A camera monitoring method and device, storage medium and electronic device

Abstract

The application discloses a camera monitoring method and device, a storage medium and an electronic device. The method comprises the following steps: if a moving object is monitored, acquiring first feature information of the object; if target feature information matched with the first feature information exists in a false touch feature set, stopping monitoring the object; and if target feature information matched with the first feature information does not exist in the false touch feature set, identifying the object. The false touch feature set is generated based on second feature information of a false touch object. The application uses the false touch feature set generated based on the feature information of the false touch object to determine whether the object is a false touch object, avoids objects that are easy to cause false touch of the radar, reduces the situation that the device is falsely woken up, improves the monitoring accuracy, and reduces the power consumption of the device.

Description

Technical Field

[0001] This application relates to the field of security monitoring, and in particular to a video monitoring method, device, storage medium and electronic equipment. Background Technology

[0002] Existing security and monitoring equipment often uses smart cameras for monitoring. Most existing cameras are equipped with intelligent recognition functions. Due to the limitations of installation location or method, cameras are usually not convenient to be directly plugged into a power source, but instead have built-in batteries. Therefore, monitoring equipment has the need to save power and extend the battery life of camera equipment. Summary of the Invention

[0003] This application provides a camera monitoring method, device, storage medium, and electronic device. It can determine whether an object is a false trigger by using a set of false-trigger feature information generated from the feature information of the falsely triggered object. This avoids objects that easily cause false radar triggers, thereby reducing the occurrence of false device wake-ups, improving monitoring accuracy, and reducing device power consumption. The technical solution is as follows:

[0004] In a first aspect, embodiments of this application provide a camera monitoring method, the method comprising:

[0005] If a moving object is detected, the first feature information of the object is obtained;

[0006] If the set of accidental touch features contains target feature information that matches the first feature information, then the monitoring of the object is stopped;

[0007] If there is no target feature information in the set of accidental touch features that matches the first feature information, then the object is identified;

[0008] The set of accidental touch features is generated based on the second feature information of the accidentally triggered object, and stopping the monitoring of the object means not waking up the camera module to monitor the object.

[0009] Based on the above embodiments, the first feature information of the object is compared with the feature information in the false trigger feature set, which avoids objects that are easy to cause the radar to be falsely triggered, thus improving the monitoring accuracy.

[0010] Optionally, before acquiring the first feature information of a moving object if it is detected, the method further includes:

[0011] At least one falsely triggered object is detected using a radar sensor, and the second characteristic information of each falsely triggered object is obtained.

[0012] A set of accidental trigger features is generated based on the second feature information of each of the accidentally triggered objects.

[0013] Based on the above embodiments, before the camera monitoring device is put into operation, a set of false trigger features is generated by classifying the second feature information of the falsely triggered objects. This improves the efficiency of screening objects that are likely to cause false triggering of the radar and further improves the monitoring accuracy.

[0014] Optionally, the step of using a radar sensor to detect at least one falsely triggered object and obtaining second feature information of each of the at least one falsely triggered object includes:

[0015] At least one moving object is detected using a radar sensor, and facial recognition processing is performed on the at least one moving object;

[0016] Among the at least one moving object, at least one falsely triggered object that has not passed the human face recognition process is obtained, and the second feature information of each falsely triggered object among the at least one falsely triggered object is obtained.

[0017] Based on the above embodiments, falsely triggered objects are found in moving objects through facial recognition processing, limiting the scope of falsely triggered objects to non-humans, so that the false touch feature set preserves the characteristics of the falsely triggered objects, further improving the monitoring accuracy.

[0018] Optionally, generating a set of accidental touch features based on the second feature information of each accidentally triggered object includes:

[0019] Based on the second feature information of each falsely triggered object, a classification algorithm is used to generate a false-trigger polar coordinate matrix.

[0020] Based on the above embodiments, since the objects that are mistakenly triggered are spatially related, the classification algorithm can improve the effectiveness of the classification algorithm.

[0021] Optionally, if a moving object is detected, the first feature information of the object is acquired, including:

[0022] If a moving object is detected based on image analysis, the first feature information of the object is obtained.

[0023] Based on the above embodiments, frame-by-frame image comparison and analysis can be used to monitor moving objects, obtain the first feature information of the objects, provide multiple object monitoring methods, and further improve monitoring accuracy.

[0024] Optionally, the first feature information includes the polar coordinates and physical features of the object;

[0025] If the set of accidental touch features contains target feature information that matches the first feature information, then stop monitoring the object, including:

[0026] If the similarity between the polar coordinates and physical features of the object and the target feature information in the false polar coordinate matrix is ​​higher than the similarity threshold, then the monitoring of the object shall be stopped.

[0027] Based on the above embodiments, the similarity between the first feature information and the erroneous polar coordinates is determined. If the similarity is too high, the object is likely to cause the radar to be falsely triggered, and the monitoring of the object is stopped, thus saving the power consumption of the camera monitoring device.

[0028] Optionally, if no target feature information matching the first feature information exists in the set of accidental touch features, then identifying the object includes:

[0029] If there is no target feature information in the set of accidental touch features that matches the first feature information, then the object is subjected to human face recognition processing;

[0030] If the object is processed by facial recognition, an early warning notification will be issued.

[0031] Based on the above embodiments, facial recognition processing is performed on objects that do not match the accidental touch feature matrix to further improve the monitoring function.

[0032] Optionally, the method further includes:

[0033] If the object has not passed the human face recognition process, the mis-touch feature set is updated based on the first feature information of the object.

[0034] Based on the above embodiments, the set of accidental touch features is updated using the first feature information of the object, so that the camera monitoring device can continue to improve the set of accidental touch features during normal use.

[0035] Secondly, embodiments of this application provide a camera monitoring device, the device comprising:

[0036] The feature acquisition module is used to acquire the first feature information of the object if a moving object is detected.

[0037] The matrix matching module is used to stop monitoring the object if there is a target feature information in the accidental touch feature set that matches the first feature information.

[0038] An object recognition module is used to recognize the object if there is no target feature information in the set of accidental touch features that matches the first feature information.

[0039] The set of accidental touch features is generated based on the second feature information of the accidentally triggered object, and stopping the monitoring of the object means not waking up the camera module to monitor the object.

[0040] Thirdly, embodiments of this application provide an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, the computer program being adapted to be loaded by the processor and to execute the above-described method steps.

[0041] In one or more embodiments of this application, if a moving object is detected, first feature information of the object is acquired. If a target feature information matching the first feature information exists in the false-touch feature set, monitoring of the object is stopped. If no target feature information matching the first feature information exists in the false-touch feature set, the object is identified. The false-touch feature set is generated based on the second feature information of the falsely triggered object. By using the false-touch feature set generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a falsely triggered object, avoiding objects that are likely to cause false triggering of the radar, thereby reducing the possibility of the device being falsely woken up, improving monitoring accuracy, and reducing device power consumption. Attached Figure Description

[0042] 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 only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the structure of a camera monitoring device provided in an embodiment of this application;

[0044] Figure 2 This is a schematic flowchart of a camera monitoring method provided in an embodiment of this application;

[0045] Figure 3 This is a schematic flowchart of a camera monitoring method provided in an embodiment of this application;

[0046] Figure 4 This is an example diagram illustrating a similarity calculation provided in an embodiment of this application;

[0047] Figure 5 This is a schematic diagram of the structure of a camera monitoring device provided in an embodiment of this application;

[0048] Figure 6 This is a schematic diagram of the structure of a camera monitoring device provided in an embodiment of this application;

[0049] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0050] 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, and 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.

[0051] Please see also Figure 1 This application provides a schematic diagram of a camera monitoring device. The camera monitoring device includes a radar sensor, a camera module, and a processor. One end of the processor is connected to the radar sensor, and the other end of the processor is connected to the camera module, which is also connected to the radar sensor. The radar sensor can use radio waves to detect targets and determine their spatial positions. It is an electronic device that can detect targets using electromagnetic waves. The radar sensor emits electromagnetic waves to illuminate the target and receives its echo, thereby obtaining information such as the distance from the target to the electromagnetic wave emission point, the rate of change of distance (radial velocity), azimuth, and height. The camera module can acquire images of the surrounding environment, facilitating the observation of objects or people in the environment. The camera monitoring device can use the radar sensor and camera module to monitor a space within a set distance range. It is understood that the sensing range of the radar sensor and the imaging range of the camera module are limited. To ensure the accuracy of the monitoring results and protect the privacy of others, the camera monitoring device can be set to a set distance, monitoring only the space within the set distance range.

[0052] Camera monitoring devices use radar sensors to monitor moving objects and acquire their feature information. This feature information can include the object's coordinates (including polar or spatial coordinates) and physical characteristics. The camera monitoring device can generate the object's polar coordinates based on the distance and angle from the object to the radar sensor. Since the object is moving, the polar coordinates can represent a series of coordinates representing the object's trajectory. Physical characteristics can include the object's size, the amount of radar wave energy reflected by the object, and the object's speed. The radar sensor sends the object's feature information to a processor. The processor determines whether the object is a false trigger based on this information. Since the camera monitoring device is used to monitor whether someone is within a set distance range, a false trigger is any object other than a person that is moving and detected by the radar sensor. If the processor determines the object is a false trigger, it stops monitoring the object. Otherwise, if the object is not a false trigger, the camera monitoring device identifies the object, determines whether it is a person, and can also acquire facial images for facial recognition and other operations. The camera monitoring device uses radar to acquire the feature information of objects and determines whether an object is a false trigger based on the feature information. It avoids objects that are likely to cause false triggering of the radar, thereby reducing the situation of the device being falsely awakened, improving the monitoring accuracy, and reducing the power consumption of the device.

[0053] based on Figure 1 The system architecture shown below will be combined with... Figures 2-4 This application provides a detailed description of the video surveillance method provided in its embodiments. Figures 2-4 The illustrated embodiment can be specifically implemented in scenarios involving camera monitoring of objects.

[0054] Please see Figure 2 The diagram below illustrates a camera monitoring method as provided in this application. Figure 1 As shown, the method described in this application embodiment may include the following steps S101-S103.

[0055] S101, if a moving object is detected, the first feature information of the object is obtained.

[0056] Specifically, the camera monitoring device can use a radar sensor to monitor the space within a set distance range. When an object is moving, the energy of the reflected radar waves will fluctuate to a certain extent. When the radar sensor detects fluctuations in the received radar wave energy within the set distance range, it can determine that a moving object has been detected. It is understandable that different objects and different states of motion produce different amplitudes of radar wave energy fluctuations; for example, faster-moving and larger objects produce larger amplitude fluctuations. To avoid the influence of objects with slight displacement due to the natural environment on camera monitoring, the camera monitoring device can be set to only confirm the presence of a moving object if the radar wave energy fluctuation exceeds a preset amplitude, avoiding the activation of the camera module by non-detectable target movements such as swaying plants. The camera monitoring device can use a radar sensor to obtain the object's first feature information, which may include the object's polar coordinates and physical characteristics. It is also understood that the camera monitoring device can use a camera module to acquire images of the space within the set distance range. Through image analysis, i.e., frame-by-frame comparison of the images, it can monitor moving objects and obtain their first feature information.

[0057] S102, if there is target feature information in the false touch feature set that matches the first feature information, then stop monitoring the object.

[0058] Specifically, when the camera monitoring device acquires second feature information from the radar sensor when at least one falsely triggered object moves within a set distance range, the second feature information may include the polar coordinates and physical features of the falsely triggered object. The camera monitoring device generates a false trigger feature set based on the second feature information of each falsely triggered object. The false trigger feature set stores the second feature information of each falsely triggered object and projects the physical features of each falsely triggered object onto a coordinate system corresponding to the space within the set distance range. For example, the camera monitoring device can use a classification algorithm to calculate and generate a false trigger polar coordinate matrix. The position of the target element in the false trigger polar coordinate matrix corresponds to the polar coordinates of the falsely triggered object after the classification algorithm calculates it. The target feature information on the target element represents the physical features of the falsely triggered object after the classification algorithm calculates it.

[0059] If the false-touch feature set contains target feature information that matches the first feature information—for example, if the target feature information at the same position as the first feature information in the false-touch polar coordinate matrix has the same or similar physical characteristics as the first feature information—then it indicates that the first feature information matches the false-touch polar coordinate matrix. The camera monitoring device can then confirm that the object is also a falsely triggered object and stop monitoring it, thereby avoiding waking up the camera module and saving power. In practical applications, movement of non-detectable targets caused by extreme weather often leads to the camera module waking up and working for extended periods, consuming a large amount of battery power. This embodiment avoids this problem at its source.

[0060] S103, if there is no target feature information in the mis-touch feature set that matches the first feature information, then the object is identified.

[0061] Specifically, if no target feature information matching the first feature information is found in the set of accidental trigger features, the camera monitoring device confirms that the object is not an accidental trigger and can identify the object. For example, the camera monitoring device can perform facial recognition processing on the object to determine if it is a person. If the object passes the facial recognition processing, it means that the camera monitoring device confirms that the object is a person. It can also acquire facial images for identification to determine whether the person has permission to enter the space, and can also issue an early warning notification to notify relevant staff that an outsider has entered the space.

[0062] In this embodiment, if a moving object is detected, first feature information of the object is acquired. If a target feature matching the first feature information exists in the false-touch feature set, monitoring of the object is stopped. If no target feature matching the first feature information exists in the false-touch feature set, the object is identified. The false-touch feature set is generated based on the second feature information of the falsely triggered object. By using the false-touch feature set generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a falsely triggered object, avoiding objects that are likely to cause false triggering of the radar, thereby reducing the possibility of the device being falsely woken up, improving monitoring accuracy, and reducing device power consumption.

[0063] Please see Figure 3 The diagram below illustrates a camera monitoring method as provided in this application. Figure 3 As shown, the method described in this application embodiment may include the following steps S201-S208.

[0064] S201, at least one falsely triggered object is detected by a radar sensor, and the second characteristic information of each falsely triggered object is obtained.

[0065] Specifically, before formally adopting the camera monitoring equipment for monitoring, the camera monitoring equipment can be tested for a period of time. During the test period, the camera monitoring equipment can use radar sensors to detect at least one falsely triggered object and obtain the second feature information of these falsely triggered objects. The second feature information may include the polar coordinates and physical characteristics of the falsely triggered object.

[0066] Optionally, when an object is moving, the energy of the reflected radar waves will fluctuate to a certain extent. When the radar sensor detects fluctuations in the received radar wave energy within a set distance range, it can determine that a moving object has been detected. It is understandable that different objects and different states of motion produce different amplitudes of radar wave energy fluctuations. For example, faster-moving and larger objects produce larger amplitude fluctuations. To avoid the influence of objects with slight displacement due to the natural environment on camera monitoring, the camera monitoring device can be set to only confirm the presence of a moving object if the radar wave energy fluctuation exceeds a preset amplitude. For example, a tree branch will move due to wind. The radar sensor will detect fluctuations in radar wave energy at the location of the branch. However, because the branch is small and moves slowly, the amplitude of the radar wave energy fluctuation generated by the branch is small and will not be considered a moving object by the camera monitoring device, further avoiding the influence of the natural environment on the radar sensor.

[0067] The camera monitoring device can use a radar sensor to detect at least one moving object within a set distance range during a test period. It then performs facial recognition processing on these at least one moving object. If the facial recognition process passes, the moving object is considered a person; otherwise, it is considered a falsely triggered object. The camera monitoring device can acquire at least one falsely triggered object from among the at least one moving object that failed the facial recognition process, and also acquire the second characteristic information of each of the at least one falsely triggered object.

[0068] S202, Generate a set of accidental trigger features based on the second feature information of each accidentally triggered object.

[0069] Specifically, the camera monitoring device generates a set of false-touch features based on the second feature information of each falsely triggered object. This set stores the second feature information of each object and projects the physical features of each object onto a coordinate system corresponding to a space within a set distance range. For example, the camera monitoring device can use a classification algorithm to generate a false-touch polar coordinate matrix. The position of the target element within the matrix corresponds to the polar coordinates of the falsely triggered object calculated by the classification algorithm, and the target feature information on the target element represents the physical features of the falsely triggered object after the classification algorithm's calculation. In another embodiment, the coordinate system can also be a Cartesian coordinate system, calculated based on the spatial coordinates of the object's location.

[0070] Optionally, since the objects that are accidentally triggered are similar in space, the camera monitoring device can use classification algorithms such as the k-nearest neighbor algorithm to generate the polar coordinate matrix of the false triggers.

[0071] S203, if a moving object is detected based on the radar sensor, then the first feature information of the object is obtained.

[0072] Specifically, after generating the polar coordinate matrix of accidental touches, the camera monitoring device can officially monitor the space within a set distance range. It can detect moving objects based on radar sensors and acquire the object's first feature information, including its polar coordinates and physical characteristics. Understandably, the camera monitoring device can also use a camera module to acquire images of the space within the set distance range. Through image analysis—that is, by comparing images frame by frame—it can monitor moving objects and acquire their first feature information.

[0073] S204. If the similarity between the polar coordinates and physical features of the object and the target feature information in the false polar coordinate matrix is ​​higher than the similarity threshold, then stop monitoring the object.

[0074] Specifically, the camera monitoring device can calculate the similarity between the polar coordinates and physical features of an object and the target feature information in the false-touch polar coordinate matrix. For example, it can obtain the target feature information at the same position as the polar coordinates in the first feature information in the false-touch polar coordinate matrix, calculate the similarity between the target feature information and the physical features in the first feature information, and if the similarity is higher than the similarity threshold, the camera monitoring device can confirm that the object is also a false-touch object and stop monitoring the object.

[0075] Please see also Figure 4 This document provides an example of similarity calculation in an embodiment of this application. The camera monitoring device detects a moving object A and its corresponding first feature information based on a radar sensor. Since the distance between object A and the radar sensor is 'a', and the angle between the connection and the coordinate axis is 'θ', the polar coordinates of object A are (a, θ), and the physical features of object A can be obtained. Then, the image monitoring device can find the target feature information of the element corresponding to the polar coordinates of object A in the false-touch polar coordinate matrix. For example, the number of rows in the false-touch polar coordinate matrix corresponds to the distance between the object and the radar sensor. If the set distance of the camera monitoring device is n, the false-touch polar coordinate matrix can have n rows, and the number of columns in the false-touch polar coordinate matrix corresponds to the angle between the object connection and the coordinate axis. The element X of the false-touch polar coordinate is obtained based on the polar coordinates (a, θ) of object A. aθ Then calculate the physical characteristics of object A and element X. aθIf the similarity of the target feature information represented by the object is higher than the similarity threshold, the camera monitoring device can confirm that the object is also a false trigger object and stop monitoring the object.

[0076] S205, if there is no target feature information in the erroneous touch feature set that matches the first feature information, then perform human face recognition processing on the object.

[0077] Specifically, if there is no target feature information in the false touch feature set that matches the first feature information, and there is no target feature information in the false touch polar coordinate matrix that has a similarity higher than the similarity threshold with the first feature information, then the camera monitoring device confirms that the object is not a falsely triggered object, and can perform facial recognition processing on the object to determine whether the object is a person.

[0078] S206, determine whether the object has passed the facial recognition process.

[0079] Specifically, if the object passes the facial recognition process, it indicates that the object is a person, and S207 is executed; if the object does not pass the facial recognition process, it indicates that the object is also a falsely triggered object, and S208 is executed.

[0080] S207, issued a warning notice.

[0081] Specifically, if an object passes the facial recognition process, it means that the camera monitoring device has confirmed that the object is a person and belongs to an outsider. The camera monitoring device can issue an early warning notification to notify relevant staff that an outsider has entered the space.

[0082] Optionally, the camera monitoring device can acquire facial images of visitors to determine whether they have permission to enter the space. If they have permission, no warning notification will be issued; otherwise, a warning notification will continue to be issued.

[0083] S208, Update the set of accidental touch features based on the first feature information of the object.

[0084] Specifically, if an object fails to pass the facial recognition process, it means that the object is a falsely triggered object that has not been recorded by the camera monitoring device before. The camera monitoring device can use the object's first feature information and all previously acquired second feature information to calculate and update the false trigger polar coordinate matrix using a classification algorithm, so that the camera monitoring device can continue to improve the false trigger polar coordinate matrix during normal use.

[0085] In this embodiment, a radar sensor is used in conjunction with a preset amplitude to acquire at least one moving object, avoiding the influence of the natural environment on the radar sensor. Similarly, image analysis can also be used to acquire moving objects, providing multiple methods for object monitoring and further improving monitoring accuracy. Then, facial recognition processing is used to identify at least one falsely triggered object among the at least one moving object. Based on the second feature root information of the falsely triggered object, a classification algorithm is used to generate a false-trigger polar coordinate matrix. If a moving object is detected by the radar sensor, the object's first feature information is acquired. If the first feature information matches the false-trigger polar coordinate matrix, monitoring of the object is stopped. If the first feature information does not match the false-trigger polar coordinate matrix, the object is identified. The false-trigger polar coordinate matrix is ​​generated based on the second feature information of the falsely triggered object. By using the false-trigger polar coordinate matrix generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a false trigger, avoiding objects that easily cause false radar triggers, thereby reducing the possibility of the device being falsely awakened, improving monitoring accuracy while reducing device power consumption. If the object is a falsely triggered object that has not yet been recorded by the camera monitoring device, the false trigger polar coordinate matrix is ​​updated using the object's first feature information, continuously improving the monitoring function of the camera monitoring device and further enhancing the accuracy of monitoring.

[0086] based on Figure 1 The system architecture will be discussed below in conjunction with the appendix. Figure 5 -Appendix Figure 6 This application provides a detailed description of the camera monitoring device provided in its embodiments. It should be noted that the appendix... Figure 5 -Appendix Figure 6 The data monitoring device in the middle is used to perform this application. Figures 2-4 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figures 2-4 The example shown.

[0087] Please see Figure 5 This illustration shows a schematic diagram of a camera monitoring device provided in an exemplary embodiment of this application. The camera monitoring device can be implemented as all or part of a device through software, hardware, or a combination of both. The device 1 includes a feature acquisition module 11, a matrix matching module 12, and an object recognition module 13.

[0088] The feature acquisition module 11 is used to acquire the first feature information of the object if a moving object is detected.

[0089] The matrix matching module 12 is used to stop monitoring the object if there is target feature information in the accidental touch feature set that matches the first feature information.

[0090] The object recognition module 13 identifies the object if there is no target feature information in the set of accidental touch features that matches the first feature information.

[0091] The set of accidental touch features is generated based on the second feature information of the accidentally triggered object, and stopping the monitoring of the object means not waking up the camera module to monitor the object.

[0092] In this embodiment, if a moving object is detected, the object's first feature information is acquired. If a target feature matching the first feature information exists in the false-touch feature set, monitoring of the object is stopped. If no target feature matching the first feature information exists in the false-touch feature set, the object is identified. The false-touch feature set is generated based on the second feature information of the falsely triggered object. By using the false-touch feature set generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a false-touch object, avoiding objects that are likely to cause false triggering of the radar, thereby reducing the possibility of the device being falsely woken up, improving monitoring accuracy, and reducing device power consumption.

[0093] Please see Figure 6 This illustration shows a schematic diagram of a camera monitoring device provided in an exemplary embodiment of this application. The camera monitoring device can be implemented as all or part of a device through software, hardware, or a combination of both. The device 1 includes a feature acquisition module 11, a matrix matching module 12, an object recognition module 13, an accidental touch object detection module 14, a matrix generation module 15, and a matrix update module 16.

[0094] The accidental triggering object detection module 14 is used to detect at least one accidentally triggered object using a radar sensor and obtain the second characteristic information of each accidentally triggered object among the at least one accidentally triggered object;

[0095] Optionally, the accidental touch object detection module 14 is specifically used to detect at least one moving object using a radar sensor and perform facial recognition processing on the at least one moving object;

[0096] Among the at least one moving object, at least one falsely triggered object that has not passed the human face recognition process is obtained, and the second feature information of each falsely triggered object among the at least one falsely triggered object is obtained.

[0097] Matrix generation module 15 is used to generate a set of accidental trigger features based on the second feature information of each accidentally triggered object;

[0098] Optionally, the matrix generation module 15 is specifically used to generate a polar coordinate matrix of false triggers based on the second feature information of each falsely triggered object using a classification algorithm.

[0099] The feature acquisition module 11 is used to acquire the first feature information of the object if a moving object is detected.

[0100] Optionally, the feature acquisition module 11 is specifically used to acquire the first feature information of the object if a moving object is detected based on image analysis.

[0101] The matrix matching module 12 is used to stop monitoring the object if there is target feature information in the accidental touch feature set that matches the first feature information.

[0102] Optionally, the matrix matching module 12 is specifically used to stop monitoring the object if the similarity between the polar coordinates and physical features of the object and the target feature information in the falsely touched polar coordinate matrix is ​​higher than a similarity threshold; wherein, the first feature information includes the polar coordinates and physical features of the object.

[0103] The object recognition module 13 is used to recognize the object if there is no target feature information matching the first feature information in the set of accidental touch features; wherein, the set of accidental touch features is generated based on the second feature information of the accidentally triggered object, and stopping the monitoring of the object means not waking up the camera module to monitor the object;

[0104] Optionally, the object recognition module 13 is specifically used to perform human face recognition processing on the object if there is no target feature information that matches the first feature information in the set of accidental touch features.

[0105] If the object is processed by facial recognition, an early warning notification will be issued.

[0106] The matrix update module 16 is used to update the mis-touch feature set based on the first feature information of the object if the object has not passed the human face recognition process.

[0107] In this embodiment, a radar sensor is used in conjunction with a preset amplitude to acquire at least one moving object, avoiding the influence of the natural environment on the radar sensor. Similarly, image analysis can also be used to acquire moving objects, providing multiple methods for object monitoring and further improving monitoring accuracy. Then, facial recognition processing is used to identify at least one falsely triggered object among the at least one moving object. Based on the second feature root information of the falsely triggered object, a classification algorithm is used to generate a false-trigger polar coordinate matrix. If a moving object is detected by the radar sensor, the object's first feature information is acquired. If the first feature information matches the false-trigger polar coordinate matrix, monitoring of the object is stopped. If the first feature information does not match the false-trigger polar coordinate matrix, the object is identified. The false-trigger polar coordinate matrix is ​​generated based on the second feature information of the falsely triggered object. By using the false-trigger polar coordinate matrix generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a false trigger, avoiding objects that easily cause false radar triggers, thereby reducing the possibility of the device being falsely awakened, improving monitoring accuracy while reducing device power consumption. If the object is a falsely triggered object that has not yet been recorded by the camera monitoring device, the false trigger polar coordinate matrix is ​​updated using the object's first feature information, continuously improving the monitoring function of the camera monitoring device and further enhancing the accuracy of monitoring.

[0108] It should be noted that the camera monitoring device provided in the above embodiments is only illustrated by the division of the above functional modules when performing the camera monitoring method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the camera monitoring device and the camera monitoring method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0109] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0110] This application also provides a computer storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 2-4 The camera monitoring method described in the illustrated embodiment can be found in the following document for a detailed execution process. Figures 2-4 The specific details of the illustrated embodiments will not be elaborated here.

[0111] This application also provides a computer program product storing at least one instruction, which is loaded and executed by the processor as described above. Figures 2-4 The camera monitoring method described in the illustrated embodiment can be found in the following document for a detailed execution process. Figures 2-4 The specific details of the illustrated embodiments will not be elaborated here.

[0112] Please refer to Figure 7 This diagram illustrates a structural block diagram of an electronic device provided in an exemplary embodiment of this application. The electronic device in this application may include one or more components such as a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, memory 120, input device 130, and output device 140 may be connected via the bus 150.

[0113] Processor 110 may include one or more processing cores. Processor 110 connects to various parts of the electronic device using various interfaces and lines, and executes various functions of terminal 100 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 120, and by calling data stored in memory 120. Optionally, processor 110 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Arrays (PLA). Processor 110 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user page, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 110 and may be implemented separately using a communication chip.

[0114] The memory 120 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 120 may include non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the various method embodiments described above, etc. The operating system may be the Android system, including systems deeply developed based on the Android system, the iOS system developed by Apple Inc., including systems deeply developed based on the iOS system, or other systems.

[0115] The memory 120 can be divided into operating system space and user space. The operating system runs in the operating system space, while native and third-party applications run in user space. To ensure that different third-party applications can achieve good running performance, the operating system allocates corresponding system resources for each application. However, different application scenarios within the same third-party application have different requirements for system resources. For example, in local resource loading scenarios, third-party applications have high requirements for disk read speed; in animation rendering scenarios, third-party applications have high requirements for GPU performance. Since the operating system and third-party applications are independent of each other, the operating system often cannot promptly perceive the current application scenario of a third-party application, resulting in the operating system's inability to adapt system resources accordingly.

[0116] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to establish data communication between the third-party applications and the operating system. This would allow the operating system to obtain the current scenario information of the third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.

[0117] The input device 130 is used to receive input instructions or data, and includes, but is not limited to, a keyboard, mouse, camera, microphone, or touch device. The output device 140 is used to output instructions or data, and includes, but is not limited to, a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 can be a touch display screen.

[0118] The touch display screen can be designed as a full-screen, curved screen, or irregularly shaped screen. It can also be designed as a combination of a full-screen and a curved screen, or a combination of an irregularly shaped screen and a curved screen; however, this application does not limit the specific design in this regard.

[0119] In addition, those skilled in the art will understand that the structure of the electronic device shown in the above figures does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. For example, the electronic device may also include radio frequency circuits, input units, sensors, audio circuits, Wireless Fidelity (WiFi) modules, power supplies, Bluetooth modules, etc., which will not be described in detail here.

[0120] exist Figure 7 In the illustrated electronic device, the processor 110 can be used to call the camera monitoring application stored in the memory 120 and specifically perform the following operations:

[0121] If a moving object is detected, the first feature information of the object is obtained;

[0122] If the set of accidental touch features contains target feature information that matches the first feature information, then the monitoring of the object is stopped;

[0123] If there is no target feature information in the set of accidental touch features that matches the first feature information, then the object is identified;

[0124] The set of accidental touch features is generated based on the second feature information of the accidentally triggered object, and stopping the monitoring of the object means not waking up the camera module to monitor the object.

[0125] In one embodiment, before the processor 110 performs the operation of acquiring first feature information of an object if a moving object is detected based on a radar sensor, the processor 110 also performs the following operations:

[0126] At least one falsely triggered object is detected using a radar sensor, and the second characteristic information of each falsely triggered object is obtained.

[0127] A set of accidental trigger features is generated based on the second feature information of each of the accidentally triggered objects.

[0128] In one embodiment, when the processor 110 executes the operation of detecting at least one falsely triggered object using a radar sensor and acquiring the second feature information of each of the at least one falsely triggered object, it specifically performs the following operations:

[0129] At least one moving object is detected using a radar sensor, and facial recognition processing is performed on the at least one moving object;

[0130] Among the at least one moving object, at least one falsely triggered object that has not passed the human face recognition process is obtained, and the second feature information of each falsely triggered object among the at least one falsely triggered object is obtained.

[0131] In one embodiment, when the processor 110 generates a set of false-touch features based on the second feature information of each falsely triggered object, it specifically performs the following operations:

[0132] Based on the second feature information of each falsely triggered object, a classification algorithm is used to generate a false-trigger polar coordinate matrix.

[0133] In one embodiment, when the processor 110 executes the command "If a moving object is detected, acquire the first feature information of the object", it specifically performs the following operations:

[0134] If a moving object is detected based on image analysis, the first feature information of the object is obtained.

[0135] In one embodiment, when the processor 110 executes the command "If there is target feature information in the accidental touch feature set that matches the first feature information, then stop monitoring the object", it specifically performs the following operations:

[0136] If the similarity between the polar coordinates and physical features of the object and the target feature information in the falsely touched polar coordinate matrix is ​​higher than a similarity threshold, then the monitoring of the object is stopped; wherein, the first feature information includes the polar coordinates and physical features of the object.

[0137] In one embodiment, when the processor 110 performs the operation of identifying the object if no target feature information matching the first feature information exists in the set of accidental touch features, the processor 110 specifically performs the following operations:

[0138] If there is no target feature information in the set of accidental touch features that matches the first feature information, then the object is subjected to human face recognition processing;

[0139] If the object is processed by facial recognition, an early warning notification will be issued.

[0140] In one embodiment, when executing the camera monitoring method, the processor 110 also performs the following operations:

[0141] If the object has not passed the human face recognition process, the mis-touch feature set is updated based on the first feature information of the object.

[0142] In this embodiment, a radar sensor is used in conjunction with a preset amplitude to acquire at least one moving object, avoiding the influence of the natural environment on the radar sensor. Similarly, image analysis can also be used to acquire moving objects, providing multiple methods for object monitoring and further improving monitoring accuracy. Then, facial recognition processing is used to identify at least one falsely triggered object among the at least one moving object. Based on the second feature root information of the falsely triggered object, a classification algorithm is used to generate a false-trigger polar coordinate matrix. If a moving object is detected by the radar sensor, the object's first feature information is acquired. If the first feature information matches the false-trigger polar coordinate matrix, monitoring of the object is stopped. If the first feature information does not match the false-trigger polar coordinate matrix, the object is identified. The false-trigger polar coordinate matrix is ​​generated based on the second feature information of the falsely triggered object. By using the false-trigger polar coordinate matrix generated from the feature information of the falsely triggered object, it is possible to determine whether an object is a false trigger, avoiding objects that easily cause false radar triggers, thereby reducing the possibility of the device being falsely awakened, improving monitoring accuracy while reducing device power consumption. If the object is a falsely triggered object that has not yet been recorded by the camera monitoring device, the false trigger polar coordinate matrix is ​​updated using the object's first feature information, continuously improving the monitoring function of the camera monitoring device and further enhancing the accuracy of monitoring.

[0143] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0144] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A camera monitoring method characterized by, The method comprises: if a moving object is monitored, acquiring first feature information of the object; if target feature information matching the first feature information exists in a false touch feature set, stopping monitoring of the object; if target feature information matching the first feature information does not exist in the false touch feature set, identifying the object; wherein the false touch feature set is generated based on second feature information of a false touch object, and the stopping of monitoring of the object is not awakening a camera module to monitor the object; if target feature information with a similarity higher than a similarity threshold to the first feature information exists in the false touch feature set, determining that the object is a false touch object and stopping monitoring of the object; if target feature information with a similarity higher than a similarity threshold to the first feature information does not exist in the false touch feature set, determining that the object is not a false touch object and identifying the object to determine whether the object is a person; and if the object is not a person, updating the false touch feature set based on the first feature information. before the if a moving object is monitored, acquiring first feature information of the object, the method further comprises: monitoring at least one false touch object by using a radar sensor, and acquiring second feature information of each false touch object in the at least one false touch object; 2. The method of claim 1, wherein, generating a false touch feature set based on the second feature information of each false touch object. the monitoring at least one false touch object by using a radar sensor, and acquiring second feature information of each false touch object in the at least one false touch object, comprises: monitoring at least one moving object by using a radar sensor, and performing portrait identification processing on the at least one moving object; 3. The method of claim 2, wherein, acquiring at least one false touch object that does not pass the portrait identification processing from the at least one moving object, and acquiring second feature information of each false touch object in the at least one false touch object. the generating a false touch feature set based on the second feature information of each false touch object, comprises: generating a false touch polar coordinate matrix by using a classification algorithm based on the second feature information of each false touch object.

4. The method of claim 2, wherein, the if a moving object is monitored, acquiring first feature information of the object, comprises: if a moving object is monitored based on image analysis, acquiring first feature information of the object.

5. The method of claim 1, wherein, the first feature information comprises polar coordinates and physical features of the object. the if target feature information matching the first feature information exists in a false touch feature set, stopping monitoring of the object, comprises:

6. The method of claim 4, wherein, if a similarity of the polar coordinates and the physical features of the object to target feature information in a false touch polar coordinate matrix is higher than a similarity threshold, stopping monitoring of the object. ​ ​ 7. The method of claim 3, wherein, If the target feature information matching the first feature information does not exist in the false touch feature set, the object is identified. If the target feature information matching the first feature information does not exist in the false touch feature set, the object is subjected to portrait recognition processing. If the object passes the portrait recognition processing, a pre-warning notification is sent.

8. The method of claim 7, wherein, The method further comprises: If the object does not pass the portrait recognition processing, the false touch feature set is updated based on the first feature information of the object.

9. A camera monitoring apparatus characterized by comprising: The device comprises: A feature acquisition module is configured to acquire first feature information of the object if a moving object is monitored. A matrix matching module is configured to stop monitoring the object if the target feature information matching the first feature information exists in the false touch feature set. An object identification module is configured to identify the object if the target feature information matching the first feature information does not exist in the false touch feature set. The false touch feature set is generated based on second feature information of false touch objects, and the stop monitoring the object means not waking up the camera module to monitor the object. The matrix matching module is specifically configured to determine the object as a false touch object and stop monitoring the object if the target feature information with a similarity higher than a similarity threshold to the first feature information exists in the false touch feature set. The object identification module is specifically configured to determine the object as not a false touch object and identify the object to determine whether the object is a person if the target feature information with a similarity higher than a similarity threshold to the first feature information does not exist in the false touch feature set.

10. An electronic device, comprising: The object identification module is specifically configured to determine the object as not a false touch object and identify the object to determine whether the object is a person if the target feature information with a similarity higher than a similarity threshold to the first feature information does not exist in the false touch feature set. A processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the method steps of any one of claims 1-8.

Images