is located comprises:

starting to acquire the image of the environment where the television is located at the monitoring starting time;

and stopping collecting the image of the environment where the television is located at the monitoring closing time.

3. The video surveillance alarm method according to claim 1, further comprising:

determining at least one preset alarm action type, wherein the alarm action type corresponds to a plurality of alarm trigger actions;

the detecting whether the user action presented in the detection area matches a preset alarm triggering action includes:

detecting whether the user action presented in the detection area matches at least one of the corresponding alert trigger actions under the at least one alert action type.

4. The video surveillance alarm method of claim 3, wherein said confirming the detection area in the image for monitoring user actions comprises:

and determining a detection area corresponding to the alarm action type from the image.

5. The video surveillance alarm method of claim 1, wherein said confirming the detection area in the image for monitoring user actions comprises:

calling a mapping template with a determined mapping relation with the image, wherein the preset mapping template comprises a plurality of mapping areas;

determining a region of the mapping template where at least one of the mapping regions maps in the image as the detection region; or, determining that the region of the mapping template, in which at least one of the mapping regions is mapped outside the region in the image, is the detection region.

6. The video surveillance alarm method according to claim 1, further comprising:

saving one or more of the following readable information:

the image;

the moment of sending the warning information to the user;

when the user action presented by the image is used as the alarm triggering action, screenshot of the image is displayed;

and sending the execution result of the alarm information to the user.

7. A television set, comprising:

the acquisition module is used for acquiring images of the environment where the television is located;

the confirming module is used for confirming a detection area used for monitoring the user action in the image;

the detection module is used for detecting whether the user action presented in the detection area is matched with a preset alarm triggering action or not;

and the warning module is used for sending warning information to the user under the condition that the detection module detects that the user action is matched with the warning trigger action.

8. The television set according to claim 7, further comprising:

the time module is used for determining monitoring on time and monitoring off time;

the collecting the image of the environment where the television is located comprises:

starting to acquire the image of the environment where the television is located at the monitoring starting time;

and stopping collecting the image of the environment where the television is located at the monitoring closing time.

9. The television set according to claim 7, further comprising:

the type determining module is used for determining at least one preset alarm action type, wherein the alarm action type corresponds to a plurality of alarm trigger actions;

the detecting whether the user action presented in the detection area matches a preset alarm triggering action includes:

detecting whether the user action presented in the detection area matches at least one of the corresponding alert trigger actions under the at least one alert action type.

10. The television set according to claim 9, wherein the confirming of the detection area for monitoring the user action in the image comprises:

and determining a detection area corresponding to the alarm action type from the image.

11. The television set according to claim 7, wherein the confirming of the detection area for monitoring the user action in the image comprises:

calling a mapping template with a determined mapping relation with the image, wherein the preset mapping template comprises a plurality of mapping areas;

12. The television set according to claim 7, further comprising:

a storage module for storing one or more of the following readable information:

the image;

the moment of sending the warning information to the user;

when the user action presented by the image is used as the alarm triggering action, screenshot of the image is displayed;

and sending the execution result of the alarm information to the user.

13. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the video surveillance alarm method of any of claims 1-6.

14. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the video surveillance alarm method according to any one of claims 1 to 6.

Technical Field

The application relates to the technical field of video monitoring, in particular to a video monitoring alarm method, a television, electronic equipment and a computer readable storage medium.

Background

The television is almost the indispensable household electrical appliance of every family, along with the improvement of technique and the update of product, the function of television also begins to become abundantly various, some televisions begin to have the function of making a video recording, can realize functions such as video chat, interactive game, but the application of television in the video monitoring field still is in blank state, the video monitoring of common family environment need purchase and install extra network camera, not only increased economic cost, still additionally occupy indoor very limited space.

Disclosure of Invention

In view of the above, an object of the present application is to provide a video monitoring alarm method, a television, an electronic device and a computer-readable storage medium, which can implement safe and efficient video monitoring alarm through a home-use television, so that a user can timely handle unexpected situations such as falling, falling and the like.

The invention specifically discloses a video monitoring and alarming method which is applied to a television and comprises the following steps:

collecting an image of an environment where the television is located;

confirming a detection area for monitoring user action in the image;

detecting whether the user action presented in the detection area is matched with a preset alarm triggering action;

and if the user action is matched with the alarm triggering action, sending alarm information to the user.

Further, before the acquiring the image of the environment where the television is located, the method further includes:

determining monitoring on time and monitoring off time;

the collecting the image of the environment where the television is located comprises:

starting to acquire the image of the environment where the television is located at the monitoring starting time;

and stopping collecting the image of the environment where the television is located at the monitoring closing time.

Further, the video monitoring and warning method further comprises the following steps:

determining at least one preset alarm action type, wherein the alarm action type corresponds to a plurality of alarm trigger actions;

the detecting whether the user action presented in the detection area matches a preset alarm triggering action includes:

detecting whether the user action presented in the detection area matches at least one of the corresponding alert trigger actions under the at least one alert action type.

Further, the confirming a detection area for monitoring a user action in the image includes:

and determining a detection area corresponding to the alarm action type from the image.

Further, the confirming a detection area for monitoring a user action in the image includes:

calling a mapping template with a determined mapping relation with the image, wherein the preset mapping template comprises a plurality of mapping areas;

Further, the video monitoring and warning method further comprises the following steps:

saving one or more of the following readable information:

the image;

the moment of sending the warning information to the user;

when the user action presented by the image is used as the alarm triggering action, screenshot of the image is displayed;

and sending the execution result of the alarm information to the user.

The invention also discloses a television, comprising:

the acquisition module is used for acquiring images of the environment where the television is located;

the confirming module is used for confirming a detection area used for monitoring the user action in the image;

the detection module is used for detecting whether the user action presented in the detection area is matched with a preset alarm triggering action or not;

and the warning module is used for sending warning information to the user under the condition that the detection module detects that the user action is matched with the warning trigger action.

Further, the television set further includes:

the time module is used for determining monitoring on time and monitoring off time;

the collecting the image of the environment where the television is located comprises:

starting to acquire the image of the environment where the television is located at the monitoring starting time;

and stopping collecting the image of the environment where the television is located at the monitoring closing time.

Further, the television set further includes:

the type determining module is used for determining at least one preset alarm action type, wherein the alarm action type corresponds to a plurality of alarm trigger actions;

the detecting whether the user action presented in the detection area matches a preset alarm triggering action includes:

detecting whether the user action presented in the detection area matches at least one of the corresponding alert trigger actions under the at least one alert action type.

Further, the confirming a detection area for monitoring a user action in the image includes:

and determining a detection area corresponding to the alarm action type from the image.

Further, the confirming a detection area for monitoring a user action in the image includes:

calling a mapping template with a determined mapping relation with the image, wherein the preset mapping template comprises a plurality of mapping areas;

Further, the television set further includes:

a storage module for storing one or more of the following readable information:

the image;

the moment of sending the warning information to the user;

when the user action presented by the image is used as the alarm triggering action, screenshot of the image is displayed;

and sending the execution result of the alarm information to the user.

The invention also discloses an electronic device, comprising: the video monitoring alarm system comprises a processor, a storage medium and a bus, wherein the storage medium stores machine readable instructions executable by the processor, when an electronic device runs, the processor is communicated with the storage medium through the bus, and the processor executes the machine readable instructions to execute the video monitoring alarm method.

A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the video surveillance alarm method described above.

The invention has at least the following beneficial effects:

the invention is applied to the television, can monitor the video in the family through the camera of the television, and greatly reduces the economic cost compared with the existing additionally configured network camera. On one hand, the invention can monitor a part of area in the video image according to the condition of the user, thereby not only reducing the calculation amount of detection, but also preventing the occurrence of false detection and false alarm caused by overlarge monitoring range; on the other hand, the invention can shield partial content of the image according to the requirement, thereby effectively ensuring that the privacy of the user is not invaded.

Other advantageous effects of the present invention will be described in detail in the detailed description section.

In order to make the aforementioned and other objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 shows a flowchart of a video monitoring alarm method provided in an embodiment of the present application;

FIG. 2 is a schematic diagram illustrating a mapping template provided by an embodiment of the present application;

fig. 3 shows a block diagram of a television set provided in an embodiment of the present application;

FIG. 4 is a flow chart of another video surveillance alarm method provided by an embodiment of the present application;

fig. 5 shows a schematic structural diagram of an electronic device provided in 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 technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.

To enable those skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario (i.e., video surveillance alarm for a home environment television). It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of video surveillance alerts for a television in a home environment, it should be understood that this is merely one exemplary embodiment.

As shown in fig. 1, an embodiment of the present invention discloses a video monitoring and warning method, which mainly includes the following steps:

step 101: and acquiring an image of the environment where the television is located.

Preferably, based on the lifting type or integrated type camera carried by the television, a user can turn on or off the camera by operating the television, and the camera can be used for shooting video images of indoor environments (such as bedrooms and hall lamps) where the television is located, which is also a main place for family member activities. In order to adapt to different application scenes, the camera of the television can also adopt an infrared camera, a field depth camera and the like.

Step 102: and confirming a detection area for monitoring the user action in the image.

Preferably, the user may input the relevant configuration in advance, and the television set can recognize the configuration content to confirm the detection area, and only the information included in the detection area part in the image is subsequently calculated or processed and analyzed. Compared with other security or monitoring environments, the home environment is special, the floor area is small, but the part needing to be monitored is very targeted, for example, for mobile monitoring of the baby, the moving capability of the baby as a monitoring target is limited, only the crib and the area nearby the crib need to be mainly detected, and the indoor wall and ceiling parts in the image do not need to be monitored at all, so that the calculated amount can be effectively reduced by only selecting the detection area in the image for detection, meanwhile, the interference of the action of a non-monitoring target on the monitoring result can be avoided, and the accuracy of monitoring and alarming is improved.

Step 103: and detecting whether the user action presented in the detection area is matched with a preset alarm triggering action.

Preferably, the action recognition model may be established in advance by a machine learning method, and since the model is obtained by training based on a preset alarm triggering action, after the detection area presenting the user action is input into the action recognition model, the action recognition model may recognize whether the user action is consistent with the alarm triggering action, for example, a forward falling action is an alarm triggering action, a large number of pictures presenting the forward falling action are obtained by a web crawler method, and a falling action recognition model is obtained by training based on the pictures, and if the forward falling user action is also presented in the image input into the model, the model may obtain a positive conclusion by calculation, that is, the user action presented by the image is consistent with the alarm triggering action. The specific model building and detection principle is also applied to the prior art of face recognition and the like, so the invention is not explained in detail.

Step 104: and if the user action is matched with the alarm triggering action, sending alarm information to the user.

Preferably, the alarm sound can be sent out through a loudspeaker of the television, the alarm image can be displayed on a screen of the television, the television can be connected with a network and sends alarm information to a specified terminal, and any existing alarm mode can be adopted in the invention, which is not listed in the text.

In some embodiments of the invention, at step 101: before the image of the environment where the television is located is collected, the method further comprises the following steps: a monitor on time and a monitor off time are determined. Preferably, the user can input time-related configuration information on the television at any time to set the monitored on-time and off-time, and the television can confirm the configuration information.

Further, step 101 specifically includes: starting to acquire the image of the environment where the television is located at the monitoring starting time; and stopping collecting the image of the environment where the television is located at the monitoring closing time. For example, when carrying out the removal control to the baby at night, set for in advance control opening time and control closing time for the TV set can implement the control when the head of a family sleeps, prevents the emergence of unexpected condition, and the baby is not in the sleep state daytime, and the TV set just can the automatic shutdown gather the image, provides the use convenience, has promoted user's use experience and feels.

Preferably, after the monitoring on time, the television camera may continuously acquire images, and may acquire images at a fixed time or in a fixed period, and the like, and may adopt a corresponding image acquisition strategy based on different application scenarios.

In some embodiments of the present invention, the video monitoring alarm method further includes: and determining at least one preset alarm action type, wherein the alarm action type corresponds to a plurality of alarm trigger actions. Preferably, the step 103 specifically includes: detecting whether the user action presented in the detection area matches at least one of the corresponding alert trigger actions under the at least one alert action type.

In order to expand the application range, the invention can detect and identify various user actions under different alarm action types, therefore, the invention can establish a plurality of action identification models based on the alarm triggering actions of various alarm action types, and the television can confirm the alarm action type required by detection and the corresponding alarm triggering action under the type according to the selection of the user when in use, and the action of the user in the image can be calculated by the action identification model no matter which alarm triggering action under which alarm action type is consistent with the action of the user in the image. For example, the invention can simultaneously detect the fall alarm action type and the mobile alarm action type, the fall alarm action type also includes the alarm trigger actions of forward falling, backward falling and the like, the television can input the detection area of the image into the alarm action model corresponding to each alarm trigger action of the two alarm action types for calculation and analysis, so as to obtain whether the user action in the image is at least matched with one of the alarm trigger actions, and if so, the step 104 is carried out. Through the preferred scheme, the invention can monitor different types of user actions simultaneously, and has wide application range.

In some embodiments of the present invention, step 102 specifically includes: and determining a detection area corresponding to the alarm action type from the image. In practical application, the configuration of the home environment is relatively fixed, different alarm action types often appear in a specific range of an image, for example, for mobile monitoring of a baby, only a crib and a nearby area need to be monitored, so that a user can configure a range of a corresponding detection area in the image and input the range into a television in advance aiming at a certain alarm action type or a certain alarm trigger action under a certain alarm action type, the television establishes a matching relationship between the certain alarm action type or the certain alarm trigger action under the certain alarm action type and the detection area based on the configuration content, and as long as the television determines the preset alarm action type or the alarm trigger action, the detection area having the matching relationship with the certain alarm action type or the alarm trigger action can be obtained. The method greatly optimizes the confirmation process of the detection area and enables the monitoring alarm under different conditions to be more pertinent.

In some embodiments of the present invention, step 102 specifically includes:

calling a mapping template with a determined mapping relation with the image, wherein the preset mapping template comprises a plurality of mapping areas; determining a region of the mapping template where at least one of the mapping regions maps in the image as the detection region; or, determining that the region of the mapping template, in which at least one of the mapping regions is mapped outside the region in the image, is the detection region.

As shown in fig. 2, a schematic structural diagram of a mapping template 201 provided in an embodiment of the present invention is that any point on the mapping template 201 has a mapping point on a captured image, and a position corresponding to a specific mapping is determined by mapping parameters, so that each mapping area 202 on the mapping template also necessarily has a mapping area on the image, although the captured image is generally a rectangle with a scale of 16:9, 4:3, the mapping template 201 may have any shape, for convenience of description, the embodiment also employs a rectangular mapping template 201, and the size and shape of the mapping template are the same as those of the captured image, the mapping template 201 may be displayed to a user in a graphic form through a display of a television, or the transparent mapping template 201 is directly superimposed on the captured image and displayed to the user through the display, so that the user can configure a selected mapping area 202 more intuitively through an operation manner of a remote controller, a touch screen, or the like, as shown in phantom in fig. 2. The detection area is determined by using each divided mapping area 202 on the mapping template 201, so that the operation difficulty of a user is reduced, and the selection accuracy of the detection area is improved. It should be noted that the mapping template 201 does not have to have the same size and shape as the image, but only has certain mapping parameters with the image, and the mapping template 201 may have any shape and size.

The region determined by the mapping relation of the mapping region 202 may be a detection region to be detected or a mask region not to be detected. In a home environment, a privacy area is often involved, and is not suitable for being monitored, so that an area of the mapping area 202 corresponding to the image can be determined as a shielding area by the scheme disclosed in the embodiment, specifically, image information included in the shielding area can be hidden by adding color blocks, printing codes and the like, and in the image, an area other than the shielding area is a detection area.

In some embodiments of the present invention, the video monitoring alarm method further includes:

saving one or more of the following readable information:

(1) the collected images are convenient for the user to review the historical video at any time;

(2) the moment of sending the alarm information to the user enables the user to directly find the video clip with the alarm triggering action in the video;

(3) when the user action presented by the image is taken as the alarm triggering action, the screenshot of the image saves a video clip of the alarm triggering action which needs to appear in the historical video actively by the user;

(4) and sending the execution result of the alarm information to the user.

To further illustrate the aspects of the present invention, the following specific examples of the present invention are described in detail, it being understood that the following examples are only preferred embodiments of the present invention and are not intended to limit the claimed invention:

as shown in fig. 4, the tv with the camera is provided with an APP, a user can interact with the user through the APP, the user can configure various information after opening the APP, the configurations can be read and identified by the tv, and the video monitoring alarm method is implemented based on the configurations, specifically, the monitoring on time and the monitoring off time of the collected image can be set, so that the camera can start to collect the image at the monitoring on time, and automatically stop collecting the image at the monitoring off time; the user can also configure the alarm action type and the alarm triggering action under the type, and realize mobile monitoring for babies, fall monitoring for the elderly and the like, wherein the above processes can be configured in the process of acquiring images by the camera and can also be configured before/after the images are acquired. And after the user configuration is finished, the APP can be quitted, and the related configuration content is subjected to television background identification processing. And when the reserved time is reached, namely the starting time is monitored, acquiring the image acquired by the camera.

The embodiment may determine the detection area in various ways, one of which is preconfigured, and select the detection area according to the previously configured alarm action type or alarm trigger action, and it is worth mentioning that, for the part related to privacy in the image, the privacy area is shielded and modified into a color block to ensure the privacy security of the user. However, for monitoring the falling of the old people or the patients, because the moving range of the old people or the patients is large and the falling area is not fixed, the whole image needs to be detected, and the detection area does not need to be specified, namely, all the contents of the image are the detection area; the second is field configuration, the mapping template 201 shown in fig. 2 can be called and displayed through a display of a television, the mapping template 201 is displayed as a grid (mapping area 202) with transparency, wherein a layer of M: N (such as 4:3, 16:9) is covered on a video layer (acquired image), the grid is realized through a user-defined UI control, a focus receiving key can be captured, a grid is selected to be confirmed, and the upper left corner of the selected grid is displayed and is subjected to hook printing and transparency reduction (shown by shading in fig. 2) to represent the selected meaning. And pressing the confirmation key of the remote controller or other television control equipment again on the selected grid to indicate the meaning of cancellation, and restoring the transparency while checking out. After the configuration is completed, the television can determine a corresponding area of the selected mapping area 202 on the image according to the preset mapping parameters, and the area can be confirmed as a detection area or a shielding area, so as to protect the privacy of the user.

According to the alarm action type or the configuration of the alarm trigger action set in the background of the television, judging whether the alarm action type or the alarm trigger action is opened, if so, monitoring, namely, sending the image of the determined detection area to the corresponding action recognition model through each data channel, wherein the specific method can include but is not limited to the following steps: and (4) mobile detection (mobile monitoring) and fall detection (fall monitoring), if the user action presented in the image is monitored to be consistent with the alarm triggering action, storing related alarm data and sending alarm information to the user.

The collected images also need to be stored so that a user can conveniently view historical videos, specifically, after a privacy area is shielded and a detection area is confirmed, image data coding compression is carried out through a corresponding data channel, and then coding frames are stored in files to form recording files.

Through the APP, all recorded and stored files can be displayed. It is worth mentioning that, considering that the Flash space of the television is limited, a configuration strategy of the upper limit of the size of the storage space must be made. The user may select the maximum time period for the loop recording, such as 24 hours, 48 hours, 72 hours, and so on. When the recording time exceeds the longest time period, the new recording file covers the oldest recording file to ensure circulation. Considering that the complicated operation reduces the user experience, the content UI is not displayed, and the user does not configure the content UI by himself/herself. Furthermore, the user can select one or more of the recording files for collection and storage, so that the files stored in the collection and storage are not covered by the circular recording.

In addition, the user can also realize normal operations such as deletion, watching, screenshot and the like of the recorded file through the television, and the detailed description of the embodiment is omitted.

And finally, closing all the data channels after the monitoring closing time is reached.

Based on the same inventive concept, the embodiment of the present application further provides a television corresponding to the video monitoring and warning method, and as the principle of solving the problem of the television device in the embodiment of the present application is similar to that of the video monitoring and warning method in the embodiment of the present application, the implementation of the television can refer to the implementation of the method, and repeated details are not repeated.

As shown in fig. 3, the television set includes:

the acquisition module 301 is configured to acquire an image of an environment where the television is located;

a confirming module 302, configured to confirm a detection area for monitoring a user action in the image;

a detection module 303, configured to detect whether the user action presented in the detection area matches a preset alarm trigger action;

an alarm module 304, configured to send alarm information to the user when the detection module detects that the user action matches the alarm trigger action.

In some embodiments of the invention, the television further comprises: