Camera control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to a camera control method and device, electronic equipment and a storage medium, and the method comprises the steps: determining the features of a monitoring object at one or more target moments in a target moment set, and obtaining an object feature set; the target moment is a moment in a target time period; based on the object feature set, determining whether the monitoring object belongs to a target object, and obtaining first discrimination information; and based on the first discrimination information, controlling the camera to wake up or sleep. Therefore, the wake-up accuracy of the camera can be improved, and the power consumption of the camera is further reduced.

Description

Technical Field

[0001] This application relates to the field of security, and particularly to a control method, device, electronic device and storage medium for a camera. Background Art

[0002] In the prior art, current battery-powered cameras have strict requirements for power consumption. If the power consumption can be reduced and the device usage time can be increased, the user experience can be greatly improved. Therefore, such devices usually need to adopt some power-saving strategies. For example, some products will first detect whether there are moving objects. When there are no moving objects, the device goes into sleep mode, and when there are moving objects, the camera is awakened to record video.

[0003] However, in the above solutions, the problem of false awakening often occurs, which increases the power consumption of the camera. Summary of the Invention

[0004] In view of this, this application provides a control method, device, electronic device and storage medium for a camera to reduce the power consumption of the camera device.

[0005] In a first aspect, an embodiment of this application provides a control method for a camera, and the method includes:

[0006] Determine the characteristics of the monitored object at one or more target times in the target time set to obtain an object feature set; the target time is the time in the target time period;

[0007] Based on the object feature set, determine whether the monitored object belongs to the target object to obtain a first discrimination information;

[0008] Based on the first discrimination information, control the camera to wake up or go to sleep.

[0009] In a possible implementation manner, the determining the characteristics of the monitored object at one or more target times in the target time set to obtain an object feature set includes:

[0010] Determine the characteristics of the monitored object within the monitoring range of the camera at the target times in the target time sequence to obtain an object feature sequence, where the target times in the target time sequence are arranged in chronological order; and

[0011] The determining whether the monitored object belongs to the target object based on the object feature set includes:

[0012] Based on the object feature sequence, determine whether the monitored object belongs to the target object.

[0013] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the object feature sequence includes:

[0014] Determine whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence.

[0015] In a possible implementation, the determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence includes:

[0016] Generate second discrimination information and third discrimination information based on adjacent object features in the object feature sequence; wherein, the adjacent object features respectively represent the positions of the monitored objects; the target vector points from the position of the monitored object represented by one object feature in the adjacent object features to the position of the monitored object represented by another object feature; the second discrimination information represents whether the direction of the projection vector of the target vector in the first direction is the same as the first direction; the third discrimination information represents whether the direction of the projection vector of the target vector in the second direction is the same as the second direction;

[0017] Determine whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information.

[0018] In a possible implementation, the type of the second discrimination information is the first type or the second type, the first type represents that the projection vector of the target vector in the first direction is the same as the first direction, the second type represents that the projection vector of the target vector in the first direction is opposite to the first direction, the type of the third discrimination information is the third type or the fourth type, the third type represents that the projection vector of the target vector in the second direction is the same as the second direction, the fourth type represents that the projection vector of the target vector in the second direction is opposite to the second direction; and

[0019] The determining whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information includes:

[0020] Determine the first quantity of the second discrimination information belonging to the first type and the second quantity of the second discrimination information belonging to the second type among the obtained second discrimination information;

[0021] Determine the third quantity of the third discrimination information belonging to the third type and the fourth quantity of the third discrimination information belonging to the fourth type among the obtained third discrimination information;

[0022] Determine whether the monitored object belongs to the target object based on the first quantity, the second quantity, the third quantity, and the fourth quantity.

[0023] In a possible implementation manner, determining whether the monitored object belongs to the target object based on the first quantity, the second quantity, the third quantity, and the fourth quantity includes:

[0024] Determine the sum of the first quantity and the second quantity to obtain a first value;

[0025] Determine the sum of the third quantity and the fourth quantity to obtain a second value;

[0026] Determine the ratio of the larger value between the first quantity and the second quantity to the first value to obtain a first result;

[0027] Determine the ratio of the larger value between the third quantity and the fourth quantity to the second value to obtain a second result;

[0028] When a preset condition is satisfied, determine that the monitored object belongs to the target object; or, when the preset condition is not satisfied, determine that the monitored object does not belong to the target object;

[0029] Wherein, the preset condition includes: the first result is greater than or equal to a first preset value, or the second result is greater than or equal to the first preset value.

[0030] In a possible implementation manner, determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence includes:

[0031] Determine the distance between adjacent object features in the object feature sequence to obtain a target distance;

[0032] Determine the quotient of the target distance and a first duration as the target speed, where the first duration is the duration for the monitored object to move from the monitored object feature to the second object feature;

[0033] Based on the obtained target speeds, determine whether the monitored object belongs to the target object.

[0034] In a possible implementation manner, determining whether the monitored object belongs to the target object based on the obtained target speeds includes:

[0035] Determine the average value of the obtained target speeds;

[0036] When the average value belongs to a preset speed range, determine that the monitored object belongs to the target object; or, when the average value does not belong to the preset speed range, determine that the monitored object does not belong to the target object.

[0037] In a possible implementation, determining whether the monitored object belongs to the target object based on the set of object features includes:

[0038] When the number of object features in the set of object features is less than or equal to a second preset value, determine that the monitored object does not belong to the target object.

[0039] In a possible implementation, determining whether the monitored object belongs to the target object based on the set of object features includes:

[0040] Determine the diameter of the smallest enclosing circle including each of the object features in the set of object features to obtain a first diameter;

[0041] Based on the first diameter, determine whether the monitored object belongs to the target object.

[0042] In a possible implementation, determining whether the monitored object belongs to the target object based on the first diameter includes:

[0043] When the first diameter belongs to a preset value range, determine that the monitored object belongs to the target object; or

[0044] When the first diameter does not belong to the preset value range, determine that the monitored object does not belong to the target object.

[0045] In a possible implementation, determining the features of the monitored object at the target moments in the target moment sequence within the monitoring range of the camera to obtain an object feature sequence includes:

[0046] Based on the object features, determine the features of the monitored object at each of the target moments in the target moment sequence to obtain an initial feature sequence;

[0047] Divide the initial feature sequence into multiple feature subsequences;

[0048] Filter the features in the feature subsequences;

[0049] Based on each of the filtered feature subsequences, determine the object feature sequence.

[0050] In a possible implementation, filtering the features in the feature subsequences includes:

[0051] Determine the diameter of the smallest enclosing circle including each of the features in the feature subsequence to obtain a second diameter;

[0052] For the features in the feature subsequence, determine the third diameter corresponding to the feature; wherein, the third diameter is: the diameter of the smallest circle that includes the areas of the features other than the feature in the feature subsequence;

[0053] For the obtained third diameter, determine the difference between the second diameter and the third diameter to obtain the difference corresponding to the third diameter;

[0054] Sort the obtained differences in ascending order of numerical value to obtain the first difference sequence;

[0055] Exclude a target number of differences from the first difference sequence to obtain a second difference sequence, where the target number is less than the number of features included in the feature subsequence;

[0056] Determine the sequence formed by the features corresponding to the differences in the second difference sequence as the filtered feature subsequence.

[0057] In a possible implementation, the controlling the camera to wake up or sleep based on the first discrimination information includes:

[0058] When the first discrimination information indicates that the monitored object belongs to the target object, control the camera to wake up; or

[0059] When the first discrimination information indicates that the monitored object does not belong to the target object, control the camera to sleep.

[0060] In a possible implementation, the determining whether the monitored object belongs to the target object based on the object feature set includes:

[0061] Based on the object feature set, determine the target features of the monitored object, where the target features include at least one of a motion trend feature, a speed feature, and a motion dispersion degree feature;

[0062] Based on the target features, determine whether the monitored object belongs to the target object.

[0063] In a possible implementation, when the target features include a motion trend feature, the determining whether the monitored object belongs to the target object based on the target features includes:

[0064] When the motion trend feature indicates that the monitored object has a motion trend, determine that the monitored object belongs to the target object;

[0065] When the motion trend feature indicates that the monitored object has no motion trend, determine that the monitored object does not belong to the target object.

[0066] In a possible implementation, when the target feature includes a speed feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0067] When the speed feature indicates that the speed of the monitored object belongs to a preset speed interval, determining that the monitored object belongs to the target object;

[0068] When the speed feature indicates that the speed of the monitored object does not belong to the preset speed interval, determining that the monitored object does not belong to the target object.

[0069] In a possible implementation, when the target feature includes a motion dispersion degree feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0070] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is less than or equal to a preset motion dispersion degree threshold, determining that the monitored object belongs to the target object;

[0071] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is greater than the preset motion dispersion degree threshold, determining that the monitored object does not belong to the target object.

[0072] In a second aspect, an embodiment of the present application provides a control device for a camera, and the device includes:

[0073] An acquisition unit, configured to determine the features of the monitored object at one or more target times in the target time set to obtain an object feature set; the target time is a time in the target time period;

[0074] A first determination unit, configured to determine whether the monitored object belongs to the target object based on the object feature set to obtain first discrimination information;

[0075] A control unit, configured to control the camera to wake up or sleep based on the first discrimination information.

[0076] In a possible implementation, determining the features of the monitored object at one or more target times in the target time set to obtain an object feature set includes:

[0077] Determining the features of the monitored object within the monitoring range of the camera at the target times in the target time sequence to obtain an object feature sequence, where the target times in the target time sequence are arranged in chronological order; and

[0078] Determining whether the monitored object belongs to the target object based on the object feature set includes:

[0079] Based on the object feature sequence, determine whether the monitored object belongs to the target object.

[0080] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the object feature sequence includes:

[0081] Based on the adjacent object features in the object feature sequence, determine whether the monitored object belongs to the target object.

[0082] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the adjacent object features in the object feature sequence includes:

[0083] Generate second discrimination information and third discrimination information based on the adjacent object features in the object feature sequence; wherein, the adjacent object features respectively represent the positions of the monitored objects; the target vector points from the position of the monitored object represented by one object feature in the adjacent object features to the position of the monitored object represented by another object feature; the second discrimination information represents whether the direction of the projection vector of the target vector in the first direction is the same as the first direction; the third discrimination information represents whether the direction of the projection vector of the target vector in the second direction is the same as the second direction;

[0084] Based on the obtained second discrimination information and the obtained third discrimination information, determine whether the monitored object belongs to the target object.

[0085] In a possible implementation manner, the type of the second discrimination information is the first type or the second type, the first type represents that the projection vector of the target vector in the first direction is the same as the first direction, the second type represents that the projection vector of the target vector in the first direction is opposite to the first direction, the type of the third discrimination information is the third type or the fourth type, the third type represents that the projection vector of the target vector in the second direction is the same as the second direction, the fourth type represents that the projection vector of the target vector in the second direction is opposite to the second direction; and

[0086] The determining whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information includes:

[0087] Determine the first quantity of the second discrimination information belonging to the first type and the second quantity of the second discrimination information belonging to the second type among the obtained second discrimination information;

[0088] Determine the third quantity of the third discrimination information belonging to the third type and the fourth quantity of the third discrimination information belonging to the fourth type among the obtained third discrimination information;

[0089] Based on the first quantity, the second quantity, the third quantity, and the fourth quantity, determine whether the monitored object belongs to the target object.

[0090] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the first quantity, the second quantity, the third quantity, and the fourth quantity includes:

[0091] Determine the sum of the first quantity and the second quantity to obtain a first value;

[0092] Determine the sum of the third quantity and the fourth quantity to obtain a second value;

[0093] Determine the ratio of the larger value between the first quantity and the second quantity to the first value to obtain a first result;

[0094] Determine the ratio of the larger value between the third quantity and the fourth quantity to the second value to obtain a second result;

[0095] When a preset condition is satisfied, determine that the monitored object belongs to the target object; or, when the preset condition is not satisfied, determine that the monitored object does not belong to the target object;

[0096] Wherein, the preset condition includes: the first result is greater than or equal to a first preset value, or the second result is greater than or equal to the first preset value.

[0097] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence includes:

[0098] Determine the distance between adjacent object features in the object feature sequence to obtain a target distance;

[0099] Determine the quotient of the target distance and a first time period as a target speed, where the first time period is the time period for the monitored object to move from the monitored object feature to the second object feature;

[0100] Based on the obtained target speeds, determine whether the monitored object belongs to the target object.

[0101] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the obtained target speeds includes:

[0102] Determine the average value of each of the obtained target speeds;

[0103] When the average value belongs to a preset speed range, determine that the monitored object belongs to the target object; or, when the average value does not belong to the preset speed range, determine that the monitored object does not belong to the target object.

[0104] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the object feature set includes:

[0105] When the number of object features in the object feature set is less than or equal to a second preset value, determine that the monitored object does not belong to the target object.

[0106] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the object feature set includes:

[0107] Determine the diameter of the smallest circle enclosing each of the object features in the object feature set to obtain a first diameter;

[0108] Based on the first diameter, determine whether the monitored object belongs to the target object.

[0109] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the first diameter includes:

[0110] When the first diameter belongs to a preset numerical range, determine that the monitored object belongs to the target object; or

[0111] When the first diameter does not belong to the preset numerical range, determine that the monitored object does not belong to the target object.

[0112] In a possible implementation manner, the obtaining the feature of the target moment of the monitored object within the monitoring range of the camera in the target moment sequence to obtain an object feature sequence includes:

[0113] Based on the object feature, determine the feature of the monitored object at each target moment in the target moment sequence to obtain an initial feature sequence;

[0114] Divide the initial feature sequence into multiple feature subsequences;

[0115] Filter the features in the feature subsequences;

[0116] Based on each of the filtered feature subsequences, determine the object feature sequence.

[0117] In a possible implementation, filtering the features in the feature subsequence includes:

[0118] Determining the diameter of the smallest-area circle that includes each feature in the feature subsequence to obtain a second diameter;

[0119] For the features in the feature subsequence, determining a third diameter corresponding to the feature; wherein, the third diameter is: the diameter of the smallest-area circle that includes each feature in the feature subsequence except this feature;

[0120] For the obtained third diameter, determining the difference between the second diameter and the third diameter to obtain the difference corresponding to the third diameter;

[0121] Sorting the obtained differences in ascending order of numerical value to obtain a first difference sequence;

[0122] Eliminating a target number of differences from the first difference sequence to obtain a second difference sequence, where the target number is less than the number of features included in the feature subsequence;

[0123] Determining the sequence composed of the features corresponding to the differences in the second difference sequence as the feature subsequence obtained after filtering.

[0124] In a possible implementation, based on the first discrimination information, controlling the camera to wake up or sleep includes:

[0125] When the first discrimination information indicates that the monitored object belongs to the target object, controlling the camera to wake up; or

[0126] When the first discrimination information indicates that the monitored object does not belong to the target object, controlling the camera to sleep.

[0127] In a possible implementation, based on the object feature set, determining whether the monitored object belongs to the target object includes:

[0128] Based on the object feature set, determining the target features of the monitored object, where the target features include at least one of a motion trend feature, a speed feature, and a motion dispersion degree feature;

[0129] Based on the target features, determining whether the monitored object belongs to the target object.

[0130] In a possible implementation, when the target features include a motion trend feature, based on the target features, determining whether the monitored object belongs to the target object includes:

[0131] When the motion trend feature indicates that the monitored object has a motion trend, it is determined that the monitored object belongs to the target object;

[0132] When the motion trend feature indicates that the monitored object has no motion trend, it is determined that the monitored object does not belong to the target object.

[0133] In a possible implementation, when the target feature includes a speed feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0134] When the speed feature indicates that the speed of the monitored object belongs to a preset speed interval, it is determined that the monitored object belongs to the target object;

[0135] When the speed feature indicates that the speed of the monitored object does not belong to the preset speed interval, it is determined that the monitored object does not belong to the target object.

[0136] In a possible implementation, when the target feature includes a motion dispersion degree feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0137] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is less than or equal to a preset motion dispersion degree threshold, it is determined that the monitored object belongs to the target object;

[0138] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is greater than the preset motion dispersion degree threshold, it is determined that the monitored object does not belong to the target object.

[0139] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0140] A memory for storing a computer program;

[0141] A processor for executing the computer program stored in the memory, and when the computer program is executed, implementing the method of any one of the embodiments of the camera control method in the first aspect of the present application.

[0142] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, implementing the method of any one of the embodiments of the camera control method in the first aspect as described above.

[0143] Fifth aspect, an embodiment of the present application provides a computer program, which includes computer-readable code. When the computer-readable code runs on a device, it enables a processor in the device to implement the method of any one of the embodiments of the camera control method in the first aspect described above.

[0144] The camera control method provided by the embodiment of the present application can determine the characteristics of a monitoring object at one or more target times in a set of target times to obtain an object feature set; the target time is a time in a target time period. Then, based on the object feature set, it is determined whether the monitoring object belongs to a target object to obtain first discrimination information. Finally, based on the first discrimination information, the camera is controlled to wake up or sleep. Thus, it is possible to determine whether the monitoring object belongs to the target object by means of multiple characteristics of the monitoring object within a period of time, and then control the camera to wake up or sleep. In this way, the accuracy of camera wake-up can be improved, and thus the power consumption of the camera can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0145] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0146] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0147] One or more embodiments are exemplarily illustrated by the pictures in the corresponding drawings. These exemplary illustrations do not limit the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements, unless otherwise stated, and the drawings in the figures do not constitute a proportional limitation.

[0148] Figure 1 It is a schematic flowchart of a camera control method provided by an embodiment of the present application;

[0149] Figure 2 It is a schematic flowchart of another camera control method provided by an embodiment of the present application;

[0150] Figure 3A It is a schematic diagram of the determination method of the object feature sequence in a camera control method provided by an embodiment of the present application;

[0151] Figure 3B It is a schematic diagram of the determination method of the second discrimination information and the third discrimination information in a camera control method provided by an embodiment of the present application;

[0152] Figure 3C Schematic diagram of the determination method of the first diameter in a camera control method provided by an embodiment of the present application;

[0153] Figure 4 Schematic diagram of the structure of a monitoring system provided by an embodiment of the present application;

[0154] Figure 5 Schematic diagram of the structure of a camera control device provided by an embodiment of the present application;

[0155] Figure 6 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0156] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present application.

[0157] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present application are only used to distinguish different steps, devices or modules, etc., and do not represent any specific technical meaning, nor do they represent the logical order between them.

[0158] It should also be understood that in this embodiment, "a plurality" may refer to two or more, and "at least one" may refer to one, two or more.

[0159] It should also be understood that for any component, data or structure mentioned in the embodiments of the present application, without clear limitation or contrary indication in the context, it can generally be understood as one or more.

[0160] In addition, the term "and / or" in the present application is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the associated objects before and after.

[0161] It should also be understood that the present application emphasizes the differences between various embodiments. Their similarities or similarities can be referred to each other. For the sake of brevity, they will not be described one by one.

[0162] The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present application or its application or use.

[0163] Known technologies, methods, and devices that are well-known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods, and devices should be regarded as part of the specification.

[0164] It should be noted that like reference numerals and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it will not be discussed further in subsequent figures.

[0165] It should be noted that, without conflict, the embodiments and features in the embodiments of the present application may be combined with each other. To facilitate the understanding of the embodiments of the present application, the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0166] To solve the technical problem of how to reduce the power consumption of a camera, the present application provides a control method for a camera, which can reduce the power consumption of the camera.

[0167] Figure 1 The figure is a schematic flow chart of a control method for a camera provided by an embodiment of the present application. This method can be applied to one or more electronic devices such as a security system, a door lock, a doorbell, a smart phone, a laptop computer, a desktop computer, a portable computer, a server, etc. In addition, the execution subject of this method can be hardware or software. When the above execution subject is hardware, the execution subject can be one or more of the above electronic devices. For example, a single electronic device can execute this method, or multiple electronic devices can cooperate with each other to execute this method. When the above execution subject is software, this method can be implemented as multiple software or software modules, or can be implemented as a single software or software module. No specific limitation is made here.

[0168] As Figure 1 shown, the method specifically includes:

[0169] Step 101, determining the characteristics of one or more target times of a monitoring object in a set of target times, to obtain an object feature set; the target time is a time in a target time period.

[0170] In this embodiment, the set of target times may include one or more target times. The target time period may include the earliest time and the latest time in the set of target times. The set of target times may be a set of each time at a preset time interval within the target time period. In addition, the set of target times may also be a set of multiple randomly selected times within the target time period. For example, if the target time is from 11:00 to 13:00, then the set of target times may include the following target times: 11:00, 11:30, 13:00, 12:00, 12:30.

[0171] The above set of object features may include one or more object features, and the object features may be the features of the monitored object at the target times in the set of target times. The object features can be obtained after being collected by devices such as radar sensors and infrared sensors.

[0172] Among them, the object features in the above set of object features may correspond one by one to the target times in the set of target times, that is, the number of object features in the set of object features may be equal to the number of target times in the set of target times. Or, the number of object features in the above set of object features may be less than the number of target times in the set of target times. For example, in the case of omission detection, the number of object features in the set of object features may be less than the number of target times in the set of target times.

[0173] In practice, devices such as radar sensors and infrared sensors can continuously (for example, continuously within the target time period) obtain the distance between an object (such as the above-mentioned monitored object) within a certain range (such as the above-mentioned monitoring range) and the device, and then determine the features of the object, that is, the object features. By processing and analyzing the data collected by the above devices, the features of the monitored object at any time (such as each target time in the above set of target times) within the above target time period can be determined, thereby obtaining the set of object features.

[0174] Step 102, based on the set of object features, determine whether the monitored object belongs to the target object to obtain the first discrimination information.

[0175] In this embodiment, based on the set of object features, the target features of the monitored object within the above target time period can be determined, where the target features may represent motion features, such as motion states, and the motion states may include at least one of motion trend features, speed features, and motion dispersion degree features. Then, based on the target features, it is determined whether the monitored object belongs to the target object, thereby obtaining the first discrimination information.

[0176] In some alternative implementation manners of this embodiment, the following method may be adopted to determine whether the monitored object belongs to the target object based on the set of object features:

[0177] First, based on the set of object features, determine the target features of the monitored object.

[0178] Among them, the target features include at least one of a motion trend feature, a speed feature, and a motion dispersion degree feature.

[0179] The motion trend feature indicates whether the monitored object has a motion trend. In some cases, the motion trend feature can be measured by the number of object features in the set of object features described later. For specific details, please refer to the following description and will not be elaborated here.

[0180] The speed feature indicates the motion speed of the monitored object.

[0181] The motion dispersion degree feature indicates the motion dispersion degree of the monitored object. In some cases, the motion dispersion degree feature can be measured by the first diameter described later. For specific details, please refer to the following description and will not be elaborated here.

[0182] After that, based on the target features, determine whether the monitored object belongs to the target object.

[0183] As an example, when the target conditions are met, it can be determined that the monitored object belongs to the target object; when the target conditions are not met, it can be determined that the monitored object does not belong to the target object.

[0184] Among them, the target conditions include at least one of the following: the monitored object has a motion trend, the motion speed of the monitored object belongs to a preset speed interval, and the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object belongs to a preset interval threshold.

[0185] In some application scenarios of the above optional implementation manners, when the target features include the motion trend feature, the following method can be used to determine whether the monitored object belongs to the target object based on the target features:

[0186] When the motion trend feature indicates that the monitored object has a motion trend, determine that the monitored object belongs to the target object; when the motion trend feature indicates that the monitored object does not have a motion trend, determine that the monitored object does not belong to the target object.

[0187] In some application scenarios of the above optional implementation manners, when the target features include the speed feature, the following method can be used to determine whether the monitored object belongs to the target object based on the target features:

[0188] When the speed feature indicates that the speed of the monitored object belongs to a preset speed range, it is determined that the monitored object belongs to the target object; when the speed feature indicates that the speed of the monitored object does not belong to the preset speed range, it is determined that the monitored object does not belong to the target object.

[0189] In some application scenarios of the above optional implementation manners, when the target feature includes a motion dispersion degree feature, the following method may be adopted to determine whether the monitored object belongs to the target object based on the target feature:

[0190] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is less than or equal to a preset motion dispersion degree threshold, it is determined that the monitored object belongs to the target object; when the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is greater than the preset motion dispersion degree threshold, it is determined that the monitored object does not belong to the target object.

[0191] It can be understood that in the above optional implementation manners, by using at least one of the motion trend feature, the speed feature, and the motion dispersion degree feature to determine whether the monitored object belongs to the target object, the accuracy of determining whether the monitored object is the target object can be improved.

[0192] Step 103, control the camera to wake up or sleep based on the first discrimination information.

[0193] In this embodiment, after the camera is woken up, it can start collecting images within the monitoring range. When the camera is in the sleep state, it can be in a low-power state.

[0194] In some optional implementation manners of this embodiment, the following method may be adopted to determine whether the monitored object belongs to the target object based on the object feature set:

[0195] When the number of object features in the object feature set is less than or equal to a second preset value, it is determined that the monitored object does not belong to the target object. That is, if the number of object features in the object feature set is less than or equal to the second preset value, then it can be considered that the monitored object does not belong to the target object.

[0196] Here, the number of object features in the above object feature set can be used to represent the motion trend feature.

[0197] It can be understood that in the above optional implementation manners, it is possible to determine whether the monitored object belongs to the target object by determining whether the number of object features in the object feature set is less than or equal to a second preset value. Thus, once the number of object features in the object feature set is less than or equal to the second preset value, it can be quickly determined that the monitored object does not belong to the target object.

[0198] In some optional implementation manners of this embodiment, the following manner can be adopted to determine whether the monitored object belongs to the target object based on the object feature set:

[0199] First, determine the diameter of the smallest circle in area that includes each of the object features in the object feature set, and obtain a first diameter.

[0200] Among them, the above first diameter can be the diameter of the smallest circle in area (i.e., the circle with the smallest area) that includes each of the object features in the object feature set.

[0201] Here, the degree of movement dispersion feature can be represented by the above first diameter.

[0202] After that, based on the first diameter, determine whether the monitored object belongs to the target object.

[0203] It can be understood that in the above optional implementation manners, since the first diameter can represent the degree of dispersion of the features (i.e., the above object features) where the monitored object is located during the target time period, thus, it is possible to determine whether the monitored object belongs to the target object through the above degree of dispersion, and further control the wake-up or sleep of the camera. Thus, the accuracy of controlling the wake-up of the camera is further improved, and the power consumption of the camera is reduced.

[0204] In some application scenarios of the above optional implementation manners, the following manner can be adopted to determine whether the monitored object belongs to the target object based on the first diameter:

[0205] In the case where the first diameter belongs to a preset value range, determine that the monitored object belongs to the target object.

[0206] Or,

[0207] In the case where the first diameter does not belong to the preset value range, determine that the monitored object does not belong to the target object.

[0208] Among them, the above preset value range can be determined based on the duration of the above target time period and the moving speed of the target object (such as a person or a vehicle). For example, if the duration of the above target time period is 1 second, then the preset value range can be from 1 meter to 1.5 meters.

[0209] It can be understood that in the above application scenarios, by monitoring the degree of dispersion of the features of the monitored object in the target time period, it can be determined whether the monitored object belongs to the target object, and then the camera can be controlled to wake up or sleep. Thereby, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0210] In some optional implementation manners of this embodiment, the following manner can be adopted to control the camera to wake up or sleep based on the first discrimination information:

[0211] When the first discrimination information indicates that the monitored object belongs to the target object, control the camera to wake up.

[0212] Or,

[0213] When the first discrimination information indicates that the monitored object does not belong to the target object, control the camera to sleep.

[0214] It can be understood that in the above optional implementation manners, when the monitored object belongs to the target object (such as a vehicle, a person, etc.), the camera is controlled to wake up, and when the monitored object does not belong to the target object, the camera is controlled to sleep. In this way, the camera can be controlled to accurately and timely collect images of the target object.

[0215] The camera control method provided by the embodiments of the present application can determine the features of a monitored object at one or more target times in a target time set to obtain an object feature set; the target time is a time in the target time period. After that, based on the object feature set, it is determined whether the monitored object belongs to the target object to obtain the first discrimination information. Finally, based on the first discrimination information, the camera is controlled to wake up or sleep. Thereby, through multiple features of the monitored object within a period of time, it can be determined whether the monitored object belongs to the target object, and then the camera is controlled to wake up or sleep. In this way, the accuracy of camera wake-up can be improved, and further the power consumption of the camera can be reduced.

[0216] Figure 2 It is a schematic flowchart of another camera control method provided by the embodiments of the present application. As Figure 2 shown, this method specifically includes:

[0217] Step 201, determine the features of the monitored object within the monitoring range of the camera at the target time in the target time sequence to obtain an object feature sequence, where the target times in the target time sequence are arranged in chronological order, and the target time is a time in the target time period.

[0218] In this embodiment, the target time sequence may include one or more target times. The target time period may include the first target time and the last target time in the target time sequence. The target time sequence may be a sequence composed of each time with a preset time interval in the target time period in chronological order. In addition, the target time sequence may also be a sequence composed of multiple randomly selected times (i.e., the time interval may be a non-fixed value) in the target time period in chronological order. For example, if the target time is from 11 to 13 o'clock, then the target time set may include the following target times: 11 o'clock, 11:30, 12 o'clock, 12:30, 13 o'clock.

[0219] In practice, devices such as radar sensors and infrared sensors can continuously obtain the distance between an object (such as the above-mentioned monitored object) within a certain range (such as the above-mentioned monitoring range) and the device, and then determine the characteristics of the object, that is, object characteristics. By processing and analyzing the data collected by the above-mentioned device, the characteristics of the monitored object at any time (such as each target time in the above-mentioned target time sequence) in the above-mentioned target time period can be determined, so as to obtain an object characteristic sequence.

[0220] The target time sequence may be a sequence of multiple times with a preset time interval in the target time period. In addition, the target time sequence may also be a sequence composed of multiple randomly selected times in the target time period.

[0221] Among them, the object characteristics in the above-mentioned object characteristic set may correspond one-to-one with the target times in the target time sequence, that is, the number of object characteristics in the object characteristic set may be equal to the number of target times in the target time sequence. Or, the number of object characteristics in the above-mentioned object characteristic set may be less than the number of target times in the target time sequence. For example, in the case of omission detection, the number of object characteristics in the object characteristic set may be less than the number of target times in the target time sequence.

[0222] In addition, step 201 is basically the same as Figure 1 step 101 in the corresponding embodiment, and will not be elaborated here.

[0223] Step 202, based on the object characteristic sequence, determine whether the monitored object belongs to the target object, and obtain the first discrimination information.

[0224] In this embodiment, the first discrimination information indicates whether the monitored object belongs to the target object.

[0225] In this embodiment, based on the object feature sequence, the target features of the monitored object in the above target time period can be determined, where the target features can include at least one of the moving speed, moving direction, and the degree of dispersion of the motion features. Then, based on the target features, it can be determined whether the monitored object belongs to the target object, and thus the first discrimination information can be obtained.

[0226] Step 203: Control the camera to wake up or sleep based on the first discrimination information.

[0227] In this embodiment, step 203 is basically the same as Figure 1 step 103 in the corresponding embodiment, and will not be elaborated here.

[0228] In some optional implementation manners of this embodiment, the following method can be used to determine whether the monitored object belongs to the target object based on the object feature sequence:

[0229] Based on the adjacent object features in the object feature sequence, determine whether the monitored object belongs to the target object.

[0230] As an example, based on the distance between adjacent object features in the object feature sequence, it can be determined whether the monitored object belongs to the target object.

[0231] As another example, it can also be determined whether the monitored object belongs to the target object based on the time duration for the monitored object to move from the monitored object feature in the object feature sequence to the second object feature.

[0232] It can be understood that in the above optional implementation manners, it can be determined whether the monitored object belongs to the target object through the adjacent object features in the object feature sequence, and then the camera can be controlled to wake up or sleep. Thus, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0233] In some application scenarios of the above optional implementation manners, the following method can be used to determine whether the monitored object belongs to the target object based on the adjacent object features in the object feature sequence:

[0234] First, generate the second discrimination information and the third discrimination information based on the adjacent object features in the object feature sequence.

[0235] Here, multiple pairs of adjacent object features can be determined from the object feature sequence. For example, if the object feature sequence is "object feature A, object feature B, object feature C, object feature D", then at least the following pairs of adjacent object features can be determined: monitored object feature A and second object feature B; monitored object feature B and second object feature C; monitored object feature C and second object feature D.

[0236] Among them, the adjacent object features respectively represent the positions of the monitored objects; the target vector points from the position of the monitored object represented by one object feature among the adjacent object features to the position of the monitored object represented by another object feature.

[0237] The second discrimination information represents whether the direction of the projection vector of the target vector in the first direction is the same as the first direction. The third discrimination information represents whether the direction of the projection vector of the target vector in the second direction is the same as the second direction.

[0238] Among them, the above-mentioned first direction is different from the above-mentioned second direction. In some cases, the first direction is perpendicular to the second direction.

[0239] After that, based on the obtained second discrimination information and the obtained third discrimination information, it is determined whether the monitored object belongs to the target object.

[0240] It can be understood that in the above application scenario, by analyzing the content of the second discrimination information and the third discrimination information, it can be determined whether the monitored object belongs to the target object, and then the camera can be controlled to wake up or sleep. Thus, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0241] In some cases in the above application scenario, the type of the second discrimination information is the first type or the second type. The first type means that the projection vector of the target vector in the first direction is the same as the first direction. The second type means that the projection vector of the target vector in the first direction is opposite to the first direction. The type of the third discrimination information is the third type or the fourth type. The third type means that the projection vector of the target vector in the second direction is the same as the second direction. The fourth type means that the projection vector of the target vector in the second direction is opposite to the second direction.

[0242] On this basis, the following method can be adopted to determine whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information:

[0243] First, determine the first quantity of the second discrimination information belonging to the first type and the second quantity of the second discrimination information belonging to the second type among the obtained second discrimination information.

[0244] Among them, the first quantity can be the quantity of the second discrimination information belonging to the first type among the obtained second discrimination information.

[0245] The second quantity may be the quantity of the second discrimination information belonging to the second type among the obtained respective second discrimination information.

[0246] After that, determine the third quantity of the third discrimination information belonging to the third type and the fourth quantity of the third discrimination information belonging to the fourth type among the obtained respective third discrimination information.

[0247] Among them, the third quantity may be the quantity of the third discrimination information belonging to the third type among the obtained respective third discrimination information. The fourth quantity may be the quantity of the third discrimination information belonging to the fourth type among the obtained respective third discrimination information.

[0248] Then, based on the first quantity, the second quantity, the third quantity, and the fourth quantity, determine whether the monitored object belongs to the target object.

[0249] As an example, it is possible to determine whether the monitored object belongs to the target object based on the ratio of the first quantity to the second quantity and the ratio of the third quantity to the fourth quantity.

[0250] In addition, the above steps may also be performed in the manner described later, which will not be elaborated here for the time being.

[0251] It can be understood that in the above case, it is possible to determine whether the monitored object belongs to the target object by analyzing the magnitude relationship of the first quantity, the second quantity, the third quantity, and the fourth quantity, and then control the camera to wake up or sleep. Thus, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0252] In some examples of the above case, the following method may be adopted to determine whether the monitored object belongs to the target object based on the first quantity, the second quantity, the third quantity, and the fourth quantity:

[0253] First, determine the sum of the first quantity and the second quantity to obtain a first value.

[0254] Among them, the first value may be the sum of the first quantity and the second quantity.

[0255] After that, determine the sum of the third quantity and the fourth quantity to obtain a second value.

[0256] Among them, the second value may be the sum of the third quantity and the fourth quantity.

[0257] Then, determine the ratio of the larger value between the first quantity and the second quantity to the first value to obtain a first result.

[0258] Wherein, the above first result may be the ratio of the larger value between the first quantity and the second quantity to the first value.

[0259] Subsequently, determine the ratio of the larger value between the third quantity and the fourth quantity to the second value to obtain a second result.

[0260] Wherein, the above second result may be the ratio of the larger value between the third quantity and the fourth quantity to the second value.

[0261] Finally, when the preset condition is satisfied, determine that the monitored object belongs to the target object; or, when the preset condition is not satisfied, determine that the monitored object does not belong to the target object.

[0262] Wherein, the preset condition includes: the first result is greater than or equal to a first preset value, or the second result is greater than or equal to the first preset value.

[0263] It can be understood that in the above example, the above first result and second result can reflect the movement trend of the monitored object in the target time period. Thus, based on the movement trend, it is determined whether the monitored object belongs to the target object, and further, the camera wake-up or sleep is controlled. Thereby, the accuracy of controlling the camera wake-up is further improved, and the power consumption of the camera is reduced.

[0264] In some application scenarios of the above optional implementation manners, the following method may be adopted to determine whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence:

[0265] First, determine the distance between adjacent object features in the object feature sequence to obtain a target distance.

[0266] Wherein, the target distance may be the distance between adjacent object features in the object feature sequence.

[0267] After that, determine the quotient of the target distance and the first duration as the target speed.

[0268] Wherein, the first duration is the duration for the monitored object to move from the monitored object feature to the second object feature.

[0269] Then, based on the obtained target speeds, determine whether the monitored object belongs to the target object.

[0270] As an example, it can be determined whether the monitored object belongs to the target object by determining whether there is a target speed that does not belong to the preset speed range among the obtained target speeds.

[0271] It can be understood that in the above application scenarios, by monitoring the speed of the monitored object moving from the monitored object feature to the second object feature, it can be determined whether the monitored object belongs to the target object, and then the camera can be controlled to wake up or sleep. Thus, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0272] In some cases of the above application scenarios, the following method can be adopted to determine whether the monitored object belongs to the target object based on each of the obtained target speeds:

[0273] First, determine the average value of each of the obtained target speeds.

[0274] After that, when the average value belongs to the preset speed range, it is determined that the monitored object belongs to the target object. Or, when the average value does not belong to the preset speed range, it is determined that the monitored object does not belong to the target object.

[0275] It can be understood that in the above cases, by monitoring the average speed of the monitored object within the target time period, it can be determined whether the monitored object belongs to the target object, and then the camera can be controlled to wake up or sleep. Thus, the accuracy of controlling the camera to wake up is further improved, and the power consumption of the camera is reduced.

[0276] In some optional implementation manners of this embodiment, the time duration between two adjacent moments in the target moment sequence is the second time duration (for example, a pre-determined time duration).

[0277] On this basis, the following method can be adopted to determine the features of the monitored object within the monitoring range of the camera at the target moments in the target moment sequence, and obtain an object feature sequence:

[0278] First, based on the object features, determine the features of the monitored object at each target moment in the target moment sequence respectively, and obtain an initial feature sequence.

[0279] Among them, the initial feature sequence can be a sequence composed of the features of the monitored object at each target moment in the target moment sequence.

[0280] The features in the initial feature sequence and the target moments in the target moment sequence can correspond one by one.

[0281] After that, divide the initial feature sequence into multiple feature subsequences.

[0282] Among them, the number of features included in each of the divided feature subsequences can be equal or unequal.

[0283] Then, filter the features in the feature subsequences.

[0284] Here, one or more features with dispersed features in the feature subsequence can be filtered out.

[0285] Finally, based on each filtered feature subsequence, an object feature sequence is determined.

[0286] As an example, the sequence composed of the features in each filtered feature subsequence can be determined as the object feature sequence.

[0287] As another example, the central feature of each filtered feature subsequence can also be determined. Then, the sequence composed of the obtained central features is determined as the object feature sequence.

[0288] It can be understood that in the above optional implementation, by filtering the features in the initial feature sequence, the error caused by the drift phenomenon in the feature acquisition of the monitored object can be reduced. Thus, the accuracy of controlling the camera wake-up is further improved, and the power consumption of the camera is reduced.

[0289] In some application scenarios of the above optional implementation, the following method can be used to filter the features in the feature subsequence:

[0290] First, determine the diameter of the smallest circle in area that includes each feature in the feature subsequence to obtain a second diameter.

[0291] Among them, the second diameter can be the diameter of the smallest circle in area (i.e., the circle with the smallest area) that includes each feature in the feature subsequence.

[0292] After that, for the features in the feature subsequence, determine the third diameter corresponding to the feature.

[0293] Among them, the third diameter is: the diameter of the smallest circle in area that includes each feature in the feature subsequence except this feature.

[0294] Then, for the obtained third diameter, determine the difference between the second diameter and the third diameter to obtain the difference corresponding to the third diameter.

[0295] Among them, the difference corresponding to the third diameter can be the difference between the second diameter and the third diameter.

[0296] Subsequently, sort the obtained differences in ascending order of numerical value to obtain a first difference sequence.

[0297] Among them, the first difference sequence can be the result of sorting the obtained differences in ascending order of numerical value.

[0298] Next, a target number of differences are removed from the first difference sequence to obtain a second difference sequence.

[0299] Wherein, the target number is less than the number of features included in the feature subsequence. As an example, the target number can be a preset percentage of the number of features included in the feature subsequence, such as 10% or 20%.

[0300] Finally, the sequence composed of the features corresponding to the differences in the second difference sequence is determined as the filtered feature subsequence.

[0301] It can be understood that in the above application scenario, the features that have a great influence on the diameter can be filtered out, and the true features of the monitored object can be determined based on the remaining features. Furthermore, the camera can be controlled to wake up or sleep through the true features, so that the accuracy of camera wake-up can be improved, and the power consumption of the camera can be reduced.

[0302] It should be noted that in addition to the above-mentioned content, this embodiment may further include Figure 1 the corresponding technical features described in the corresponding embodiments, so as to achieve Figure 1 the technical effects of the control method of the camera shown, for details, please refer to Figure 1 the relevant descriptions. For the sake of brevity, they will not be elaborated here.

[0303] The control method of the camera provided by the embodiment of the present application determines whether the monitored object belongs to the target object by the features of the monitored object within a period of time and the order in which the target user appears on each feature, and then controls the camera to wake up or sleep. In this way, the accuracy of camera wake-up can be improved, and the power consumption of the camera can be reduced.

[0304] Next, the embodiments of the present application will be described exemplarily. However, it should be noted that the embodiments of the present application may have the features described below, but the following description does not constitute a limitation on the protection scope of the embodiments of the present application.

[0305] Currently, battery-powered security cameras usually have strict requirements on power consumption. If the power consumption can be reduced and the device usage time can be increased, the user experience can be greatly improved. Therefore, such devices usually need to adopt some power-saving strategies. For example, some products use radar sensors to detect the presence of moving objects, sleep when there are no moving objects, and record videos when there are moving objects.

[0306] Radar sensors have high measurement accuracy and good detection effects on moving objects. However, when using radar sensors, problems such as false video recording often occur in scenarios such as the movement of flowers and plants and rain. This problem will result in the generation of invalid videos and an increase in device power consumption.

[0307] Thus, the components of the security camera device in this method are: a high-power camera module (including a camera), a low-power microprocessor module (including a processor), and a radar sensor module (including a radar sensor). Among them, the radar sensor is mounted on the microprocessor, and the microprocessor is responsible for collecting and processing the data of the radar sensor. When the device is in the sleep state, the camera module (including the camera) stops working, and only the microprocessor module and the radar sensor are working. At this time, the power consumption of the device is relatively low. When the radar sensor detects a moving object, it transmits the data to the microprocessor. The microprocessor extracts the feature information in the data. If it conforms to the feature information of the video recording scenario, it wakes up the camera module to start video recording. If it does not conform, the device continues to remain in the sleep state.

[0308] Among them, the above-mentioned radar sensor is a sensor that can detect the characteristic coordinates of a moving object. The microprocessor is a low-power processor with certain data processing capabilities. The camera module can capture and save images, and has a high power consumption during operation.

[0309] Generally, a security camera device hopes to capture the scene of people moving in and out, and does not hope to capture the scene of trees swaying. In these scenarios, the radar sensor has different characteristic information, and these characteristic information can be used to filter out the scenes that are not desired to be recorded, avoiding invalid video recording.

[0310] In practice, the coordinate points detected by the radar sensor for the moving object (i.e., the object features in the above-mentioned object feature set) will drift. Therefore, it is necessary to perform filtering processing on the radar data before extracting the radar feature information.

[0311] The method adopted is: collect the coordinate points (i.e., the above-mentioned feature subsequence) for a short period of time (such as 0.5 seconds), draw a smallest circle (i.e., the smallest circular area including each feature in the above-mentioned feature subsequence), so that the circle can accommodate all the coordinate points. Try to remove several (i.e., the above-mentioned target number) coordinate points in turn, and filter out the coordinate points that have a great influence on the diameter. The center of the circle formed by the remaining points is considered to be the true coordinate point of the moving object (i.e., the object feature in the above-mentioned object feature set).

[0312] It should be noted that the subsequent mentioned radar coordinates are all considered to be the true coordinate points of the moving object after filtering processing.

[0313] Specifically, the extraction of radar feature information can be implemented from multiple angles, such as: motion trend (i.e., the above-mentioned first result and second result), speed (i.e., the above-mentioned average value), and dispersion degree (i.e., the above-mentioned first diameter).

[0314] For example, generally, when a person appears in the radar's field of view, there should be an obvious trend of movement and not suddenly appear and disappear from the screen. The walking speed of a person is generally fixed within a certain range. If the speed of the object detected by the radar far exceeds this range, the scenario of a person walking can be excluded. When a person is walking, the coordinates of the moving object detected by the radar within a short period are relatively concentrated. In the case of scenarios such as rain or snow, the degree of dispersion of the coordinates of the moving object detected by the radar is relatively large.

[0315] The trend of movement can be determined in the following way: Record the coordinates within a short period of time (i.e., the above-mentioned target time period), and successively calculate the moving distances of the x-axis (i.e., the above-mentioned first direction) and y-axis (i.e., the above-mentioned second direction) of the subsequent coordinate (such as the above-mentioned second object feature) from the previous coordinate (such as the above-mentioned monitored object feature). Calculate the proportions of positive and negative numbers among all the moving distances (i.e., the above-mentioned first result and second result). If the proportion of positive numbers in the x-axis moving distance is significantly larger (e.g., greater than or equal to 70%), and the proportion of negative numbers in the y-axis moving distance is significantly larger (e.g., greater than or equal to 70%), then it can be considered that the moving object has a tendency to move in the positive direction of the x-axis and the negative direction of the y-axis. If there are too few coordinate points or there are no obvious characteristics in the proportions of positive and negative numbers (e.g., less than 70%), then it is considered that this moving object has no trend of movement.

[0316] The movement speed can be determined in the following way: Set a fixed time T (i.e., the above-mentioned second duration). Every time after time T, record a coordinate (such as the coordinate representing the above-mentioned second object feature), subtract it from the previously recorded coordinate (such as the coordinate representing the above-mentioned monitored object feature), calculate the movement distance D (i.e., the above-mentioned target distance) within time T, divide D by T to obtain the movement speed V (i.e., the above-mentioned target speed). Repeat the above process for each collected coordinate point to obtain multiple speeds V, and take the average (i.e., the above-mentioned average value) as the average movement speed of the object.

[0317] The degree of dispersion can be determined in the following way: Record several coordinates within a short period of time (i.e., the above-mentioned target time period), and draw the smallest circle that can contain all the coordinates. The diameter of this circle (i.e., the above-mentioned first diameter) can be regarded as the degree of dispersion of the coordinates.

[0318] Analyze the situations of the above several features in each scenario and save them. When the radar detects a moving object, the microcontroller starts to collect and analyze the feature information of the moving object at this time. If the feature requirements of the video recording scenario are met (for example, the first diameter belongs to a preset numerical range, the average value belongs to a preset speed range, and the first result is greater than or equal to the first preset value; or, the first diameter belongs to a preset numerical range, the average value belongs to a preset speed range, and the second result is greater than or equal to the first preset value), the microprocessor wakes up the camera module, and the camera module starts to record video. If the feature requirements of the video recording scenario are not met, the microcontroller does not wake up the camera module, and the device continues to sleep.

[0319] As Figure 3A shown, Figure 3A This is a schematic diagram of the determination method of the object feature sequence in a camera control method provided by an embodiment of the present application.

[0320] In Figure 3A it, the solid dots and the hollow dots are all coordinate points collected by the radar. The dashed circle is an auxiliary result in the filtering process, and the solid circle is the final result. The pentagram is the center of the solid circle, that is, the actual coordinates of the moving object obtained after filtering.

[0321] As Figure 3B shown, Figure 3B This is a schematic diagram of the determination method of the second discriminant information and the third discriminant information in a camera control method provided by an embodiment of the present application.

[0322] In Figure 3B it, the black dots are the coordinates (actual coordinates) of the moving object, and the arrow line segments represent the coordinate movement sequence and distance. Among these coordinate points, the proportion of the negative Y-axis is very large, and there is no obvious feature on the X-axis. Therefore, it can be considered that the moving object has a tendency to move in the negative direction of the Y-axis.

[0323] As Figure 3C shown, Figure 3C This is a schematic diagram of the determination method of the first diameter in a camera control method provided by an embodiment of the present application.

[0324] In Figure 3C it, the black dots are the coordinate points for a short period of time, and the circle is the smallest circle that can contain all the coordinate points. The diameter of the circle can be used to represent the degree of dispersion of the coordinate points of the moving object.

[0325] It should be noted that in addition to the above-recorded content, this embodiment may also include the technical features described in the above embodiments, so as to achieve the technical effects of the camera control method shown above. For details, please refer to the above description. For the sake of concise description, it will not be elaborated here.

[0326] The control method of the camera provided by the embodiment of the present application makes the device more accurate in recognizing moving objects by extracting and identifying the characteristic information of radar data. Filtering invalid videos using the radar characteristic information can reduce the power consumption of the device and increase the battery life of the device.

[0327] Figure 4 It is a schematic structural diagram of a monitoring system provided by the embodiment of the present application. As Figure 4 shown, the monitoring system 1000 includes: a camera 100 and a processor 200. The camera 100 is connected to the processor 200. The processor is used to implement the control method of the camera described in any one of the above.

[0328] The monitoring system provided by the embodiment of the present application includes a camera and a processor. The camera is connected to the processor. The processor is used to determine the characteristics of the monitoring object at one or more target times in the target time set to obtain an object feature set; the target time is the time in the target time period. After that, based on the object feature set, it is determined whether the monitoring object belongs to the target object to obtain the first discrimination information. Finally, based on the first discrimination information, the camera is controlled to wake up or sleep. Thus, it is possible to determine whether the monitoring object belongs to the target object by multiple characteristics of the monitoring object within a period of time, and then control the camera to wake up or sleep. In this way, the accuracy of the camera wake-up can be improved, and the power consumption of the camera can be reduced.

[0329] Figure 5 It is a schematic structural diagram of a control device of a camera provided by the embodiment of the present application. Specifically, it includes:

[0330] An acquisition unit 401, configured to determine the characteristics of the monitoring object at one or more target times in the target time set to obtain an object feature set; the target time is the time in the target time period;

[0331] A first determination unit 402, configured to determine whether the monitoring object belongs to the target object based on the object feature set to obtain the first discrimination information;

[0332] A control unit 403, configured to control the camera to wake up or sleep based on the first discrimination information.

[0333] In a possible implementation manner, the determining the characteristics of the monitoring object at one or more target times in the target time set to obtain an object feature set includes:

[0334] Determining the characteristics of the monitoring object within the monitoring range of the camera at the target times in the target time sequence to obtain an object feature sequence, where the target times in the target time sequence are arranged in chronological order; and

[0335] Determining whether the monitored object belongs to the target object based on the set of object features includes:

[0336] Determining whether the monitored object belongs to the target object based on the object feature sequence.

[0337] In a possible implementation, determining whether the monitored object belongs to the target object based on the object feature sequence includes:

[0338] Determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence.

[0339] In a possible implementation, determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence includes:

[0340] Generating second discrimination information and third discrimination information based on adjacent object features in the object feature sequence; wherein, the adjacent object features respectively represent the positions of the monitored object; the target vector points from the position of the monitored object represented by one object feature in the adjacent object features to the position of the monitored object represented by another object feature; the second discrimination information represents whether the direction of the projection vector of the target vector in the first direction is the same as the first direction; the third discrimination information represents whether the direction of the projection vector of the target vector in the second direction is the same as the second direction;

[0341] Determining whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information.

[0342] In a possible implementation, the type of the second discrimination information is the first type or the second type, the first type represents that the projection vector of the target vector in the first direction is the same as the first direction, the second type represents that the projection vector of the target vector in the first direction is opposite to the first direction, the type of the third discrimination information is the third type or the fourth type, the third type represents that the projection vector of the target vector in the second direction is the same as the second direction, the fourth type represents that the projection vector of the target vector in the second direction is opposite to the second direction; and

[0343] Determining whether the monitored object belongs to the target object based on the obtained second discrimination information and the obtained third discrimination information includes:

[0344] Determining the first quantity of the second discrimination information belonging to the first type and the second quantity of the second discrimination information belonging to the second type among the obtained second discrimination information;

[0345] Determine the third quantity of the third discrimination information belonging to the third type and the fourth quantity of the third discrimination information belonging to the fourth type among the obtained third discrimination information;

[0346] Based on the first quantity, the second quantity, the third quantity, and the fourth quantity, determine whether the monitored object belongs to the target object.

[0347] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on the first quantity, the second quantity, the third quantity, and the fourth quantity includes:

[0348] Determine the sum of the first quantity and the second quantity to obtain a first value;

[0349] Determine the sum of the third quantity and the fourth quantity to obtain a second value;

[0350] Determine the ratio of the larger value between the first quantity and the second quantity to the first value to obtain a first result;

[0351] Determine the ratio of the larger value between the third quantity and the fourth quantity to the second value to obtain a second result;

[0352] When a preset condition is satisfied, determine that the monitored object belongs to the target object; or, when the preset condition is not satisfied, determine that the monitored object does not belong to the target object;

[0353] Wherein, the preset condition includes: the first result is greater than or equal to a first preset value, or the second result is greater than or equal to the first preset value.

[0354] In a possible implementation manner, the determining whether the monitored object belongs to the target object based on adjacent object features in the object feature sequence includes:

[0355] Determine the distance between adjacent object features in the object feature sequence to obtain a target distance;

[0356] Determine the quotient of the target distance and a first duration as the target speed, where the first duration is the duration for the monitored object to move from the monitored object feature to the second object feature;

[0357] Based on the obtained target speeds, determine whether the monitored object belongs to the target object.

[0358] In a possible implementation, determining whether the monitored object belongs to the target object based on each of the obtained target speeds includes:

[0359] Determining the average value of each of the obtained target speeds;

[0360] When the average value belongs to a preset speed range, determining that the monitored object belongs to the target object; or, when the average value does not belong to the preset speed range, determining that the monitored object does not belong to the target object.

[0361] In a possible implementation, determining whether the monitored object belongs to the target object based on the object feature set includes:

[0362] When the number of object features in the object feature set is less than or equal to a second preset value, determining that the monitored object does not belong to the target object.

[0363] In a possible implementation, determining whether the monitored object belongs to the target object based on the object feature set includes:

[0364] Determining the diameter of the smallest circle enclosing each of the object features in the object feature set to obtain a first diameter;

[0365] Based on the first diameter, determining whether the monitored object belongs to the target object.

[0366] In a possible implementation, determining whether the monitored object belongs to the target object based on the first diameter includes:

[0367] When the first diameter belongs to a preset numerical range, determining that the monitored object belongs to the target object; or

[0368] When the first diameter does not belong to the preset numerical range, determining that the monitored object does not belong to the target object.

[0369] In a possible implementation, the time duration between two adjacent times in the target time sequence is a second time duration; and

[0370] Determining the features of the monitored object at the target times in the target time sequence to obtain an object feature sequence includes:

[0371] Based on the object features, determining the features of the monitored object at each of the target times in the target time sequence to obtain an initial feature sequence;

[0372] Dividing the initial feature sequence into a plurality of feature subsequences;

[0373] Filter the features in the feature subsequence;

[0374] Based on each filtered feature subsequence, determine the object feature sequence.

[0375] In a possible implementation, the filtering of the features in the feature subsequence includes:

[0376] Determine the diameter of the smallest enclosing circle including each feature in the feature subsequence to obtain a second diameter;

[0377] For the features in the feature subsequence, determine the third diameter corresponding to the feature; wherein, the third diameter is: the diameter of the smallest enclosing circle including each feature other than the feature in the feature subsequence;

[0378] For the obtained third diameter, determine the difference between the second diameter and the third diameter to obtain the difference corresponding to the third diameter;

[0379] Sort the obtained differences in ascending order of numerical value to obtain a first difference sequence;

[0380] Remove a target number of differences from the first difference sequence to obtain a second difference sequence, where the target number is less than the number of features included in the feature subsequence;

[0381] Determine the sequence composed of the features corresponding to the differences in the second difference sequence as the filtered feature subsequence.

[0382] In a possible implementation, the controlling the camera to wake up or sleep based on the first discrimination information includes:

[0383] When the first discrimination information indicates that the monitored object belongs to the target object, control the camera to wake up; or

[0384] When the first discrimination information indicates that the monitored object does not belong to the target object, control the camera to sleep.

[0385] In a possible implementation, the determining whether the monitored object belongs to the target object based on the object feature set includes:

[0386] Based on the object feature set, determine the target features of the monitored object, where the target features include at least one of a motion trend feature, a speed feature, and a motion dispersion degree feature;

[0387] Based on the target features, determine whether the monitored object belongs to the target object.

[0388] In a possible implementation, when the target feature includes a motion trend feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0389] When the motion trend feature indicates that the monitored object has a motion trend, determining that the monitored object belongs to the target object;

[0390] When the motion trend feature indicates that the monitored object has no motion trend, determining that the monitored object does not belong to the target object.

[0391] In a possible implementation, when the target feature includes a speed feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0392] When the speed feature indicates that the speed of the monitored object belongs to a preset speed interval, determining that the monitored object belongs to the target object;

[0393] When the speed feature indicates that the speed of the monitored object does not belong to the preset speed interval, determining that the monitored object does not belong to the target object.

[0394] In a possible implementation, when the target feature includes a motion dispersion degree feature, determining whether the monitored object belongs to the target object based on the target feature includes:

[0395] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is less than or equal to a preset motion dispersion degree threshold, determining that the monitored object belongs to the target object;

[0396] When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is greater than the preset motion dispersion degree threshold, determining that the monitored object does not belong to the target object.

[0397] The control device of the camera provided in this embodiment may be the control device of the camera as shown in Figure 5 , and can execute all steps of the above-mentioned control methods of each camera, thereby achieving the technical effects of the above-mentioned control methods of each camera. For specific reference, please refer to the above relevant descriptions. For the sake of brevity, it will not be elaborated here.

[0398] Figure 6 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. Figure 6The illustrated electronic device 500 includes: at least one processor 501, a memory 502, at least one network interface 504, and other user interfaces 503. Each component in the electronic device 500 is coupled together through a bus system 505. It can be understood that the bus system 505 is used to implement the connection and communication between these components. In addition to a data bus, the bus system 505 further includes a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 6 all kinds of buses are labeled as the bus system 505.

[0399] Among them, the user interface 503 may include a display, a keyboard, or a pointing device (for example, a mouse, a trackball, a touchpad, or a touch screen, etc.).

[0400] It can be understood that the memory 502 in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synch link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). The memory 502 described herein is intended to include but not be limited to these and any other suitable types of memory.

[0401] In some embodiments, the memory 502 stores the following elements, executable units, or data structures, or subsets thereof, or extended sets thereof: an operating system 5021 and an application program 5022.

[0402] Among them, the operating system 5021 includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., which are used to implement various basic services and handle hardware-based tasks. The application programs 5022 include various application programs, such as the Media Player, the Browser, etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application may be included in the application programs 5022.

[0403] In this embodiment, by calling the program or instruction stored in the memory 502, specifically, it may be the program or instruction stored in the application programs 5022, the processor 501 is used to execute the method steps provided by each method embodiment, for example, including:

[0404] Determine the characteristics of the monitored object at one or more target times in the target time set to obtain an object feature set; the target time is the time in the target time period;

[0405] Based on the object feature set, determine whether the monitored object belongs to the target object to obtain first discrimination information;

[0406] Based on the first discrimination information, control the camera to wake up or sleep.

[0407] The method disclosed in the embodiments of the present application can be applied to or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed by the integrated logic circuit in hardware or instructions in software form in the processor 501. The above-mentioned processor 501 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software units in the decoding processor. The software unit may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 502, and the processor 501 reads the information in the memory 502 and combines its hardware to complete the steps of the above method.

[0408] It can be understood that these embodiments described herein can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing unit can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the above functions of the present application, or a combination thereof.

[0409] For a software implementation, the above-mentioned technology herein can be implemented by units that execute the above functions herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented inside or outside the processor.

[0410] The electronic device provided in this embodiment may be the electronic device shown in Figure 6 and can execute all steps of the control method of each camera described above, thereby achieving the technical effects of the control methods of the above-mentioned cameras. For specific reference, please refer to the above relevant descriptions. For the sake of brevity, it will not be elaborated here.

[0411] This application embodiment also provides a storage medium (computer-readable storage medium). One or more programs are stored in this storage medium. Among them, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state drive; the memory may also include a combination of the above types of memory.

[0412] When one or more programs in the storage medium can be executed by one or more processors to implement the control method of the camera executed on the electronic device side.

[0413] The above-mentioned processor is used to execute the control program of the camera stored in the memory to implement the following steps of the control method of the camera executed on the electronic device side:

[0414] Determine the characteristics of the monitoring object at one or more target times in the target time set to obtain an object feature set; the target time is the time in the target time period;

[0415] Based on the object feature set, determine whether the monitoring object belongs to the target object to obtain the first discrimination information;

[0416] Based on the first discrimination information, control the camera to wake up or sleep.

[0417] Professional personnel should also be able to further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0418] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be implemented in hardware, software modules executed by a processor, or a combination of both. The software modules may be disposed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0419] It should be understood that the terms used herein are for the purpose of describing particular example embodiments only and are not intended to be limiting. Unless the context clearly dictates otherwise, the singular forms "a", "an", and "the" as used herein may also include the plural forms. The terms "comprises", "comprising", "includes", and "having" are inclusive and thus specify the presence of the stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order described or illustrated, unless explicitly indicated as an order of performance. It should also be understood that additional or alternative steps may be used.

[0420] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A control method for a camera, characterized in that, the method includes: determining the characteristics of a monitoring object at one or more target times in a set of target times to obtain an object feature set; the target times are the times in a target time period; based on the object feature set, determining whether the monitoring object belongs to a target object to obtain a first discrimination information; based on the first discrimination information, controlling the camera to wake up or sleep.

2. The method according to claim 1, characterized in that, the step of determining the characteristics of a monitoring object at one or more target times in a set of target times to obtain an object feature set includes: determining the characteristics of the monitoring object within the monitoring range of the camera at the target times in a target time sequence to obtain an object feature sequence, wherein the target times in the target time sequence are arranged in chronological order; and the step of determining whether the monitoring object belongs to a target object based on the object feature set includes: determining whether the monitoring object belongs to a target object based on the object feature sequence.

3. The method according to claim 2, characterized in that, the step of determining whether the monitoring object belongs to a target object based on the object feature sequence includes: determining whether the monitoring object belongs to a target object based on adjacent object features in the object feature sequence.

4. The method according to claim 3, characterized in that, the step of determining whether the monitoring object belongs to a target object based on adjacent object features in the object feature sequence includes: generating a second discrimination information and a third discrimination information based on adjacent object features in the object feature sequence; wherein, the second discrimination information indicates whether the direction of the projection vector of the target vector in the first direction is the same as the first direction; the third discrimination information indicates whether the direction of the projection vector of the target vector in the second direction is the same as the second direction; the adjacent object features respectively represent the positions of the monitoring object; the target vector points from the position of the monitoring object represented by one object feature in the adjacent object features to the position of the monitoring object represented by another object feature; determining whether the monitoring object belongs to a target object based on the obtained second discrimination information and the obtained third discrimination information.

5. The method according to claim 4, characterized in that, the type of the second discrimination information is the first type or the second type, the first type indicates that the projection vector of the target vector in the first direction is the same as the first direction, the second type indicates that the projection vector of the target vector in the first direction is opposite to the first direction, the type of the third discrimination information is the third type or the fourth type, the third type indicates that the projection vector of the target vector in the second direction is the same as the second direction, the fourth type indicates that the projection vector of the target vector in the second direction is opposite to the second direction; and the step of determining whether the monitoring object belongs to a target object based on the obtained second discrimination information and the obtained third discrimination information includes: Determine a first quantity of the second discrimination information belonging to the first type and a second quantity of the second discrimination information belonging to the second type among the obtained respective second discrimination information; Determine a third quantity of the third discrimination information belonging to the third type and a fourth quantity of the third discrimination information belonging to the fourth type among the obtained respective third discrimination information; Based on the first quantity, the second quantity, the third quantity, and the fourth quantity, determine whether the monitored object belongs to the target object.

6. The method according to claim 1, wherein, the determining whether the monitored object belongs to the target object based on the object feature set includes: Based on the object feature set, determine the target features of the monitored object, where the target features include at least one of a motion trend feature, a speed feature, and a motion dispersion degree feature; Based on the target features, determine whether the monitored object belongs to the target object.

7. The method according to claim 6, wherein, when the target features include a motion trend feature, the determining whether the monitored object belongs to the target object based on the target features includes: When the motion trend feature indicates that the monitored object has a motion trend, determine that the monitored object belongs to the target object; When the motion trend feature indicates that the monitored object has no motion trend, determine that the monitored object does not belong to the target object.

8. The method according to claim 6, wherein, when the target features include a speed feature, the determining whether the monitored object belongs to the target object based on the target features includes: When the speed feature indicates that the speed of the monitored object belongs to a preset speed interval, determine that the monitored object belongs to the target object; When the speed feature indicates that the speed of the monitored object does not belong to the preset speed interval, determine that the monitored object does not belong to the target object.

9. The method according to claim 6, wherein, when the target features include a motion dispersion degree feature, the determining whether the monitored object belongs to the target object based on the target features includes: When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is less than or equal to a preset motion dispersion degree threshold, determine that the monitored object belongs to the target object; When the motion dispersion degree feature indicates that the motion dispersion degree of the monitored object is greater than the preset motion dispersion degree threshold, determine that the monitored object does not belong to the target object.

10. A control device for a camera, wherein, the device includes: A first determination unit, configured to determine the features of the monitored object at one or more target times in the target time set to obtain an object feature set; the target time is a time in the target time period; A second determination unit, configured to determine whether the monitored object belongs to the target object based on the object feature set to obtain first discrimination information; A control unit, configured to control the wake-up or sleep of the camera based on the first discrimination information.

11. A monitoring system, characterized in that the monitoring system includes: a camera and a processor, the camera is connected to the processor, wherein: the processor is configured to implement the method according to any one of claims 1-9 above.

Images