Monitoring identification method, device and equipment and storage medium

Abstract

The application provides a monitoring identification method and device, equipment and storage medium, and relates to the technical field of Internet of Things. The method is: acquiring a video monitoring image in a preset monitoring area through a video monitoring device in real time, judging whether a first video monitoring image at a current time and a second video monitoring image at a previous time are the same; if not, determining first image difference information of the first video monitoring image relative to the second video monitoring image; judging whether the first image difference information belongs to light and shadow shaking alarm information; if not, continuing to determine whether the first image difference information belongs to preset alarm object information; if yes, identifying behavior information of a preset alarm object corresponding to the first image difference information according to the first infrared monitoring image at the current time and a second infrared monitoring image at a next time; and if the behavior information indicates that the preset alarm object implements a preset action on a target object in the preset monitoring area, sending monitoring alarm information to a target terminal.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a monitoring and identification method, apparatus, device, and storage medium. Background Technology

[0002] With the development of IoT technology, more and more users are choosing to use remote monitoring systems. These systems consist of image acquisition devices and servers. The server receives monitoring images captured by the acquisition devices. The server and user terminals can connect via a network, and the server can determine whether to send alarm information to the user terminals based on the received monitoring images.

[0003] The steps of monitoring and identification in existing technology include: the server receiving monitoring images captured by the image acquisition device in real time; the server determining whether the monitoring image at the current moment is the same as the monitoring image at the previous moment; if the monitoring image at the current moment is different from the monitoring image at the previous moment, an alarm message is sent to the user terminal.

[0004] However, the inventors have found that the prior art has at least the following technical problems: because there are many factors that cause changes in the monitoring image (for example, changes in brightness cause changes in the monitoring image), false alarms occur frequently in the prior art, and therefore, the accuracy of the monitoring and identification methods in the prior art is poor. Summary of the Invention

[0005] This application provides a monitoring and identification method, apparatus, device, and storage medium that can improve the accuracy of the monitoring and identification method.

[0006] Firstly, this application provides a monitoring and identification method applied to a monitoring server, the method comprising:

[0007] The video surveillance device acquires video surveillance images within a preset monitoring area in real time and determines whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment.

[0008] If they are not the same, then determine the first image difference information between the first video surveillance image and the second video surveillance image;

[0009] Determine whether the first image difference information belongs to light and shadow sway alarm information, wherein the light and shadow sway alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in a local area;

[0010] If the first image difference information does not belong to the light and shadow shaking alarm information, then it is further determined whether the first image difference information belongs to the preset alarm object information, wherein the preset alarm object information includes multiple pre-stored life information;

[0011] If the first image difference information belongs to the preset alarm object information, then the infrared monitoring image of the preset monitoring area is acquired in real time through the infrared monitoring device;

[0012] Based on the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment, identify the behavioral information of the preset alarm object corresponding to the difference information in the first image;

[0013] If the behavior information indicates that the preset alarm object performs a preset action on a target item within the preset monitoring area, then a monitoring alarm message is sent to the target terminal.

[0014] Optionally, the process of determining whether the first image difference information belongs to the preset alarm object information includes: determining whether the first image difference information matches the pre-stored information of multiple life forms; if the first image difference information matches any of the life forms, then the first image difference information is determined to belong to the preset alarm object information; if the first image difference information does not match any of the multiple life forms, then the first image difference information does not belong to the preset alarm object information.

[0015] Optionally, the first image difference information includes first coordinate information corresponding to multiple difference points, and the organism information includes second coordinate information corresponding to multiple feature points. Accordingly, determining whether the first image difference information matches the pre-stored multiple organism information includes: for each organism information, calculating a matching parameter between the first coordinate information corresponding to the multiple difference points and the second coordinate information corresponding to the multiple feature points included in the organism information using a preset recursive algorithm; if the matching parameter is less than or equal to a preset threshold, then the first image difference information matches the organism information; if the matching parameter is greater than the preset threshold, then the first image difference information does not match the organism information.

[0016] Optionally, the method further includes: if the first image difference information does not belong to the light and shadow motion information, then switching the acquisition mode of the video monitoring device, wherein the acquisition mode includes night vision mode or daytime mode; acquiring a third video monitoring image within the preset monitoring area after switching the acquisition mode; determining the second image difference information of the third video monitoring image relative to the second video monitoring image; determining whether the second image difference information belongs to the light and shadow motion information; if the second image difference information belongs to the light and shadow motion information, then further determining whether the first image difference information belongs to a preset alarm object; if the second image difference information does not belong to the light and shadow motion information, then not sending monitoring alarm information to the target terminal.

[0017] Optionally, the behavior information of the preset alarm object corresponding to the first image difference information includes: if the preset alarm object is detected to press, move or touch a target item in the preset monitoring area, then it is determined that the preset alarm object performs a preset action on the target item in the preset monitoring area.

[0018] Optionally, it further includes: if the behavior information indicates that the preset alarm object has not performed a preset action on the target item within the preset monitoring area; then, video monitoring images of the preset alarm object from multiple angles are acquired, wherein the multiple angles include the front, back, left side, and right side.

[0019] Optionally, before sending the monitoring alarm information to the target terminal, the method further includes: acquiring multiple sets of monitoring information within a preset time period, each set of monitoring information including first image difference information, movement trajectory information corresponding to a preset alarm object in the infrared monitoring image, and light and shadow sway alarm information corresponding to the first image difference information; determining the correlation parameters between the first image difference information, movement trajectory information, and light and shadow sway alarm information in each set of monitoring information to obtain multiple correlation coefficients corresponding to the multiple sets of monitoring information; if the target correlation coefficient corresponding to the last set of monitoring information is within a preset correlation coefficient range, and the number of correlation coefficients among the multiple correlation coefficients that are close to the target correlation coefficient is greater than a preset number, then the step of sending the monitoring alarm information to the target terminal is executed.

[0020] Secondly, this application provides a monitoring and identification device applied to a monitoring server, the device comprising:

[0021] The first acquisition module is used to acquire video surveillance images within a preset monitoring area in real time through a video surveillance device, and to determine whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment.

[0022] The first determining module is used to determine first image difference information between the first video surveillance image and the second video surveillance image if they are not the same.

[0023] The judgment module is used to determine whether the first image difference information belongs to the light and shadow sway alarm information, wherein the light and shadow sway alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in a local area;

[0024] The second determining module is used to determine whether the first image difference information belongs to preset alarm object information if the first image difference information does not belong to the light and shadow shaking alarm information, wherein the preset alarm object information includes multiple pre-stored life information.

[0025] The second acquisition module is used to acquire infrared monitoring images in the preset monitoring area in real time through an infrared monitoring device if the first image difference information belongs to the preset alarm object information.

[0026] The identification module is used to identify the behavior information of a preset alarm object corresponding to the difference information in the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment.

[0027] The sending module is used to send monitoring alarm information to the target terminal if the behavior information indicates that the preset alarm object has performed a preset action on the target item in the preset monitoring area.

[0028] Thirdly, this application provides an electronic device, including: at least one processor and a memory;

[0029] The memory stores computer-executed instructions;

[0030] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the monitoring and identification method as described in the first aspect and various possible designs of the first aspect.

[0031] Fourthly, this application provides a computer storage medium storing computer execution instructions, which, when executed by a processor, implement the monitoring and identification method described in the first aspect and various possible designs of the first aspect.

[0032] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the monitoring and identification method described in the first aspect and various possible designs of the first aspect.

[0033] The monitoring and identification method, apparatus, equipment, and storage medium provided in this application firstly acquire video monitoring images within a preset monitoring area in real time using a video monitoring device, and determine whether the first video monitoring image at the current moment is the same as the second video monitoring image at the previous moment; if they are different, determine the first image difference information between the first video monitoring image and the second video monitoring image; then, determine whether the first image difference information belongs to light and shadow flicker alarm information, wherein light and shadow flicker alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in certain areas; if the first image difference information does not belong to light and shadow flicker alarm information, further determine whether the first image difference information belongs to preset alarm object information, wherein preset alarm object information includes multiple pre-stored life entity information; finally, if the first image difference information belongs to preset alarm object information, acquire infrared monitoring images within the preset monitoring area in real time using an infrared monitoring device; based on the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment, identify the behavior information of the preset alarm object corresponding to the first image difference information; if the behavior information indicates that the preset alarm object performs a preset action on a target item within the preset monitoring area, send monitoring alarm information to the target terminal. This application determines monitoring alarm information from multiple perspectives by using light and shadow motion alarm information, light and shadow motion alarm information, and behavioral information of preset alarm objects, thereby reducing the probability of false alarms and improving the accuracy of monitoring and identification methods. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram illustrating an application scenario of the monitoring and identification method provided in the embodiments of this application;

[0036] Figure 2 The monitoring and identification method flow provided in the embodiments of this application Figure 1 ;

[0037] Figure 3 A schematic diagram illustrating the monitoring and identification method provided in the embodiments of this application;

[0038] Figure 4 The monitoring and identification method flow provided in the embodiments of this application Figure 2 ;

[0039] Figure 5 This is a schematic diagram of the structure of the monitoring and identification device provided in the embodiments of this application;

[0040] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0043] With the development of IoT technology, more and more users are choosing to use remote monitoring systems. These systems consist of image acquisition devices and servers. The server receives monitoring images captured by the acquisition devices. The server and user terminals can connect via a network, and the server can determine whether to send alarm information to the user terminals based on the received monitoring images.

[0044] The steps in existing monitoring and identification technologies include: a server receiving monitoring images captured by an image acquisition device in real time; the server determining whether the current monitoring image is the same as the previous monitoring image; if the current monitoring image is different from the previous monitoring image, an alarm message is sent to the user terminal. However, because many factors can cause changes in monitoring images (e.g., changes in brightness), false alarms frequently occur in existing technologies, resulting in poor accuracy of existing monitoring and identification methods.

[0045] Therefore, improving the accuracy of monitoring and identification methods in remote monitoring systems is a pressing technical problem that needs to be solved.

[0046] To address the aforementioned technical problems, this application proposes the following technical concept: First, a video surveillance device acquires video surveillance images within a preset monitoring area in real time, determining whether the current first video surveillance image and the previous second video surveillance image are identical. If they are not identical, first image difference information is determined relative to the second video surveillance image. Then, it is determined whether the first image difference information belongs to light and shadow flicker alarm information, which includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows. If the first image difference information does not belong to light and shadow flicker alarm information, it is further determined whether the first image difference information belongs to preset alarm object information, which includes pre-stored information on multiple living entities. Finally, if the first image difference information belongs to preset alarm object information, an infrared monitoring device acquires infrared surveillance images within the preset monitoring area in real time. Based on the current first infrared surveillance image and the next second infrared surveillance image, the behavioral information of the preset alarm object corresponding to the first image difference information is identified. If the behavioral information indicates that the preset alarm object performs a preset action on a target item within the preset monitoring area, a monitoring alarm is sent to the target terminal.

[0047] Therefore, this application determines the monitoring alarm information from multiple perspectives by using light and shadow motion alarm information, light and shadow motion alarm information, and behavioral information of preset alarm objects, thereby reducing the probability of false alarms and improving the accuracy of the monitoring identification method.

[0048] Figure 1 This is a schematic diagram illustrating an application scenario of the monitoring and identification method provided in the embodiments of this application. For example... Figure 1 As shown, server 102 can acquire video surveillance images of a preset monitoring area in real time via a video surveillance device, and can also acquire infrared surveillance images of the preset monitoring area in real time via an infrared surveillance device. When server 102 determines that a monitoring alarm needs to be issued based on the video surveillance images and infrared surveillance images, it sends the monitoring alarm information to terminal 101. Terminal 101 and server 102 can be connected via wired or wireless means. It should be noted that the aforementioned video surveillance device and infrared surveillance device are used to monitor the preset monitoring area, and the video surveillance device and infrared surveillance device can transmit monitoring data to server 102 via wired or wireless means.

[0049] There are relationships between terminal 101, preset monitoring areas, video surveillance devices, and infrared monitoring devices. For example, when server 102 determines that preset monitoring area A needs to issue a monitoring alarm, it sends the monitoring alarm information to terminal 101 corresponding to preset monitoring area A. When server 102 determines that preset monitoring area B needs to issue a monitoring alarm, it sends the monitoring alarm information to terminal 101 corresponding to preset monitoring area B. It can be understood that the number of terminals 101 corresponding to each preset monitoring area can be one or more.

[0050] The monitoring and identification method proposed in this application will be described in detail below through detailed embodiments.

[0051] Figure 2 Flowchart of the monitoring and identification method provided in the embodiments of this application Figure 1 In this embodiment, the executing entity can be a terminal or a server; this embodiment will be described using a server as the executing entity. Figure 2 As shown, the method includes:

[0052] S201. The video monitoring device acquires video monitoring images within a preset monitoring area in real time and determines whether the first video monitoring image at the current moment is the same as the second video monitoring image at the previous moment.

[0053] In this step, the video surveillance device can be a high-definition camera, where a high-definition camera is one with a video / image resolution greater than a preset resolution. It is understood that there can be one or more high-definition cameras. When there are multiple high-definition cameras, they can be located at different positions within the preset monitoring area. The server can receive video surveillance images captured by multiple high-definition cameras and monitor and identify the preset monitoring area from multiple directions. Accordingly, for each high-definition camera, the server will determine whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment.

[0054] The preset monitoring area can be any area. Optionally, the preset monitoring area can be an outdoor area (such as a square) or an indoor area (such as an elevator).

[0055] S202. If they are not the same, then determine the first image difference information between the first video surveillance image and the second video surveillance image.

[0056] The first image difference information is used to represent the different areas in the first video surveillance image and the second video surveillance image.

[0057] In some embodiments, the first image difference information may be information about changes in the image grayscale values. Accordingly, the server can determine the first image difference information based on the grayscale values ​​of the first video surveillance image and the grayscale values ​​of the second video surveillance image.

[0058] S203. Determine whether the difference information of the first image belongs to the light and shadow shaking alarm information, wherein the light and shadow shaking alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in a local area.

[0059] Optionally, the server stores image difference information corresponding to multiple light and shadow flicker alarm messages. The stored image difference information includes differences in light brightness, differences in natural light brightness, and differences in the presence of localized shadows. Accordingly, this step involves comparing the first image difference information with the stored image difference information; if they are the same, the first image difference information is determined to be a light and shadow flicker alarm message (i.e., a light and shadow flicker alarm message is confirmed to exist); if they are different, the first image difference information is determined not to be a light and shadow flicker alarm message (i.e., a light and shadow flicker alarm message is confirmed to exist).

[0060] S204. If the first image difference information does not belong to the light and shadow shaking alarm information, then continue to determine whether the first image difference information belongs to the preset alarm object information, wherein the preset alarm object information includes multiple pre-stored life information.

[0061] The process of determining whether the first image difference information belongs to the preset alarm object information includes: determining whether the first image difference information matches multiple pre-stored life form information (that is, determining whether there is still a life form intrusion); if the first image difference information matches any life form information, then the first image difference information is determined to belong to the preset alarm object information; if the first image difference information does not match any of the multiple life form information, then the first image difference information does not belong to the preset alarm object information.

[0062] Optionally, the first image difference information includes first coordinate information corresponding to multiple difference points, and the organism information includes second coordinate information corresponding to multiple feature points. Accordingly, determining whether the first image difference information matches the pre-stored multiple organism information includes: for each organism information, calculating the matching parameter between the first coordinate information corresponding to multiple difference points and the second coordinate information corresponding to multiple feature points included in the organism information using a preset recursive algorithm; if the matching parameter is less than or equal to a preset threshold, then the first image difference information matches the organism information; if the matching parameter is greater than the preset threshold, then the first image difference information does not match the organism information.

[0063] For example, the first coordinate information can be represented by X, and the second coordinate information can be represented by Y. Accordingly, the specific steps for calculating the matching parameters between the first coordinate information corresponding to multiple difference points and the second coordinate information corresponding to multiple feature points included in the organism information, through a preset recursive algorithm, are as follows: input the first coordinate information X and the second coordinate information Y into the following recursive formula one to obtain the matching parameters.

[0064] Among them, the first recursive formula is:

[0065]

[0066] Where k represents the number of recursions, Used to represent the covariance between the first coordinate information X and the second coordinate information Y. The variance used to represent the first coordinate information X. The variance used to represent the second coordinate information Y. This parameter is used to represent the matching parameters between the first coordinate information X and the second coordinate information Y.

[0067] It should be noted that, as Figure 3 As shown, if the first image difference information does not belong to light and shadow motion information, the acquisition mode of the video monitoring device is switched, where the acquisition mode includes night vision mode or daytime mode; a third video monitoring image is acquired within the preset monitoring area after the acquisition mode is switched; the second image difference information of the third video monitoring image relative to the second video monitoring image is determined; it is determined whether the second image difference information belongs to light and shadow motion information (that is, whether light and shadow motion alarm information still exists); if the second image difference information belongs to light and shadow motion information, it is further determined whether the first image difference information belongs to the preset alarm object (at this time, it is further determined whether there is still a life intrusion); if the second image difference information does not belong to light and shadow motion information, no monitoring alarm information is sent to the target terminal (at this time, the light and shadow motion alarm information is determined to be a false alarm).

[0068] S205. If the first image difference information belongs to the preset alarm object information, then the infrared monitoring image in the preset monitoring area is obtained in real time through the infrared monitoring device.

[0069] The infrared monitoring device can detect the temperature of different areas to obtain infrared monitoring images. Optionally, the infrared monitoring device can be an infrared monitoring camera. The number of infrared monitoring devices is not specifically limited in this step and can be set according to the needs of the monitored area.

[0070] S206. Based on the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment, identify the behavior information of the preset alarm object corresponding to the difference information in the first image.

[0071] Optionally, behavioral information includes pressing, moving, or touching the target object. The target object can be a monitored object within the monitored area, such as exhibits.

[0072] Accordingly, the step of identifying the behavior information of the preset alarm object corresponding to the first image difference information is as follows: if it is identified that the preset alarm object presses, moves or touches the target item in the preset monitoring area, then it is determined that the preset alarm object performs a preset action on the target item in the preset monitoring area.

[0073] S207. If the behavior information indicates that the preset alarm object has performed a preset action on the target item in the preset monitoring area, then a monitoring alarm information is sent to the target terminal.

[0074] In this step, the target terminal can be a terminal device corresponding to the preset monitoring area, such as a mobile phone or computer. It should be noted that when sending monitoring alarm information to the target terminal, the server can also record the monitoring information and alarm time, obtaining monitoring alarm records, which facilitates users in querying alarm records for different time periods.

[0075] In some embodiments, the target terminal may also send a request to the server to view surveillance video or surveillance alarm records, and the server may send the current surveillance video or surveillance alarm records to the target terminal. Optionally, before sending the request to the server, the target terminal may also identify and verify the user's identity information. For example, facial recognition, fingerprint recognition, etc.

[0076] In this embodiment, if the behavior information indicates that the preset alarm object has not performed a preset action on the target item within the preset monitoring area, then video monitoring images of the preset alarm object from multiple angles are acquired, including the front, back, left side, and right side.

[0077] Here, by recording video surveillance images from multiple angles, it is convenient to conduct secondary or manual confirmation based on the recorded video surveillance images, thereby avoiding the omission of alarm information and improving the accuracy of alarm information.

[0078] This application provides a monitoring and identification method. First, a video monitoring device acquires video monitoring images within a preset monitoring area in real time. It then determines whether the current first video monitoring image and the previous second video monitoring image are the same. If they are different, it identifies first image difference information between the first and second video monitoring images. Next, it determines whether the first image difference information belongs to a light and shadow motion alarm. Finally, if the first image difference information does not belong to a light and shadow motion alarm, it further determines whether the first image difference information belongs to a preset alarm object. If the first image difference information belongs to a preset alarm object, an infrared monitoring device acquires infrared monitoring images within the preset monitoring area in real time. Based on behavioral information, it determines whether to send a monitoring alarm. Because the monitoring alarm information is determined from multiple perspectives—including light and shadow motion alarm information, light and shadow motion alarm information, and behavioral information of the preset alarm object—the probability of false alarms is reduced, and the accuracy of the monitoring and identification method is improved.

[0079] Figure 4 Flowchart of the monitoring and identification method provided in the embodiments of this application Figure 2 In this embodiment of the application, to further improve the accuracy of monitoring alarm information, the monitoring alarm information can be further verified before being sent to the target terminal, such as... Figure 4 As shown, the specific steps are as follows:

[0080] S401. Obtain multiple sets of monitoring information within a preset time period. Each set of monitoring information includes first image difference information, movement trajectory information corresponding to the preset alarm object in the infrared monitoring image, and light and shadow swaying alarm information corresponding to the first image difference information.

[0081] In this step, the preset duration is not specifically limited. Optionally, the preset duration can be 10 minutes, 20 minutes, or 30 minutes. The movement trajectory information can be determined based on the coordinate changes of the preset alarm object in two or more infrared monitoring images. For example, the coordinates of the preset alarm object A in multiple adjacent infrared monitoring images are x1, x2, and x3; connecting x1, x2, and x3 yields the movement trajectory information corresponding to the preset alarm object A. The light and shadow flicker alarm information corresponding to the first image difference information includes either: the first image difference information belongs to the light and shadow flicker alarm information, or the first image difference information does not belong to the light and shadow flicker alarm information.

[0082] S402. Determine the correlation parameters between the first image difference information, movement trajectory information, and light and shadow sway alarm information in each group of monitoring information, and obtain multiple correlation coefficients corresponding to multiple groups of monitoring information.

[0083] Optionally, the server can obtain other influencing factor parameters and uncontrollable factor parameters, and then determine the relevant parameters between the first image difference information, movement trajectory information, and light and shadow sway alarm information based on the other influencing factor parameters, uncontrollable factor parameters, first image difference information, movement trajectory information, and light and shadow sway alarm information.

[0084] Other influencing factors can include environmental impact parameters, network impact parameters, energy impact parameters, etc. Uncontrollable factors can include temperature parameters, time parameters, weather parameters, etc.

[0085] For example, the first image difference information can be set as x, the movement trajectory information as y, the light and shadow sway alarm information as z, other influencing factor parameters as d, and the uncontrollable factor parameter as e; the relevant parameters between the first image difference information, the movement trajectory information, and the light and shadow sway alarm information can be determined by the following relevant parameter formula two.

[0086] Among them, the relevant parameter formula two is:

[0087]

[0088] Where f(x,y,z) represents the relevant parameters between the first image difference information, the movement trajectory information, and the light and shadow sway alarm information; i represents the i-th group of monitoring information; a, b, and c are preset values, and a, b, and c are greater than 0 and less than 1; d and e are preset values ​​greater than or equal to 0.

[0089] S403. If the target correlation coefficient corresponding to the last set of monitoring information is within the preset correlation coefficient range, and the number of correlation coefficients that are close to the target correlation coefficient among multiple correlation coefficients is greater than the preset number, then the step of sending monitoring alarm information to the target terminal is executed.

[0090] Optionally, a correlation coefficient close to the target correlation coefficient is defined as one where the difference between the two correlation coefficients is less than a preset value. In this embodiment, the preset value and preset quantity are not specifically limited. For example, the preset value can be 0.2, 0.5, or 0.8. For example, the preset quantity can be 5, 10, or 15, etc.

[0091] In this step, the preset correlation coefficient range is not specifically limited. Optionally, the preset correlation coefficient range can be the area corresponding to the target region in three-dimensional space. Here, the first image difference information, movement trajectory information, and light and shadow sway alarm information each correspond to point coordinates in three-dimensional space. Optionally, the first image difference information x represents the coordinate along the x-direction in three-dimensional space, the movement trajectory information y represents the coordinate along the y-direction in three-dimensional space, and the light and shadow sway alarm information z represents the coordinate along the z-direction in three-dimensional space. The area corresponding to the target region in three-dimensional space can be represented by F(S), where the target region can be any region in three-dimensional space.

[0092] In this embodiment, the monitoring alarm information is further verified by using the relevant parameters between the first image difference information, the movement trajectory information, and the light and shadow sway alarm information, thereby further improving the accuracy of the monitoring alarm information.

[0093] Figure 5 This is a schematic diagram of the monitoring and identification device provided in an embodiment of this application. Figure 5 As shown, the monitoring and identification device includes: a first acquisition module 501, a first determination module 502, a judgment module 503, a second determination module 504, a second acquisition module 505, an identification module 506, and a sending module 507.

[0094] The first acquisition module 501 is used to acquire video surveillance images within a preset monitoring area in real time through a video surveillance device, and to determine whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment.

[0095] The first determining module 502 is used to determine the first image difference information between the first video surveillance image and the second video surveillance image if they are not the same.

[0096] The judgment module 503 is used to determine whether the first image difference information belongs to the light and shadow sway alarm information, wherein the light and shadow sway alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in a local area;

[0097] The second determining module 504 is used to determine whether the first image difference information belongs to the preset alarm object information if the first image difference information does not belong to the light and shadow shaking alarm information. The preset alarm object information includes multiple pre-stored life information.

[0098] The second acquisition module 505 is used to acquire infrared monitoring images in the preset monitoring area in real time through the infrared monitoring device if the first image difference information belongs to the preset alarm object information.

[0099] The identification module 506 is used to identify the behavior information of the preset alarm object corresponding to the difference information of the first image based on the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment.

[0100] The sending module 507 is used to send monitoring alarm information to the target terminal if the behavior information indicates that the preset alarm object has performed a preset action on the target item in the preset monitoring area.

[0101] In one possible design, the second determining module 504 determines whether the first image difference information belongs to the preset alarm object information. Specifically, this process includes: determining whether the first image difference information matches multiple pre-stored life information; if the first image difference information matches any of the life information, then the first image difference information is determined to belong to the preset alarm object information; if the first image difference information does not match any of the multiple life information, then the first image difference information does not belong to the preset alarm object information.

[0102] Optionally, the first image difference information includes first coordinate information corresponding to multiple difference points, and the organism information includes second coordinate information corresponding to multiple feature points; correspondingly, the second determining module 504 determines whether the first image difference information matches the pre-stored multiple organism information, specifically including: for each organism information, calculating the matching parameters between the first coordinate information corresponding to multiple difference points and the second coordinate information corresponding to multiple feature points included in the organism information using a preset recursive algorithm; if the matching parameters are less than or equal to a preset threshold, then the first image difference information matches the organism information; if the matching parameters are greater than the preset threshold, then the first image difference information does not match the organism information.

[0103] Optionally, the device further includes: a switching module; the switching module is used to switch the acquisition mode of the video monitoring device if the first image difference information does not belong to light and shadow motion information, wherein the acquisition mode includes night vision mode or daytime mode; acquire a third video monitoring image within a preset monitoring area after switching the acquisition mode; determine the second image difference information of the third video monitoring image relative to the second video monitoring image; determine whether the second image difference information belongs to light and shadow motion information; if the second image difference information belongs to light and shadow motion information, then continue to determine whether the first image difference information belongs to a preset alarm object; if the second image difference information does not belong to light and shadow motion information, then do not send monitoring alarm information to the target terminal.

[0104] Optionally, the recognition module 506 recognizes the behavior information of the preset alarm object corresponding to the first image difference information, specifically including: if the preset alarm object is recognized to press, move or touch the target item in the preset monitoring area, then it is determined that the preset alarm object performs a preset action on the target item in the preset monitoring area.

[0105] Optionally, the device further includes: a third acquisition module; the third acquisition module is used to acquire video surveillance images of the preset alarm object from multiple angles if the behavior information indicates that the preset alarm object has not performed a preset action on the target object within the preset monitoring area, wherein the multiple angles include the front, back, left side and right side.

[0106] Optionally, the device further includes: a verification module; the verification module is used to acquire multiple sets of monitoring information within a preset time period, each set of monitoring information including first image difference information, movement trajectory information corresponding to a preset alarm object in the infrared monitoring image, and light and shadow sway alarm information corresponding to the first image difference information; determine the correlation parameters between the first image difference information, movement trajectory information, and light and shadow sway alarm information in each set of monitoring information, and obtain multiple correlation coefficients corresponding to the multiple sets of monitoring information; if the target correlation coefficient corresponding to the last set of monitoring information is within the preset correlation coefficient range, and the number of correlation coefficients among the multiple correlation coefficients that are close to the target correlation coefficient is greater than the preset number, then the step of sending monitoring alarm information to the target terminal is executed.

[0107] The apparatus provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effects are similar, and will not be described again here.

[0108] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device of this embodiment includes: a processor 601 and a memory 602; wherein

[0109] Memory 602 is used to store instructions executed by the computer;

[0110] The processor 601 is used to execute computer execution instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiments. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0111] Alternatively, the memory 602 can be either standalone or integrated with the processor 601.

[0112] When the memory 602 is set up independently, the electronic device also includes a bus 603 for connecting the memory 602 and the processor 601.

[0113] This application also provides a computer storage medium storing computer execution instructions. When the processor executes the computer execution instructions, it implements the monitoring and identification methods of the above-described method embodiments.

[0114] This application also provides a computer program product, including a computer program, which, when executed by a processor, implements the monitoring and identification methods of the above-described method embodiments.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0116] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0117] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0118] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute partial steps of the methods in the various embodiments of this application.

[0119] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0120] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0121] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0122] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0123] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0124] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A monitoring and identification method, characterized in that, Applied to a monitoring server, the method includes: The video surveillance device acquires video surveillance images within a preset monitoring area in real time and determines whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment. If they are not the same, then determine the first image difference information between the first video surveillance image and the second video surveillance image; Determine whether the first image difference information belongs to light and shadow sway alarm information, wherein the light and shadow sway alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of local shadows; If the first image difference information does not belong to the light and shadow shaking alarm information, then it is further determined whether the first image difference information belongs to the preset alarm object information, wherein the preset alarm object information includes multiple pre-stored life information; If the first image difference information belongs to the preset alarm object information, then the infrared monitoring image of the preset monitoring area is acquired in real time through the infrared monitoring device; Based on the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment, identify the behavioral information of the preset alarm object corresponding to the difference information in the first image; If the behavior information indicates that the preset alarm object performs a preset action on a target item within the preset monitoring area, then a monitoring alarm message is sent to the target terminal.

2. The method according to claim 1, characterized in that, The process of determining whether the first image difference information belongs to the preset alarm object information includes: Determine whether the first image difference information matches the pre-stored information on multiple life forms; If the first image difference information matches any living organism information, then the first image difference information is determined to belong to the preset alarm object information; if the first image difference information does not match multiple living organism information, then the first image difference information does not belong to the preset alarm object information.

3. The method according to claim 2, characterized in that, The first image difference information includes first coordinate information corresponding to multiple difference points, and the organism information includes second coordinate information corresponding to multiple feature points; Accordingly, determining whether the first image difference information matches the pre-stored information on multiple life forms includes: For each life form information, a pre-defined recursive algorithm is used to calculate the matching parameters between the first coordinate information corresponding to the multiple difference points and the second coordinate information corresponding to the multiple feature points included in the life form information. If the matching parameter is less than or equal to a preset threshold, then the first image difference information is determined to match the life information; if the matching parameter is greater than the preset threshold, then the first image difference information is determined to not match the life information.

4. The method according to claim 1, characterized in that, Also includes: If the first image difference information does not belong to the light and shadow sway information, then the acquisition mode of the video monitoring device is switched, wherein the acquisition mode includes night vision mode or daytime mode; Acquire the third video surveillance image within the preset monitoring area after switching the acquisition mode; Determine the second image difference information between the third video surveillance image and the second video surveillance image; Determine whether the difference information in the second image belongs to light and shadow motion information; If the second image difference information belongs to the light and shadow sway information, then it is further determined whether the first image difference information belongs to the preset alarm object. If the second image difference information does not belong to the light and shadow sway information, then no monitoring alarm information is sent to the target terminal.

5. The method according to claim 1, characterized in that, The behavioral information of the preset alarm object corresponding to the first image difference information includes: If the preset alarm object is detected to press, move, or touch a target item within the preset monitoring area, it is determined that the preset alarm object has performed a preset action on the target item within the preset monitoring area.

6. The method according to claim 1, characterized in that, Also includes: If the behavior information indicates that the preset alarm object has not performed a preset action on the target item within the preset monitoring area, then video monitoring images of the preset alarm object from multiple angles are acquired, including the front, back, left side, and right side.

7. The method according to any one of claims 1-6, characterized in that, Before sending the monitoring alarm information to the target terminal, the process also includes: Acquire multiple sets of monitoring information within a preset time period. Each set of monitoring information includes first image difference information, movement trajectory information corresponding to a preset alarm object in the infrared monitoring image, and light and shadow swaying alarm information corresponding to the first image difference information. Determine the relevant parameters among the first image difference information, movement trajectory information, and light and shadow sway alarm information in each group of monitoring information to obtain multiple correlation coefficients corresponding to multiple groups of monitoring information; If the target correlation coefficient corresponding to the last set of monitoring information is within the preset correlation coefficient range, and the number of correlation coefficients that are close to the target correlation coefficient among multiple correlation coefficients is greater than the preset number, then the step of sending monitoring alarm information to the target terminal is executed.

8. A monitoring and identification device, characterized in that, The device, used in a monitoring server, includes: The first acquisition module is used to acquire video surveillance images within a preset monitoring area in real time through a video surveillance device, and to determine whether the first video surveillance image at the current moment is the same as the second video surveillance image at the previous moment. The first determining module is used to determine first image difference information between the first video surveillance image and the second video surveillance image if they are not the same. The judgment module is used to determine whether the first image difference information belongs to the light and shadow sway alarm information, wherein the light and shadow sway alarm information includes one or more of the following: changes in light brightness, changes in natural light brightness, and the appearance of shadows in a local area; The second determining module is used to determine whether the first image difference information belongs to preset alarm object information if the first image difference information does not belong to the light and shadow shaking alarm information, wherein the preset alarm object information includes multiple pre-stored life information. The second acquisition module is used to acquire infrared monitoring images in the preset monitoring area in real time through an infrared monitoring device if the first image difference information belongs to the preset alarm object information. The identification module is used to identify the behavior information of a preset alarm object corresponding to the difference information in the first infrared monitoring image at the current moment and the second infrared monitoring image at the next moment. The sending module is used to send monitoring alarm information to the target terminal if the behavior information indicates that the preset alarm object has performed a preset action on the target item in the preset monitoring area.

9. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the monitoring and identification method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, it implements the monitoring and identification method as described in any one of claims 1 to 7.

Images